PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 1235001 (2022) https://doi.org/10.1117/12.2660176
This PDF file contains the front matter associated with SPIE Proceeding Volume 12350 including the Title Page, Copywrite information, Table of Contents, and Conference Committee Page.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Power Grid System and Industrial Product Control Technology
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 1235002 (2022) https://doi.org/10.1117/12.2652881
Genetic algorithm is an algorithm that searches for the optimal solution by simulating the natural evolutionary process. The development of fuel cell vehicles is of great significance to the traditional automobile industry as well as the energy industry, and is an important initiative to protect the environment and conserve resources. However, fuel cell vehicles still face the problem of insufficient range. One solution is to form a multi-energy source system by combining fuel cells with secondary charging auxiliary power or other power sources. Therefore, to give full play to the advantages of hybrid power, it is necessary to solve the energy management problems brought about by hybrid power. In this study, the applicability of energy management strategy optimization for fuel cell vehicles is analyzed with the help of hybrid genetic algorithms.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 1235003 (2022) https://doi.org/10.1117/12.2653343
Considering the green development of enterprises and combining the connotation characteristics of agricultural product cold chain logistics, the factors affecting the efficiency of agricultural product cold chain logistics enterprises are constructed from five dimensions: finance, customers, green environmental protection, cold chain operation, and technological development. Combined with DEMATEL method for empirical analysis. According to the research results, it is shown that the utilization rate of refrigerated trucks, environmental management system certification, and R&D investment rate are the key factors affecting its development. Based on this, we can promote the long-term development of agricultural cold chain logistics enterprises by improving the efficiency of cold chain operation, strengthening green environmental protection capabilities, and attaching importance to the construction of smart logistics.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 1235004 (2022) https://doi.org/10.1117/12.2652857
Due to the unreasonable use of surface water and groundwater for a long time, the shortage of water resources has become an important factor restricting the northern country's social and economic development. As a demonstration area for Shaanxi, Shanxi and Henan to undertake industrial transfer while accelerating economic development, it also inevitably faces the realistic problem of the increasingly deteriorating contradiction between the supply and demand of hydropower stations. Considering that the traditional hydropower station configuration method will lead to deviation in results, this paper constructs a comprehensive evaluation function aiming at social benefit, economic benefit and ecological benefit based on ensuring the balance of supply and demand and establishing a more targeted hydropower station optimal configuration model, and analyzed the rationality of the configuration results through the configuration goals. The results show that the optimal allocation model conforms to the characteristics and changing trends of the multi-objective optimization model, can scientifically adjust the regional water supply structure, allocate water resources reasonably and effectively, improve the utilization level of hydropower stations, and provide support for the sustainable development of society and economy.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 1235005 (2022) https://doi.org/10.1117/12.2652542
Due to coal wall spalling is also one of the sources of flying gangue, and the displacement of coal wall can qualitatively reflect the degree of wall caving, so this paper use flying gangue in steeply dipping seam as the object of study, based on distinct element method (DEM). By using numerical simulation, the derivative mechanism for flying gangue under the different mining height in steeply dipping seam were systematically studied. The results show that the severity of wall caving has an increasing trend along with mining height increases, and the extent of injury of flying gangue caused by wall caving also has an increasing trend.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 1235006 (2022) https://doi.org/10.1117/12.2652714
With the continuous development of society, indoor monitoring is increasingly widely used. At present, video surveillance mainly uses artificial real-time monitoring or post-monitoring to check indoor conditions and people. This paper describes the components and working principle of YOLOv5, and uses YOLOv5 algorithm to conduct network simulation and training for indoor common targets. Through the indoor photography head to collect the scene, using YOLOv5 algorithm to process the original photos, when there is an abnormal person in the image, the system will issue an alarm to remind the owner to deal with it in time. The experiment shows that the system can respond the indoor situation economically, quickly and effectively and meet the demand of indoor anti-theft.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 1235007 (2022) https://doi.org/10.1117/12.2652827
Power usage quota transaction is a process of reallocation of user power usage quota through the market on the basis of orderly electricity utilization. It is an effective power supply mechanism to deal with the extreme power shortage in China’s power market. However, the traditional centralized power usage quota transaction based on user quotation does not consider user energy efficiency and environmental benefits. Therefore, a centralized power usage quota transaction mechanism is proposed in this work considering the energy efficiency priority of users. Firstly, based on the industry energy efficiency target- and benchmark level specified by the government, user energy efficiency priority index is proposed to correct the bid and offer of market players. Then, a market clearing model of power usage quota transaction is constructed based on user corrected quotation, and an optimal bidding model for power usage quota buyer under the proposed mechanism is also proposed. The power usage quota transaction simulation is carried out for users with different energy efficiency. The results show that the proposed centralized trading mechanism can adjust the trading order according to the energy efficiency of users, so as to promote transaction which is more conducive to energy consumption control and environmental benefits.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 1235008 (2022) https://doi.org/10.1117/12.2652485
The user-controlled K shortest path problem with diversity (UKSPD) is a general form of the K shortest path (KSP) problem in graphs. Instead of finding the K shortest from point to point, the UKSPD determines the level of similarity of the K shortest paths through user input parameters. In this paper, we formally describe the UKSPD problem, which acts as a multi-objective optimization problem. Considering the application of genetic algorithm in multi-objective optimization, we propose an improved genetic algorithm to solve the UKSPD problem. The basic mechanism of the whole algorithm is as follows: chromosomes are directly represented as paths, crossover and mutation operations are performed to ensure the connectivity of the paths, and the user input parameter in each iteration determines the similarity of the selected paths. The proposed algorithm is tested on the New York City Map and compared with the improved Dijkstra algorithm, and the experimental results illustrate the effectiveness of the proposed genetic algorithm.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 1235009 (2022) https://doi.org/10.1117/12.2652508
For the purpose of meeting the further requirements of East operation experiment for gyrotron power, a set of gyrotron power real-time control system is designed. Through mode switching, the system can realize two real-time control modes of gyrotron power: ECRH local control and EAST center console remote control. The system uses NI CompactRIO and its components as the lower computer hardware platform and LabVIEW as the programming language. The test results show that the control system performances stably and accurately, meeting the requirements of EAST operation experiment for real-time control of gyrotron power. It has important application value for the further research of EAST operation experiment and popularization value for the development of similar control systems.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 123500A (2022) https://doi.org/10.1117/12.2652365
In order to improve the forecast accuracy of daily rainfall, it is convenient for flood control departments to make decisions. Under the condition of abundant meteorological data, a combined BiLSTM precipitation forecast model based on denoising autoencoder is proposed. The combined model is mainly used for training and prediction through noise reduction of input data, feature extraction and distinguishing the importance of meteorological information. The model uses 19 meteorological factors related to daily precipitation (including 20 to 20 hours' cumulative precipitation) as input vector, and the next 24 hours' precipitation as output vector. The results show that the model has the best prediction performance with root mean square error of 13.04 to about 15.18mm in the study area except for the three stations closest to the sea. The three cities closest to the sea in the study area have achieved the best prediction results by using the DBNPF model, and the root mean square error is 17.83 to about 18.95mm. The experimental results show that the combined model proposed in this paper is feasible and provides a new idea for daily rainfall prediction.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 123500B (2022) https://doi.org/10.1117/12.2652760
In order to ensure the system performance while considering the economic utilization of network resources, this paper investigates the problem of the L2-L∞ control for a class of distributed-delay networked control systems (NCSs) with model parameter uncertainty under the event-triggered mechanism (ETM). Firstly, a non-fragile state feedback controller model structure with different time-varying parameter matrices is adopted. Secondly, the time-varying delay information combined with the ETM is considered in stability analysis, based on the delay-dependent Lyapunov-Krasovskii functional and the free weight matrix method, sufficient conditions are obtained to guarantee the robust asymptotic stability and the L2-L∞ performance of the closed-loop system. Then the co-design method of the controller and the ETM is given by using linear matrix inequalities (LMIs). Finally, the feasibility of the co-design scheme is verified by a numerical example and some comparison results. Compared with some existing works, the proposed method leads to larger inter-event transmission intervals, which can save network resources while preserving the desired control performance.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 123500C (2022) https://doi.org/10.1117/12.2653222
The projection synchronization issue of complex Lü chaotic systems is examined in this work. Firstly, the system is presented, the complex chaotic system is transformed into the equivalent real number system, on this basis, the existence of the projection synchronization problem is proved and solution is obtained by an algorithm. Secondly, combines feedback controller and uncertainty and disturbance estimator (UDE), where one is used to implement the projection synchronization of nominal complex chaotic systems and the UDE controller is used to remove uncertainty and disturbance. Finally, the validity of the proposed results is proved by numerical simulation.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 123500D (2022) https://doi.org/10.1117/12.2652692
Aiming at the characteristics of low intelligence, low real-time data acquisition and low accuracy of the traditional plasma ammonia cracker control system, the intelligent real-time data acquisition and control system with CRIO-9047 as the hardware body is designed and realized, and the LabVIEW development environment combined with the PID algorithm is used as the software development environment, with precision and intelligence as the goal. Realize the real-time acquisition of ammonia plasma data in the cracker, and control the reaction conditions that affect the ammonia cracking during the reaction process. The test results show that the use of this system can timely and accurately realize the collection, analysis and precise control of various indicators in the process of ammonia plasma cracking reaction, and increase the corresponding speed, and the current control accuracy can be controlled at 0.5%, which improves the data real-time, intelligent and accurate acquisition.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 123500E (2022) https://doi.org/10.1117/12.2652746
In order to alleviate the traffic congestion of expressway, an on-ramp metering algorithm for urban expressway based on hierarchical fuzzy logic is proposed. The hierarchical fuzzy control algorithm consists of three layers and reduces fuzzy rules effectively. The speed, density of vehicles on the upstream and downstream at the ramp mergence and the ramp queue length are taken as its input variables, and the ramp metering rate deviation is taken as its output variable. VISSIM combined with MATLAB is used to carry out simulation experiment. The proposed hierarchical fuzzy control algorithm is compared with PI-ALINEA and two-input fuzzy control algorithm in the simulation experiment. The experimental results show that the hierarchical fuzzy control algorithm can effectively increase the mainline speed and reduce the queue length of vehicles on the ramp.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 123500F (2022) https://doi.org/10.1117/12.2653170
With the increasing demand for electricity and more stringent requirements for electrical protection and environmental protection, the overall efficiency of coal-fired units needs to be improved rapidly. The pan optimization technology can be divided into two parts: the establishment of an accurate pan prediction model and the multi-objective optimization method. According to the speed and accuracy of data modeling and optimization method results, and based on the prepared samples, the design of the CSVR (Constraint Support Vector Regression) algorithm for high NO2 emission atomization and NO2 extraction efficiency optimization can obtain the optimal solution. The experimental method is mainly to preprocess the input data, then model and set the parameters. Finally, the CSVR algorithm is compared with the LSSVR algorithm, and it is concluded that the CSVR algorithm has the highest modeling accuracy, and at the same time, it can further improve the efficiency of boiler combustion. But the CSVR algorithm can extract as many possible solutions as possible in one operation. It can reflect the different changes of the same degradation corresponding to the difference of NOx observed after optimization, and provide different optimization references for operators.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 123500G (2022) https://doi.org/10.1117/12.2653191
This paper mainly studies the partial anti-synchronization of laser hyperchaos system. First, transform complex systems into real systems. Secondly, in order to realize the full synchronization and partial anti synchronization of the system, the dynamic gain feedback control method and the dynamic feedback method based on uncertainty and disturbance estimator (UDE) are used to design simple and physically feasible controllers respectively. Finally, through MATLAB numerical simulation, it is proved that the error system is asymptotically stable, and the master-slave system realizes partial anti synchronization.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 123500H (2022) https://doi.org/10.1117/12.2652854
With the development of new energy vehicles, the demand for auto parts is also rising. It is difficult to design the control strategy of EPS system because of multiple control objectives. In this study, a control strategy is introduced which is based on the super twisting algorithm. The control objectives are to provide ideal assist torque, respond quickly and return road information. The EPS dynamic analysis and built model in order to generate the desired motor angle. In order to achieve control objectives, the controller based on super-twisting algorithm is designed. To estimate the EPS system state and unknow inputs, the observer with unknow input is employed. Auxiliary outputs are constructed because the EPS system is not satisfied the observer-matching condition. Using of the second order SM differentiators estimate the auxiliary outputs. Finally, the performance of the controller, observer and differentiator is verified by simulation, and the controller can provide expected the assist torque. The result of simulation show that the control strategy is effectiveness and robustness.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Mingduan Zhou, Jiayi Shi, Zhongzheng Wang, Xu Ji, Yuelan Li
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 123500I (2022) https://doi.org/10.1117/12.2652867
The amount of engineering volume estimation is crucial for cost decision of regulation consumption project of construction and demolition waste. In view of the fact that the traditional tool software because of the disadvantage of algorithm model encapsulation, it is difficult to meet the data analysis requirements for regulation consumption project of construction and demolition waste, the algorithm model for regulation consumption project of construction and demolition waste is proposed based on the depth analysis of convex hull polygon generation algorithm, D-TIN model construction algorithm and triangle volume estimation algorithm, and the analysis software named as CWVMS for regulation consumption project of consumption and demolition waste is designed and developed via c# programming language based on the development platform of visual studio 2015. Through the calculation and analysis of engineering example, the correctness of function module design of the CVWMS software is verified, and the proposed algorithm model is effective. The digitization data analysis tool of the volume estimation for regulation consumption project of construction and demolition waste is provided in this paper.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 123500J (2022) https://doi.org/10.1117/12.2652887
The detection collaborative of self-propelled anti-aircraft combat vehicles effectively solves the problem that the combat vehicle cannot complete the combat function in the absence of key information, and improves the combat effectiveness of the combat vehicle. To ensure the availability of detection collaborative, spatio-temporal alignment of target information shared between combat vehicles is required. The transmission error of the target information obtained by the master vehicle during spatial alignment is affected by the relative position and vehicle attitude between the master and slave vehicles. In order to correct the transmission error and improve the accuracy of spatial alignment, this paper proposes an improved decorrelated unbiased converted measurement Kalman filtering algorithm based on BP neural network correction. The algorithm uses the untraced transform to calculate the statistics of one-step predicted values on the coordinate system that establishes the measurement equation, and uses singular value decomposition to solve the problem that the untraced transform is prone to crash in practical applications. After that, the parameters that affect the filtering accuracy are used as inputs, and the difference between the filtered state estimate and the true value of the state is used as the desired output to train the neural network. Use the trained neural network to correct the filtering results. The simulation results show the effectiveness of the method.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 123500K (2022) https://doi.org/10.1117/12.2653934
In this paper, based on the discussion of the multi-layer composite insulation structure and interface in the dry glue impregnated paper sleeve, the expressions of interface charge and field strength in the double-layer composite medium are deduced by using Maxwell equation and corresponding boundary conditions. The three-layer composite medium is discussed by expanding the formula system. The theoretical calculation results show that there is interaction between three-layer composite media, and the distortion of space charge and electric field is much larger than that in double-layer composite media. Further, the allowable field strength of the outgoing line device at the tail of the converter transformer under various operating conditions is analyzed, the finite element simulation calculation model of the typical outgoing line structure is established, the transient potential and electric field distribution characteristics of the outgoing line device are discussed under various voltage types such as polarity reversal, and the insulation margin value of the critical path is obtained by combining the allowable field strength. The allowable field strength and insulation structure design of outgoing line device are proposed, which can provide reference for the design of outgoing line structure of converter transformer.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 123500L (2022) https://doi.org/10.1117/12.2653074
Warehouse activity is the intermediate link between supply and consumption, which can buffer and balance the contradiction between supply and demand. The right choice of warehouse location can reduce transportation costs and improve service quality fundamentally. In this paper, the analytic hierarchy process (AHP) and fuzzy comprehensive evaluation method are combined to construct an evaluation model. Taking two alternative warehouses in the urban area as examples, the analysis of site selection and fuzzy evaluation are completed, so as to determine the best site selection in order to provide a favorable decision for the reasonable choice of managers.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 123500M (2022) https://doi.org/10.1117/12.2652688
With the emergence and application of various unmanned platforms, standardized navigation technology has become a new hot spot. Aiming at the standardization of the navigation system of unmanned platforms working in different environments, a multi-sensor integrated navigation system based on Mission Oriented Operating Suite (MOOS) architecture is proposed. A modular hardware circuit and a distributed software solution are designed and implemented. On this basis, an integrated navigation algorithm based on compass, Doppler Velocity Log (DVL) and Ultra-Short Baseline (USBL) is designed. The test of underwater integrated navigation carried out by the experimental vehicle shows that the hardware and software of the integrated navigation system can operate stably, and the functions of multi-sensor integrated navigation can be realized with high positioning accuracy.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 123500N (2022) https://doi.org/10.1117/12.2652801
This paper aims to provide a global sliding mode control (GSMC) method using nonlinear extended state observer (NESO) for thermal-structure test (TST). Firstly, the designed control method adopts NESO to observe the internal and external disturbances of the system. Then, the nonlinear global sliding mode surface is constructed to improve control accuracy, speed up convergence and reduce the chattering phenomenon. Finally, the effectiveness and superiority of the proposed method compared with existing control methods are verified by comparison of simulation and experimental results.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 123500O (2022) https://doi.org/10.1117/12.2653203
This paper introduces the working principle of the underwater spherical detection robot BYSQ-3. Through the known kinematics and dynamic models of the underwater spherical robot, using the combination of dynamic feedback gain control and UDE control, several designs are designed. The simple physical controller realizes the stabilization control of the system, and ensures that the whole system can achieve global asymptotic stability quickly. It is simpler and simpler than the traditional nonlinear control method, and the simulation results show that the correctness and effectiveness of the theory are verified.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 123500P (2022) https://doi.org/10.1117/12.2653927
A heat-resistant probe humidity sensor based on tunable diode laser absorption spectroscopy is designed and studied, which is equipped with heat-resistant probe, infrared laser, gas cell, detector, temperature and pressure sensor and circuit board. The diffusion part of the probe is 3cm, and the actual length of the optical path is 6cm. An absorption line of H2O near 1368.6nm in the v2+v3 band is selected by the sensor as the targeted line, and combined with the techniques of software lock-in amplification and Savitzky-Golay filtering, it achieved a rapid and accurate measurement of high temperature and humidity environment. The characteristics of the sensor under variable temperature and pressure and measurement index are studied experimentally on a experimental platform of humidity detection with controllable temperature and pressure. The results show that with the increase of temperature, signal intensity decreases gradually, and as pressure increase, the line broadening gradually widens. The measurement accuracy of sensor is RH⪅0.5% at high temperature. It can be found out that our sensor can meet the requirement of humidity detection in high temperature drying process. In contrast to the traditional humidity detection methods, this sensor has the advantages of fast measurement speed, high accuracy, fast response time and not susceptible to fluctuations in air flow, which can be a promising technical means for the development of related industries.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 123500Q (2022) https://doi.org/10.1117/12.2652922
Aiming at the problem that the vibration signal of the ball mill is non-linear and non-stationary, which makes the load state difficult to identify, this paper proposes a method combining FastICA and wavelet packet to detect the load state of the ball mill. First, use the FastICA algorithm to denoise the collected original vibration signal; then use the demy wavelet basis function to perform wavelet packet energy spectrum analysis on the denoised vibration signal to obtain the vibration signal of each frequency band, and calculate each frequency band to the energy ratio of the internal vibration signal. By analyzing the vibration signals of the ball mill under different load conditions, the most sensitive characteristic frequency band with the change of the mill load is obtained. Finally, in the characteristic frequency band, the relationship model between energy and mill load is established to achieve the purpose of mill load detection. The experimental results show that the energy proportions of the characteristic frequency bands between the three load states of the ball machine are very different, which can well identify the load state of the ball mill and has practical application value.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Hongwei Zhang, Jiafang Shan, Liang Zhu, Wendong Ma
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 123500R (2022) https://doi.org/10.1117/12.2652712
This paper takes 2450MHz/1KW solid-state source as the control object, and designs a control system with STM32F103 as the control core. On the basis of analyzing the system requirements and main functions, the design of the hardware circuit and software flow is explained, and the test and result analysis are carried out. The system uses ADC to sample the analog signal and cooperates with DMA to detect the power and temperature of the solid-state source, which realizes the function of real-time monitoring. Use the buzzer and quick switch to realize the protection function of the system when the power and temperature are too high. Using the single-chip microcomputer to control the operating frequency of the fast switch, two working modes of steady state and pulse are realized. Use the voltage-power fitting function and the PID control algorithm to realize the control function of the power output. Experiments show that this design meets the requirements of a 2450MHz/1KW solid-state source control system, with high control accuracy and practical value.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 123500S (2022) https://doi.org/10.1117/12.2653508
Stranded conductor is widely used in the transmission line, and corona of stranded conductor is one of key problems in the operation of transmission line, so the research on the surface electric field distribution and corona onset voltage of stranded conductors provides theoretical basis in the design of transmission lines. In the paper, a calculation method of surface electric field distribution and corona onset voltage of stranded conductors using corona onset criterion and FEM was proposed. The simulation calculation results indicate the corona onset voltage increases with the increase of the overall conductor radius and the number of external strands as expected, and tends to be saturated. Besides, the relation between surface roughness coefficient and the overall conductor radius, including the number of external strands was analyzed, and the efficiency of the calculation method proposed was proved based on the informed experimental data.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 123500T (2022) https://doi.org/10.1117/12.2653917
In this paper, for the core material of the UHVDC converter bushing, its electrical performance parameters and thermal performance parameters are coupled and correlated with each other. How to take into account the interaction between them, the quantitative relationship between the temperature distribution of casing core and the electric field distribution with the current carrying capacity is obtained through the analytical theoretical formula: under the current carrying capacity of 3kA, 4kA and 5kA respectively, radial electric field distribution of casing core has the reversal effect. By changing the structural size of the bushing core, the characteristics of internal unequal temperature and equal radial electric field distribution can be realized. The proposed electro-thermal coupling theory, finite element model, electro-thermal decoupling calculation method and core optimization design process can provide reference for the development of high voltage dry direct current bushing.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 123500U (2022) https://doi.org/10.1117/12.2653425
With the development of economy and society, the competition among companies is becoming more and more fierce. In order to effectively protect the interests of enterprises and investors, it is particularly important to predict the financial distress of companies. There are many ways to complete a financial distress prediction, e.g. logistic regression, K-Nearest Neighbor, random forest etc. But it is a little hard to know which algorithm is the most suitable in this task. This paper will consider this issue by using eight algorithms consisting of four single algorithms and four ensemble learning algorithms. During the research, this paper has collected more than 3,800 pieces of data from 95 Chinese real estate listed companies. Four indicators namely Accuracy, Precision, Recall, F1-score was employed to evaluate the performance of different algorithms. The results show that the accuracy of the Random Forest algorithm is as high as 90%, which is the highest of these eight algorithms.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 123500V (2022) https://doi.org/10.1117/12.2653307
Hypersonic vehicles pose a serious challenge to the existing defense systems due to the fast flight velocity, long flight distance, strong lateral maneuverability. Concerning the problem of accurately intercepting hypersonic vehicles, the present study investigates the hypersonic vehicle interception problem under a small velocity ratio of the missile and the target based on the nonlinear differential game theory. In this case, the interception problem is transformed into the solution of the state-dependent coefficient (SDC) and the algebraic Riccati equation. Moreover, it also provides the analytical form of the differential game guidance law by adopting the State-dependent Riccati Equation (SDRE) method, which does not need to calculate the remaining flying time of the missile. Based on the simulation results, the interception performance of the recommended differential game guidance law can be better than that of the proportional navigation guidance (PNG) together with the adaptive sliding mode guidance (ASMG) laws.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 123500W (2022) https://doi.org/10.1117/12.2652499
Employment has an important impact on the social development needs and economic development needs of the country. It is also the fundamental demand for people’s increasingly better life and the basic premise and important way to improve people 's lives. In order to understand the current employment form in China, the time series analysis method is used to predict the number of new employment and re-employment in China. According to the number of new employment and re-employment in cities and towns from the first quarter of 2013 to the fourth quarter of 2021, the number of new employment and re-employment in cities and towns in the first quarter of 2022 is predicted, and the combined prediction model of seasonal time series model and dynamic regression model is constructed. From the prediction results, most of the combined prediction accuracy is concentrated in less than 3%. Compared with the single prediction model, the prediction accuracy has been significantly improved. The number of predicted people is 237.7535 million, and the prediction results are credible. It can provide valuable reference for the problems existing in the employment situation.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 123500X (2022) https://doi.org/10.1117/12.2652533
The classification of cotton aphid disease severity is conducive to the accurate control of cotton aphids. Because the cotton aphid images taken in the natural environment have some problems, such as complex background, different lighting conditions and difficult to distinguish between different grades, the existing convolutional neural networks do not have high accuracy in the classification of cotton aphid grades in the natural scene images. This study proposes an improved DenseNet classification network, CA_DenseNet_BC_100. It is used to classify the severity of cotton aphids in natural scene images. CA_DenseNet_BC_100 network inherits the advantages of DenseNet_BC_100 network design and applies a novel attention coordination module. The experimental results show that the classification accuracy of CA_DenseNet_BC_100 network for the severity of cotton aphids in natural scene images is better than that of a series of existing networks such as resnet50, ShuffleNetv2, GhostNet, MobileNetv3 and DenseNet.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 123500Y (2022) https://doi.org/10.1117/12.2653546
Natural Language Processing (NLP) is a science that integrates computer knowledge, mathematical knowledge and linguistic knowledge, and text classification and recognition is considered to be an important research field and direction of natural language processing. This paper mainly studies the realization of text classification model through the processing method of text data in natural language processing and the theoretical knowledge and technical means of machine learning. We summarize the existing text classification algorithms, analyze their applicable scenarios, and optimize on the basis of these algorithm models. The paper proposes a Chinese text classification algorithm based on weight preprocessing. Algorithm based on the weight preprocessing link, so that the optimized classifier model can improve the accuracy of the existing text classifier. In this paper, the English Newsgroups corpus is used for experimental verification. The experimental results show that the classification accuracy and accuracy of the improved algorithm are better than those of the traditional text classification algorithm, thereby improving the accuracy of English text classification.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 123500Z (2022) https://doi.org/10.1117/12.2653894
At present, there are few personalized information recommendation services in online education platforms. The resources received by users are basically the same, and there is no personalized recommendation based on user preferences. How to accurately locate relevant resources from massive resources according to the needs of learners, and provide personalized online education services for them, has become a current research hotspot. Although the research on recommendation algorithms in other fields has achieved good results, there are relatively few applications of online course resource recommendation systems. This paper improves the collaborative filtering recommendation algorithm. On the basis of the traditional algorithm, the dual-attribute scoring matrix is used for attribute division and the BP neural network is used for scoring prediction. This improvement is to fill the scoring matrix and solve the problem of the recommendation quality degradation caused by "cold start" and too sparse scoring data in traditional algorithms. Finally, the effectiveness of the improved algorithm is proved by experiments.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 1235010 (2022) https://doi.org/10.1117/12.2653363
With the rapid development of the new era, the market competition is showing an increasingly fierce trend. In order to survive and develop in the competition, enterprises need to formulate optimal ordering and transshipment strategies. This paper studies the problem that a production enterprise determines the raw material suppliers to be ordered and the corresponding weekly raw material order quantity according to the production capacity requirements, and entrusts a logistics company to transfer the supplier's weekly raw material supply quantity to the enterprise warehouse. The optimal proportion scheme is determined by flexible use of parameter estimation method, and MATLAB software is used to perform image analysis on the order relationship of raw materials and the loss rate of forwarders, so as to reasonably allocate the demand for suppliers and forwarders. Then the heuristic optimization algorithm is used to solve the corresponding optimal model, and under certain constraints, the rational allocation of resources in all aspects is guaranteed. Develop optimal solutions to minimize uncertainty, reduce production costs, and help companies enhance their core market competitiveness.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Algorithm Model and Analysis of Electromechanical Fault Monitoring
Yao Kang, Mingxiang Shi, Lingling Zhao, Sijie Zhang
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 1235011 (2022) https://doi.org/10.1117/12.2653339
With increasing growth of the Internet and rapid development of search engine technology, people can transmit or acquire all kinds of information that happens all the time on a variety of social media and network platforms. The network information management departments of local governments attach great importance to these online public opinions which have a certain impact on the society. The crawling of network public opinion information in Shunyi District of Beijing from Weibo is taken as an example and analyzed in this Paper for final focuses on livelihood concerns and providing reference for the situation awareness of public opinion in Shunyi District by clustering analysis on public opinion with the LDA text clustering algorithm and determination of topic characteristics of each category of public opinions.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 1235012 (2022) https://doi.org/10.1117/12.2653657
With the spread of the new crown epidemic and the increasing number of confirmed cases, wearing correct masks is an effective means of keeping the virus at bay. Using artificial intelligence technology to determine whether masks are being worn correctly is a possible solution. By training and learning from a certain amount of image data, target detection of masks can be achieved. RCNN or FAST-RCNN is widely used in the related field of research, although the method has good accuracy and robustness. However, there are some disadvantages such as low efficiency and long training time. In addition to this, most of the current work only stops detecting whether or not a mask is worn, but does not consider whether or not the mask is worn correctly. Therefore, this paper proposes a mask detection model based on the YOLO v5 algorithm, which uses a self-made training set to detect whether a pedestrian is wearing a mask and whether he or she is wearing it correctly. The experimental validation shows that the detection accuracy is higher, and the robustness is almost the same based on the original data set, while the practicality is greatly improved.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Sheng He, Shaohua Yue, Gang Wang, Wei Liu, Siyuan Wang, Jiayi Liu
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 1235013 (2022) https://doi.org/10.1117/12.2653305
This paper briefly analyzed the operational background and characteristics of regional joint air defense, summarized the requirements of mission planning for regional joint air defense operations, and pointed out the deficiencies of current research. Finally, it is suggested that the command level should be adjusted, the charging mode should be optimized, the target allocation model and solving algorithm should be improved, and the evaluation system of joint air defense operation should be improved in the future development of joint air defense operation.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 1235014 (2022) https://doi.org/10.1117/12.2652852
Accurate anomaly detection of remote maintenance control system of natural gas pipeline is of great significance in ensuring the safe and stable operation of gas pipeline network. A supervised anomaly detection method based on k-nearest neighbors searching and clustering is proposed. Firstly, the labels of neighbor samples are used to determine whether the sample is noise or belongs to an anomaly cluster, and the iterative search is conducted in the neighbor samples until no more abnormal samples belonging to this cluster are found. Then, the noise samples are filtered and the numbers of new abnormal samples to be generated in each cluster are calculated. Finally, SMOTE is used to generate the artificial samples in each cluster to balance the data. The experiment results on public datasets and the remote maintenance control system monitoring dataset show that the proposed method outperforms the compared methods in terms of F-measure and G-mean.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 1235015 (2022) https://doi.org/10.1117/12.2652406
In derive analytical formula of the critical stable sectional area of surge tank, toma stable formula, E/N correction formula ignores the influence of the inertial time constant of flow. Considering the inertia of flow, this paper established a hydroelectric generating set with surge of five order analytical model, then using the model, analysis the inertia of flow and the relationship between the critical stable sectional area of surge tank, finally combining with typical hydropower station on the head and flow rate, the sensitivity analysis of channel length.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 1235016 (2022) https://doi.org/10.1117/12.2652518
The kinematic behavior of the collision between the flying gauge and the bottom plate, existing in steep seam mining on longwall mining working face, is improved, and the flying gauge applied in steep seam mining on longwall mining working face, is studied. Based on non-probability interval analysis, which is convenient and practical in uncertain measurement, the motion model of flying gangue is established under uncertain environment. With theoretical analysis and numerical simulation, the kinematic characteristics of a flying gangue in steep seam mining on longwall mining working face, is investigated, and the kinematic mechanism of flying gangue is demonstrated. The accurate estimations of the kinematic motion and energy of a flying gangue, will improve both the flying gauge control in steep seam mining on long wall mining working face and the safe mining in steep seam.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 1235017 (2022) https://doi.org/10.1117/12.2653208
At present, engineering education emphasizes the development of students' skills and the cultivation of their professional quality. The society has a high demand for students' technical ability and professional quality, but there are many problems in the process of practical teaching. Faced with the demand of the current software development employment market, many colleges and universities regard Java-related courses as the core curriculum system of computer specialty. The system has many contents and strong relevance. If there is no comprehensive teaching design and reasonable practice cases, we can not really achieve the goal of training applied talents. Due to the complexity of Java course group, it is difficult for students to really understand it. To improve the teaching effect of the course, the construction and practice method of Java course group based on EIP-CDIO mode is studied. The basic information of students is collected and recorded in the teaching system in the form of data. The construction and practice of Java course group are carried out, and the effect of construction and practice is comprehensively analyzed. The final results of Java class (1) and class (2) are compared to further determine the effect of construction and practice of Java course group. The results show that the academic performance of students in Class 1 is significantly higher than that in Class 2, and the construction and practice of Java course group is better. It shows that under the EIP-CDIO mode, the construction and practice of Java course group has achieved remarkable results, which is of great significance to the development of software development.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 1235018 (2022) https://doi.org/10.1117/12.2652716
The parameterization of airfoil geometry has a profound influence on optimization results and calculation efficiency. A good parametric method should have a large optimization space, good local control ability, fewer design variables, and at the same time ensure the requirements of geometric shape smoothness in the optimization process. The class and Shape Transformation method proposed by Kulfan has been widely used for its excellent robustness and smooth geometric description ability. This method can ensure that the leading edge radii of the upper and lower airfoil surfaces are equal. In this paper, NACA0012 and RAE2822 airfoil are fitted with different order shape functions. An application was carried out to generate a new airfoil mesh based on an existing mesh and a new airfoil using CST method and dynamic mesh technology.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 1235019 (2022) https://doi.org/10.1117/12.2652782
Aiming at the PM2.5 concentration in the air, which is affected by meteorological factors and atmospheric pollutants, and has the characteristics of nonlinearity and uncertainty, a prediction method of LMBP neural network based on Harris Hawk optimization algorithm is proposed. In the process of LMBP neural network weight threshold optimization process, Harris Hawk optimization algorithm (HHO) is introduced, and a LMBP initial weights and thresholds optimization method based on HHO algorithm is designed. This method utilizes the global optimization ability of HHO algorithm and effectively avoids the LMBP neural network is trapped in a local minimum worth of possibilities. The simulation results show that the prediction model based on the HHO-LMBP algorithm has higher accuracy and better stability than the DELMBP and LMBP algorithms.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 123501A (2022) https://doi.org/10.1117/12.2653255
In the big data environment, network security problems emerge in endlessly. If using traditional methods to predict the risk of the network security situation, network security situational awareness methods have the problems of inaccurate risk assessment and misjudgment of the risk level. Therefore, this paper proposes research on network security situations based on a big data environment. In the context of a big data environment, this paper constructs a network security situation assessment system and determines the membership degree of risk indicators according to the index assessment system. It also calculates the risk value of the security situation to clarify the risk level of network security situation, and to compare the security situation prediction method designed in this paper with the traditional prediction method through experimental demonstration. The results show that, compared with the traditional method, the results of the network security situation assessment of the prediction method designed in this paper are consistent with the actual security situation risk value of the network system. There is almost no error, which proves that the new method designed in this paper has higher prediction accuracy and is more efficient and reliable for the assessment of network security situation.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Zongrong Li, Denghui Ma, Ning Zhang, Nanfang Li, Xiang Li, Haishan Cao
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 123501B (2022) https://doi.org/10.1117/12.2653205
At present, the existing anomaly traffic detection methods rely on the statistical characteristics of traffic for detection, which can not adapt to the unknown nature of network traffic, resulting in low detection accuracy, high false detection rate, and poor generalization ability of the methods. This paper studies the anomaly traffic detection method of a convolutional neural network based on the Dynamic Adaptive Pooling Algorithm (DAPA). The DAPA algorithm is used to improve the pooling layer of the CNN network to reduce the overfitting interference of unknown features; after the t-SNE algorithm reduces the dimensionality of the data, using clustering to transform the data feature map to get anomaly identification output. The experimental results show that the false detection rate is reduced by about 37.46%. The actual detection results are close to the prediction results, and the method has better generalization ability.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 123501C (2022) https://doi.org/10.1117/12.2653230
This paper takes virtual reality technology (VR) as the core, combines 3D digital modeling technology and Web3D technology, and aims to realize the innovative integration of virtual simulation technology with experimental or practical teaching in colleges and universities, and form a virtual simulation experiment system. This system focuses on the shortcomings of practical teaching courses of air conditioning system selection and duct design, and puts forward comprehensive application solutions. Under the environment of ASP.NET, the system is designed and developed in the form of Web application, Innovative online education and virtual simulation experiment teaching method are introduced into the teaching activities of air-conditioning pipe network, and many functional modules such as theoretical study, simulation experiment, summary report, interactive question and answer are used to meet the actual needs of students and teachers. While making up for the deficiency of practical teaching in the current teaching mode, the system can strengthen students' ability to integrate theory with practice and promote their all-round development into high-quality qualified talents. In addition, the full implementation and application of the system will also effectively promote the information reform of higher education, and also make a beneficial attempt for the discipline construction under the new engineering background.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 123501D (2022) https://doi.org/10.1117/12.2653223
The construction of colleges and universities needs a set of scientific and reasonable performance appraisal schemes that can promote personnel training. In the field of education, the performance appraisal system is not yet mature, and the performance appraisal of colleges and universities needs to be further studied and improved. In this paper, the integer coding method is used to establish a suitable mapping relationship between the position of particles in the search space and the solution to the environmental economic scheduling problem. An effective constraint handling method for equality constraints is used to quickly adjust the infeasible solution of the environmental and economic dispatch problem. The fuzzy set theory is introduced to extract the compromise solution of the environmental economic dispatch problem. Through the simulation comparison with other algorithms, the effectiveness of the proposed algorithm in solving the EED problem is verified. The research results of this paper can achieve a scientific and reasonable performance appraisal. In the actual implementation, it can stimulate the maximum potential and value of teachers, and ultimately promote the realization of school organizational goals.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Yuxiang Zhang, Jiujiang Han, Jian Liu, Ming Xian, Huimei Wang, Yu Chen, Renfei Zhang, Lei Zhang
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 123501E (2022) https://doi.org/10.1117/12.2652770
With the rapid development of virtualization, cloud computing and other technologies, and their gradual application in various industries, how to use the cloud computing infrastructure well and make the cloud computing play the maximum capacity is an important issue in cloud computing technology. In this context, the concept of "cloud-native" was born. With the development of cloud-native technology, its related research has gradually become a field of concern and research for scholars, but there is still a lack of research on the development trend of cloud-native technology. Therefore, in this paper, 904 high-quality papers were downloaded from web of science and correlation analysis was conducted by Citespace and VOSviewer with the help of bibliometric research methods, including literature quantity analysis, co-citation analysis, keyword co-occurrence analysis and research hotspot analysis.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 123501F (2022) https://doi.org/10.1117/12.2652781
Spiking neural networks (SNNs) has made great achievements in pattern recognition. Among the existing SNNs, unsupervised SNNs, especially those using spike-time-dependent plasticity (STDP), have a biological mechanism more in line with human brain cognition and are considered to have great potential in simulating the learning process of the biological brain. However, most of the existing SNNs based on STDP will be directly or indirectly used in the full connection layer, which leads to large computational overhead and over-training of the network. On the basis of predecessors, this paper uses the concurrent sparse spike neural network and achieves very good recognition accuracy when the number of synapses is reduced by nearly 1/10.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 123501G (2022) https://doi.org/10.1117/12.2653174
In this paper, taking the conveying equipment as the research object, aiming at the main characteristics and intelligent requirements of the current dry bulk terminal conveying system, a monitoring and diagnosis model of the dry bulk terminal conveying equipment based on the edge-cloud collaborative technology is proposed. The technical advantages of the company can jointly realize the tasks of perception, integration, monitoring and diagnosis of the conveying equipment, improve the monitoring and diagnosis function of the conveying equipment in the dry bulk terminal, and improve the safety supervision ability of the dry bulk terminal.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 123501H (2022) https://doi.org/10.1117/12.2652509
In order to reduce the aggregation of personnel and realize the intelligent prevention and control of campus epidemics, a campus epidemic monitoring system based on the Internet of Things has been designed and implemented, including a population flow data acquisition module, a network epidemic data acquisition module, and a campus Internet of Things and data visualization module, which can quickly establish the Internet of Things platform and realize the synchronous monitoring of local and cloud data. The system uses the STM32F429 as the main control chip, with the HC-SR501 human infrared sensing module and the LoRa node module. The bidirectional detection algorithm is used to collect real-time human flow data throughout the campus, and the Python network crawler is used to obtain real-time network epidemic data. The campus Internet of Things, based on LoRa wireless communication technology, is built to achieve data transmission with network servers. For the data obtained through the software driver cleaning and stored in the database for human-computer interaction interface calls. After testing the system function, the results show that the data collected by the front end can be displayed on the LCD terminal and the cloud HTML terminal. The collected data can be intuitively displayed on the terminal interface through the Internet of Things transmission, which provides effective human flow data and epidemic data for campus teachers and students.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 123501I (2022) https://doi.org/10.1117/12.2652522
In real scenarios, cryptanalysts can only obtain ciphertext of unknown cryptographic algorithms to conduct ciphertext only attacks. Cryptosystem identification is a prerequisite for further cryptanalysis. This paper proposes a new method of division for ciphertext sequence based on the four widely used cryptographic algorithms DES, 3DES, AES, and Blowfish, which have high security. We redesigned the ciphertext features using five detection methods in the NIST randomness test standard. In the case of using two working modes (ECB and CBC) of block ciphers, the proposed method in this paper obtains lower feature dimensionality and higher final recognition accuracy compared to some previous research works. This study has certain reference significance for the fast and accurate identification of large volume of ciphertext.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 123501J (2022) https://doi.org/10.1117/12.2653175
The coordinated development of regional economy is an important concept in the transitional period of my country's economic development. It is necessary to strengthen coordination and cooperation between regions to jointly promote regional economic growth and stability, mutual benefit and mutual benefit of various regions, and realize a development model of healthy and sustainable regional development. This article aims to study the construction of a research platform for the collaborative development of regional industries based on neural networks. Based on the analysis of the characteristics of the collaborative development of regional industries and the evaluation criteria of industrial synergy, a certain domestic economic circle is the research object, and the industrial synergy of this economic circle The degree evaluation index system was constructed, and the regional industrial synergy evaluation model was constructed through the neural network method, and finally the industrial synergy degree was measured. The calculation results show that the orderly development of the three sub-systems should be based on the self-coordinated development of the internal system, and the development gap between the order parameters should not be too large. It is necessary to seize the advantages of development and to develop in a stable and balanced manner.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 123501K (2022) https://doi.org/10.1117/12.2652834
Electronic reconnaissance system has complex structure, high research cost and long research cycle, so it needs to rely on realistic and practical simulation system to help test and evaluate. The functional level simulation system relies on the artificial setting of parameters, which can not reflect the whole signal processing. The signal level simulation system can truly reflect details of the whole process of generation, transmission and processing of zero intermediate frequency signal in the system. It is rich in detail information, but has the prominent problems of slow simulation speed and large memory consumption. Therefore, the signal level simulation has high requirements for computer performance, which is difficult for ordinary computers to meet. To address the problems of insufficient details of functional level simulation and high computer performance requirements of signal level simulation in large-scale simulation scenarios, this paper designs a hybrid simulation scheme for electronic reconnaissance systems by integrating functional-level simulation and signal-level simulation. By comparing, selecting and correlating multiple granularity simulation models, a hybrid electronic reconnaissance simulation system was finally built to achieve a balance between simulation speed and simulation fidelity.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 123501L (2022) https://doi.org/10.1117/12.2652505
In the automatic unpacking control system, the control accuracy of the flipping speed of the flipping platform is of great significance to the dumping effect and the service life of the equipment. This paper conducts research based on this. Aiming at the fact that the standard extreme learning machine (ELM) is prone to fall into local optimum, this paper proposes a model for extreme learning machine (ASSA-ELM) optimization based on improved salp swarm optimization algorithm is proposed and applied to an example of flipping speed prediction of flipping platform. Based on the salp group optimization algorithm (SSA), a position update strategy combining the adaptive weight method and the proportional weight of the improved step size Euclidean distance is introduced. The weights and hidden layer biases are optimized, which greatly improves the generalization ability of the ELM model and the accuracy of the predicted value. The algorithm models before and after the improvement are compared and analyzed. The results show that the predicted value of the ASSA-ELM model has the highest fitting degree with the actual value collected in the industrial field, and has a high prediction accuracy, which verifies the feasibility and effectiveness of the ASSA-ELM model in the prediction of the turning speed of the turning platform.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Keyu Wang, Wei Liu, Qun Gao, Manyu Zhao, Quanyi Li
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 123501M (2022) https://doi.org/10.1117/12.2652728
To obtain the quality of water more economically and flexibly, it improves the traditional node optimization layout method — dynamic proximity degree method from the perspective of unmanned ship. Based on considering the data correlation and time factors of the monitoring nodes, and considering the influence of the relative position relationship between the nodes on the length of the inspection path, a simple and efficient genetic algorithm is designed to further optimize the node selection with a faster convergence speed. The water quality monitoring experiment of lake in the university was carried out by an unmanned surface vehicle and MATLAB platform. The results show that the improved dynamic proximity algorithm retains the representativeness of the nodes to the water quality and greatly shorts the cruise path of the ship. In the optimization experiment of 14 nodes, compared with the traditional node selection method, the path length is shortened by 14.85% on average.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 123501N (2022) https://doi.org/10.1117/12.2652486
Aiming at the technical problems of intelligent recognition and accurate positioning of steel rolling surface defects, a target detection method based on machine vision and depth neural network was proposed. YOLOX_M was introduced as the model of surface defect detection using the weights trained on the COCO dataset as the initial weights. To realize the identification and location of surface defect categories of rolled steel, the YOLOX_M model was further trained using the practical dataset. The performance of YOLOX_M was compared with the other five YOLOX models. The test results show that YOLOX_M can effectively detect six different forms of surface defects, and the test accuracy (P), recall rate (R) and detection mAP can respectively reach 88.81%, 80.88% and 90.12%. The mAP of the YOLOX_M model is higher than 90% and the model size is less than 100 MB, so it can be better applied in the embedded system for real-time detection.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 123501O (2022) https://doi.org/10.1117/12.2652837
In the field of artificial intelligence and machine learning, only when enterprises obtain a large amount of data can they train enough reliable models [1]. How to obtain massive data at a low cost has become one of the key prerequisites for the success of data intelligence enterprises. Mastering a large amount of data is an important prerequisite for gaining competitive advantage [2]. There is a cognitive trend among enterprises with massive data. If the massive data as their advantages are collected by peers, their advantages will be weakened or even lost. Therefore, more and more massive data owners adopt various mechanisms to protect their public data in network applications and avoid data being crawled by crawlers [3]. From the perspective of data collectors, this paper introduces some common anti crawling mechanisms in details based on the Scrapy framework and the recruitment website of a well-known internet enterprise, and then gives some techniques to circumvent the above crawling mechanism. Finally, it successfully crawls all the job information on the recruitment website of the enterprise. The experimental results show that the techniques provided by the paper can effectively bypass the anti-crawling mechanism of some large websites, so as to help collectors obtain massive data.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 123501P (2022) https://doi.org/10.1117/12.2653182
Aiming at the problem of poor real-time monitoring performance of the Internet of Things (IoT) card, an online automatic monitoring method based on the optimized time series is designed. Based on the concept of time series, the automatic monitoring function of the life cycle of the Internet of Things card is deduced. On the basis of this function, the online process automatic monitoring model is constructed to shorten the time of data transmission in the monitoring process, to realize the online process real-time monitoring of the life cycle of the Internet of Things card. In this paper, the performance of the design method is analyzed by means of comparative experiments. The data transmission time of this automatic monitoring method is all below 0.40ms, and the transmission time of business statistical analysis is the highest, and reached 2.7ms. Therefore, the method effectively reduces the transmission time of monitoring process data and improves the monitoring efficiency.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 123501Q (2022) https://doi.org/10.1117/12.2652492
Aiming at the problem of low recognition accuracy of maneuvering trajectories, this paper constructs a relatively complete maneuvering unit library by analyzing the characteristics of maneuvering trajectory, and expresses complex trajectories with simple units; Combine the coyote optimization algorithm(COA) with the Least Squares Support Vector Machine (LSSVM) classifier, and use the COA algorithm to adaptively adjust the width factor and the penalty factor δ of the kernel function in the LSSVM according to the error; Five classification algorithms, LSSVM, SSA-LSSVM, HHO-LSSVM, AOA-LSSVM, and AEO-LSSVM are selected for comparative experiments. The results show that the method proposed in this paper has higher accuracy in maneuvering trajectory recognition.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Fang Qin, Lin Li, Weijia Zeng, Tao Wang, Lijuan Wang
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 123501R (2022) https://doi.org/10.1117/12.2653260
With the rapid development of the Internet, the way of education is gradually tending to the network platform, so the intelligent education platform plays an extremely important role in the diversified way of education. It has always been an important issue in software engineering teaching to provide learners with reading materials of appropriate complexity. At present, the automatic classification of text complexity is still mainly based on the construction of linear model formulas. But due to the limited number of features eventually entering the model, the accuracy is generally not high, and it is difficult to extend to other data sets. This paper aims to explore the performance of neural network technology in the text complexity classification models with the help of multi-dimensional features and feature optimization. After comparative experiments, the text complexity classification model based on the neural network has the best performance. Its accuracy, recall, and F1 comprehensive evaluation indicators in cross-validation are better than other methods, which not only have higher prediction accuracy, but also have more stable performance. The model established from that has a strong generalization ability for new data, with obvious advantages.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 123501S (2022) https://doi.org/10.1117/12.2653486
Based on the theoretical analysis and investigation of the infrared absorption spectra of two SF6 characteristic decomposition products, SO2F2 and SOF2, an experimental system of the influence of temperature and pressure is constructed, and the influence characteristics of temperature and pressure on the absorption spectra are measured. Through theoretical analysis and experiments, the best mid infrared laser spectrum detection technology is compared and studied; investigated and experimentally studied the low adsorption materials suitable for gas pool; the optical gas absorption cell and photoacoustic gas cell are designed and simulated; the mid infrared inter band cascade laser and quantum cascade laser were purchased, and the tuning characteristics of the laser were analyzed. The experimental platform of TDLAS laser spectrum measurement and photoacoustic spectrum are built. The experimental research on SO2F2 and SOF2 in the alternative wave band is carried out, and good measurement results are obtained. The photoacoustic gas cell and some electronic control modules of the device are developed. Based on the laser light transmission theory, this paper deeply studies and analyzes the theory of long-range multiple reflection gas absorption cell used in TDLAS system, simulates and designs Herriott multiple reflection gas absorption cell with the help of TracePro ray tracing software, and obtains the design parameters of high stability multiple reflection long-range gas cell. Using the multi physical field finite element simulation software, the thermal viscous acoustic theory simulation of the photoacoustic cell required for photoacoustic spectroscopy technology is studied. Two photoacoustic cells are designed, and the resonance conditions, intrinsic oscillation frequency, sound pressure, temperature and other parameters are obtained. The above theoretical and simulation research on the gas pool provides important parameter guarantee for the development of the device.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 123501T (2022) https://doi.org/10.1117/12.2653337
Live streaming is an emerging industry derived from the Internet platform in the 21st century, which attracts many commercial resources with its complex categories and strong traffic monetization capabilities. Although a large number of high-quality talents have poured into the ranks of live streaming, live streaming can still divide the blue ocean track from the Red Sea market. At present, most of the existing live streaming research focuses on the normative governance of the platform department, the purchase psychology mechanism of consumers and the macro e-commerce live broadcast market development trend research, and there is still a lack of subdivision research on the live broadcast revenue of the live streaming category, the author obtains data through the live broadcast data analysis platform, using a multi-linear regression model for empirical research, and explores the live streaming category and other non-core variables such as the number of fans, the number of viewers per game, the unit price of customers, etc The degree of relevance to the revenue of the live broadcast. The study found that in the case of the same non-core variables, the average revenue (traffic realization ability) of live streaming goods was sorted from high to low as :( jewelry literary play> beauty personal care> home> daily necessities> men's and women's> food and drink> books>shoes and hats bags> maternal and infant products> Mobile digitally). By constructing the theoretical model of live streaming categories and live broadcast revenues, and taking the correlation between various variables and live broadcast revenue as the starting point, this paper expands the theoretical research of social self-media with goods categories, which helps practitioners to understand the development status of each category of live streaming from the model construction mechanism and conclusion data, so as to grasp the market trend and fully expand the blue ocean category. Create a live streaming market with a variety of flowers.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 123501U (2022) https://doi.org/10.1117/12.2653334
The prediction of the stock price has been a complex issue. Here, we introduce a stock forecasting model based on a dynamic relationship that combines historical transaction data and knowledge extracted from news, which is mainly divided into subgraph and global relation learning two modules. The subgraph relationship is extracted from the existing industry classification and news information in the market, and the global learning module is based on the shared features between subgraphs and combines the attention mechanism to complete the prediction task. Experiments on the Chinese CSI100 stock and CSMAR news datasets show that our proposed model has certain effectiveness.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 123501V (2022) https://doi.org/10.1117/12.2653209
This paper sets up the research progress on adopting k-prototype clustering technology to achieve talent evaluation driven by digitization and intelligence. With context integration and massive data information technology, the graph analysis technology is adopted to evaluate the first-line team leaders of the power system by integrating the developed scenarios with the working scenarios, and a new model of "scenario assessment" + action mode + potential mining is explored, which not only solves practical problems, but also provides a new paradigm for the development of enterprise talent echelon.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 123501W (2022) https://doi.org/10.1117/12.2652819
To solve the problem that it is difficult and inaccurate to artificially detect the normalization of Word document titles, this paper proposes a normalization detection method for document titles based on XML logical structure description. This method converts the title content and style information of the template Word document and the test Word document into a document title tree with a logical structure. By comparing the consistency of the title trees of the two documents, the title normalization of the test Word document is realized. The experimental results show that this method can detect the logical structure, content, format, and other normalization of Word documents quickly and effectively, which is helpful to improve the document normalization level.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Advanced Algorithm Application and Intelligent Data Analysis
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 123501X (2022) https://doi.org/10.1117/12.2652850
Line loss is an important indicator for evaluating the economic operation of the power system. With the development of smart grid, it has accumulated a large amount of line loss data, which allows us to use a data-driven approach for line loss estimation. In this paper, an algorithm based on K-Medoids clustering and ensemble learning (KMC-EL) is proposed for feeder loss estimation. Firstly, considering the difference between feeders, an unsupervised learning algorithm, which is called the K-Medoids clustering, is used for feeders clustering. And then, for each type of feeder, an ensemble learning algorithm based on bagging, boosting and weighted integrated algorithm are proposed to estimate line loss. Compared with the traditional algorithms, the KMC-EL model has a lower MSE value, which means it has a better generalization ability and can be applied in different feeder loss estimation scenarios.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 123501Y (2022) https://doi.org/10.1117/12.2654876
In recent years, with the continuous expansion of natural gas pipelines, the energy consumption of natural gas pipelines has gradually increased. In order to further reduce the energy consumption of the natural gas pipeline, a general steady-state operation model of a natural gas long-distance pipeline is established in this paper, which can calculate the pressure and temperature changes along the pipeline. The paper takes the China-Russia eastern natural gas pipeline as a practical case, and uses the Grey Wolf optimization algorithm to solve it. The results show that the overall pressure drop and temperature drop of the pipeline are reduced after the optimization of the algorithm, and the energy consumption of the pipeline can be reduced by 17.52%, which provides a theoretical basis for the field operation.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 123501Z (2022) https://doi.org/10.1117/12.2652734
Robot path planning is to find the best path for robot movement considering the interference of surrounding obstacles. In this paper, the feasible region is rasterized and the robot path planning problem is transformed into abstract space that can be dealt with. In order to improve the computational efficiency, the improved particle swarm optimization algorithm combined with artificial potential field method was used to find the best moving path in the grid environment. Bessel curve is used for final smoothing operation to solve the problem of multiple path breaks in grid environment and obtain the final moving path. An example shows that this method can overcome the shortcomings of traditional algorithms and intelligent algorithms in robot path planning, and has strong search and convergence ability.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 1235020 (2022) https://doi.org/10.1117/12.2652708
With artificial intelligence and economic development entering the "fast lane" stage, the construction of tourist attractions is more intelligent and unmanned. Aiming at the problems of path planning of unescorted robots in tourist attractions, long calculation time of traditional ant colony algorithm and many turns, a path planning method for unescorted robots based on improved ant colony algorithm is proposed. Firstly, the driving rules of the escort robot in the scenic area are proposed, and the ant colony algorithm is applied to the path planning problem of the unmanned escort robot. Combined with the characteristics of the ant colony algorithm, the secondary planning of the first planned path and the method of the secondary planning are proposed. Perform secondary pheromone update on the shortest path to optimize the problem of unreasonable turning points in the traditional ant colony algorithm planning path; use the grid method to build a simulated environment model, and initialize the information of the improved ant colony algorithm according to the algorithm flow of the improved ant colony algorithm, set the start and end points of the escort robot, send the ants to iterate and output the improved planning route, and conduct simulation experiments on Matlab. The simulation results show that compared with the traditional ant colony algorithm, the number of iterations of the improved algorithm planning is significantly reduced, and the path unreasonable turning points are less, which verifies the efficiency and superiority of the improved algorithm.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 1235021 (2022) https://doi.org/10.1117/12.2653173
Digital mining technology is a network information processing technology based on the perspective of big data analysis, and its important value in the construction of library knowledge service management system is prominent. This paper starts with the realization of the knowledge service and management system of university library under the digital mining technology, as well as the business flow and composition of the knowledge service and management system, and discusses how to improve its performance design and safety design, and realize the optimization service and management decision-making function of the system, to meet the needs of users for knowledge acquisition in the digital age, and to meet the greatest needs of teaching and research construction in colleges and universities.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 1235022 (2022) https://doi.org/10.1117/12.2654046
Image segmentation is the basis of image processing and an important technology in computer vision and other fields. With the continuous development of computer technology, image segmentation also presents a new look. Therefore, the research on image segmentation methods has far-reaching significance to make it better serve people's lives. The quality of image segmentation results will directly affect the quality of subsequent applications such as image processing. The Fuzzy C-means Clustering (FCM) algorithm also has certain defects or deficiencies. The traditional FCM algorithm is divided based on the grayscale of the image pixels, which is unreasonable to some extent. In order to speed up the convergence speed of the algorithm and improve the noise resistance of the algorithm, this paper selects an FCM based on spatial information for improvement, and proposes an improved FCM segmentation algorithm. The experimental results show that the improved algorithm has high segmentation efficiency, high segmentation accuracy and strong anti-noise.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Li Wan, Yuemeng Li, Yue Cheng, Shuang Wang, Bochen Li
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 1235023 (2022) https://doi.org/10.1117/12.2652803
Concerning the traditional GIS-based civil air defense management application system not meeting the requirements of the internet of things big data, the construction ideas and key technologies of the air defense big data management application platform based on Internet of Things (IoT) technology are studied. After analyzing big data of civil air defense, five-layer SOA architecture is proposed to build the cloud framework of topological structure. Then, the design of the database and distributed storage of images is described. Finally, aiming at the practical application requirements, four modules of real-time data acquisition, large data management, real-time statistical analysis of data, and online data display are realized. The system is of great significance to the management and application of large data information for civil air defense projects.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 1235024 (2022) https://doi.org/10.1117/12.2653619
Credit business is one of the most important components in many businesses of a bank, and has a very important impact on the bank's income and development. The most important part of credit business is the assessment of credit risk. Accurate assessment can enable banks to increase returns with the lowest possible risk. Traditional credit risk assessment models will face difficulties in feature selection in the high-dimensional and sparse big data environment; in addition, the high noise in big data will also affect the evaluation effect of the model. In response to the above problems, this paper firstly analyzes the common credit risk control algorithms. Then, based on the framework of deep learning, a stack noise reduction self-encoding neural network algorithm is designed, which is applied to the problem of bank credit risk assessment. Through experimental demonstration and comparative analysis, the use of deep learning for credit risk assessment in the big data environment can better provide early warning of credit risks and reduce bank credit risks.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Shiyang Shi, Linna Liu, Jianyin Fang, Huaijun Deng
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 1235025 (2022) https://doi.org/10.1117/12.2652487
With the continuous development of artificial intelligence technology, the method based on deep learning has become a research hotspot in the field of engineering. However, the setting of super parameters and the amount of training data are strictly required for the deep neural networks, which is difficult to meet the needs of rapid, accurate and stable diagnosis in practical industry. To solve above problems, a diagnosis method based on improved deep forest was proposed, which is applied to small-scale data sets. The cascade forest stage of traditional deep forest model has problems like high computational cost and redundant data processing, therefore, in the paper a deep forest model based on Linear Discriminant Analysis (LDA) feature extraction is designed. The improved deep forest model improves the data transmission and processing ability in multi-granularity scanning and cascade forest, and enhances the feature representation in the model while ensuring the data diversity, so as to improve the operation efficiency and diagnosis performance of the algorithm. Compared with the traditional machine learning methods, the experimental results show that the improved method has better accuracy.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 1235026 (2022) https://doi.org/10.1117/12.2654572
As the amount of information on the Web continues to expand, the way people access information has also changed. Instead of searching for information in paper books or libraries, people are now searching for relevant information on the Web. However, the amount of data on the Web is so large that it is almost impossible to construct an effective data warehouse to replicate, store and integrate all the data on the Web, and there is neither a unified category code nor an effective organisation of indexing in such a large collection of data, which makes content management and information filtering on the Web increasingly difficult and important. In traditional Web applications there are a large number of redundant words, syntax and other problems that make it impossible to use computers to extract useful information accurately and efficiently, so how to effectively use the available resources is one of the urgent and pressing issues that need to be addressed. Therefore, this paper explores Web text clustering based on the DBSCAN optimization algorithm.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 1235027 (2022) https://doi.org/10.1117/12.2653190
In order to shorten the time of interior design recommendation and quickly recommend interested interior design to users, an interior design data analysis technology based on collaborative filtering algorithm model is proposed. By analyzing the word segmentation of interior design, the weight distribution of collaborative filtering of interior design is analyzed. Carry out keyword feature selection and data analysis for interior design content. When the similar keywords in the data analysis are more than 35%, the interior design feature extraction based on collaborative filtering model will be completed. According to the initial score of the user's interior design, calculate the weight of the interior design, predict the final score of the user's interior design through the weight vector value, use the interior design data analysis to determine the implementation steps of the recommendation algorithm, and complete the design of the interior design recommendation algorithm model. Finally, through the interior design collaborative filtering recommendation model, we can achieve 100% interior design recommendation. The experimental results show that compared with the traditional recommendation technology, the indoor design recommendation time based on collaborative filtering algorithm is reduced by 80%.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 1235028 (2022) https://doi.org/10.1117/12.2652494
Automatic gauge control (AGC) system is widely used in cold rolling process, however, the complexity, nonlinearity and time-varying characteristics of AGC system make the control of AGC system a challenging task. This paper presents a control strategy based on Genetic-Particle Swarm Optimization (GA-PSO) fusion algorithm to optimize the fuzzy PID controller. It combines the advantages of GA and PSO algorithm. By optimizing the membership function of the fuzzy controller, the dynamic characteristics of AGC system can be further improved. Simulink simulation platform of commercial software MATLAB is used to simulate the actual rolling process to study the effectiveness of the fusion algorithm, and the dynamic characteristics of the system with and without disturbance were discussed. The simulation results show that, compared with the fuzzy PID control strategy, the fuzzy PID based on GA-PSO fusion algorithm can greatly enhance the rapidity and robustness of the system. The simulation results proved that the GA-PSO fusion algorithm can effectively improve the dynamic characteristics of rolling system.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 1235029 (2022) https://doi.org/10.1117/12.2653215
By extending and optimizing the COSMIC-FFP model, a measurement method for embedded network systems is proposed, which solves the problem that the COSMIC-FFP model does not support the measurement of real-time systems. At the same time, the network fault analysis and the measurement method based on the network scale are designed to improve the accuracy of the network scale. The experimental results show that through the fault analysis and accurate measurement of the embedded network, the proposed method can find out the weak links of risk management in the process of network engineering, realize the real-time measurement of the network system, and reduce the risk of the network engineering process.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 123502A (2022) https://doi.org/10.1117/12.2653451
In the process of continuous development of e-commerce, to better meet the needs of users and tap the consumption potential of users, personalized recommendation systems have emerged on various e-commerce platforms. Although the clustering algorithm is suitable for solving the user segmentation problem, the traditional K-means algorithm has some shortcomings, such as the quality of the initial center point determined randomly is not high, and there is no definite criterion to select the value of K. Therefore, this paper proposes an optimized K-means algorithm, which uses the value of effectiveness index CH to determine the value of K, and combines with particle swarm algorithm to solve the initial center point. Experiments show that the optimization algorithm CH-PSO-K-means algorithm proposed in this paper has improved the DB index, accuracy rate, and error square index. The comprehensive performance of the clustering effect has been significantly improved, which can effectively solve the problem of e-commerce user segmentation with large data and multiple characteristics. The optimization algorithm not only makes up for the shortcomings of the K-means algorithm, but also improves the maintenance strategy of individual e-commerce users, which is conducive to enterprise cost control and profit improvement.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 123502B (2022) https://doi.org/10.1117/12.2653159
In order to quickly solve the optimal path of logistics transportation in complex traffic environment, a logistics transportation path optimization model based on improved ant colony algorithm is proposed on the basis of traditional ant colony algorithm. First, by adding constraints based on transportation time, cost, and average road smoothness factor in the traditional ant colony algorithm, and at the same time improving the traditional pheromone update method. The pheromone concentration on the road is subject to a minimum and maximum limit, thereby changing the routing transition probability. Finally, the experimental data using the improved ant colony algorithm, the CSAACO algorithm and the ACO algorithm show that the improved ant colony algorithm is significantly lower than the CSAACO algorithm and the ACO algorithm in terms of transportation distance and transportation time. The improved ant colony algorithm has stronger global optimization ability, converges faster, takes less time and obtains a shorter optimal path, which improves the transportation efficiency of the entire logistics industry.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 123502C (2022) https://doi.org/10.1117/12.2653166
Forecasting models have a high value in the field of finance, we can better gain in investment and it provide a better basis for the national macroeconomic control strategy. In this paper we build three forecasting models based on a combination of linear ARIMA time series and nonlinear Back-Propagation neural networks to improve the accuracy of forecasting. The first model uses direct summation; the second uses ARIMA and Back-Propagation neural network forecasting results as independent variables and actual prices as dependent variables to build a multiple linear regression model; the third uses bp neural network to indirectly compensate for the residuals of ARIMA results. The more representative gold in the international market was selected as the forecasting object, and the final errors were respectively, proving that the new combination method can improve the accuracy.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 123502D (2022) https://doi.org/10.1117/12.2653161
We propose a novel hybrid algorithm that effectively combines K-means clustering and hierarchical and uses triangle inequality to accelerate the clustering speed. The HTK clustering algorithm can produce the same results as the standard K-means clustering algorithm. The proposed algorithm is superior to the standard K-means clustering algorithm in terms of running time and memory usage, thus improving the clustering speed and time complexity of the algorithm. The proposed clustering methods are tested on sci-kit learn datasets, and they are more favorable than the random restart K-means algorithm.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 123502E (2022) https://doi.org/10.1117/12.2653258
Route planning is the key technical difficulty of logistics distribution. In this paper, a mathematical model is established for road network selection and real-time path planning. The improved genetic algorithm is used to select the road network of rail transit. Based on the traditional ant colony algorithm, the time-varying factor and line risk factor are introduced to improve the algorithm in line with real-time path planning. The experimental results show that the improved algorithm can change the route more quickly and accurately according to the real-time traffic changes to effectively improve the logistics transportation efficiency for complex routes and traffic conditions, and save the transportation cost.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 123502F (2022) https://doi.org/10.1117/12.2652790
Clustering by fast search and find of Density Peaks (referred to as DP) was introduced by Alex Rodriguez and Alessandro Laio. DP algorithm is based on the idea that cluster centers are characterized by a higher density than their neighbors and by a relatively large distance from points with higher densities. This algorithm can discover clusters regardless of their shapes and the dimensions of the space containing them. However, it cannot effectively detect clusters with different sizes and densities of arbitrary shapes, especially the same cluster with multiple peaks. Moreover, the DP algorithm needs to select the centers of the clusters by using a decision graph manually. Despite a highly improved performance in semi-supervised clustering, to address this problem, we propose a semi-supervised framework for DP, namely SMpeaks, by integrating pairwise must-link and cannot-link constraints to guide the clustering procedure. We tested the SMpeaks algorithm on complex data sets having clusters with arbitrary shapes, different sizes, and densities. The experimental results have demonstrated that this algorithm is more effective in finding clusters of complex shapes and different densities than DP.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 123502G (2022) https://doi.org/10.1117/12.2653439
With the practical application of the self-marking system, it can give an objective and fair score, but it can not meet the needs of classroom teaching. It also needs to give students rapid feedback on the vocabulary, sentence, text structure, content relevance, and other dimensions presented in the test paper. The scoring method based on artificial features is the earliest self-marking scoring method, which uses experts to design some scoring features from the language quality, content quality, and text structure of the test paper. It takes the scoring task as a regression or classification task to score or rate the test paper. In this paper, based on the deep learning theory, a method for text similarity detection using a twin network is proposed. Considering the interaction between text pairs, we integrate expressivity pooling based on bidirectional GRU and measure the similarity by distance calculation formula. The experimental data show that the two-way GRU network integrated with expression pooling can obtain the interaction between text pairs so that the extracted features of the text are more comprehensive. The model has a better effect in the study of the similarity of text pairs. This method can reduce the difference in scoring results caused by different subjective consciousness of raters, make the scoring results more objective and persuasive, and improve the accuracy and efficiency of scoring.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 123502H (2022) https://doi.org/10.1117/12.2653035
With the development of technology, the status and role of the air force in the future war are becoming more and more important. As the main component of the air force strength, the importance of the research and development of fighters are becoming more and more prominent. Researches on operational effectiveness evaluation can effectively promote the development of high-performance weapon systems such as fighter. Among these researches, sensitivity analysis of effectiveness index can establish mapping relationships between performance index and the effectiveness index when aircrafts finally participate in a combat, at the early stage of aircraft design, and guide the demonstration of aircraft index, reducing the development cycle and cost. In this paper, a sensitivity analysis method of effectiveness index based on machine learning is proposed, aiming at the performance index of fighter with different granularity. Neural network is used to fit a large number of simulation data, and mine the implicit relationship between the data, then analyze the sensitivity of performance index (i.e., sensitive factor) to the final effectiveness index, so as to guide aircraft design and parameter index trade-off.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 123502I (2022) https://doi.org/10.1117/12.2653038
The development of the Industrial Internet has caused a change that traditional internet technologies gradually sink into the field of industrial manufacturing. Due to the high degree of business coupling at the edge of industrial production, the relationships between the data are complex and difficult to comprehensively analyze and apply. This paper proposes a data semantic association retrieval method for industrial data at the industrial edge. Firstly, the framework of semantic association retrieval of industrial data is established, and then the construction method of inverted table in association retrieval is explained, including the formation method of keyword set and concept set, and the algorithm for realizing semantic association retrieval is given. The algorithm is verified in the actual scene of the test production line, and the results show that the algorithm in this paper is feasible and effective in relational retrieval.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 123502J (2022) https://doi.org/10.1117/12.2653167
The existing scheduling strategies do not have enough granularity in the division of execution units, and can not flexibly use the attack feedback information. Lack of security to some extent. Therefore, this paper proposes a scheduling algorithm considering the similarity between components and the historical performance of executors. Firstly, a specific component similarity quantification method is designed to improve the heterogeneous differentiation of executors. Then, the historical work performance is incorporated into the executor scheduling strategy to improve the utilization efficiency and system security of the executor. Finally, two attributes are integrated to calculate the comprehensive score. Experiments show that compared with existing algorithms, this method can better distinguish similar executors. At the same time, it dynamically adjusts the selection of executors through the attack feedback information, taking into account the system dynamics and security, and has good practicality.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 123502K (2022) https://doi.org/10.1117/12.2652787
With the advent of the era of massive data, algorithmic optimization and data mining have been applied in many industries in an unprecedented and innovative way. In the field of enterprise supply chain management, big data and algorithmic optimization technologies have been well applied. The establishment of the innovative model of supply chain management efficiency optimization can improve the management efficiency in the supply process and can greatly promote market development. The use of big data technology can make supply chain management more informative and intelligent. This study proposes a discrete modeling analysis of enterprise supply chain management optimization based on big data analysis. The main use of big data technology is to analyze the obtained data information and quantify the abstract features of the supply process. The discrete dynamic modeling technique is also used to develop a three-level intelligent planning algorithm, focusing on the quality issues in the upstream supply process and the cost issues in ordering and forwarding for management optimization. In addition, this study also have innovatively developed intelligently selected time series for forecasting the supply potential of companies.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 123502L (2022) https://doi.org/10.1117/12.2652903
Studies by grassland workers have shown that the occurrence of degradation indicator plants in grassland is an important sign of grassland degradation. The detection of degradation indicator plants can provide a certain data basis for the study of grassland degradation. In this paper, a target detection algorithm for improving YOLOv5 model is proposed to detect the degradation indicator plants (wolfsbane) in grassland. Firstly, the target detection dataset of the grassland degradation indicator plant(wolfsbane)is constructed, and then the backbone network is optimized by adding a coordinate attention mechanism on the basis of the original YOLOv5 model; The original feature pyramid module in the feature fusion module is replaced by a weighted bidirectional feature pyramid (BiFPN) network structure, which realizes effective weighted feature fusion and bi-directional cross-scale connection; A small target detection layer is also added to further improve the detection accuracy of small targets. Experimental results show that the proposed improved algorithm achieves an average precision (AP) of 80.4%, which is 3.4% better than the original YOLOv5 model, and verifies the effectiveness of the improved model for the detection of degraded indicator plants (wolfsbane).
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Jinhui Ye, Yongping Wang, Xiaolin Zhang, Li Xu, Ruizhi Ni
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 123502M (2022) https://doi.org/10.1117/12.2653117
With the wide application of deep learning object detection model, its internal security vulnerability is also highlighted. In this paper, a black box adversarial attack algorithm SAD-DE based on improved differential evolution is proposed to reveal the possible security risks of the object detection model. Taking full advantage of the high optimization efficiency and simple parameter setting of differential evolution algorithm, multi mutation strategy is adopted, and the mutation rate and crossover rate are adaptively improved to effectively improve the optimization efficiency. In this paper, two public data sets are randomly exampled as test sets to counter attacks on YOLOv3 and Fast R-CNN respectively. Experimental results show that this method achieves a high fooling rate while maintaining a low anti disturbance, and achieves a maximum improvement of 33% compared with other black box attack algorithms.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 123502N (2022) https://doi.org/10.1117/12.2652497
Web crawler (also known as web spider) is a program or script that automatically grabs data from websites according to certain rules. Like a spider crawling along the silk thread of URLs on the internet, it downloads the web page pointed to by each URL, and extracts and analyzes the contents of the page. Through the web crawler program, the massive data on the target website can be automatically collected and saved in a structured file or in database. Therefore, crawler owners can obtain a large amount of data with potential economic value at very low time cost and tiny economic cost. This article takes http://novel.tingroom.com/ as the target, and introduces in detail the general steps of how to use the Python based crawler program to obtain massive data (novel content): Firstly, analyze the structure of the target page. Secondly, use the requests module to get the target page. Thirdly: use the parsel module to extract the valuable parts of the target page. Finally, save the information into structured files. The empirical research shows that the crawler program based on Python has significant practical value.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 123502O (2022) https://doi.org/10.1117/12.2652680
The prize-collecting dominating set (PCDS) problem is the generalization of the minimum dominating set (MDS) problem. The MDS problem requires a dominating set in a given graph, namely a subset of vertexes. Any vertex in the graph belongs to the closed neighborhood of the subset of vertexes, where the subset of vertexes with the smallest cardinality is the MDS. In the PCDS problem: given an undirected graph, its vertex setV has nonnegative weighting functionω and nonnegative penalty functionπ . Finding a vertex subset D⊂V, for vertexes do not belong to the closed neighborhood of D , we need to pay penalties for them. The objective of this issue is to minimize the sum of weights and penalties. As we all know that the MDS problem is NP-hard in general graph, obviously, PCDS problem is NP-hard, too., In certain cases, the PCDS problem can achieve better results than the MDS problem, which has a certain value in practical applications such as facility location and logistics management. Whether the problem is limited to a special graph will get useful structural characterization and corresponding algorithm results is considered, designed polynomial time exact algorithm on the star and according to the r -LMP approximation algorithm, designed the 2-LMP approximation algorithm on the path and cycle.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Xiaoyiqun Zhang, Lixia Deng, Haiying Liu, Bin Li, Hui Zhang, Yang Zhao
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 123502P (2022) https://doi.org/10.1117/12.2652693
This paper presents an intelligent optimization algorithm applied to the two-dimensional path planning of a mobile robot and optimizes its trajectory. The method is based on the sparrows' behavior of finding food and avoiding predators. The method is implemented in a raster map and uses the Sparrow search algorithm for preliminary path planning to find a passable optimal path, and in order to solve the shortcomings of many folds and not being smooth enough at the folds, the use of B spline curve to smooth the path to solving the shortcomings of many fold points and not being smooth enough at the fold.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 123502Q (2022) https://doi.org/10.1117/12.2654556
In the current era of big data, semi-supervised learning algorithms are widely used. The self-training algorithm is one of the commonly used semi-supervised algorithm frameworks. During the iteration process of the self-training algorithm, the classification performance of the base classifier has a significant influence on the final classifier trained by the model. To study the effect of the base classifier on the performance of the STDPM algorithm, we use KNN, decision tree, and SVM base classifier to conduct experiments on four medical images. The experimental results show that on the four data sets diabetes, heart, hepatitis and Ilpd, the three classifiers KNN (K=1), SVM and decision tree have little effect on the STDPM algorithm. When K=3, the algorithm STDPM performs poorly using the KNN base classifier.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Zhongxin Zhang, Shusen Kuang, Jiang Song, Guoqi Ye, Li Shen
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 123502R (2022) https://doi.org/10.1117/12.2652820
Since the traditional PID control algorithm has many problems in parameter selection, it cannot meet specific requirements in engineering practice. However, the PID control algorithm after BP neural network tuning can realize adaptive learning and further improve the control ability, but due to the randomness of its initial weight selection, It is easy to lead to inconsistent training results and affect system stability. To solve these problems, this paper proposes to use the improved mayfly algorithm (IMA) to optimize BP neural network. By taking advantage of the powerful advantages of the improved mayfly algorithm in global search, the optimal position is found as the initial weight of BP neural network. Compared with the traditional method, the overshoot of IMA-BP-PID is only 0.28% in the second order control system, and the overshoot is greatly reduced without steady-state error, which can be better applied to the actual control system.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 123502S (2022) https://doi.org/10.1117/12.2652866
The orienteering problem (OP) is one of the most classical optimization problems, and the objective is to find a tour of some of the given nodes to obtain as much value as possible, with a maximum tour length constraint. Since the OP is an NP-hard problem, how to deal with it efficiently and effectively is always challenging. This study proposes to solve it through a greedy strategy based iterative local search algorithm (ILS-G). In detail, the greedy strategy is used to generate a good initial solution for accelerating the search process, and the iterative local search algorithm is proposed to further optimize the initial solution. An insertion operator, a 2-OPT operator, and a deletion operator are introduced in the iterative local search algorithm for updating the solution. Experimental results on instances with different problem sizes demonstrate the effectiveness and the efficiency of the proposed ILS-G.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 123502T (2022) https://doi.org/10.1117/12.2652560
In order to improve the utilization of cloud computing resources, this paper studies cloud computing resource scheduling based on improved Ant Colony Optimization Algorithm (ACO) and Simulated annealing algorithm (SA). We apply ACO and SA to schedule the large-scale cloud computing resource data. This paper uses SA to prevent ACO falling into the local optimal solution, and accelerate the convergence speed of ACO. The experimental results show that the proposed method is more effective compared with the already existed approaches. Our proposed method can improve the resource utilization.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 123502U (2022) https://doi.org/10.1117/12.2652433
In order to meet the monitoring requirements of the upper management of the enterprise for the production status of the production line, research on the real-time status visualization of the intelligent manufacturing production line based on digital twin is carried out. First, the visualization system architecture of intelligent manufacturing production line based on digital twin is built, and its key realization process is clarified; then, it focuses on three key technologies: real-time collection method of production data based on CNC (Computer numerical control) system and RFID technology, data management based on MySQL, information visualization and push, which elaborates the visualization method in detail. Finally, the automation production line of an intelligent manufacturing laboratory in a university is taken as an application case to realize its visualization.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 123502V (2022) https://doi.org/10.1117/12.2652910
In order to study the effects of mud moisture content, dosage and sludge specific resistance of river and lake sediment on dehydration and solidification of river and lake sediment, a prediction model between filter cake moisture content expressed by mud moisture content, dosage and sludge specific resistance was established by using machine learning (BP neural network and symbolic regression). The results showed that the prediction models obtained by the two machine learning methods had good correlation accuracy. Based on the comparison of four commonly used error evaluation indexes, the accuracy of BP neural network prediction results was better, and the contribution of mud moisture content and sludge specific resistance in the input parameters of the two models to the final filter cake moisture content was similar and large. The established correlation model provided a reliable prediction and analysis tool for the dehydration and solidification of river and lake sediment.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 123502W (2022) https://doi.org/10.1117/12.2652828
According to the problem of transmitter and receiver node arrangement of multistatic buoy in underwater area surveillance, this paper presents an array optimization method based on GAPSO (Genetic Algorithm - Particle Swarm Optimization). Firstly, the performance evaluation model of multistatic buoy array is established by probability fusion based on the bistatic sonars equation. We take the effective coverage rate of the model as the objective function, then Particle Swarm Optimization (PSO) and Genetic Algorithm (GA) are used to optimize the array. Secondly, PSO and GA are combined to improve the global searching ability and convergence speed. The simulation results show that the coverage ability of the optimized multistatic buoy array is significantly improved compared with the traditional array scheme. Compared with PSO and GA, fused GAPSO has obvious improvement in search ability and convergence speed, which achieves the purpose of optimal defense deployment.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
Proceedings Volume 6th International Workshop on Advanced Algorithms and Control Engineering (IWAACE 2022), 123502X (2022) https://doi.org/10.1117/12.2652493
Natural disasters such as forest fires, earthquakes, and droughts will have a huge impact on people's lives and the social economy, which makes people and governments pay great attention to these disasters. Therefore, the automatic extraction of disaster events and relevant information about events has high research value. The event extraction task based on Pipeline will have cascading errors and the use of natural language processing tools in the event extraction task will cause the problem of error accumulation. This paper proposes a joint event extraction method(BERT-LSTM-GRAPH, BLG) for disasters. This method converts the task of event extraction into a sequence labeling task and uses a graph convolutional neural network to fuse character information and word information to complete the joint extraction of triggers and arguments. Experiments show that the BLG model can improve the extraction performance of triggers and arguments in the field of disasters.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.