KEYWORDS: Data processing, Data modeling, Modeling, Tunable filters, Machine learning, Image processing, Feature extraction, Image filtering, Deep learning, Signal processing
Effective preprocessing of image data plays a pivotal role in enhancing the discriminative modeling capabilities in downstream machine learning tasks. This study investigates the significance of adequately mapping image data into a new feature space during the preprocessing phase, emphasizing its criticality in facilitating more robust and accurate models. While traditional methods such as signal/image processing transforms have been previously explored for this purpose, this study introduces a novel approach leveraging deep learning techniques. Specifically, convolutional and pooling layers are employed to process the image data, offering a more sophisticated and adaptive method for feature extraction and representation. By employing deep learning architectures, the preprocessing phase becomes more flexible and capable of capturing intricate patterns and structures within the data. Through empirical evaluation, our approach demonstrates significant improvements in discriminative modeling across various traditional machine learning approaches. This highlights the effectiveness and versatility of deep learning-based preprocessing in enhancing the performance of downstream tasks, showcasing its potential to advance the field of image data processing and analysis.
The study in this paper builds on previous research in reinforcement learning to address the challenges of computational complexity and scalability in multi-agent, multi-target satellite sensor tasking systems. Drawing on the groundwork laid by previous research conducted space-based hyperspectral imaging systems, novel approaches are introduced to optimize satellite tasking efficiency. The primary innovation is the implementation of a continuous space expansion method, which enhances system adaptability without necessitating intricate adjustments. Additionally, the study investigates transfer learning within larger state-action spaces, utilizing insights from smaller spaces to accelerate training in more extensive and intricate environments. Through a series of comprehensive experiments conducted in an enhanced physics-based Python simulation environment, the effectiveness and practicality of these strategies are confirmed. The outcomes reveal significant reductions in computational complexity in multi-agent, multi-target satellite tasking, rendering it more viable for real-world implementation. This research contributes to the advancement of AI-driven satellite tasking, enhancing its efficiency in managing extensive satellite constellations.
In the context of the advancing digital landscape, there is a discernible demand for robust and defensible methodologies in addressing the challenges in multi-class image classification. The evolution of intelligent systems mandates swift evaluations of environmental variables to facilitate decision-making within an authorized workflow. Recognizing the imperative role of ensemble models, this paper undertakes an exploration into the efficacy of layered Convolutional Neural Network (CNN) architectures for the nuanced task of multi-class image classification, specifically applied to traffic signage recognition in the dynamic context of a moving vehicle. The research methodology employs a YOLO (You Only Look Once) model to establish a comprehensive training and testing dataset. Subsequently, a stratified approach is adopted, leveraging layered CNN architectures to categorize clusters of objects and, ultimately, extrapolate the pertinent speed limit values. Our endeavor aims to elucidate the procedural framework for integrating CNN models, providing insights into their accuracy within the application domain.
Support Vector Machines (SVM) have emerged as a powerful and versatile machine learning technique for solving classification and regression problems. This paper presents a thorough review of SVM, encompassing its motivation, derivation of the optimization problem, the utilization of kernels for data transformation, and a comprehensive analysis of solution methods. The review is supported by experiments conducted on a data set derived from the Traffic Sign data set. The motivation for SVM lies in its ability to address complex classification tasks by transforming the data into a higher-dimensional feature space. This is particularly beneficial for data sets derived from multiple sources. The findings presented in this paper contribute to a better understanding of SVM’s capabilities.
As the world progresses further into the digital era, we see a growing utility for combining datasets gathered on different devices and receivers as well as on varying time ranges, for use in machine learning. However, machine learning classification introduces a requirement for standardized data, which in turn hampers the ability to utilize diverse sets of data at a given timestamp. In this paper, we investigate the application of various signal pre-processing techniques (Daubecheis wavelet, discrete cosine and discrete fourier transform among others) for multi-modal, multi-class machine learning. Following the pre-processing, the multi-faceted signals are represented solely by features generated from first order statistics, eigen decomposition, and linear discriminant. Utilizing these generated features, as opposed to the signals themselves, these diverse datasets may now be combined as input to machine learning methods. Furthermore, we apply Fisher’s linear discriminant ratio and Random Forest feature importance metrics for feature ranking and feature space reduction followed by a comparison of the approaches. Our work demonstrates that dissimilar datasets with common classes may be combined using the proposed methods with a classification accuracy ≥ 95%. This paper demonstrates that the feature space may be reduced by approximately 60% with ≤ 5% loss in classification accuracy, and in some cases, a slight increase in classification accuracy.
Machine learning and artificial intelligence algorithms have expanded dramatically in use across diverse fields of research and practice. Despite the extensive benefits that these algorithms can bring to researchers, system designers, and operators alike, the adoption of these algorithms in space-related scenarios has lagged behind other fields. In order to encourage the increased adoption of artificial intelligence and machine learning techniques to space-domain-related problems, flexible modeling and simulation capabilities are needed to build stakeholder trust in these techniques. This research presents the development of a flexible Python-based modeling and simulation environment for applying Reinforcement Learning to Low Earth Orbit satellite Hyper Spectral Imaging sensor tasking. With the transition away from small numbers of highly exquisite on-orbit systems to proliferated architectures characterized by constellations of lower cost and complexity spacecraft, the methods by which payload sensors are tasked have become dynamic and complex, making the problem of determining effective sensor tasking methods an important area of research. Such a problem lends itself well to the application of Reinforcement Learning. The focus of this work is on developing the role of intelligent systems in improving the data acquisition process in a space-based hyperspectral imaging system, and showing how the developed modeling and simulation framework can be successfully employed to improve the acquisition of targets of interest. A key strength of the presented reinforcement learning application framework is its non-commercial, extensible nature, suitable for both research and educational purposes.
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.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
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.