There are two heterogeneous data types in hyperspectral image (HSI): rich spectral data and spatial information. Recent research has shown that the application of spectral–spatial information significantly improves HSI accuracy; thus, multiple-feature combination-based methods have been favored by researchers in the field of HSI classification. A multiple-feature combination approach, based on the particle swarm optimization (PSO) algorithm, is proposed for improving the accuracy of HSI classification. The proposed method couples a multiple kernel support vector machine (SVM) with a PSO algorithm to assign optimal weights to different kernels. Moreover, it also solves the problem of artificially selecting weights when learning multiple features by implementing adaptive weights on different datasets. In addition, it has fewer parameters and a shorter training time than deep learning methods, thus, the model is smaller and easier to train. The proposed method was tested on four datasets, containing two and three kernels. The experimental results show that our optimized method improves the classification accuracy; additionally, the kappa performance of the classification is also better.
A model of synergistic coupling for land-use data mining based on extension theory is put forward in this paper, which
can mine the relation of synergistic coupling for various land use activity in land use database to guide all kinds of
activity. In order to mine the knowledge of synergistic coupling, some knowledge must be obtained from database of
land use. Changjiang is a county in west of Hainan province, China. The data of land use is studied as a case through the
changes of construction to influence other land use types. The results show that the model can be used for the mining in
the land-use synergistic coupling relations. The knowledge that obtain in this case based on the model of synergistic
coupling for land-use data mining is essential for decision-makers to deal with the paradoxical problem of land-use.
One quality estimate model was put forward. It combined the common-point comparison with the scale of wavelet
analysis. So, the study on uncertainty estimate based on single data set gained enormously advance. The result indicates
that when the ratio between the number of common-points and the number of wavelet low-frequency coefficients is 1.5,
the model can estimate the quality for multi-scale representation of linear feature. It provided the quality estimate model
for multi-scale representation of linear feature based on wavelet analysis.
The optimization of land use structure is always considered as the quantitative optimization. Moreover, it's the
optimization of spatial allocation and different scales. This paper obtains the spatial elements of land use by use the
remote sensing technology. The optimization model and convolution algorithm of optimization is proposed based on
remote sensing and ecological green equivalent. We can use these model and algorithm to optimize the data of land use
structure from multi-scales for every region which do not rely on the administrative boundaries, and they are evaluated
by the image data of Huangpi which obtain from landsat7 in 2005.The result indicates that the method can be applied to
optimize the land use structure for actual land use planning. They can realize the multi-scales land use structure
optimization for each region by dynamic control based on the RS and the ecological green equivalent. The reasonable
and accuracy is improved in land use planning.
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.