Geodesic
Land-use classification via ensemble dropout information discriminative extreme learning machine based on deep convolution feature
Computer Science and Information Systems, Tome 17 (2020) no. 2 Cet article a éte moissonné depuis la source Computer Science and Information Systems website

Voir la notice de l'article

Classifying land-use scenes with high quality and accuracy is an important research direction in current hyperspectral remote sensing images, which is conducive to scientific management and utilization of land. An effective classifier and feature extractor can improve classification stability and accuracy. Therefore, based on deep learning technique, a dropout-based ensemble learning method is proposed in this paper, which combines convolutional neural network (CNN) and information discriminating extreme learning machine (IELM). Pre-trained CNN is used to learn effective and robust features, and deep convolution features are fed to the IELM classifier. Then the adoption of dropout technique and ensemble method can improve generalization capabilities and stability. The effectiveness of the proposed algorithm is tested by hyperspectral remote sensing image classification experiments. The experimental results show that the proposed E-CNN-dropIELM has achieved satisfactory results compared to state-of-the-art methods in terms of classification accuracy and stability.
Keywords: Extreme learning machine (ELM), Convolutional neural network (CN-N), Dropout, Ensemble, Land-use classification 
@article{CSIS_2020_17_2_a4,
     author = {Tianle Zhang and Muzhou Hou and Tao Zhou and Zhaode Liu and Weirong Cheng and Yangjin Cheng},
     title = {Land-use classification via ensemble dropout information discriminative extreme learning machine based on deep convolution feature},
     journal = {Computer Science and Information Systems},
     year = {2020},
     volume = {17},
     number = {2},
     url = {http://geodesic.mathdoc.fr/item/CSIS_2020_17_2_a4/}
}
TY  - JOUR
AU  - Tianle Zhang
AU  - Muzhou Hou
AU  - Tao Zhou
AU  - Zhaode Liu
AU  - Weirong Cheng
AU  - Yangjin Cheng
TI  - Land-use classification via ensemble dropout information discriminative extreme learning machine based on deep convolution feature
JO  - Computer Science and Information Systems
PY  - 2020
VL  - 17
IS  - 2
UR  - http://geodesic.mathdoc.fr/item/CSIS_2020_17_2_a4/
ID  - CSIS_2020_17_2_a4
ER  - 
%0 Journal Article
%A Tianle Zhang
%A Muzhou Hou
%A Tao Zhou
%A Zhaode Liu
%A Weirong Cheng
%A Yangjin Cheng
%T Land-use classification via ensemble dropout information discriminative extreme learning machine based on deep convolution feature
%J Computer Science and Information Systems
%D 2020
%V 17
%N 2
%U http://geodesic.mathdoc.fr/item/CSIS_2020_17_2_a4/
%F CSIS_2020_17_2_a4
Tianle Zhang; Muzhou Hou; Tao Zhou; Zhaode Liu; Weirong Cheng; Yangjin Cheng. Land-use classification via ensemble dropout information discriminative extreme learning machine based on deep convolution feature. Computer Science and Information Systems, Tome 17 (2020) no. 2. http://geodesic.mathdoc.fr/item/CSIS_2020_17_2_a4/