期刊
NEUROCOMPUTING
卷 185, 期 -, 页码 1-10出版社
ELSEVIER
DOI: 10.1016/j.neucom.2015.11.044
关键词
Deep learning (DL); Hyperspectral remote sensing; Data reduction; Segmented stacked autoencoder (S-SAE)
资金
- University of Strathclyde
- National Natural Science Foundation of China [61272381, 61471132, 61401163]
- Science and Technology Major Project of Education Department of Guangdong Province [2014KZDXM060]
- Fundamental Research Funds for the Central Universities [2015ZZ032]
- Science and Technology Project of Guangzhou City [2014J4100078]
- BBSRC [BB/P004873/1] Funding Source: UKRI
Stacked autoencoders (SAEs), as part of the deep learning (DL) framework, have been recently proposed for feature extraction in hyperspectral remote sensing. With the help of hidden nodes in deep layers, a high-level abstraction is achieved for data reduction whilst maintaining the key information of the data. As hidden nodes in SAEs have to deal simultaneously with hundreds of features from hypercubes as inputs, this increases the complexity of the process and leads to limited abstraction and performance. As such, segmented SAE (S-SAE) is proposed by confronting the original features into smaller data segments, which are separately processed by different smaller SAEs. This has resulted in reduced complexity but improved efficacy of data abstraction and accuracy of data classification. (C) 2016 Published by Elsevier B.V.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据