Share Email Print
cover

Proceedings Paper

Improving the performance of extreme learning machine for hyperspectral image classification
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

Extreme learning machine (ELM) and kernel ELM (KELM) can offer comparable performance as the standard powerful classifier―support vector machine (SVM), but with much lower computational cost due to extremely simple training step. However, their performance may be sensitive to several parameters, such as the number of hidden neurons. An empirical linear relationship between the number of training samples and the number of hidden neurons is proposed. Such a relationship can be easily estimated with two small training sets and extended to large training sets so as to greatly reduce computational cost. Other parameters, such as the steepness parameter in the sigmodal activation function and regularization parameter in the KELM, are also investigated. The experimental results show that classification performance is sensitive to these parameters; fortunately, simple selections will result in suboptimal performance.

Paper Details

Date Published: 21 May 2015
PDF: 8 pages
Proc. SPIE 9501, Satellite Data Compression, Communications, and Processing XI, 950109 (21 May 2015); doi: 10.1117/12.2178013
Show Author Affiliations
Jiaojiao Li, Xidian Univ. (China)
Qian Du, Mississippi State Univ. (United States)
Wei Li, Beijing Univ. of Chemical Technology (China)
Yunsong Li, Xidian Univ. (China)


Published in SPIE Proceedings Vol. 9501:
Satellite Data Compression, Communications, and Processing XI
Bormin Huang; Chein-I Chang; Chulhee Lee; Yunsong Li; Qian Du, Editor(s)

© SPIE. Terms of Use
Back to Top