Improving the performance of extreme learning machine for hyperspectral image classification

Jiaojiao Li, Qian Du*, Wei Li, Yunsong Li

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Citation (Scopus)

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.

Original languageEnglish
Title of host publicationSatellite Data Compression, Communications, and Processing XI
EditorsYunsong Li, Chein-I Chang, Bormin Huang, Qian Du, Chulhee Lee
PublisherSPIE
ISBN (Electronic)9781628416176
DOIs
Publication statusPublished - 2015
Externally publishedYes
EventSatellite Data Compression, Communications, and Processing XI - Baltimore, United States
Duration: 23 Apr 201524 Apr 2015

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume9501
ISSN (Print)0277-786X
ISSN (Electronic)1996-756X

Conference

ConferenceSatellite Data Compression, Communications, and Processing XI
Country/TerritoryUnited States
CityBaltimore
Period23/04/1524/04/15

Keywords

  • Classification
  • Extreme Learning Machine
  • Hyperspectral Imagery
  • Kernel Method
  • Neural Network
  • Support Vector Machine

Fingerprint

Dive into the research topics of 'Improving the performance of extreme learning machine for hyperspectral image classification'. Together they form a unique fingerprint.

Cite this