Relevance assignment and fusion of multiple learning methods applied to remote sensing image analysis

Peter Bajcsy, Wei Wen Feng, Praveen Kumar

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

With the advances in remote sensing, various machine learning techniques could be applied to study variable relationships. Although prediction models obtained using machine learning techniques has proven to be suitable for predictions, they do not explicitly provide means for determining input-output variable relevance. We investigated the issue of relevance assignment for multiple machine learning models applied to remote sensing variables in the context of terrestrial hydrology. The relevance is defined as the influence of an input variable with respect to predicting the output result. We introduce a methodology for assigning relevance using various machine learning methods. The learning methods we use include Regression Tree, Support Vector Machine, and K-Nearest Neighbor. We derive the relevance computation scheme for each learning method and propose a method for fusing relevance assignment results from multiple learning techniques by averaging and voting mechanism. All methods are evaluated in terms of relevance accuracy estimation with synthetic and measured data.

Original languageEnglish (US)
Title of host publicationProceedings - SMC-IT 2006
Subtitle of host publication2nd IEEE International Conference on Space Mission Challenges for Information Technology
Pages291-298
Number of pages8
DOIs
StatePublished - Dec 1 2006
EventSMC-IT 2006: 2nd IEEE International Conference on Space Mission Challenges for Information Technology - Pasadena, CA, United States
Duration: Jul 17 2006Jul 20 2006

Publication series

NameProceedings - SMC-IT 2006: 2nd IEEE International Conference on Space Mission Challenges for Information Technology
Volume2006

Other

OtherSMC-IT 2006: 2nd IEEE International Conference on Space Mission Challenges for Information Technology
CountryUnited States
CityPasadena, CA
Period7/17/067/20/06

ASJC Scopus subject areas

  • Computer Science(all)
  • Aerospace Engineering

Fingerprint Dive into the research topics of 'Relevance assignment and fusion of multiple learning methods applied to remote sensing image analysis'. Together they form a unique fingerprint.

Cite this