Probabilistic DBNN via expectation-maximization with multi-sensor classification applications

Shang Hung Lin, Sun-Yuan Kung

Research output: Contribution to conferencePaper

6 Scopus citations

Abstract

Several training rules augmenting probabilistic DBNN (decision-based neural network) learning, based largely on the Expectation Maximization (FM) algorithm are investigated. The objective is to establish evidences that the probabilistic DBNN offers an effective tool for multi-sensor classification. Two approaches to multisensor classification are proposed and the enhanced performances studied. The first involves a hierarchical classification, where sensor informations are cascaded in sequential processing stages. The second is multi-sensor fusion, where sensor information are laterally combined to yield improved classification.

Original languageEnglish (US)
Pages236-239
Number of pages4
StatePublished - Dec 1 1995
EventProceedings of the 1995 IEEE International Conference on Image Processing. Part 3 (of 3) - Washington, DC, USA
Duration: Oct 23 1995Oct 26 1995

Other

OtherProceedings of the 1995 IEEE International Conference on Image Processing. Part 3 (of 3)
CityWashington, DC, USA
Period10/23/9510/26/95

All Science Journal Classification (ASJC) codes

  • Hardware and Architecture
  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Probabilistic DBNN via expectation-maximization with multi-sensor classification applications'. Together they form a unique fingerprint.

  • Cite this

    Lin, S. H., & Kung, S-Y. (1995). Probabilistic DBNN via expectation-maximization with multi-sensor classification applications. 236-239. Paper presented at Proceedings of the 1995 IEEE International Conference on Image Processing. Part 3 (of 3), Washington, DC, USA, .