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

Shang Hung Lin; S. Y. Kung

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

Shang Hung Lin, S. Y. Kung

Research output: Contribution to conference › Paper › peer-review

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 language	English (US)
Pages	236-239
Number of pages	4
State	Published - 1995
Event	Proceedings of the 1995 IEEE International Conference on Image Processing. Part 3 (of 3) - Washington, DC, USA Duration: Oct 23 1995 → Oct 26 1995

Other

Other	Proceedings of the 1995 IEEE International Conference on Image Processing. Part 3 (of 3)
City	Washington, DC, USA
Period	10/23/95 → 10/26/95

All Science Journal Classification (ASJC) codes

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

Cite this

@conference{f37965d44fd4498ebd53d907949a5b01,

title = "Probabilistic DBNN via expectation-maximization with multi-sensor classification applications",

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.",

author = "Lin, {Shang Hung} and Kung, {S. Y.}",

year = "1995",

language = "English (US)",

pages = "236--239",

note = "Proceedings of the 1995 IEEE International Conference on Image Processing. Part 3 (of 3) ; Conference date: 23-10-1995 Through 26-10-1995",

}

TY - CONF

T1 - Probabilistic DBNN via expectation-maximization with multi-sensor classification applications

AU - Lin, Shang Hung

AU - Kung, S. Y.

PY - 1995

Y1 - 1995

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=0029493102&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0029493102&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:0029493102

SP - 236

EP - 239

T2 - Proceedings of the 1995 IEEE International Conference on Image Processing. Part 3 (of 3)

Y2 - 23 October 1995 through 26 October 1995

ER -

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

Abstract

Other

All Science Journal Classification (ASJC) codes

Other files and links

Fingerprint

Cite this