Display Publications by [Year] [Type] [Topic]
The identification and classification of underwater acoustic signals is an extremely difficult problem because of low SNRs and a high degree of variability in the signals emanated from the same type of sound source. Since different classification techniques have different inductive biases, a single method cannot give the best results for all signal types. Rather, more accurate and robust classification can obtained by combining the outputs (evidences) of multiple classifiers based on neural network and/or statistical pattern recognition techniques. In this paper, five approaches are compared for integrating the decisions made by networks using sigmoidal activation functions exhibiting global responses with those made by localized basis function networks. These methods are compared using realistic oceanic data. The first method uses an entropy-based weighting of individual classifier outputs. The second is based on combination of confidence factors in a manner similar to that used in MYCIN. The other three methods use simpler techniques of majority voting, averaging, and density estimation with little extra computational overhead. The results indicate that evidence integration provides significant gains when networks are trained on qualitatively different feature sets. Integration techniques also provide a basis for detecting outliers and false alarms.
(unavailable)
@incollection{ghosh-tumer_cds96,
author = "J. Ghosh and K. Tumer and S. Beck and L. Deuser",
title = "Integration of Neural Classifiers for Passive Sonar Signals",
booktitle= "Control and Dynamic Systems---Advances in Theory and Applications",
editor = "C.T. Leondes",
publisher="Academic Press",
volume={77},
pages = {301-338},
abstract={The identification and classification of underwater acoustic signals is an extremely difficult problem because of low SNRs and a high degree of variability in the signals emanated from the same type of sound source. Since different classification techniques have different inductive biases, a single method cannot give the best results for all signal types. Rather, more accurate and robust classification can obtained by combining the outputs (evidences) of multiple classifiers based on neural network and/or statistical pattern recognition techniques. In this paper, five approaches are compared for integrating the decisions made by networks using sigmoidal activation functions exhibiting global responses with those made by localized basis function networks. These methods are compared using realistic oceanic data. The first method uses an entropy-based weighting of individual classifier outputs. The second is based on combination of confidence factors in a manner similar to that used in MYCIN. The other three methods use simpler techniques of majority voting, averaging, and density estimation with little extra computational overhead. The results indicate that evidence integration provides significant gains when networks are trained on qualitatively different feature sets. Integration techniques also provide a basis for detecting outliers and false alarms.},
bib2html_pubtype = {Book Chapters},
bib2html_rescat = {Classifier Ensembles},
year= {1996}
}
Generated by bib2html.pl (written by Patrick Riley ) on Wed Apr 01, 2020 17:39:43