Show simple item record

dc.contributor.authorDobeck, Gerald J.
dc.contributor.authorJamshidi, Arta A.
dc.contributor.authorYao, De
dc.contributor.authorAzimi-Sadjadi, Mahmood R.
dc.date.accessioned2007-01-03T04:48:23Z
dc.date.available2007-01-03T04:48:23Z
dc.date.issued2002
dc.descriptionIncludes bibliographical references.
dc.description.abstractA new adaptive underwater target classification system to cope with environmental changes in acoustic backscattered data from targets and nontargets is introduced in this paper. The core of the system is the adaptive feature mapping that minimizes the classification error rate of the classifier. The goal is to map the feature vector in such a way that the mapped version remains invariant to the environmental changes. A K-nearest neighbor (K-NN) system is used as a memory to provide the closest matches of an unknown pattern in the feature space. The classification decision is done by a backpropagation neural network (BPNN). Two different cost functions for adaptation are defined. These two cost functions are then combined together to improve the classification performance. The test results on a 40-kHz linear FM acoustic backscattered data set collected from six different objects are presented. These results demonstrate the effectiveness of the adaptive system versus nonadaptive system when the signal-to-reverberation ratio (SRR) in the environment is varying.
dc.description.sponsorshipThis work was supported by the Office of Naval Research, Bisonar Program under Contracts N00014-99-1-0166 and N00014-01-1-0307.
dc.format.mediumborn digital
dc.format.mediumarticles
dc.identifier.bibliographicCitationAzimi-Sadjadi, Mahmood R., et al., Underwater Target Classification in Changing Environments Using an Adaptive Feature Mapping, IEEE Transactions on Neural Networks 13, no. 5 (September 2002): 1099-1111.
dc.identifier.urihttp://hdl.handle.net/10217/928
dc.languageEnglish
dc.publisherColorado State University. Libraries
dc.publisher.originalIEEE
dc.relation.ispartofFaculty Publications - Department of Electrical and Computer Engineering
dc.rights©2002 IEEE
dc.subjectin situ learning
dc.subjectfeature mapping
dc.subjectadaptive classification
dc.subjectneural networks
dc.subjectunderwater target classification
dc.titleUnderwater target classification in changing environments using an adaptive feature mapping
dc.typeText


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record