Accession Number : ADA326367
Title : Classification of Aspect-Dependent Targets by a Biomimetic Neural Network.
Descriptive Note : Technical rept.,
Corporate Author : NAVAL COMMAND CONTROL AND OCEAN SURVEILLANCE CENTER RDT AND E DIV SAN DIEGO CA
Personal Author(s) : Helweg, D. A. ; Moore, P. W.
PDF Url : ADA326367
Report Date : JUN 1997
Pagination or Media Count : 13
Abstract : A biomimetic neural network was used to model a bottlenose dolphin's ability to recognize aspect-dependent targets. Researchers used echo trains recorded during the dolphin trials to train an Integrator Gateway Network (IGN) to discriminate among the targets using echo spectra. The IGN classifies targets using an average-like sum of the spectra from successive echoes. However, combining echoes may reduce classification accuracy if the spectra vary from echo to echo. The dolphin and the IGN learned to recognize the geometric targets, even though orientation could vary. The process of recognition using cumulated echoes was robust for nonstationary raw input. The results support the notion that ensonified mines with complex shapes and echoes may be reliably classified using neural network architectures that are motivated through understanding of Marine Mammal System echolocation signals and performance.
Descriptors : *NEURAL NETS, *ACOUSTIC DETECTORS, SIGNAL PROCESSING, TARGET RECOGNITION, ACOUSTIC DETECTION, LEARNING MACHINES, TARGET DISCRIMINATION, MARINE BIOLOGY, PATTERN RECOGNITION, HYDROPHONES, TARGET CLASSIFICATION, TARGET ECHOES, UNDERWATER SOUND SIGNALS, DOLPHINS(MAMMALS).
Subject Categories : Cybernetics
Acoustic Detection and Detectors
Distribution Statement : APPROVED FOR PUBLIC RELEASE