CLASSIFYING SIMULATED ACOUSTIC SOURCES USING A BACKPROPAGATION NEURAL NETWORK: A RESEARCHER'S TOOLKIT

PDF

Authors
  1. Cutmore, T.R.H.
  2. Arrabito, G.R.
Corporate Authors
Defence and Civil Inst of Environmental Medicine, Downsview ONT (CAN)
Abstract
Traditionally, passive sonar signals have been processed by the human operator using visual and/or auditory displays to achieve detection and classification of target vessels. Based on the presence or absence of features, the operator attempts to determine the identity of the target. Training is often intensive and lengthy. Consequently, it is necessary to develop tools and explore techniques which can assist the human operator. This report describes tools for simulating complex non-speech time series data of the type received by a hydrophone, and a backpropagation (BP) artificial neural network (ANN) for classifying the data. We use the Cmusic (26) sound synthesis program to simulate complex non-speech sounds such as those received by a hydrophone.
Report Number
DCIEM-94-63 —
Date of publication
01 Dec 1994
Number of Pages
28
DSTKIM No
95-01540
CANDIS No
150662
Format(s):
Hardcopy;Document Image stored on Optical Disk

Permanent link

Document 1 of 1

Date modified: