Record Details

A neural network based seafloor classification using acoustic backscatter

DRS at CSIR-National Institute of Oceanography

View Archive Info
 
 
Field Value
 
Title A neural network based seafloor classification using acoustic backscatter
 
Creator Chakraborty, B.
 
Subject ocean floor
echosounders
backscatter
data acquisition
continental shelves
 
Description This paper presents a study results of the Artificial Neural Network (ANN) architectures [Self-Organizing Map (SOM) and Multi-Layer Perceptron (MLP)] using single beam echosounding data. The single beam echosounder, operable at 12 kHz, has been used for backscatter data acquisitions from three distinctly different seafloor's from the Arabian Sea. With some preprocessing of the snapshots, the performance of the SOM network is observed to be quite good. For unsupervised SOM network, only single snapshot is used for the training, and number of snapshots for subsequent testing of the network. Feature selection from ASCII data is an important component for a supervised MLP based network. Four selected features are used for training the network. The test results of the MLP based network are also discussed in the text.
 
Date 2008-08-11T12:32:40Z
2008-08-11T12:32:40Z
2002
 
Type Conference Article
 
Identifier Advances in soft computing - AFSS 2002. 2nd ed.. eds. by: Pal, N.R.; Sugeno, M.(2002 AFSS Int. Conf. on Fuzzy Systems; Calcutta; India; 3-6 Feb 2002). (Lecture Notes in Computer ScienceArtificial Intelligence; 2275), 245-250p.
no
http://drs.nio.org/drs/handle/2264/1449
 
Language en
 
Rights Springer
 
Publisher Springer-Verlag; Berlin, Heidelberg