A neural network based seafloor classification using acoustic backscatter
DRS at CSIR-National Institute of Oceanography
View Archive InfoField | 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
|
|