An episodal neural-net computing approach to the detection and interpretation of underwater acoustic transients

Yoh Han Pao; Thomas L. Hemminger; Dennis J. Adams; Stuart Clary

An episodal neural-net computing approach to the detection and interpretation of underwater acoustic transients

Yoh Han Pao, Thomas L. Hemminger, Dennis J. Adams, Stuart Clary

School of Engineering (Behrend)

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

6 Scopus citations

Abstract

Acoustic transients develop and fade away continually in ocean environments. Accordingly, detection and interpretation of these are complicated by the fact that detection and classification cannot be made on the basis of temporal snapshots alone. Interpretation of transients must rest on the processing and classification of entire episodes of such continuing signals. The authors describe experiments in the design and implementation of such an episodal associative classifier which makes concurrent use of neural network self-organization and supervised learning methodologies. This system has no difficulty classifying signals from within test data sets and is also fast, robust, adaptive, and well suited for a wide range of sequence lengths.

Original language	English (US)
Title of host publication	IEEE Conference on Neural Networks for Ocean Engineering
Publisher	Publ by IEEE
Pages	21-28
Number of pages	8
ISBN (Print)	0780302052
State	Published - Dec 1 1991
Event	Proceedings of the IEEE Conference on Neural Networks for Ocean Engineering - Washington, DC, USA Duration: Aug 15 1991 → Aug 17 1991

Publication series

Name	IEEE Conference on Neural Networks for Ocean Engineering

Other

Other	Proceedings of the IEEE Conference on Neural Networks for Ocean Engineering
City	Washington, DC, USA
Period	8/15/91 → 8/17/91

All Science Journal Classification (ASJC) codes

Engineering(all)

Cite this

@inproceedings{a5ce19cdff7b43f8a95b8636cfb633e4,

title = "An episodal neural-net computing approach to the detection and interpretation of underwater acoustic transients",

abstract = "Acoustic transients develop and fade away continually in ocean environments. Accordingly, detection and interpretation of these are complicated by the fact that detection and classification cannot be made on the basis of temporal snapshots alone. Interpretation of transients must rest on the processing and classification of entire episodes of such continuing signals. The authors describe experiments in the design and implementation of such an episodal associative classifier which makes concurrent use of neural network self-organization and supervised learning methodologies. This system has no difficulty classifying signals from within test data sets and is also fast, robust, adaptive, and well suited for a wide range of sequence lengths.",

author = "Pao, {Yoh Han} and Hemminger, {Thomas L.} and Adams, {Dennis J.} and Stuart Clary",

year = "1991",

month = dec,

day = "1",

language = "English (US)",

isbn = "0780302052",

series = "IEEE Conference on Neural Networks for Ocean Engineering",

publisher = "Publ by IEEE",

pages = "21--28",

booktitle = "IEEE Conference on Neural Networks for Ocean Engineering",

note = "Proceedings of the IEEE Conference on Neural Networks for Ocean Engineering ; Conference date: 15-08-1991 Through 17-08-1991",

}

Pao, YH, Hemminger, TL, Adams, DJ & Clary, S 1991, An episodal neural-net computing approach to the detection and interpretation of underwater acoustic transients. in IEEE Conference on Neural Networks for Ocean Engineering. IEEE Conference on Neural Networks for Ocean Engineering, Publ by IEEE, pp. 21-28, Proceedings of the IEEE Conference on Neural Networks for Ocean Engineering, Washington, DC, USA, 8/15/91.

An episodal neural-net computing approach to the detection and interpretation of underwater acoustic transients. / Pao, Yoh Han; Hemminger, Thomas L.; Adams, Dennis J. et al.

IEEE Conference on Neural Networks for Ocean Engineering. Publ by IEEE, 1991. p. 21-28 (IEEE Conference on Neural Networks for Ocean Engineering).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - An episodal neural-net computing approach to the detection and interpretation of underwater acoustic transients

AU - Pao, Yoh Han

AU - Hemminger, Thomas L.

AU - Adams, Dennis J.

AU - Clary, Stuart

PY - 1991/12/1

Y1 - 1991/12/1

N2 - Acoustic transients develop and fade away continually in ocean environments. Accordingly, detection and interpretation of these are complicated by the fact that detection and classification cannot be made on the basis of temporal snapshots alone. Interpretation of transients must rest on the processing and classification of entire episodes of such continuing signals. The authors describe experiments in the design and implementation of such an episodal associative classifier which makes concurrent use of neural network self-organization and supervised learning methodologies. This system has no difficulty classifying signals from within test data sets and is also fast, robust, adaptive, and well suited for a wide range of sequence lengths.

AB - Acoustic transients develop and fade away continually in ocean environments. Accordingly, detection and interpretation of these are complicated by the fact that detection and classification cannot be made on the basis of temporal snapshots alone. Interpretation of transients must rest on the processing and classification of entire episodes of such continuing signals. The authors describe experiments in the design and implementation of such an episodal associative classifier which makes concurrent use of neural network self-organization and supervised learning methodologies. This system has no difficulty classifying signals from within test data sets and is also fast, robust, adaptive, and well suited for a wide range of sequence lengths.

UR - http://www.scopus.com/inward/record.url?scp=0026375062&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0026375062&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0026375062

SN - 0780302052

T3 - IEEE Conference on Neural Networks for Ocean Engineering

SP - 21

EP - 28

BT - IEEE Conference on Neural Networks for Ocean Engineering

PB - Publ by IEEE

T2 - Proceedings of the IEEE Conference on Neural Networks for Ocean Engineering

Y2 - 15 August 1991 through 17 August 1991

ER -

An episodal neural-net computing approach to the detection and interpretation of underwater acoustic transients

Abstract

Publication series

Other

All Science Journal Classification (ASJC) codes

Other files and links

Fingerprint

Cite this