Neural network based novelty filtering for signal detection enhancement

Hanseok Ko, Robert Baran, Mohammed Arozullah

Research output: Chapter in Book/Report/Conference proceedingConference contribution

10 Citations (Scopus)

Abstract

This paper concerns the analytical basis for designing adaptive novelty filter (ANF), based on a multilayer feedforward neural network, to enhance the detectability of weak, transient signals in the presence of comparatively high level background noise or interference which has unknown, uncharacterized, or time varying statistical properties. The ANF serves as a front end pre-processor to any device which performs signal detection, estimation, or classification. The ideal ANF would selectively filter out the noise while passing the signal without attenuation or distortion. The conditions under which the novelty filtering effect is most pronounced are presented.

Original languageEnglish
Title of host publication1992 Proceedings of the 35th Midwest Symposium on Circuits and Systems
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages252-255
Number of pages4
ISBN (Electronic)0780305108
DOIs
Publication statusPublished - 1992 Jan 1
Externally publishedYes
Event35th Midwest Symposium on Circuits and Systems, MWSCAS 1992 - Washington, United States
Duration: 1992 Aug 91992 Aug 12

Publication series

NameMidwest Symposium on Circuits and Systems
Volume1992-August
ISSN (Print)1548-3746

Conference

Conference35th Midwest Symposium on Circuits and Systems, MWSCAS 1992
CountryUnited States
CityWashington
Period92/8/992/8/12

Fingerprint

Signal detection
Adaptive filters
Neural networks
Feedforward neural networks
Multilayer neural networks

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Electrical and Electronic Engineering

Cite this

Ko, H., Baran, R., & Arozullah, M. (1992). Neural network based novelty filtering for signal detection enhancement. In 1992 Proceedings of the 35th Midwest Symposium on Circuits and Systems (pp. 252-255). [271387] (Midwest Symposium on Circuits and Systems; Vol. 1992-August). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/MWSCAS.1992.271387

Neural network based novelty filtering for signal detection enhancement. / Ko, Hanseok; Baran, Robert; Arozullah, Mohammed.

1992 Proceedings of the 35th Midwest Symposium on Circuits and Systems. Institute of Electrical and Electronics Engineers Inc., 1992. p. 252-255 271387 (Midwest Symposium on Circuits and Systems; Vol. 1992-August).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Ko, H, Baran, R & Arozullah, M 1992, Neural network based novelty filtering for signal detection enhancement. in 1992 Proceedings of the 35th Midwest Symposium on Circuits and Systems., 271387, Midwest Symposium on Circuits and Systems, vol. 1992-August, Institute of Electrical and Electronics Engineers Inc., pp. 252-255, 35th Midwest Symposium on Circuits and Systems, MWSCAS 1992, Washington, United States, 92/8/9. https://doi.org/10.1109/MWSCAS.1992.271387
Ko H, Baran R, Arozullah M. Neural network based novelty filtering for signal detection enhancement. In 1992 Proceedings of the 35th Midwest Symposium on Circuits and Systems. Institute of Electrical and Electronics Engineers Inc. 1992. p. 252-255. 271387. (Midwest Symposium on Circuits and Systems). https://doi.org/10.1109/MWSCAS.1992.271387
Ko, Hanseok ; Baran, Robert ; Arozullah, Mohammed. / Neural network based novelty filtering for signal detection enhancement. 1992 Proceedings of the 35th Midwest Symposium on Circuits and Systems. Institute of Electrical and Electronics Engineers Inc., 1992. pp. 252-255 (Midwest Symposium on Circuits and Systems).
@inproceedings{d68e464bbef445e0bbe52b0bed39ad21,
title = "Neural network based novelty filtering for signal detection enhancement",
abstract = "This paper concerns the analytical basis for designing adaptive novelty filter (ANF), based on a multilayer feedforward neural network, to enhance the detectability of weak, transient signals in the presence of comparatively high level background noise or interference which has unknown, uncharacterized, or time varying statistical properties. The ANF serves as a front end pre-processor to any device which performs signal detection, estimation, or classification. The ideal ANF would selectively filter out the noise while passing the signal without attenuation or distortion. The conditions under which the novelty filtering effect is most pronounced are presented.",
author = "Hanseok Ko and Robert Baran and Mohammed Arozullah",
year = "1992",
month = "1",
day = "1",
doi = "10.1109/MWSCAS.1992.271387",
language = "English",
series = "Midwest Symposium on Circuits and Systems",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "252--255",
booktitle = "1992 Proceedings of the 35th Midwest Symposium on Circuits and Systems",

}

TY - GEN

T1 - Neural network based novelty filtering for signal detection enhancement

AU - Ko, Hanseok

AU - Baran, Robert

AU - Arozullah, Mohammed

PY - 1992/1/1

Y1 - 1992/1/1

N2 - This paper concerns the analytical basis for designing adaptive novelty filter (ANF), based on a multilayer feedforward neural network, to enhance the detectability of weak, transient signals in the presence of comparatively high level background noise or interference which has unknown, uncharacterized, or time varying statistical properties. The ANF serves as a front end pre-processor to any device which performs signal detection, estimation, or classification. The ideal ANF would selectively filter out the noise while passing the signal without attenuation or distortion. The conditions under which the novelty filtering effect is most pronounced are presented.

AB - This paper concerns the analytical basis for designing adaptive novelty filter (ANF), based on a multilayer feedforward neural network, to enhance the detectability of weak, transient signals in the presence of comparatively high level background noise or interference which has unknown, uncharacterized, or time varying statistical properties. The ANF serves as a front end pre-processor to any device which performs signal detection, estimation, or classification. The ideal ANF would selectively filter out the noise while passing the signal without attenuation or distortion. The conditions under which the novelty filtering effect is most pronounced are presented.

UR - http://www.scopus.com/inward/record.url?scp=84964730271&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84964730271&partnerID=8YFLogxK

U2 - 10.1109/MWSCAS.1992.271387

DO - 10.1109/MWSCAS.1992.271387

M3 - Conference contribution

AN - SCOPUS:84964730271

T3 - Midwest Symposium on Circuits and Systems

SP - 252

EP - 255

BT - 1992 Proceedings of the 35th Midwest Symposium on Circuits and Systems

PB - Institute of Electrical and Electronics Engineers Inc.

ER -