Improved type-based detection of analog signals

Don H. Johnson; Paulo A. Goncalves; Richard G. Baraniuk

Improved type-based detection of analog signals

Don H. Johnson, Paulo A. Goncalves, Richard G. Baraniuk

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

Abstract

When applied to continuous-time observations, type-based detection strategies are limited by the necessity to crudely quantize each sample. To alleviate this problem, we smooth the types for both the training and observation data with a linear filter. This post-processing improves detector performance significantly (error probabilities decrease by over a factor of three) without incurring a significant computational penalty. However, this improvement depends on the amplitude distribution and on the quantizer's characteristics.

Original language	English (US)
Title of host publication	ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Editors	Anon
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	3717-3720
Number of pages	4
Volume	5
State	Published - 1997
Event	Proceedings of the 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP. Part 1 (of 5) - Munich, Ger Duration: Apr 21 1997 → Apr 24 1997

Other

Other	Proceedings of the 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP. Part 1 (of 5)
City	Munich, Ger
Period	4/21/97 → 4/24/97

ASJC Scopus subject areas

Signal Processing
Electrical and Electronic Engineering
Acoustics and Ultrasonics

Cite this

Improved type-based detection of analog signals. / Johnson, Don H.; Goncalves, Paulo A.; Baraniuk, Richard G.

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. ed. / Anon. Vol. 5 Institute of Electrical and Electronics Engineers Inc., 1997. p. 3717-3720.

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

Johnson, DH, Goncalves, PA & Baraniuk, RG 1997, Improved type-based detection of analog signals. in Anon (ed.), ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. vol. 5, Institute of Electrical and Electronics Engineers Inc., pp. 3717-3720, Proceedings of the 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP. Part 1 (of 5), Munich, Ger, 4/21/97.

@inproceedings{3a1a66e2bc2e418d91e76e2dfe498bc0,

title = "Improved type-based detection of analog signals",

abstract = "When applied to continuous-time observations, type-based detection strategies are limited by the necessity to crudely quantize each sample. To alleviate this problem, we smooth the types for both the training and observation data with a linear filter. This post-processing improves detector performance significantly (error probabilities decrease by over a factor of three) without incurring a significant computational penalty. However, this improvement depends on the amplitude distribution and on the quantizer's characteristics.",

author = "Johnson, {Don H.} and Goncalves, {Paulo A.} and Baraniuk, {Richard G.}",

year = "1997",

language = "English (US)",

volume = "5",

pages = "3717--3720",

editor = "Anon",

booktitle = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

address = "United States",

note = "Proceedings of the 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP. Part 1 (of 5) ; Conference date: 21-04-1997 Through 24-04-1997",

}

TY - GEN

T1 - Improved type-based detection of analog signals

AU - Johnson, Don H.

AU - Goncalves, Paulo A.

AU - Baraniuk, Richard G.

PY - 1997

Y1 - 1997

N2 - When applied to continuous-time observations, type-based detection strategies are limited by the necessity to crudely quantize each sample. To alleviate this problem, we smooth the types for both the training and observation data with a linear filter. This post-processing improves detector performance significantly (error probabilities decrease by over a factor of three) without incurring a significant computational penalty. However, this improvement depends on the amplitude distribution and on the quantizer's characteristics.

AB - When applied to continuous-time observations, type-based detection strategies are limited by the necessity to crudely quantize each sample. To alleviate this problem, we smooth the types for both the training and observation data with a linear filter. This post-processing improves detector performance significantly (error probabilities decrease by over a factor of three) without incurring a significant computational penalty. However, this improvement depends on the amplitude distribution and on the quantizer's characteristics.

UR - http://www.scopus.com/inward/record.url?scp=0030673272&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0030673272&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0030673272

VL - 5

SP - 3717

EP - 3720

BT - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

A2 - Anon, null

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - Proceedings of the 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP. Part 1 (of 5)

Y2 - 21 April 1997 through 24 April 1997

ER -

Improved type-based detection of analog signals

Abstract

Other

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this