Deteriorative effects on feature-based signal detection due to imperfect training

Quang Thai; Sam Reisenfeld

doi:10.1109/WCNC.2012.6214504

Deteriorative effects on feature-based signal detection due to imperfect training

Quang Thai^*, Sam Reisenfeld

^*Corresponding author for this work

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

Abstract

Feature-based detection techniques have been advocated for robust spectrum sensing in cognitive radios. Cognitive radios must be able to train themselves to identify the features for a specific primary user at a given channel, time or location. However, 'in-the-field' training relies on signal observations where there is uncertainty about whether or not it is truly representative of the primary user. This work considers this uncertainty, how it effects the detector's training time and performance, and identifies a trade-off between these outcomes. A two-stage detector structure is also illustrated to fulfill both the training and operational requirements of such detectors.

Original language	English
Title of host publication	2012 IEEE Wireless Communications and Networking Conference, WCNC 2012
Place of Publication	Piscataway, N.J
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
Pages	914-919
Number of pages	6
ISBN (Print)	9781467304375
DOIs	https://doi.org/10.1109/WCNC.2012.6214504
Publication status	Published - 2012
Event	2012 IEEE Wireless Communications and Networking Conference, WCNC 2012 - Paris, France Duration: 1 Apr 2012 → 4 Apr 2012

Other

Other	2012 IEEE Wireless Communications and Networking Conference, WCNC 2012
Country/Territory	France
City	Paris
Period	1/04/12 → 4/04/12

Keywords

cognitive radio
detection algorithms
detectors
feature extraction
learning systems
signal analysis
signal detection
supervised learning
training

Access to Document

10.1109/WCNC.2012.6214504

Cite this

@inproceedings{2376d5593daf4e1e9154aef3999f7fd9,

title = "Deteriorative effects on feature-based signal detection due to imperfect training",

abstract = "Feature-based detection techniques have been advocated for robust spectrum sensing in cognitive radios. Cognitive radios must be able to train themselves to identify the features for a specific primary user at a given channel, time or location. However, 'in-the-field' training relies on signal observations where there is uncertainty about whether or not it is truly representative of the primary user. This work considers this uncertainty, how it effects the detector's training time and performance, and identifies a trade-off between these outcomes. A two-stage detector structure is also illustrated to fulfill both the training and operational requirements of such detectors.",

keywords = "cognitive radio, detection algorithms, detectors, feature extraction, learning systems, signal analysis, signal detection, supervised learning, training",

author = "Quang Thai and Sam Reisenfeld",

year = "2012",

doi = "10.1109/WCNC.2012.6214504",

language = "English",

isbn = "9781467304375",

pages = "914--919",

booktitle = "2012 IEEE Wireless Communications and Networking Conference, WCNC 2012",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

address = "United States",

note = "2012 IEEE Wireless Communications and Networking Conference, WCNC 2012 ; Conference date: 01-04-2012 Through 04-04-2012",

}

Thai, Q & Reisenfeld, S 2012, Deteriorative effects on feature-based signal detection due to imperfect training. in 2012 IEEE Wireless Communications and Networking Conference, WCNC 2012., 6214504, Institute of Electrical and Electronics Engineers (IEEE), Piscataway, N.J, pp. 914-919, 2012 IEEE Wireless Communications and Networking Conference, WCNC 2012, Paris, France, 1/04/12. https://doi.org/10.1109/WCNC.2012.6214504

Deteriorative effects on feature-based signal detection due to imperfect training. / Thai, Quang; Reisenfeld, Sam.
2012 IEEE Wireless Communications and Networking Conference, WCNC 2012. Piscataway, N.J: Institute of Electrical and Electronics Engineers (IEEE), 2012. p. 914-919 6214504.

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

TY - GEN

T1 - Deteriorative effects on feature-based signal detection due to imperfect training

AU - Thai, Quang

AU - Reisenfeld, Sam

PY - 2012

Y1 - 2012

N2 - Feature-based detection techniques have been advocated for robust spectrum sensing in cognitive radios. Cognitive radios must be able to train themselves to identify the features for a specific primary user at a given channel, time or location. However, 'in-the-field' training relies on signal observations where there is uncertainty about whether or not it is truly representative of the primary user. This work considers this uncertainty, how it effects the detector's training time and performance, and identifies a trade-off between these outcomes. A two-stage detector structure is also illustrated to fulfill both the training and operational requirements of such detectors.

AB - Feature-based detection techniques have been advocated for robust spectrum sensing in cognitive radios. Cognitive radios must be able to train themselves to identify the features for a specific primary user at a given channel, time or location. However, 'in-the-field' training relies on signal observations where there is uncertainty about whether or not it is truly representative of the primary user. This work considers this uncertainty, how it effects the detector's training time and performance, and identifies a trade-off between these outcomes. A two-stage detector structure is also illustrated to fulfill both the training and operational requirements of such detectors.

KW - cognitive radio

KW - detection algorithms

KW - detectors

KW - feature extraction

KW - learning systems

KW - signal analysis

KW - signal detection

KW - supervised learning

KW - training

UR - http://www.scopus.com/inward/record.url?scp=84864350379&partnerID=8YFLogxK

U2 - 10.1109/WCNC.2012.6214504

DO - 10.1109/WCNC.2012.6214504

M3 - Conference proceeding contribution

AN - SCOPUS:84864350379

SN - 9781467304375

SP - 914

EP - 919

BT - 2012 IEEE Wireless Communications and Networking Conference, WCNC 2012

PB - Institute of Electrical and Electronics Engineers (IEEE)

CY - Piscataway, N.J

T2 - 2012 IEEE Wireless Communications and Networking Conference, WCNC 2012

Y2 - 1 April 2012 through 4 April 2012

ER -

Deteriorative effects on feature-based signal detection due to imperfect training

Abstract

Other

Keywords

Access to Document

Other files and links

Fingerprint

Cite this