Signal detection on graphs: Bernoulli noise model

Siheng Chen, Yaoqing Yang, Aarti Singh, Jelena Kovacevic

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

Abstract

We consider detecting localized binary attributes on a graph. A localized binary attribute means that the nodes activated by the attribute form form a subgraph that can be easily separated from the other nodes. We formulate a statistical hypothesis test to decide whether a given attribute is localized or not. We propose two statistics: graph wavelet statistic and graph scan statistic. Both are shown to be efficient and statistically effective. We further apply the proposed methods to rank research keywords as attributes in a coauthorship network collected from IEEE Xplore. The experimental results show that the proposed graph wavelet statistic and graph scan statistic are effective and efficient.1

Original languageEnglish (US)
Title of host publication2016 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2016 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages395-399
Number of pages5
ISBN (Electronic)9781509045457
DOIs
StatePublished - Apr 19 2017
Event2016 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2016 - Washington, United States
Duration: Dec 7 2016Dec 9 2016

Other

Other2016 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2016
CountryUnited States
CityWashington
Period12/7/1612/9/16

Fingerprint

Signal detection
Statistics
Statistical tests

ASJC Scopus subject areas

  • Signal Processing
  • Computer Networks and Communications

Cite this

Chen, S., Yang, Y., Singh, A., & Kovacevic, J. (2017). Signal detection on graphs: Bernoulli noise model. In 2016 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2016 - Proceedings (pp. 395-399). [7905871] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/GlobalSIP.2016.7905871

Signal detection on graphs : Bernoulli noise model. / Chen, Siheng; Yang, Yaoqing; Singh, Aarti; Kovacevic, Jelena.

2016 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2016 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2017. p. 395-399 7905871.

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

Chen, S, Yang, Y, Singh, A & Kovacevic, J 2017, Signal detection on graphs: Bernoulli noise model. in 2016 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2016 - Proceedings., 7905871, Institute of Electrical and Electronics Engineers Inc., pp. 395-399, 2016 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2016, Washington, United States, 12/7/16. https://doi.org/10.1109/GlobalSIP.2016.7905871
Chen S, Yang Y, Singh A, Kovacevic J. Signal detection on graphs: Bernoulli noise model. In 2016 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2016 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2017. p. 395-399. 7905871 https://doi.org/10.1109/GlobalSIP.2016.7905871
Chen, Siheng ; Yang, Yaoqing ; Singh, Aarti ; Kovacevic, Jelena. / Signal detection on graphs : Bernoulli noise model. 2016 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2016 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 395-399
@inproceedings{a6955f88d15c4dcfab0b56c34d0811f2,
title = "Signal detection on graphs: Bernoulli noise model",
abstract = "We consider detecting localized binary attributes on a graph. A localized binary attribute means that the nodes activated by the attribute form form a subgraph that can be easily separated from the other nodes. We formulate a statistical hypothesis test to decide whether a given attribute is localized or not. We propose two statistics: graph wavelet statistic and graph scan statistic. Both are shown to be efficient and statistically effective. We further apply the proposed methods to rank research keywords as attributes in a coauthorship network collected from IEEE Xplore. The experimental results show that the proposed graph wavelet statistic and graph scan statistic are effective and efficient.1",
author = "Siheng Chen and Yaoqing Yang and Aarti Singh and Jelena Kovacevic",
year = "2017",
month = "4",
day = "19",
doi = "10.1109/GlobalSIP.2016.7905871",
language = "English (US)",
pages = "395--399",
booktitle = "2016 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2016 - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Signal detection on graphs

T2 - Bernoulli noise model

AU - Chen, Siheng

AU - Yang, Yaoqing

AU - Singh, Aarti

AU - Kovacevic, Jelena

PY - 2017/4/19

Y1 - 2017/4/19

N2 - We consider detecting localized binary attributes on a graph. A localized binary attribute means that the nodes activated by the attribute form form a subgraph that can be easily separated from the other nodes. We formulate a statistical hypothesis test to decide whether a given attribute is localized or not. We propose two statistics: graph wavelet statistic and graph scan statistic. Both are shown to be efficient and statistically effective. We further apply the proposed methods to rank research keywords as attributes in a coauthorship network collected from IEEE Xplore. The experimental results show that the proposed graph wavelet statistic and graph scan statistic are effective and efficient.1

AB - We consider detecting localized binary attributes on a graph. A localized binary attribute means that the nodes activated by the attribute form form a subgraph that can be easily separated from the other nodes. We formulate a statistical hypothesis test to decide whether a given attribute is localized or not. We propose two statistics: graph wavelet statistic and graph scan statistic. Both are shown to be efficient and statistically effective. We further apply the proposed methods to rank research keywords as attributes in a coauthorship network collected from IEEE Xplore. The experimental results show that the proposed graph wavelet statistic and graph scan statistic are effective and efficient.1

UR - http://www.scopus.com/inward/record.url?scp=85019183692&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85019183692&partnerID=8YFLogxK

U2 - 10.1109/GlobalSIP.2016.7905871

DO - 10.1109/GlobalSIP.2016.7905871

M3 - Conference contribution

AN - SCOPUS:85019183692

SP - 395

EP - 399

BT - 2016 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2016 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

ER -