A neuromorphic architecture for anomaly detection in autonomous large-area traffic monitoring

Qiuwen Chen; Qinru Qiu; Hai Li; Qing Wu

doi:10.1109/ICCAD.2013.6691119

A neuromorphic architecture for anomaly detection in autonomous large-area traffic monitoring

Qiuwen Chen, Qinru Qiu, Hai Li, Qing Wu

Department of Electrical Engineering & Computer Science

Research output: Chapter in Book/Entry/Poem › Conference contribution

13 Scopus citations

Abstract

The advanced sensing and imaging capability of today's sensor networks enables real time monitoring in a large area. In order to provide continuous monitoring and prompt situational awareness, an abstract-level autonomous information processing framework is developed that is able to detect various categories of abnormal traffic events with unsupervised learning. The framework is based on cogent confabulation model, which performs statistical inference in a manner inspired by human neocortex system. It enables detection and recognition of abnormal target vehicles within the context of surrounding traffic activities and previous events using likelihood-ratio test. A neuromorphic architecture is proposed which accelerates the computation for real-time detection by leveraging memristor crossbar arrays.

Original language	English (US)
Title of host publication	2013 IEEE/ACM International Conference on Computer-Aided Design, ICCAD 2013 - Digest of Technical Papers
Pages	202-205
Number of pages	4
DOIs	https://doi.org/10.1109/ICCAD.2013.6691119
State	Published - 2013
Event	2013 32nd IEEE/ACM International Conference on Computer-Aided Design, ICCAD 2013 - San Jose, CA, United States Duration: Nov 18 2013 → Nov 21 2013

Publication series

Name	IEEE/ACM International Conference on Computer-Aided Design, Digest of Technical Papers, ICCAD
ISSN (Print)	1092-3152

Other

Other	2013 32nd IEEE/ACM International Conference on Computer-Aided Design, ICCAD 2013
Country/Territory	United States
City	San Jose, CA
Period	11/18/13 → 11/21/13

Keywords

anomaly detection
cogent confabulation
neuromorphic architecture

ASJC Scopus subject areas

Software
Computer Science Applications
Computer Graphics and Computer-Aided Design

Access to Document

10.1109/ICCAD.2013.6691119

Cite this

Chen, Q., Qiu, Q., Li, H., & Wu, Q. (2013). A neuromorphic architecture for anomaly detection in autonomous large-area traffic monitoring. In 2013 IEEE/ACM International Conference on Computer-Aided Design, ICCAD 2013 - Digest of Technical Papers (pp. 202-205). Article 6691119 (IEEE/ACM International Conference on Computer-Aided Design, Digest of Technical Papers, ICCAD). https://doi.org/10.1109/ICCAD.2013.6691119

A neuromorphic architecture for anomaly detection in autonomous large-area traffic monitoring. / Chen, Qiuwen; Qiu, Qinru; Li, Hai et al.
2013 IEEE/ACM International Conference on Computer-Aided Design, ICCAD 2013 - Digest of Technical Papers. 2013. p. 202-205 6691119 (IEEE/ACM International Conference on Computer-Aided Design, Digest of Technical Papers, ICCAD).

Research output: Chapter in Book/Entry/Poem › Conference contribution

Chen, Q, Qiu, Q, Li, H & Wu, Q 2013, A neuromorphic architecture for anomaly detection in autonomous large-area traffic monitoring. in 2013 IEEE/ACM International Conference on Computer-Aided Design, ICCAD 2013 - Digest of Technical Papers., 6691119, IEEE/ACM International Conference on Computer-Aided Design, Digest of Technical Papers, ICCAD, pp. 202-205, 2013 32nd IEEE/ACM International Conference on Computer-Aided Design, ICCAD 2013, San Jose, CA, United States, 11/18/13. https://doi.org/10.1109/ICCAD.2013.6691119

Chen Q, Qiu Q, Li H, Wu Q. A neuromorphic architecture for anomaly detection in autonomous large-area traffic monitoring. In 2013 IEEE/ACM International Conference on Computer-Aided Design, ICCAD 2013 - Digest of Technical Papers. 2013. p. 202-205. 6691119. (IEEE/ACM International Conference on Computer-Aided Design, Digest of Technical Papers, ICCAD). doi: 10.1109/ICCAD.2013.6691119

@inproceedings{efd5d31f746241c7b1181a69557e2500,

title = "A neuromorphic architecture for anomaly detection in autonomous large-area traffic monitoring",

abstract = "The advanced sensing and imaging capability of today's sensor networks enables real time monitoring in a large area. In order to provide continuous monitoring and prompt situational awareness, an abstract-level autonomous information processing framework is developed that is able to detect various categories of abnormal traffic events with unsupervised learning. The framework is based on cogent confabulation model, which performs statistical inference in a manner inspired by human neocortex system. It enables detection and recognition of abnormal target vehicles within the context of surrounding traffic activities and previous events using likelihood-ratio test. A neuromorphic architecture is proposed which accelerates the computation for real-time detection by leveraging memristor crossbar arrays.",

keywords = "anomaly detection, cogent confabulation, neuromorphic architecture",

author = "Qiuwen Chen and Qinru Qiu and Hai Li and Qing Wu",

note = "Copyright: Copyright 2014 Elsevier B.V., All rights reserved.; 2013 32nd IEEE/ACM International Conference on Computer-Aided Design, ICCAD 2013 ; Conference date: 18-11-2013 Through 21-11-2013",

year = "2013",

doi = "10.1109/ICCAD.2013.6691119",

language = "English (US)",

isbn = "9781479910717",

series = "IEEE/ACM International Conference on Computer-Aided Design, Digest of Technical Papers, ICCAD",

pages = "202--205",

booktitle = "2013 IEEE/ACM International Conference on Computer-Aided Design, ICCAD 2013 - Digest of Technical Papers",

}

TY - GEN

T1 - A neuromorphic architecture for anomaly detection in autonomous large-area traffic monitoring

AU - Chen, Qiuwen

AU - Qiu, Qinru

AU - Li, Hai

AU - Wu, Qing

PY - 2013

Y1 - 2013

N2 - The advanced sensing and imaging capability of today's sensor networks enables real time monitoring in a large area. In order to provide continuous monitoring and prompt situational awareness, an abstract-level autonomous information processing framework is developed that is able to detect various categories of abnormal traffic events with unsupervised learning. The framework is based on cogent confabulation model, which performs statistical inference in a manner inspired by human neocortex system. It enables detection and recognition of abnormal target vehicles within the context of surrounding traffic activities and previous events using likelihood-ratio test. A neuromorphic architecture is proposed which accelerates the computation for real-time detection by leveraging memristor crossbar arrays.

AB - The advanced sensing and imaging capability of today's sensor networks enables real time monitoring in a large area. In order to provide continuous monitoring and prompt situational awareness, an abstract-level autonomous information processing framework is developed that is able to detect various categories of abnormal traffic events with unsupervised learning. The framework is based on cogent confabulation model, which performs statistical inference in a manner inspired by human neocortex system. It enables detection and recognition of abnormal target vehicles within the context of surrounding traffic activities and previous events using likelihood-ratio test. A neuromorphic architecture is proposed which accelerates the computation for real-time detection by leveraging memristor crossbar arrays.

KW - anomaly detection

KW - cogent confabulation

KW - neuromorphic architecture

UR - http://www.scopus.com/inward/record.url?scp=84893408143&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84893408143&partnerID=8YFLogxK

U2 - 10.1109/ICCAD.2013.6691119

DO - 10.1109/ICCAD.2013.6691119

M3 - Conference contribution

AN - SCOPUS:84893408143

SN - 9781479910717

T3 - IEEE/ACM International Conference on Computer-Aided Design, Digest of Technical Papers, ICCAD

SP - 202

EP - 205

BT - 2013 IEEE/ACM International Conference on Computer-Aided Design, ICCAD 2013 - Digest of Technical Papers

T2 - 2013 32nd IEEE/ACM International Conference on Computer-Aided Design, ICCAD 2013

Y2 - 18 November 2013 through 21 November 2013

ER -

A neuromorphic architecture for anomaly detection in autonomous large-area traffic monitoring

Abstract

Publication series

Other

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this