Profiling pedestrian distribution and anomaly detection in a dynamic environment

Minh Tuan Doan; Sutharshan Rajasegarar; Mahsa Salehi; Masud Moshtaghi; Christopher Leckie

doi:10.1145/2806416.2806645

Profiling pedestrian distribution and anomaly detection in a dynamic environment

Minh Tuan Doan, Sutharshan Rajasegarar, Mahsa Salehi, Masud Moshtaghi, Christopher Leckie

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

9 Citations (Scopus)

Abstract

Pedestrians movements have a major impact on the dynamics of cities and provide valuable guidance to city planners. In this paper we model the normal behaviours of pedestrian flows and detect anomalous events from pedestrian counting data of the City of Melbourne. Since the data spans an extended period, and pedestrian activities can change intermittently (e.g., activities in winter vs. summer), we applied an Ensemble Switching Model, which is a dynamic anomaly detection technique that can accommodate systems that switch between different states. The results are compared with those produced by a static clustering model (Hy-CARCE) and also cross-validated with known events. We found that the results from the Ensemble Switching Model are valid and more accurate than HyCARCE.

Original language	English
Title of host publication	CIKM'15 - Proceedings of the 24th ACM International Conference on Information and Knowledge Management
Subtitle of host publication	October 19-23, 2015 Melbourne, Australia
Editors	Charu C. Aggarwal, Maarten de Rijke, Ravi Kumar, Vanessa Murdock, Timos Sellis, Jeffrey Xu Yu
Place of Publication	New York NY USA
Publisher	Association for Computing Machinery (ACM)
Pages	1827-1830
Number of pages	4
ISBN (Electronic)	9781450337946
DOIs	https://doi.org/10.1145/2806416.2806645
Publication status	Published - 2015
Externally published	Yes
Event	ACM International Conference on Information and Knowledge Management 2015 - Melbourne, Australia Duration: 19 Oct 2015 → 23 Oct 2015 Conference number: 24th http://www.cikm-2015.org/ https://dl.acm.org/doi/proceedings/10.1145/2806416

Conference

Conference	ACM International Conference on Information and Knowledge Management 2015
Abbreviated title	CIKM 2015
Country	Australia
City	Melbourne
Period	19/10/15 → 23/10/15
Internet address	http://www.cikm-2015.org/ https://dl.acm.org/doi/proceedings/10.1145/2806416

Keywords

Anomaly detection
Application

Access to Document

10.1145/2806416.2806645

Link to publication in Scopus

Cite this

Doan, M. T., Rajasegarar, S., Salehi, M., Moshtaghi, M., & Leckie, C. (2015). Profiling pedestrian distribution and anomaly detection in a dynamic environment. In C. C. Aggarwal, M. de Rijke, R. Kumar, V. Murdock, T. Sellis, & J. Xu Yu (Eds.), CIKM'15 - Proceedings of the 24th ACM International Conference on Information and Knowledge Management: October 19-23, 2015 Melbourne, Australia (pp. 1827-1830). Association for Computing Machinery (ACM). https://doi.org/10.1145/2806416.2806645

Doan, Minh Tuan ; Rajasegarar, Sutharshan ; Salehi, Mahsa ; Moshtaghi, Masud ; Leckie, Christopher. / Profiling pedestrian distribution and anomaly detection in a dynamic environment. CIKM'15 - Proceedings of the 24th ACM International Conference on Information and Knowledge Management: October 19-23, 2015 Melbourne, Australia. editor / Charu C. Aggarwal ; Maarten de Rijke ; Ravi Kumar ; Vanessa Murdock ; Timos Sellis ; Jeffrey Xu Yu. New York NY USA : Association for Computing Machinery (ACM), 2015. pp. 1827-1830

@inproceedings{a9b384286aa44509814319660d4e280e,

title = "Profiling pedestrian distribution and anomaly detection in a dynamic environment",

abstract = "Pedestrians movements have a major impact on the dynamics of cities and provide valuable guidance to city planners. In this paper we model the normal behaviours of pedestrian flows and detect anomalous events from pedestrian counting data of the City of Melbourne. Since the data spans an extended period, and pedestrian activities can change intermittently (e.g., activities in winter vs. summer), we applied an Ensemble Switching Model, which is a dynamic anomaly detection technique that can accommodate systems that switch between different states. The results are compared with those produced by a static clustering model (Hy-CARCE) and also cross-validated with known events. We found that the results from the Ensemble Switching Model are valid and more accurate than HyCARCE.",

keywords = "Anomaly detection, Application",

author = "Doan, {Minh Tuan} and Sutharshan Rajasegarar and Mahsa Salehi and Masud Moshtaghi and Christopher Leckie",

year = "2015",

doi = "10.1145/2806416.2806645",

language = "English",

pages = "1827--1830",

editor = "{C. Aggarwal}, {Charu } and {de Rijke}, Maarten and Kumar, {Ravi } and Murdock, {Vanessa } and Sellis, {Timos } and {Xu Yu}, {Jeffrey }",

booktitle = "CIKM'15 - Proceedings of the 24th ACM International Conference on Information and Knowledge Management",

publisher = "Association for Computing Machinery (ACM)",

address = "United States of America",

note = "ACM International Conference on Information and Knowledge Management 2015, CIKM 2015 ; Conference date: 19-10-2015 Through 23-10-2015",

url = "http://www.cikm-2015.org/, https://dl.acm.org/doi/proceedings/10.1145/2806416",

}

Doan, MT, Rajasegarar, S, Salehi, M, Moshtaghi, M & Leckie, C 2015, Profiling pedestrian distribution and anomaly detection in a dynamic environment. in C C. Aggarwal, M de Rijke, R Kumar, V Murdock, T Sellis & J Xu Yu (eds), CIKM'15 - Proceedings of the 24th ACM International Conference on Information and Knowledge Management: October 19-23, 2015 Melbourne, Australia. Association for Computing Machinery (ACM), New York NY USA, pp. 1827-1830, ACM International Conference on Information and Knowledge Management 2015, Melbourne, Australia, 19/10/15. https://doi.org/10.1145/2806416.2806645

Profiling pedestrian distribution and anomaly detection in a dynamic environment. / Doan, Minh Tuan; Rajasegarar, Sutharshan; Salehi, Mahsa; Moshtaghi, Masud; Leckie, Christopher.

CIKM'15 - Proceedings of the 24th ACM International Conference on Information and Knowledge Management: October 19-23, 2015 Melbourne, Australia. ed. / Charu C. Aggarwal; Maarten de Rijke; Ravi Kumar; Vanessa Murdock; Timos Sellis; Jeffrey Xu Yu. New York NY USA : Association for Computing Machinery (ACM), 2015. p. 1827-1830.

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

TY - GEN

T1 - Profiling pedestrian distribution and anomaly detection in a dynamic environment

AU - Doan, Minh Tuan

AU - Rajasegarar, Sutharshan

AU - Salehi, Mahsa

AU - Moshtaghi, Masud

AU - Leckie, Christopher

N1 - Conference code: 24th

PY - 2015

Y1 - 2015

N2 - Pedestrians movements have a major impact on the dynamics of cities and provide valuable guidance to city planners. In this paper we model the normal behaviours of pedestrian flows and detect anomalous events from pedestrian counting data of the City of Melbourne. Since the data spans an extended period, and pedestrian activities can change intermittently (e.g., activities in winter vs. summer), we applied an Ensemble Switching Model, which is a dynamic anomaly detection technique that can accommodate systems that switch between different states. The results are compared with those produced by a static clustering model (Hy-CARCE) and also cross-validated with known events. We found that the results from the Ensemble Switching Model are valid and more accurate than HyCARCE.

AB - Pedestrians movements have a major impact on the dynamics of cities and provide valuable guidance to city planners. In this paper we model the normal behaviours of pedestrian flows and detect anomalous events from pedestrian counting data of the City of Melbourne. Since the data spans an extended period, and pedestrian activities can change intermittently (e.g., activities in winter vs. summer), we applied an Ensemble Switching Model, which is a dynamic anomaly detection technique that can accommodate systems that switch between different states. The results are compared with those produced by a static clustering model (Hy-CARCE) and also cross-validated with known events. We found that the results from the Ensemble Switching Model are valid and more accurate than HyCARCE.

KW - Anomaly detection

KW - Application

UR - http://www.scopus.com/inward/record.url?scp=84958258707&partnerID=8YFLogxK

U2 - 10.1145/2806416.2806645

DO - 10.1145/2806416.2806645

M3 - Conference Paper

AN - SCOPUS:84958258707

SP - 1827

EP - 1830

BT - CIKM'15 - Proceedings of the 24th ACM International Conference on Information and Knowledge Management

A2 - C. Aggarwal, Charu

A2 - de Rijke, Maarten

A2 - Kumar, Ravi

A2 - Murdock, Vanessa

A2 - Sellis, Timos

A2 - Xu Yu, Jeffrey

PB - Association for Computing Machinery (ACM)

CY - New York NY USA

T2 - ACM International Conference on Information and Knowledge Management 2015

Y2 - 19 October 2015 through 23 October 2015

ER -

Doan MT, Rajasegarar S, Salehi M, Moshtaghi M, Leckie C. Profiling pedestrian distribution and anomaly detection in a dynamic environment. In C. Aggarwal C, de Rijke M, Kumar R, Murdock V, Sellis T, Xu Yu J, editors, CIKM'15 - Proceedings of the 24th ACM International Conference on Information and Knowledge Management: October 19-23, 2015 Melbourne, Australia. New York NY USA: Association for Computing Machinery (ACM). 2015. p. 1827-1830 https://doi.org/10.1145/2806416.2806645