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 | |
| 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/ |
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 |
Keywords
- Anomaly detection
- Application
Cite this
}
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
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
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
ER -