TY - GEN
T1 - An Improved Smartphone-Based Non-Participatory Crowd Monitoring System in Smart Environments
AU - Kulshrestha, Tarun
AU - Saxena, Divya
AU - Niyogi, Rajdeep
AU - Misra, Manoj
AU - Patel, Dhaval
N1 - Funding Information:
VII. ACKNOWLEDGMENT This work is partially supported by RICET at IIT Roorkee under the following grants: RCI-763(2)-ECD.
Publisher Copyright:
© 2017 IEEE.
PY - 2017/8/8
Y1 - 2017/8/8
N2 - Mobile Crowd Sensing and Computing (MCSC) is a replacement of static sensing infrastructure by user's mobile sensor-enhanced devices. MCSC collects user's local knowledge such as local information, ambient, and traffic conditions using sensor-enabled devices. The collected information is further aggregated and transferred to the cloud for detailed analysis. In this paper, we propose a Smartphone-based non-participatory crowd monitoring system, named CrowdTrack, to monitor the movement patterns of one or more persons (non-participatory) using unmodified Smartphones in a densely crowded environment. CrowdTrack uses the Smartphone as a sensing unit without any hardware modification to extract the MAC ids from the wireless probe requests emitted from the users' devices. MAC ids are stored and processed locally for short-term analysis and then the filtered data is uploaded to the server for better analysis and visualization. We have also developed a real-time testbed to identify mobility patterns in the data collected from our Institute campus and it is deployed to find the visiting sequences of students. Real-time experiments on a proof-of-concept prototype testbed with our dataset show the usability of our proposed system.
AB - Mobile Crowd Sensing and Computing (MCSC) is a replacement of static sensing infrastructure by user's mobile sensor-enhanced devices. MCSC collects user's local knowledge such as local information, ambient, and traffic conditions using sensor-enabled devices. The collected information is further aggregated and transferred to the cloud for detailed analysis. In this paper, we propose a Smartphone-based non-participatory crowd monitoring system, named CrowdTrack, to monitor the movement patterns of one or more persons (non-participatory) using unmodified Smartphones in a densely crowded environment. CrowdTrack uses the Smartphone as a sensing unit without any hardware modification to extract the MAC ids from the wireless probe requests emitted from the users' devices. MAC ids are stored and processed locally for short-term analysis and then the filtered data is uploaded to the server for better analysis and visualization. We have also developed a real-time testbed to identify mobility patterns in the data collected from our Institute campus and it is deployed to find the visiting sequences of students. Real-time experiments on a proof-of-concept prototype testbed with our dataset show the usability of our proposed system.
KW - 802.11 frame
KW - Human identification and location tracking
KW - MCSC
KW - Mobile Crowd Sensing and Computing
KW - Probe request
UR - https://www.scopus.com/pages/publications/85034429942
U2 - 10.1109/CSE-EUC.2017.209
DO - 10.1109/CSE-EUC.2017.209
M3 - Conference article published in proceeding or book
AN - SCOPUS:85034429942
T3 - Proceedings - 2017 IEEE International Conference on Computational Science and Engineering and IEEE/IFIP International Conference on Embedded and Ubiquitous Computing, CSE and EUC 2017
SP - 132
EP - 139
BT - Proceedings - 2017 IEEE International Conference on Computational Science and Engineering and IEEE/IFIP International Conference on Embedded and Ubiquitous Computing, CSE and EUC 2017
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 20th IEEE International Conference on Computational Science and Engineering and 15th IEEE/IFIP International Conference on Embedded and Ubiquitous Computing, CSE and EUC 2017
Y2 - 21 July 2017 through 24 July 2017
ER -