PmA: A real-world system for people mobility monitoring and analysis based on Wi-Fi probes

Uras, Marco; Cossu, Raimondo; Ferrara, Enrico; Liotta, Antonio; Atzori, Luigi

Abstract

A UN report states that in 2050, about 70% of the total world population will live in cities. This increases the complexity of the services that the local public administrations have to provide the citizens with to keep an acceptable level of quality of life. For an appropriate design, deployment and management of these services, there is the need for tools to extract data on how the people move, which activities they conduct out and their behaviour (in an anonymous way). This need has justified extensive efforts towards the design of effective solutions for extracting this information. In this work, we present the People Mobility Analytics (PmA) solution, which collects probe requests generated by Wi-Fi devices when scanning the radio channels to detect Access Points. The PmA system processes the collected data to extract key insights on the people mobility, such as: crowd density per area of interest, people flows, time of permanence, time of return, heat maps, origin-destination matrices and estimation of people positions. The major novelty with respect to the state of the art is related to new powerful indicators that are needed for some key city services, such as security management and people transport services, and the experimental activities carried out in real scenarios.

Citation

Uras, M., Cossu, R., Ferrara, E., Liotta, A., & Atzori, L. (2020). PmA: A real-world system for people mobility monitoring and analysis based on Wi-Fi probes. Journal of Cleaner Production, 270, Article 122084. https://doi.org/10.1016/j.jclepro.2020.122084

• Journal Article Type: Article
• Acceptance Date: May 4, 2020
• Online Publication Date: Jun 5, 2020
• Publication Date: 2020-10
• Deposit Date: Dec 14, 2020
• Journal: Journal of Cleaner Production
• Print ISSN: 0959-6526
• Publisher: Elsevier
• Peer Reviewed: Peer Reviewed
• Volume: 270
• Article Number: 122084
• DOI: https://doi.org/10.1016/j.jclepro.2020.122084
• Keywords: Passive Wi-Fi sniffer, Crowd density, Pedestrian flow, Mobility patterns, Trajectory mining, Crowdsensed data
• Public URL: http://researchrepository.napier.ac.uk/Output/2698902