Detecting Co-located Mobile Users

Co-location information of devices, people, and activities can be used in numerous applications in areas of social networking, mobile networking, spatial and socio-economics, and securing interactions. People co-location can be interpreted to their communications and interactions. This information can be used for many purposes such as gaining understanding of human social interactions and behaviours. In this paper, we propose an accurate and real-time co-localization technique which provides real-time people co-location information with sub-meter accuracy. We construct a connectivity graph representing the potential co-located users based on pairwise similarity of user's RF measurements. We then apply community-detection tools to cluster users into co-located groups. Our approach does not estimate individual user's absolute location, hence it is robust to localization error and it protects the location privacy of mobile users. Our approach does not involve labour-intensive calibration task as required in most localization approaches. We prototyped our proposed solution to detect co-located users in an enterprise building scenario. Android mobile users connected to our cloud localization server were accurately clustered according to their geographical proximity.