Studies have shown that people spend 87% of their time indoors. Increasingly, massive amounts of data are being collected about the movement of people and objects in indoor settings. Unlike the GPS technology typically used for outdoor tracking, indoor positions are tracked using a combination of technologies like Wifi‐positioning, Bluetooth, RFID tags and readers, scanning of QR codes, etc. Indoor spaces are very different from outdoor spaces, both in terms of structure and use. Thus, different models and semantics are required, typically in the form of symbolic graph‐based models with annotations. As a recent development, researchers have tried to capture mixed indoor/outdoor spaces in a single comprehensive model and framework. This scenario leads to many challenges for data analytics, as existing models, algorithms, and techniques do not support the new setting and requirements. Thus, new techniques for analytics and data mining have to be developed, implemented in a comprehensive platform for indoor and mixed indoor/outdoor analytics, and tested on large amounts of real‐world tracking data. Interesting case studies include people movement in a campus environment, and world‐wide RFID‐based baggage and passenger tracking.

Main Advisor at Aalborg Universitet (AAU)
Co‐advisor at Université Libre de Bruxelles (ULB)