Discovering places of interest in everyday life from smartphone data

In this paper, a new framework to discover places-of-interest from multimodal mobile phone data is presented. Mobile phones have been used as sensors to obtain location information from users’ real lives. A place-of-interest is defined as a location where the user usually goes and stays for a while. Two levels of clustering are used to obtain places of interest. First, user location points are grouped using a time-based clustering technique which discovers stay points while dealing with missing location data. The second level performs clustering on the stay points to obtain stay regions. A grid-based clustering algorithm has been used for this purpose. To obtain more user location points, a client-server system has been installed on the mobile phones, which is able to obtain location information by integrating GPS, Wifi, GSM and accelerometer sensors, among others. An extensive set of experiments has been performed to show the benefits of using the proposed framework, using data from the real life of a significant number of users over almost a year of natural phone usage.This work was supported by Nokia Research Center Lausanne (NRC) through the LS-CONTEXT project. R. Montoliu was also supported by the Spanish Ministerio de Ciencia e Innovación under project Consolider Ingenio 2010 CSD2007-00018. Part of this work was done while R. Montoliu visited Idiap. We thank Niko Kiukkonen (NRC) and Olivier Bornet (Idiap) for their contribution to data collection, Trinh-Minh-Tri Do (Idiap) for help with data processing, and all the volunteers in the experiments for their participation