Inferring Complex Human Behavior Using a Non-obtrusive Mobile Sensing Platform

Thanks to the decreasing cost, increasing mobility, and wider use of sensors, a great number of possible applications have recently emerged, including applications that may impact the high-level goals in people’s lives. Applications can be found in many areas ranging from medical devices to consumer devices. Information about activity and context can be inferred from sensors and be used to provide automated recommendations. Previous research has suggested that, using simple sensors, devices can improve human life on an everyday basis. Interesting examples can be found in the area of fluid intake monitoring [2,7]. Also, activity and context recognition from wearable sensors have been investigated [8–11]. Still, many challenges remain open in this area, including how to effectively determine the sensor data that is valuable, how to select sensors and also how to best connect the low-level sensory data with high-level goals that are explicitly or implicitly monitored by a user. As demand for these devices increases it is desired to generalize sensor platforms to monitor a broad set of activities. Moreover, it is desirable to make devices non-obtrusive and more naturally fit into our daily life. This further motivates researchers to design simple devices able to complete complex sensor-supported tasks in real-time. In this paper we: