A framework for group activity detection and recognition using smartphone sensors and beacons

Abstract

Understanding occupant activities in a building is essential for building management systems to provide occupants with comfort and intelligent indoor environment. However, current occupant activity recognition mainly focuses on individual activity. Group activity recognition indoors has gained little attention, but remains of paramount importance, such as working together, taking classes, and discussions. In this paper, we propose a framework for group activity detection and recognition (i.e., GADAR framework) using smartphone sensors and Bluetooth beacons data. This framework consists of the following four layers: user layer, data package layer, processing layer, and output layer. As individuals within the group show similarity in motion, audio, and proximity, such similarity values are calculated and clustered into groups using hierarchical clustering. The framework then extracts the role, motion, speaking and location features from the clustered groups to distinguish different group activities. Decision tree classifier was selected to recognize the group activity that the group is engaged in. An experiment was conducted to identify the following three common group activities: taking class, seminar, and discussion. The result shows that the proposed GADAR framework could provide more than 89% accuracy in group detection and 89% accuracy in recognizing group activity.