Smartphone‐based activity recognition independent of device orientation and placement. (23rd June 2015)

• Record Type: Journal Article
• Authors: Guo, Haodong; Chen, Ling; Chen, Gencai; Lv, Mingqi
• Other Names: Yan Zheng guestEditor.; Niemi Valtteri guestEditor.; Yang Laurence T. guestEditor.
• Is Part Of: International journal of communication systems. Volume 29:Number 16(2016)
• Page Start: 2403
• Page End: 2415
• Publication Date: 2015-06-23
• Subjects: activity recognition -- sensor placement -- accelerometer -- motif discovery -- pervasive computing; Telecommunication systems -- Periodicals; 621.382
• DOI: 10.1002/dac.3010
• Languages: English
• ISSNs: 1074-5351

Abstract

Summary: Traditional activity recognition methods based on accelerometers generally assume that the orientation and placement of sensing devices are fixed. However, the orientation and placement of smartphones, the most widely used sensing devices, usually cannot be controlled in daily lives. As a result, the activity recognition performance would be greatly affected. Aiming at this problem, this paper proposes a smartphone‐based activity recognition method, which is independent of device orientation and placement. First, the original 3D acceleration signals are mapped into a uniform reference coordinate system. Then, we apply multi‐dimensional motif discovery techniques for the smartphone‐based activity recognition problem. Experimental results show that our method can achieve better performance (with 85.2% precision and 82.9% recall) than other methods under the condition of unfixed orientation and placement. Copyright © 2015 John Wiley & Sons, Ltd. Abstract : This paper proposes a smartphone‐based activity recognition method, which is independent of device orientation and placement. It works as follows. In the data collection step, sensor data collected from embedded sensors are mapped into a uniform reference coordinate system. Afterwards, activity patterns are detected by motif discovery algorithm. In the final step, vector space model (VSM) is built on the weights of each motif and used for classification.