Improved Use of Foot Force Sensors and Mobile Phone GPS for Mobility Activity Recognition

Recent advances in the development of multimodal wearable sensors enable us to gather richer contexts of mobile user activities. The combination of foot force sensor (FF) and GPS is able to afford fine-grained mobility activity recognition. We derive and identify 12 (out of 31) maximally informative FF features, and the minimal most effective insole positions (two per foot) for sensing, to improve the use of FF + GPS methods for mobility activity recognition. We tested the improved FF + GPS method using over 7000 samples collected from ten volunteers in a natural, unconstrained, environment. The results show that the improved FF + GPS can achieve an average accuracy of over 90% when detecting five different mobility activities, including walking, cycling, bus-passenger, car-passenger, and car-driver.

[1]  Deborah Estrin,et al.  Using mobile phones to determine transportation modes , 2010, TOSN.

[2]  Jian Ma,et al.  Accelerometer Based Transportation Mode Recognition on Mobile Phones , 2010, 2010 Asia-Pacific Conference on Wearable Computing Systems.

[3]  T. L. Lawrence,et al.  Wireless in-shoe force system [for motor prosthesis] , 1997, Proceedings of the 19th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. 'Magnificent Milestones and Emerging Opportunities in Medical Engineering' (Cat. No.97CH36136).

[4]  Kuan Zhang,et al.  Assessment of human locomotion by using an insole measurement system and artificial neural networks. , 2005, Journal of biomechanics.

[5]  Jane Yung-jen Hsu,et al.  GETA sandals: a footstep location tracking system , 2007, Personal and Ubiquitous Computing.

[6]  Stefan Poslad,et al.  Fine-Grained Transportation Mode Recognition Using Mobile Phones and Foot Force Sensors , 2012, MobiQuitous.

[7]  Tao Liu,et al.  Gait Analysis Using Wearable Sensors , 2012, Sensors.

[8]  Tadayoshi Kohno,et al.  Devices That Tell On You: The Nike+iPod Sport Kit , 2006 .

[9]  P. Veltink,et al.  Ambulatory measurement of ground reaction forces , 2005 .

[10]  B H Jones,et al.  Ambulatory foot contact monitor to estimate metabolic cost of human locomotion. , 1994, Journal of applied physiology.

[11]  Isabelle Guyon,et al.  An Introduction to Variable and Feature Selection , 2003, J. Mach. Learn. Res..

[12]  Ana M. Bernardos,et al.  Activity logging using lightweight classification techniques in mobile devices , 2012, Personal and Ubiquitous Computing.

[13]  Ron Kohavi,et al.  A Study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection , 1995, IJCAI.

[14]  Stefan Poslad,et al.  Design and Test of a Hybrid Foot Force Sensing and GPS System for Richer User Mobility Activity Recognition , 2013, Sensors.