A wearable real-time fall detector based on Naive Bayes classifier

In this paper, we implement a wearable real-time system using the Sun SPOT wireless sensors embedded with Naive Bayes algorithm to detect fall. Naive Bayes algorithm is demonstrated to be better than other algorithms both in accuracy performance and model building time in this particular application. At 20Hz sampling rate, two Sun SPOT sensors attached to the chest and the thigh provide acceleration information to detect forward, backward, leftward and rightward falls with 100% accuracy as well as overall 87.5% sensitivity.

[1]  Ian H. Witten,et al.  WEKA: a machine learning workbench , 1994, Proceedings of ANZIIS '94 - Australian New Zealnd Intelligent Information Systems Conference.

[2]  Toshiyo Tamura,et al.  A Wearable Airbag to Prevent Fall Injuries , 2009, IEEE Transactions on Information Technology in Biomedicine.

[3]  A. Bourke,et al.  Fall detection - Principles and Methods , 2007, 2007 29th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[4]  Li Chen,et al.  Implementation of a wearerable real-time system for physical activity recognition based on Naive Bayes classifier , 2010, 2010 International Conference on Bioinformatics and Biomedical Technology.

[5]  Xinguo Yu.  Approaches and principles of fall detection for elderly and patient , 2008, HealthCom 2008 - 10th International Conference on e-health Networking, Applications and Services.