Implementation of a wearerable real-time system for physical activity recognition based on Naive Bayes classifier

In this paper, we implement a wearable real-time system on the Sun SPOT wireless sensors with Naive Bayes algorithm to recognize physical activity. Naive Bayes algorithm is demonstrated to work better than other algorithms both in accuracy performance and computational time in this particular application. 20 Hz is selected as the sampling rate. In terms of sensor location, one sensor attached to the thigh with 87.55% overall accuracy provides the most useful information than the shank or the chest. If two sensors are available, the combination of attaching them to the left thigh and the right thigh respectively is demonstrated to be optimal solution for recognizing physical activity, with 90.52% overall accuracy.