Human action recognition using wearable sensors and neural networks

Accurate recognition of daily activities could be useful in many fields including health, sports, childcare, and homes for the elderly, etc. In this paper, we propose a human action recognition method using data acquired from wearable sensors and learned using a Neural Network. The data collected from the sensors is processed for features using the Akamatsu transform. The Akamatsu Transform is a signal processing technique that given point, P(i) in a signal, N data points before and after the selected point are used to derive the integral and differential transforms, The Akamatsu Integration is an average of the N data points while the differential is the difference between the integral and the original value. Recently, wearable sensors are emerging as an indispensable method to recognize human actions.