A Comparative Study of Supervised Learning Techniques for Human Activity Monitoring Using Smart Sensors

Abstract

In this work various supervised learning techniques such as support vector machine (SVM), perceptron neural network (PNN), recurrent neural network (RNN) and back-propagation neural network (BPNN) has been used for human activity classification using signals collected from smart sensors. Collected features are used as input to the classifiers to recognize different human activity such as Walking, Walking upstairs, Walking Downstairs, Sitting, Standing, Laying Down etc. Highest accuracy obtained for SVM, PNN, RNN and BPNN are 59.11, 94.10, 97.55, and 97.40% respectively. Highest accuracy obtained for activity classification is 97.55% which is for RNN. Hence the method can be used effectively for human activity monitoring.