A review on development of neural network system for gait analysis

Abstract

This paper presents the application of Neural Network (NN) system for classification of human gait analysis. This NN will classify the human gait either normal or abnormal. This NN will use Multilayer Perceptron (MLP) neural network for the classification. There are total 3 main features that consist of heel strike, toe-off and Minimum Foot Clearance (MFC) based features had been extracted from normal and abnormal clearance versus time graphs and used as the neural network inputs for the classification process. The training algorithm namely Levenberg-Marquardt was employed to train the MLP network.