Gait Abnormality Classification in Clinical Field

Abstract

This paper presents a novel technique of classifying the abnormalities in gait. Determining or analyzing the different movements in the limbs of human beings, gait assessment can be made. Gait prediction plays a dynamic role in the clinical field to improve the outcome of the treatment. By predicting the type of abnormalities of gait, the patients can be provided with the proper treatment and thus improving the quality of life. In the proposed method, convolutional neural network and support vector machine algorithm have been used in classifying the various abnormalities of gait such as freezing of gait, brady kinesia, Tremor, Ataxic gait, myopathic gait and muscle atrophy. This method provides greater accuracy and thus helpful in diagnosis of various abnormalities of gait.