K - Nearest Neighbor Algorithm: Proposed Solution for Human Gait Data Classification

Gait is a well-known motive means for humans. It is both energetically demanding and reflects several of human physical, mental and energetic disorders. Detecting these abnormalities can help medical professionals for better modelling and detection of biosystem chronic diseases, which enable timely treatment of patients and help control of the diseases' spread. In this paper, K-Nearest Neighbour (KNN) machine learning classification algorithm highlights the comparison between the gait patterns of normal healthy individuals and the patients suffering from irregular gait patterns caused by physical disorder conditions, including strapped muscles. Moreover, the Cross Validation test has addressed to examine how accurately the model fits the real-world clinical data. The experimental results show that the KNN algorithm can effectively be a robust learning classifier in classifying normal and abnormal human gait features. The classification performance of our proposed model is 67.7%, and its effectiveness has evaluated at a minimum square error rate.