Conference Paper

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.

Attached files


Eltanani, Shadi
Olde Scheper, Tjeerd
Dawes, Helen

Oxford Brookes departments

School of Engineering, Computing and Mathematics
Department of Sport, Health Sciences and Social Work


Year of publication: 2021
Date of RADAR deposit: 2021-10-05

“© 2021 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.”

Related resources

This RADAR resource is the Accepted Manuscript of K-nearest neighbor algorithm: Proposed solution for human gait data classification


  • Owner: Joseph Ripp
  • Collection: Outputs
  • Version: 1 (show all)
  • Status: Live
  • Views (since Sept 2022): 472