Kinematic Data Clustering for Healthy Knee Gait Characterization

Fatma Zgolli1, Khadidaja Henni2, Rim Haddad3, Amar Mitiche4, Youssef Ouakrim2, Nicola Hagemeister5, Pascal-André Vendittoli6, Aleandre Fuentes7, Neila Mezghani8

  • 1ENET'Com
  • 2TÉLUQ University
  • 3Sup'Com
  • 4Institut National de la Recherche Scientifique
  • 5École de technologie supérieure
  • 6Centre de recherche Hôpital Maisonneuve-Rosemont
  • 7EMOVI
  • 8TELUQ university



Poster Session


10:00 - 17:00 | Tue 30 Oct | Foyer | B1P-E

Rehabilitation & Assistive Technologies

Full Text


The purpose of this study is to investigate data clustering to determine representative patterns in 3D knee kinematic data. The method reduces data dimensionality by isometric mapping and clustered them by the DBSCAN algorithm. Clusters are validated in terms of the silhouette index, the Dunn index, and connectivity. Results show that a two-cluster characterization of the kinematic knee data in each plane is quite effective. Clinical investigations show that the men and women knee patterns are balanced between the two clusters and, for 80% of participants, the right and left knees are in the same cluster.

Additional Information

No information added


No videos found