Authors:
M. A. Ben Arous
1
;
2
;
M. Dunbar
3
;
S. Arfaoui
4
;
2
;
A. Mitiche
5
;
Y. Ouakrim
6
;
2
;
A. Fuentes
2
;
G. Richardson
3
and
N. Mezghani
6
;
2
Affiliations:
1
Collège Bois de Boulogne, Canada
;
2
ETS/CRCHUM, Canada
;
3
Dalhousie University, Canada
;
4
Collège Jean-de-Brébeuf, Canada
;
5
INRS Énergie, Matériaux et Télécommunications,, Canada
;
6
TELUQ University, Canada
Keyword(s):
Knee Kinematic, Biomechanical Data, Feature Selection, Complexity Measures, Arthroplasty.
Abstract:
The purpose of this study is to investigate a method to select a set of knee kinematic data features
to characterize surgical vs nonsurgical arthroplasty subjects. The kinematic features are generated from
3D knee kinematic data patterns, namely, rotations of flexion-extension, abduction-adduction, and tibial
internal-external recorded during a walking task on a dedicated treadmill. The discrimination features are
selected using three types of statistical complexity measures: the Fisher discriminant ratio, volume of overlap
region, and feature efficiency. The interclass distance measurements which the features thus selected induce
demonstrate their effectiveness to characterize surgical and nonsurgical subjects for arthroplasty.