A hybrid intelligent system for recovery and performance evaluation after

Abstract

This paper presents a hybrid intelligent system for recovery and performance evaluation of athletes after anterior cruciate ligament (ACL) injury/reconstruction. The fuzzy logic and case based reasoning approaches have been combined to build an assistive tool for sports trainers, coaches and clinicians for maintaining athletes' profile, monitoring progress of recovery, classifying recovery status and adjusting the recovery protocols for individuals. The kinematics and neuromuscular data are collected for subjects after ACL injury/reconstruction using self adjusted body-mounted wireless sensors Upon feature extraction and transformation using principal component analysis, the fuzzy clustering with automatic detection of clusters is employed to group the data according to current recovery status. A knowledge base has been designed to store subjects' profiles, recovery sessions' data and problem/solution pairs. The recovery classification and selection of similar cases has been done using fuzzy k-nearest neighbor (f-knn) and cosine similarity measure. Once relevant cases are selected, adaptation is performed and the performance evaluation will be done. The proposed system has been tested on a group of healthy and post-operated athletes and the classification accuracy of the system is found to be more than 94% using leave-one out cross validation method for walking/running activity.