Detecting gait phases unobtrusively and reliably
in real-time for long-term unsupervised walking is
important for clinical gait rehabilitation and early diagnosis
of neurological diseases. Due to hardware limitations in
wearable devices (e.g., memory and computation power),
reliable real-time gait phase detection remains a challenge
for unsupervised mobility assessment. In this work, a hybrid
algorithm combining a reduced support vector machine
(RSVM) and a finite state machine (FSM) is developed
to address this. K-means clustering is used to reduce the
number of support vectors (SVs) by constructing a smaller
dataset that contains the most informative data points.
For each gait phase prediction, an FSM is designed to
validate the prediction and correct misclassifications. After
SV reduction, the model size is reduced by 88%, and the
computation time is reduced by a factor of 36, with only
a minor degradation in prediction performance of 4.12%,
2.34%, and 4.85% for sensitivity, specificity, and accuracy,
respectively. The real-time classification performance of the
algorithm is evaluated by twenty healthy subjects walking
along a predefined route with unsupervised free-living gait.
The proposed algorithm demonstrated promising real-time
performance, with an accuracy of 91.51%, a sensitivity of
91.70%, and a specificity of 95.77% across all test subjects.
The algorithm also demonstrated its robustness with respect
to different values of walking speed, cadence, and
stride length.