Freezing of gait (FoG) is a common motor symptom in patients with Parkinson’s disease (PD). FoG impairs gait initiation and walking and increases fall risk. Intelligent external cueing systems implementing FoG detection algorithms have been developed to help patients recover gait after freezing. However, predicting FoG before its occurrence enables preemptive cueing and may prevent FoG. Such prediction remains challenging given the relative infrequency of freezing compared to non-freezing events. In this study, we investigated the ability of individual and ensemble classifiers to predict FoG. We also studied the effect of the ADAptive SYNthetic (ADASYN) sampling algorithm and classification cost on classifier performance. Eighteen PD patients performed a series of daily walking tasks wearing accelerometers on their ankles, with nine experiencing FoG. The ensemble classifier formed by Support Vector Machines, K-Nearest Neighbors, and Multi-Layer Perceptron using bagging techniques demonstrated highest performance (F1 = 90.7) when synthetic FoG samples were added to the training set and class cost was set as twice that of normal gait. The model identified 97.4% of the events, with 66.7% being predicted. This study demonstrates our algorithm’s potential for accurate prediction of gait events and the provision of preventive cueing in spite of limited event frequency.

No abstract

No abstract

A 1-DoF robot is designed and fabricated to be used for knee rehabilitation training. The mechanism (robot) is designed to perform specific set of exercises while the patient is sitting on a chair. The therapy process for patients has different stages; each stage consists of specific exercises to recover the knee to its condition before injury. The maximum torque of healthy joint during the extension/flexion exercise is evaluated by simulation and suitable actuator is selected based on the results. A prototype is then fabricated as a platform to evaluate the design and control concepts. The experiment procedure consisting of three stages of therapy indicates good tracking performance and safe operation of the system. Implication for Rehabilitation A 1-DoF mechanism for knee rehabilitation has been designed to perform three stages of therapy: passive, active assist and active resist. The assistive and resistive torque, during active assist and active resist stages, can be set according to the progress in therapy. The results of this study suggest the system has the potential to result in various benefits including reduction of physical workload of physiotherapists and improved repeatability.

No abstract