Objective Assessment of the Wrist Function Loss of Post-Stroke Patients in Haptic Virtual Environment based on Neural Network and Support Vector Machine

Stroke is a brain neurological disorder that usually results in the impairment of the patient’s neural system for performing various functions (e.g., limp function). Rehabilitation is an effective way to recover impaired functions. In the home-based rehabilitation approach, there is a need to assess the impairment of functions of patients at home. A haptic virtual environment system makes this approach possible due to its portability and simplicity. With this system, the patient performs tasks on the system, and the patient’s task performance represents the impairment of functions. This paper presents the work of implementation of this approach. This approach includes the design of tasks which the patient performs and the development of classifiers using the machine learning techniques such as neural network (NN) and support vector machine (SVM). In this study, the wrist dysfunction was taken as an example. The experiment was conducted, which demonstrates the effectiveness of the approach.