A wearable sensor system for rehabilitation apllications

In this paper an easy-to-use, wearable sensor system capable of deciphering upper-limb based functional tasks associated with stroke rehabilitation is introduced. Such a system can assist the therapist with monitoring a patient´s progress during rehabilitation, and hence can increase the efficiency of the rehabilitation process. The developed system provides quantitative, real-time feedback of a user´s functional activity. The system is designed to detect the successful completion of functional tasks that involve the grasping, movement, and subsequent release of an object. The developed system consists of an Inertial Measurement Unit (IMU) attached to a band, embedded with force sensitive resistors for extracting Force Myography (FMG) data. The band is wrapped around the user´s forearm for the purpose of detecting the onset of a grasp or release with the use of a Neural Network for data classification. Upon detection of a grasp and subsequent release, the device calculates the distance achieved during the motion using data captured from the attached IMU as a measure of task quality. The system´s ability to detect the completion of three functional tasks was evaluated with nine healthy volunteers. The system achieved an average accuracy of 92.67%. Experimental results are presented and discussed.