Automated stand-up and sit-down detection for robot-assisted body-weight support training with the FLOAT.

Patients with impaired walking function are often dependent on assistive devices to retrain gait and regain independence in life. To provide adequate support, gait rehabilitation devices have to be manually set to the correct support mode or have to recognize the type and starting point of a certain motion automatically. For automated motion type detection, machine learning-based classification algorithms using sensor signals from different body parts can achieve robust performance. However, until today, there is only little work available to detect motion onset. In this paper, we investigate task onset detection of sit-to-stand and stand-to-sit transitions. The focus of the current study is twofold: First, the optimal window size for the online classification algorithm shall be found. Second, the ideal sensor placement in a single sensor-setup, to detect movement onset with shortest detection delays possible is of interest. For our investigations a linear discriminant analysis classifier, basic kinematic features, and a leave-one-subject-out cross validation are used. As a result, an average detection time of 56 milliseconds (SD 111) for sit-to-stand and 48 milliseconds (SD 137) for stand-to-sit were achieved with a window size of 15 and 35 milliseconds respectively at a data rate of 200 hertz. For sit-to-stand transitions, a sensor close to the tenth vertebra and for stand-to-sit transitions close to the posterior pelvis provided the smallest detection times.