Wearable Automatic Feedback Devices for Physical Activities

With this work we want to illustrate new ways to assist students during sports training and to enhance their learning experience. As an example, we present the design of a wearable system intended for snowboard training on the slope. The hardware platform consists of a custom-built sensor/actuator box and a mobile phone acting as host device. These devices run algorithms for activity, context, and mistake recognition, and trigger feedback in response to classi fcation results. Instructors can use such a system to automatically supervise posture and motion of students, i.e., to detect common mistakes that are diffcult to recognize when observing students from far away, and to provide immediate audible or tactile feedback for corrections during courses. The presented approach can further be applied to supervise posture and to alert users to potentially harmful body movements performed during daily physical activities.