Shoulder Physiotherapy Activity Recognition 9-Axis Dataset

**Dataset will be uploaded soon - dataset is complete but uploader is currently freezing midway through status bar**This dataset contains inertial data consisting of 1) physiotherapy exercise recordings, and 2) unlabeled other activity data recordings, each collected by smart watches worn by healthy subjects. This dataset may be used to perform supervised classification analysis of physiotherapy exercises, or to perform out-of-distribution detection analysis with the unlabeled other activity data.It consists of 9-axis inertial sensor data (accelerometer, gyroscope, and magnetometer) collected using a Huawei Watch 2 from 20 healthy subjects (40 shoulders), as they perform 10 shoulder physiotherapy exercises. This dataset also includes ~3 hours of unlabeled other activity data for each patient that can be used to simulate out-of-distribution data (label 11).The subjects repeat each activity 20 times on each side (left and right). Isometric exercises are low-motion stability exercises.Dataset is labeled as follows:0: None1: External Rotation (Isometric)2: Scapula Retraction at 90 Degrees Flexion3: Internal Rotation (Isometric)4: Extension (Isometric)5: Abduction (Isometric)6: External Rotation at 0 Degrees Flexion7: Cross Chest Adduction8: Active Flexion9: Shoulder Girdle Stabilization with Elevation10: Triceps Pull Downs11: Unrelated activities of daily living (Out-of-Distribution)