MUSED-I: "Multi-Gesture Surface Electromyography (sEMG) Dataset for Stroke Rehabilitation”

The published Surface Electromyography (sEMG) dataset was captured under the supervision of trained physiotherapists and doctors at Mayo Hospital Lahore and National University of Sciences & Technology by following two months long experimental protocol.

Data recording was carried out following the World Medical Association's (WMA) Standard operating procedure and Declaration of Helsinki, with approval from the Research Ethical Committee of the National University of Science and Technology (approval no: M-20221206). Before data acquisition, participants received a comprehensive oral explanation of the experiment, safety measures, and associated risks. Informed written consent was obtained from stroke patients before data recording. Participants sat comfortably in an armchair with their arms vertically positioned relative to the floor. The Myo armband was carefully placed on their forearm, ensuring the electrodes remained at a consistent distance of 5 centimetres from the elbow. Participants then followed the on-screen prompts to perform the specified gestures.

Ten healthy subjects (with no prior history of upper limb pathology) and two upper limb stroke patients participated in the study.  The dataset comprises the raw surface electromyography (sEMG) signals collected for the six gestures (wrist flexion, wrist extension, hand close, wrist radial deviation, wrist ulnar deviation and rest) via Myo armband. All eight channels of the Myo armband were utilized for data acquisition.