Strength training improves overall health, well-being, physical appearance, and sports performance.There are four major factors that affect training efficacy in a training session: exercise type, number of repetitions, movement velocity, and workload. Prior research has used wearable sensors to detect exercise type, number of repetitions, and movement velocity while training. However, detecting workload remains constrained to instrumented exercise equipment, such as smart exercise machines or RFID-tagged free weights.This paper presents MuscleSense, an approach that estimates exercise workload by using wearable Surface Electromyography (sEMG) sensors and regression analysis. We evaluated the accuracy of several regression models and the effects of sensor placement through a 20-person user study. Results showed that MuscleSense achieved an accuracy of 0.68kg (root mean square error, RMSE) in sensing workload using both forearm and arm sensors and support vector regression (SVR).

MuscleSense senses exercise weights using wearable sEMG sensors. The chart on the right shows the signals from sEMG sensors on the upper arm, from Channel 1 to Channel 8.

MuscleSense: Exploring Weight Sensing using Wearable Surface Electromyography (sEMG)

Chin Guan Lim, Chin Yi Tsai, and Mike Y. Chen. 2020. MuscleSense: Exploring Weight Sensing using Wearable Surface Electromyography (sEMG). In Proceedings of the Fourteenth International Conference on Tangible, Embedded, and Embodied Interaction (TEI ’20). Association for Computing Machinery, New York, NY, USA, 255–263.
DOI: https://doi.org/10.1145/3374920.3374943