Optimization of an electromyography-based activity recognition system

We present the optimization of a wearable surface electromyography-based system for activity recognition in relation with the number of sensed muscles. The muscles of interest were four: Gastrocnemius, Tibialis Anterior, Vastus Lateralis and Erector Spinae. In particular, the system has been tested for the recognition of five everyday activities: “walking”, “running”, “cycling”, “sitting” and “standing”. We conducted two types of analysis: impersonal and subjective. The impersonal analysis aimed to evaluate the recognition rate when the system was trained over different users. On the opposite, during the subjective analysis the system has been trained using the data coming from a single user. Moreover, we computed the relative computational costs. Among the results, we can highlight that using the signals sensed from three opportunely selected muscles (Gastrocnemius, Tibialis Anterior and Vastus Lateralis) instead of four did not entail a sensible loss of accuracy, whereas it reduced the computational cost of the 24.1 %. In particular, sensing four and three muscles we achieved an activity recognition accuracy higher than 96% for the impersonal analysis; for the subjective analysis, the attained accuracy was higher than 99%.