Kinesiologic electromyography for activity recognition

Abstract

This paper presents a wearable system based on kinesiologic electromyography that recognizes the user activity in real time. In particular, the system recognizes the following five activities: "walking", "running", "cycling", "sitting" and "standing". We conducted a study in order to select the opportune muscles and sensors placement. Furthermore, we evaluated the system conducting two analyses: impersonal and subjective. The impersonal analysis evaluated the system behavior when it was trained on several users' data; on the opposite, the subjective analysis evaluated the system when it was specialized on a single subject data. In the impersonal analysis, the accuracy rate was 96.8% for the 10-fold cross-validation and 91.8% for the leave one subject out. The system accuracy rate for the subjective analysis was 99.4%.