Wearable MMG-Plus-One Armband: Evaluation of Normal Force on Mechanomyography (MMG) to Enhance Human-Machine Interfacing

In this paper, we introduce a new mode of mechanomyography (MMG) signal capture for enhancing the performance human-machine interfaces (HMIs) through modulation normal pressure at sensor location. Utilizing novel approach, increased MMG resolution is enabled by tunable degree freedom to sensor-skin contact area. We detail mechatronic design, experimental validation, and user study an armband with embedded acoustic sensors demonstrating capacity. The design motivated nonlinear viscoelasticity tissue, which increases surface pressure. This, in theory, results higher conductivity mechanical waves hypothetically allows interface deeper muscle; thus, discriminative information context space. Ten subjects (seven able-bodied three trans-radial amputees) participated consisting classification hand gestures while increasing levels force were administered. Four channels positioned around forearm placed over flexor carpi radialis, brachioradialis, extensor digitorum communis, ulnaris muscles. A total 852 spectrotemporal features extracted (213 per each channel) passed Neighborhood Component Analysis (NCA) technique select most informative neurophysiological subspace classification. linear support vector machine (SVM) then classified intended motion user. indicate that level between skin can improve power classifier, corresponding pattern be user-specific. These have significant implications enabling embedding sockets prosthetic limb control HMI.