Decoding HD-EMG Signals for Myoelectric Control - How Small Can the Analysis Window Size be?

Recently the use of high-density electromyogram (HD-EMG) signal acquisition setups has been promoted for myoelectric control and several databases have made open access scientific research. Despite this accelerated growth in literature, coupled with industry interest, some fundamental research questions are unanswered. For instance, can HD-EMG signals be decoded at smaller window sizes and, if yes, what is additional value sophisticated motor unit decomposition methods. We used three databases, 128 (8 65 hand movements) to 256 electrodes (34 explore impact varying number segmentation windows size on EMG decoding accuracy. The analysis considered from 32 ms 8 128/256. Simple time-domain auto-regressive model parameters were extracted train a linear discriminant classifier identify intended motions. Our indicates that HD-EMG, even as small ms, one achieve considerably high accuracy, e.g. $\ge\!\!90\%$ , our selected databases. As such, allow significant reductions lengths up without compromising performance.