Open Access Dataset, Toolbox and Benchmark Processing Results of High-Density Surface Electromyogram Recordings

We provide an open access dataset of High densitY Surface Electromyogram (HD-sEMG) Recordings (named “Hyser”), a toolbox for neural interface research, and benchmark results pattern recognition EMG-force applications. Data from 20 subjects were acquired twice per subject on different days following the same experimental paradigm. 256-channel HD-sEMG forearm muscles during dexterous finger manipulations. This Hyser contains five sub-datasets as: (1) (PR) 34 commonly used hand gestures, (2) maximal voluntary muscle contraction (MVC) while contracted each individual finger, (3) one-degree freedom (DoF) force-varying (4) N-DoF prescribed contractions combinations multiple fingers, (5) random task fingers without any force trajectory. Dataset 1 can be gesture studies. Datasets 2-5 also recorded forces, thus studies proportional control neuroprostheses. Our to: analyze datasets using standard methods decompose signals into motor unit action potentials via independent component analysis. expect our dataset, analyses unique platform to promote wide range research collaboration among rehabilitation engineers.