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

Abstract

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

Robust Synchronized Data Acquisition for Biometric Authentication

“…For example, the Convolutional Neural Network (CNN) has been widely used for hand gesture classification, where the image [27], radar data [28], and HD-sEMG signal [29] are used as input features for training, validation and test. So far, There exists no consensus on the optimal NN architecture [9]. Thus, in this work, we use another technique, namely, Linear Discriminant Analysis (LDA), for studying the application of D-PkCOs in hand gesture classification.…”

“…In this section, we use the Hyser dataset [9] to study the effectiveness of D-PkCOs in the HD-sEMG-based authentication system (through the hand gesture classification). Four electrode arrays are connected via cables, and are also placed on the forearm's extensor and flexor muscles for collecting the Hyser data, where twenty volunteers (i.e.…”

“…Typically, multiple (e.g. 4 in [9]) electrode arrays are used to obtain the HD-sEMG signals for authentication. However, the existence of cable connections among these electrode arrays poses challenges for signal recording in dynamic environments.…”

Random Channel Masks for Regularization of Least Squares-Based Finger EMG-Force Modeling to Improve Cross-Day Performance

“…Data of 20 subjects (12 males and 8 females, aged 22 to 34 years) from our previously published open-source "Hyser" dataset [17] were used to validate the proposed method. The experiment was approved and reviewed by the ethics committee of Fudan University (approval number: BE2035).…”

“…The experiment was approved and reviewed by the ethics committee of Fudan University (approval number: BE2035). Here we only briefly review the data collection (see [17] for details).…”