RPC-Net Dataset. Simultaneous HD-sEMG Recordings on the Forearm and angles of a 24-DOF Hand Kinematic Model

This data set refers to the journal paper "Developing RPC-Net: Leveraging High-Density electromyography and Machine Learning for Improved Hand Position Estimation", currently undergoing peer-review. We report the data acquisition process as defined in the paper. Please refer to the updated figures (fig1.png and fig2.png) and to the original paper for additional information about the acquisition process: High-Density surface EMG data: EMG was recorded on the surface of the forearm using the MEACS system, the EMG amplifier developed at LISiN (Politecnico di Torino, Turin, Italy). The system is made up of multiple Sensor Units (SU), each measuring 34 mm x 30 mm x 15 mm and sampling 32 channels at fs=2.048 kHz (192 V/V gain, 16 bit resolution, 2.4 V dynamic range). Three SUs were used, each connected to an anisotropic electrode array (2 rows and 16 columns, with 10 mm and 15 mm inter-electrode distance respectively) for a total of N=96 acquired monopolar electromyographic channels. The electrodes were arranged in 6 rows and 16 columns around the circumference of the forearm, covering approximately a third of its length (Fig. 1). The proximal row of electrodes (row 1) was positioned at 20 \% of the distance between the medial epicondyle and the pisiform bone. The reference electrode was positioned on the lateral epicondyle. The electromyographic signal was used as input for RPC-Net during the phases of training and testing. Hand position data: Hand position data were acquired using a motion capture system (VICON Motus; VICON Motion Systems, Centennial, Oxford, UK) sampling at 100 samples/s. The setup included 12 infrared cameras (Vero v2.2). A total of Mh=21 infrared reflective markers (diameter of 6 mm) were positioned on the dominant hand of the subject, embedded in a glove. Additionally, 12 markers were placed on the arm, chest and back, resulting in M=33 markers in total (Fig. 1). The hand position data, translated to joint angles using the Inverse Kinematic Algorithm (IKA) defined below, was used both as input and to provide the target values for the training phase of RPC-Net.

搜集汇总

背景与挑战

背景概述

RPC-Net数据集是一个用于手部位置估计研究的公开数据集，包含同时采集的高密度表面肌电图（HD-sEMG）记录和24自由度手部运动模型的关节角度数据。数据集采集了12名受试者的数据，HD-sEMG使用96个通道在手臂表面记录，手部位置通过运动捕捉系统获取并转换为关节角度，支持机器学习和生物医学信号处理应用。数据以.mat文件格式提供，总大小为2.1 GB，适用于开发如RPC-Net的算法模型。