EMG and data glove dataset for dexterous myoelectric control

<b>Instructions</b><br><b>Acquisition Protocol</b><br>The 8th Ninapro database is described in the paper: "Agamemnon Krasoulis, Sethu Vijayakumar &amp; Kianoush Nazarpour. Effect of user adaptation on prosthetic finger control with an intuitive myoelectric decoder, Frontiers in Neuroscience. Please cite this paper for any work related to this database.<br>More information about the protocol can be found in the original paper: "Manfredo Atzori, Arjan Gijsberts, Claudio Castellini, Barbara Caputo, Anne-Gabrielle Mittaz Hager, Simone Elsig, Giorgio Giatsidis, Franco Bassetto &amp; Henning Müller. Electromyography data for non-invasive naturally-controlled robotic hand prostheses. Scientific Data, 2014" (http://www.nature.com/articles/sdata201453)<br>The experiment comprised nine movements including single-finger as well as functional movements. The subjects had to repeat the instructed movements following visual cues (i.e. movies) shown on the screen of a computer monitor.<br>The muscular activity was recorded using 16 active double-differential wireless sensors from a Delsys Trigno IM Wireless EMG system. The sensors comprise EMG electrodes and 9-axis inertial measurement units (IMUs). The sensors were positioned in two rows of eight units around the participants’ right forearm in correspondence to the radiohumeral joint (see pictures below). No specific muscles were targeted. The sensors were fixed on the forearm using the standard manufacturer-provided adhesive bands. Moreover, a hypoallergenic elastic latex-free band was placed around the sensors to keep them fixed during the acquisition. The sEMG signals were sampled at a rate of 1111 Hz, accelerometer and gyroscope data were sampled at 148 Hz, and magnetometer data were sampled at 74 Hz. All signals were upsampled to 2 kHz and post-synchronized.<br>Hand kinematic data were recorded with a dataglove (Cyberglove 2, 18-DOF model). For all participants (i.e. both able-bodied and amputee), the data glove was worn on the left hand (i.e. contralateral to the arm where the EMG sensors were located). The Cyberglove signals correspond to data from the associated Cyberglove sensors located as shown in the picture below ("n/a" corresponds to sensors that were not available, since an 18-DOF model was used). Prior to each experimental session, the data glove was calibrated for the specific participant using the "quick calibration" procedure provided by the manufacturer. The Cyberglove signals were sampled at 100 Hz and subsequently upsampled to 2 kHz and synchronized to EMG and IMU data.<br>Ten able-bodied (Subjects 1-10) and two right-hand transradial amputee participants (Subjects 11-12) are included in the dataset. During the acquisition, the subjects were asked to repeat 9 movements using both hands (bilateral mirrored movements). The duration of each of the nine movements varied between 6 and 9 seconds and consecutive trials were interleaved with 3 seconds of rest. Each repetition started with the participant holding their fingers at the rest state and involved slowly reaching the target posture as shown on the screen and returning to the rest state before the end of the trial. The following movements were included:<br>0. rest1. thumb flexion/extension2. thumb abduction/adduction3. index finger flexion/extension4. middle finger flexion/extension5. combined ring and little fingers flexion/extension6. index pointer7. cylindrical grip8. lateral grip9. tripod grip<br> <b>Datasets</b><br>For each participant, three datasets were collected: the first two datasets (acquisitions 1 &amp; 2) comprised 10 repetitions of each movement and the third dataset (acquisition 3) comprised only two repetitions. For each subject, the associated .zip file contains three MATLAB files in .mat format, that is, one for each dataset, with synchronized variables.<br><br>The variables included in the .mat files are the following:· subject: subject number· exercise: exercise number (value set to 1 in all data files)· emg (16 columns): sEMG signals from the 16 sensors· acc (48 columns): three-axis accelerometer data from the 16 sensors· gyro (48 columns): three-axis gyroscope data from the 16 sensors· mag (48 columns): three-axis magnetometer data from the 16 sensors· glove (18 columns): calibrated signals from the 18 sensors of the Cyberglove· stimulus (1 column): the movement repeated by the subject· restimulus (1 column): again the movement repeated by the subject. In this case, the duration of the movement label is refined a-posteriori in order to correspond to the real movement.· repetition (1 column): repetition number of the stimulus· rerepetition (1 column): repetition number of restimulus<br> <b>Important notes</b><br>Given the nature of the data collection procedure (slow finger movement and lack of extended hold period), this database is intended to be used for estimation/reconstruction of finger movement rather than motion/grip classification. In other words, the purpose of this database is to provide a benchmark for decoding finger position from (contralateral) EMG measurements using regression algorithms as opposed to classification. Therefore, the use of stimulus/restimulus vectors as target variables should be avoided; these are only provided for the user to have access to the exact timings of each movement repetition.<br>Three datasets/acquisitions are provided for each subject. It is recommended that dataset 3, which comprises only two repetitions for each movement, is only used to report performance results and no training or hyper-parameter tuning is performed using this data (i.e. test dataset). The three datasets, which were recorded sequentially, can offer an out-of-the-box three-way split for model training (dataset 1), hyper-parameter tuning/validation (dataset 2), and performance testing (dataset 3). Another possibility is to merge datasets 1 &amp; 2 and perform training and validation/hyper-parameter tuning using K-fold cross-validation, then report performance results on dataset 3.

<b>数据集说明</b>
<b>采集协议</b>
第8版Ninapro数据库（Ninapro Database 8）的相关描述见于论文：Agamemnon Krasoulis、Sethu Vijayakumar与Kianoush Nazarpour发表于《Frontiers in Neuroscience》的《用户自适应对基于直观肌电解码器的假肢手指控制的影响》。若使用该数据库开展相关研究，请引用此论文。
关于采集协议的更多细节，请参阅原始论文：Manfredo Atzori等发表于《Scientific Data》2014年的《用于非侵入式自然控制机械手假肢的肌电数据》（链接：http://www.nature.com/articles/sdata201453）
本实验包含9种动作，涵盖单手指动作与功能性动作。受试者需根据电脑显示器屏幕上呈现的视觉提示（即动画演示）重复指定动作。
肌电活动通过Delsys Trigno IM无线肌电（Electromyography, EMG）系统的16个有源双差分无线传感器采集。该传感器集成了肌电电极与9轴惯性测量单元（Inertial Measurement Unit, IMU）。传感器以每排8个的方式，沿受试者右前臂绕桡肱关节排布（详见下图），未针对特定肌肉。传感器通过厂商提供的标准医用胶带固定于前臂，此外还使用了低致敏性无乳胶弹性绑带环绕传感器，以确保采集过程中传感器位置固定。表面肌电（surface Electromyography, sEMG）信号的采样率为1111 Hz，加速度计与陀螺仪数据采样率为148 Hz，磁力计数据采样率为74 Hz。所有信号均被上采样至2 kHz并进行后同步处理。
手部运动学数据通过数据手套（Cyberglove 2，18自由度（Degree of Freedom, DOF）型号）采集。所有受试者（包括健全者与截肢者）均将数据手套佩戴于左手（即与安放肌电传感器的右臂对侧的手臂）。Cyberglove的信号对应下图所示的对应传感器数据（"n/a"表示该18自由度型号未配备对应传感器）。每次实验开始前，均使用厂商提供的“快速校准”流程针对受试者个体完成数据手套校准。Cyberglove信号的采样率为100 Hz，随后被上采样至2 kHz并与肌电及惯性测量单元数据完成同步。
本数据集包含10名健全受试者（编号1-10）与2名右手经桡骨截肢受试者（编号11-12）。采集过程中，受试者需使用双手完成9种动作（双侧镜像动作）。每种动作的持续时长为6~9秒，相邻试次之间插入3秒的休息时间。每次试次以受试者手指处于休息状态为起点，随后缓慢达到屏幕所示的目标姿势，并在试次结束前返回休息状态。本次实验包含以下动作：
0. 休息
1. 拇指屈伸
2. 拇指外展/内收
3. 食指屈伸
4. 中指屈伸
5. 环指与小指联合屈伸
6. 食指指向
7. 圆柱握姿
8. 侧握姿
9. 三脚架握姿

<b>数据集详情</b>
每位受试者共采集3组数据：前两组数据（采集批次1与2）包含每种动作的10次重复，第三组数据（采集批次3）仅包含每种动作的2次重复。每位受试者对应的压缩包中包含3个.mat格式的MATLAB文件，分别对应3组数据，文件内包含已同步的变量。

.mat文件中包含的变量如下：
· subject：受试者编号
· exercise：动作编号（所有数据文件中该值均设为1）
· emg（16列）：来自16个传感器的表面肌电信号
· acc（48列）：来自16个传感器的三轴加速度计数据
· gyro（48列）：来自16个传感器的三轴陀螺仪数据
· mag（48列）：来自16个传感器的三轴磁力计数据
· glove（18列）：Cyberglove手套18个传感器的校准后信号
· stimulus（1列）：受试者完成的动作类型
· restimulus（1列）：同受试者完成的动作类型，该标签的时长经后处理优化，以匹配实际动作的真实时长
· repetition（1列）：当前试次的重复编号
· rerepetition（1列）：restimulus对应的重复编号

<b>重要说明</b>
鉴于本数据采集流程的特性（手指动作缓慢且无长时间保持姿势的阶段），本数据库旨在用于手指运动的估计/重构，而非动作或握姿分类。换言之，本数据库的核心用途是为基于对侧肌电信号通过回归算法（而非分类算法）解码手指位置提供基准测试集。因此，应避免将stimulus/restimulus向量用作目标变量；此类向量仅用于帮助使用者获取每次动作重复的精确时间信息。
每位受试者均提供3组数据/采集批次。建议仅将每组动作仅包含2次重复的第3组数据用于报告性能结果，不得使用该数据开展模型训练或超参数调优（即作为测试集）。按顺序采集的3组数据可直接划分为：模型训练集（数据集1）、超参数调优/验证集（数据集2）与性能测试集（数据集3）。另一种可行方案是将数据集1与2合并，通过K折交叉验证开展训练与验证/超参数调优，随后使用数据集3报告性能结果。