Data from "Learning a Hand Model from Dynamic Movements using High-density EMG and Convolutional Neural Networks"

FormatThis dataset contains the ground truths and predictions of all deep learning models from Sîmpetru et al (_{https://doi.org/10.1101/2022.07.29.502064}).Fig. 2-4The data is formatted as follows:The data used for <i>Fig. 2</i> is stored under <b>3D_points_{random, testset}</b> depending on whether the AI was tested with the random or the test set.The data used for <i>Fig. 3</i> is stored under <b>angle_{random, test set}</b> depending on whether the AI was tested with the random or the test set.The data used for <i>Fig. 4</i> is stored under <b>force</b>.Each of these folders contains the predicted and expected data for each of the 13 subjects stored as <b>Subject{1, ..., 13}_{predicted, expected}.pkl</b>.Fig. 5The data for Fig. 5 is stored under <b>comparison</b>.<br>To distinguish between the EMG forms used, we use: <br>5 Hz low-pass filtered as <b>3D_points_5</b>5 Hz low-pass filtered and rectified as <b>3D_points_5_rectified</b>20 Hz low-pass filtered as <b>3D_points_20</b>20 Hz low-pass filtered and rectified as <b>3D_points_20_rectified</b>raw as <b>3D_points_raw</b>raw and rectified as <b>3D_points_raw_rectified</b>raw and 20 Hz low-pass filtered combined as <b>3D_points_raw20</b><br>Each of these folders contains the predicted and expected data for each of the 4 subjects, stored as <b>Subject{1, ..., 4}_{predicted, expected}.pkl</b>.<br>General file formatThe saved <b>.pkl</b> files are tables where the columns represent the joint labels (<i>Fig. 1B</i>) and the rows represent the bin number.<br>Each cell of the table contains a series of 3 values representing the x, y and z coordinates of the respective joint label at a given time.<br><br>LoadingThe stored files are <i>pandas</i> (high-level python library for tables manipulation) dataframes stored using <i>pickle</i> (python object serialisation library).<br><br>To read such a file, we give the following minimal example:<br><br>import pandas as pd<br><br>dataframe = pd.read_pickle("PATH_TO_FILE.pkl")<br><br># display head (top 5 rows) of the dataframe<br>print(dataframe.head())<br>