# EEG Gait Decoding Challenge — Data

来源：https://www.kaggle.com/competitions/gait-data-processing/data

本地 Meta Kaggle 快照；不是本次实时页面。

# Dataset Description

The data for this competition consist of EEG and inertial signals, which were recorded with sampling rate at 512 Hz and 20 Hz, respectively, while patients with complete spinal cord injury (SCI) walked under the Lokomat's assistance. The inertial signals were resampled at 512 Hz, and together to the EEG data are provided in CSV files, which later were split into a training set and a testing set. 

## Training Data
The file "train_set.csv" contains the EEG recordings that were collected in several sessions from two SCI individuals. The file is composed of columns, indicating the following information:
1)  ID: Each row contains a unique identifier;
2) Subject: The SCIX indicates the subject;
3) Session: The number of each session takes values from 0001 to 00XX;
4) Time:512Hz: The time sequence.
5) 16 EEG locations, according to the international 10-20 system:  FP1, FP2, F3, F4, FC1, FC2, C4, C3, Cz, CP2, CP1, P4, Pz, P3, O2, and O1. 

## Labels of training
1) ID: Each row contains the same unique identifier that corresponds to the training set;
2) Angle: The inertial signal recorded simultaneously with the EEG data.

## Testing Data
The file "test_set.npy" contains EEG epochs of 1 s (16 channels x 512 samples) extracted each 0.1 s from unseen EEG recording of two SCI individuals. This file has the following structure:
To submit the results, the competitors of this challenge are required to predict the inertial signal values from the testing set, and follow the instruction below.

## Example for submission
The provided file "example_submission.csv" contains the required format to submit the predictions from the testing set. Notice that this file contains two columns with ID and prediction, where ID contains the same unique identifier corresponding to the testing set, and prediction contains the predicted inertial signal values.

It is worth noting that the training and testing sets were randomly separated from the full dataset, taking into account the session number. The competitors are allowed to use external data sources for their models, as long as they are publicly available and properly cited.