# EEG-based Biometric Competition on M3CV database — Data

来源：https://www.kaggle.com/competitions/eeg-biometric-competition/data

采集时间：2026-10-24T01:32:59Z

## Enrollment, Calibration and Testing Set
In this competition, the M3CV dataset is splited into the Enrollment Set, Calibration Set, and Testing Set:

1. Enrollment Set: the EEG data of session 1 from 95 subjects 
    - For the participants to train the biometric model.
2. Calibration Set: the EEG data of session 2 from 20 subjects
    - For the participants to observe the EEG data, analyze the commonalities and variability between different subjects, different days, and different paradigms, and conduct offline comparison between different prediction models.
    - Not all the EEG epoches in session 2 in these 20 subjects are provided in the calibration set. Part of the other EEG epoches has been arranged in testing set with subject ID unlabeled.
3. Testing Set: the EEG data of session 2 from 86 subjects
    - Public leaderboard : around 10% of epochs in testing set
    - Private leaderboard : around 90% epochs in testing set
    - 11 intruders have been contained in the testing set, which does not appear in the enrollment set.
    - The information for which epoch belongs to the public leaderboard  or the private leaderboard is hidden.

![Data format.jpg](https://pickle-ceramic-98c.notion.site/image/https%3A%2F%2Fs3-us-west-2.amazonaws.com%2Fsecure.notion-static.com%2F4d5fdde1-d452-417f-bf23-46cb72e6cfdc%2FData_format.jpg?table=block&id=661b7e86-59fa-44d1-975a-ea200141c05a&spaceId=9b832dc9-0403-4155-a62e-d4bf0be641dd&width=2000&userId=&cache=v2)




## Data format and signal preprocessing
All epoches were arranged in the mat file,named epochxxxxxx.mat, with a 2D-matrix epoch_data （$65\times 1000$ ）in it. Rows 1-64 correspond to 64 channels of EEG signal, row 65 corresponds to the marker information. xxxxxx are the random ID for each epoch. BrainAmp (brain products GmbH, Germany) was used for EEG recording with the original sampling rate 1000Hz. Each epoch are segmented from the preprocessed EEG signal, the preprocessing step including
  - Bad channel repairing
  - Rereference to TP9/TP10
  - Bandpass filter: 0.01-200Hz
  - ICA filter for artifact removing
  - Downsampling to 250Hz

## Files
Three zip files are provided with all the epoches used in this competition, which are

*   **Enrollment.zip** - the epochs in enrollment set
*   **Calibration.zip** - the epochs in calibration set
*   **Testing.zip** -the epochs in testing set
*   **Enrollment_Info.csv** -the label information for enrollment Set
*   **Calibration_Info.csv** -the label information for calibration Set
*   **Testing_Info.csv** -the label information for testing Set
*   **Baseline.zip** -matlab version code of the baseline methods
*   **Result_example_0907_181703.csv** -an example sumbission *.csv file 
 
## Columns

*   `Epoch_ID` - The ID of the epoch, 
    - ranged from epoch000001 to epoch120000
*   `Subject_ID` - The ID of the subject
    - ranged from sub001 to sub106, or None
    - if usage is 1 or 2, the Subject_ID is the real ID of the subject
    - if usage is 3, the Subject_ID is None
    - if usage is 4, the Subject_ID is the ID that the subject claim he or she is.
*   `Session` - The number of the session, from 1 to 2
*   `Task` - The label of the Task, from 1 to 13
    - 1-EC
    - 2-EO
    - 3-VEP
    - 4-AEP
    - 5-SEP
    - 6-SSVEP
    - 7-SSAEP
    - 8-SSSEP
    - 9-P300（Target and Nontarget）
    - 10-FT
    - 11-RH
    - 12-LH
    - 13-SSVEP-SA
*   `Usage` - The label for the usage of the Epoch, ranged from 1 to 4
    - 1-Enrollment
    - 2-Calibration
    - 3-Identification
    - 4-Verification


##  Electrode
* 1-Fp1
* 2-Fp2
* 3-F3
* 4-F4
* 5-C3
* 6-C4
* 7-P3
* 8-P4
* 9-O1
* 10-O2
* 11-F7
* 12-F8
* 13-T7
* 14-T8
* 15-P7
* 16-P8
* 17-Fz
* 18-Cz
* 19-Pz
* 20-FC1
* 21-FC2
* 22-CP1
* 23-CP2
* 24-FC5
* 25-FC6
* 26-CP5
* 27-CP6
* 28-FT9
* 29-FT10
* 30-TP9
* 31-TP10
* 32-F1
* 33-F2
* 34-C1
* 35-C2
* 36-P1
* 37-P2
* 38-AF3
* 39-AF4
* 40-FC3
* 41-FC4
* 42-CP3
* 43-CP4
* 44-PO3
* 45-PO4
* 46-F5
* 47-F6
* 48-C5
* 49-C6
* 50-P5
* 51-P6
* 52-AF7
* 53-AF8
* 54-FT7
* 55-FT8
* 56-TP7
* 57-TP8
* 58-PO7
* 59-PO8
* 60-Fpz
* 61-CPz
* 62-POz
* 63-Oz
* 64-FCz
* 65-Marker