{ "fetched_at": "2026-10-24T22:18:49Z", "source_url": "https://www.kaggle.com/competitions/eeg-based-biometric-competition/data", "pages": [ { "name": "data-description", "content": "## Enrollment, Calibration and Testing Set\nIn this competition, the M3CV dataset is splited into the Enrollment Set, Calibration Set, and Testing Set:\n\n1. Enrollment Set: the EEG data of session 1 from 95 subjects \n - For the participants to train the biometric model.\n2. Calibration Set: the EEG data of session 2 from 20 subjects\n - 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.\n - 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.\n3. Testing Set: the EEG data of session 2 from 106 subjects\n - Leadboard A: around 10% of epochs in testing set\n - Leadboard B: around 90% epochs in testing set\n - Eleven introuders have been contrained in the testing set, which does not appear in the enrollment set.\n - The information for which epoch belongs to Leadboard A or B is hidden.\n\n![](https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F10539915%2F2373850f6ca61e2aaff2cd2a243932cd%2Ffig3.png?generation=1658843970075106&alt=media)\n\n## Data format and signal preprocessing\nAll 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\n - Bad channel repairing\n - Rereference to TP9/TP10\n - Bandpass filter: 0.01-200Hz\n - ICA filter for artifact removing\n - Downsampling to 250Hz\n\n## Files\nThree zip files are provided with all the epoches used in this competition, which are\n\n* **Enrollment.zip** - the epochs in enrollment set\n* **Calibration.zip** - the epochs in calibration set\n* **Testing.zip** -the epochs in testing set\n* **Enrollment_Info.csv** -the label information for enrollment Set\n* **Calibration_Info.csv** -the label information for calibration Set\n* **Testing_Info.csv** -the label information for testing Set\n* **Baseline.zip** -matlab version code of the baseline methods\n* **Result_example_0615_000000.csv** -an example sumbission *.csv file \n \n## Columns\n\n* `Epoch_ID` - The ID of the epoch, \n - ranged from epoch000001 to epoch120000\n* `Subject_ID` - The ID of the subject\n - ranged from sub001 to sub106, or None\n - if usage is 1 or 2, the Subject_ID is the real ID of the subject\n - if usage is 3, the Subject_ID is None\n - if usage is 4, the Subject_ID is the ID that the subject claim he or she is.\n* `Session` - The number of the session, from 1 to 2\n* `Task` - The label of the Task, from 1 to 13\n - 1-EC\n - 2-EO\n - 3-VEP\n - 4-AEP\n - 5-SEP\n - 6-SSVEP\n - 7-SSAEP\n - 8-SSSEP\n - 9-P300（Target and Nontarget）\n - 10-FT\n - 11-RH\n - 12-LH\n - 13-SSVEP-SA\n* `Usage` - The label for the usage of the Epoch, ranged from 1 to 4\n - 1-Enrollment\n - 2-Calibration\n - 3-Identification\n - 4-Verification\n\n\n## Electrode\n* 1-Fp1\n* 2-Fp2\n* 3-F3\n* 4-F4\n* 5-C3\n* 6-C4\n* 7-P3\n* 8-P4\n* 9-O1\n* 10-O2\n* 11-F7\n* 12-F8\n* 13-T7\n* 14-T8\n* 15-P7\n* 16-P8\n* 17-Fz\n* 18-Cz\n* 19-Pz\n* 20-FC1\n* 21-FC2\n* 22-CP1\n* 23-CP2\n* 24-FC5\n* 25-FC6\n* 26-CP5\n* 27-CP6\n* 28-FT9\n* 29-FT10\n* 30-TP9\n* 31-TP10\n* 32-F1\n* 33-F2\n* 34-C1\n* 35-C2\n* 36-P1\n* 37-P2\n* 38-AF3\n* 39-AF4\n* 40-FC3\n* 41-FC4\n* 42-CP3\n* 43-CP4\n* 44-PO3\n* 45-PO4\n* 46-F5\n* 47-F6\n* 48-C5\n* 49-C6\n* 50-P5\n* 51-P6\n* 52-AF7\n* 53-AF8\n* 54-FT7\n* 55-FT8\n* 56-TP7\n* 57-TP8\n* 58-PO7\n* 59-PO8\n* 60-Fpz\n* 61-CPz\n* 62-POz\n* 63-Oz\n* 64-FCz\n* 65-Marker", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Description", "content": "\n# 1. Challenge Description\n\nIn the current digital information society, the personal authentication technique is an essential tool in many personal and enterprise security systems. Biometrics is an important personal authentication technique based on biological measurements, including physical, physiological, or behavioral characteristics. Compared with existing voice recognition, fingerprint scanning, and facial recognition, EEG-based biometrics has unique advantages (e.g., it is more difficult to be stolen, forged, or damaged, and it must be detected in vivo). Hence, EEG-based biometrics is capable of providing a more secure biometric method for identity recognition.\n\nHowever, at present, EEG-based biometric technique is still in the exploratory stage. Current EEG-based biometric studies are mostly focused on a small number of samples and lack evaluation of multi-session and multi-task EEG recordings, which made the development of EEG-based biometric systems challenging with their uniqueness, permanence, and robustness. At the same time, there is no open EEG-based biometric competition and a suitable database. The lack of a unified test benchmark and platform seriously hinders the development of this field. To this end, we collected the M3CV (A **M**ulti-subject, **M**ulti-session, and **M**ulti-task Database for Investigation of EEG **C**ommonality and **V**ariability) dataset and launched an EEG-based biometric competition.\n\nCompared with the existing open dateset, the most challenge\n\n1. Larger population size\n2. Multiple sessions of EEG recording\n3. Multiple tasks of EEG recording\n4. The intruders for the identificationand verification\n\n# 2. Task Definition\nWith the 106 subjects, 2 sessions, and 14 types of EEG recoding in M3CV database, we segmented the EEG signal and Sort them out of order. The EEG-based biometric competition was launched by focusing on the problems of personal identification and verification. Based on the enrollment dataset, the participant need to train the prediction model for the biometric system. After the model has been trained, the participant would be asked to complete the following two prediction tasks:\n- **Identification**: Determine whether a given EEG signal comes from a subject in the Enrollment Set, and further determine the subject ID if he of she is not a intruder.\n- **Verification**: Determine whether a given EEG signal comes from a certain subject.\n\n# 3. Schedule setting\n| Data | Schedule |\n| -------- | -------- |\n| 2022/6/14 | Start the competition registration|\n| 2022/6/15 | Release datasets for download|\n| 2022/6/20 | Open the entry of leaderboard A evaluation |\n| 2022/8/20 | Close the entrance of leaderboard A, and open the entry of leaderboard B to submit materials for review |\n| 2022/9/25 | Deadline for submission of review materials in leaderboard B |\n| 2022/9/26 | Announce the ranking and award of the leaderboard B |\n\n# 4. Dataset Provider\n**HUANG Gan** Assistant Professor\n**LIANG Zhen** Assistant Professor\n**ZHANG Zhiguo** Professor\n\n", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "rules", "content": "# 1 Qualified Participants\n\n1.\tThis competition is open to the whole society, no age, status, nationality, related fields of individuals, colleges and universities, research institutions, enterprises, start-up teams, etc.\n\n2.\tThose who have access to the questions and dataset in advance are not allowed to participate in the competition. Other employees can participate in the ranking of the competition, but they are not allowed to receive any prizes.\n\n# 2 Requirement\nWe encourage participation by an individual or a team. Each team can have no more than 5 members, and can be formed across universities/institutions/enterprises freely, but each person can only join one team\n\n# 3 Supplement \n\n1.\t**Fair competition:** competitors are not allowed to copy others’ works, exchange answers or use more than one trumpet in the competition. If found guilty, the results will be cancelled and dealt with seriously.\n\n2.\t**Organization statement:** the organizing committee reserves the right to adjust and modify the rules of the competition, the arrangement of the competition, the right to judge and deal with cheating in the competition, and the right to withdraw or refuse awards to the participating teams that affect the organization and fairness.\n\n3.\t**Baseline model:** the baseline model is for the reference of competitors, and can be improved upon. Competitors cannot directly submit the prediction structure of the baseline model.\n\n4.\t**Property:** The entrant agrees to grant the organizer the right to use the results free of charge, worldwide, for an unlimited period of time, including but not limited to the provision of services, further development of services, commercial use and sublicensing. For the avoidance of doubt, the organizer has full intellectual property rights in the new results based on the use of the aforementioned results, and the entrant agrees not to claim any rights or interests in the new results, including but not limited to ownership rights, and to impede the implementation of the new results based on ownership rights in the aforementioned results.\n\n# 4 Anti cheating instructions\n1.\tParticipants are not allowed to register for multiple accounts. Once found, their scores will be cancelled and dealt with seriously.\n\n2.\tParticipants are not allowed to use rules loopholes or technical loopholes and other bad ways to improve their performance ranking outside the scope of technical ability assessment. Once found, their performance will be cancelled and dealt with seriously.\n\n3.\tor those who have access to relevant data of the competition, their submitted works will not be included in the rankings and awards.\n", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false } ] }