**Overview:

The Bonn EEG Dataset is a widely recognized dataset in the field of biomedical signal processing and machine learning, specifically designed for research in epilepsy detection and EEG signal analysis. It contains electroencephalogram (EEG) recordings from both healthy individuals and patients with epilepsy, making it suitable for tasks such as seizure detection and classification of brain activity states. The dataset is structured into five distinct subsets (labeled A, B, C, D, and E), each comprising 100 single-channel EEG segments, resulting in a total of 500 segments. Each segment represents 23.6 seconds of EEG data, sampled at a frequency of 173.61 Hz, yielding 4,096 data points per segment, stored in ASCII format as text files.

****Structure and Label:

• Set A: EEG recordings from healthy individuals with eyes open, capturing normal brain activity under visual stimulation.
• Set B: EEG recordings from healthy individuals with eyes closed, reflecting brain activity in a resting state.
• Set C: EEG recordings from epilepsy patients, collected from the epileptogenic zone during an interictal (seizure-free) period.
• Set D: EEG recordings from epilepsy patients, collected from the hippocampal formation of the opposite brain hemisphere during an interictal period.
• Set E: EEG recordings from epilepsy patients during an ictal (seizure) period, capturing brain activity during an epileptic seizure. Each subset contains 100 EEG segments, ensuring a balanced distribution across the five classes, which supports both binary (e.g., healthy vs. epileptic) and multi-class (e.g., A-E classification) tasks.

**Key Characteristics

• Size: 500 EEG segments (100 segments per subset, across five subsets).
• Data Type: Single-channel EEG signals, stored in text files (ASCII format).
• Sampling Rate: 173.61 Hz, providing high temporal resolution.
• Segment Length: 23.6 seconds per segment, equivalent to 4,096 data points.
• Labels: Clearly defined for each subset (A: healthy, eyes open; B: healthy, eyes closed; C: interictal, epileptogenic zone; D: interictal, opposite hemisphere; E: ictal), enabling precise model evaluation.
• Preprocessing: The data is not pre-filtered, but a low-pass filter with a 40 Hz cutoff is recommended to remove high-frequency noise and artifacts, as suggested in the original documentation.

**Applications

The Bonn EEG Dataset is ideal for machine learning and signal processing tasks, including: - Developing algorithms for epileptic seizure detection and prediction. - Exploring feature extraction techniques, such as wavelet transforms, for EEG signal analysis. - Classifying brain states (healthy vs. epileptic, interictal vs. ictal). - Supporting research in neuroscience and medical diagnostics, particularly for epilepsy monitoring and treatment.

**Source

• The dataset is publicly available from the University of Bonn and can be downloaded from the following link: University of Bonn EEG Dataset
• The dataset is provided as five ZIP files, each containing 100 text files corresponding to the EEG segments for subsets A, B, C, D, and E.

**Citation

When using this dataset, researchers are required to cite the original publication: Andrzejak, R. G., Lehnertz, K., Mormann, F., Rieke, C., David, P., & Elger, C. E. (2001). Indications of nonlinear deterministic and finite-dimensional structures in time series of brain electrical activity: Dependence on recording region and brain state. Physical Review E, 64(6), 061907. DOI: 10.1103/PhysRevE.64.061907.

**Additional Notes

1. The dataset is randomized, with no specific information provided about patients or electrode placements, ensuring simplicity and focus on signal characteristics.

2. The data is not hosted on Kaggle or Hugging Face but is accessible directly from the University of Bonn’s repository or mirrored sources.

3. Researchers may need to apply preprocessing steps, such as filtering or normalization, to optimize the data for machine learning tasks.

4. The dataset’s balanced structure and clear labels make it an excellent choice for a one-week machine learning project, particularly for tasks involving traditional algorithms like SVM, Random Forest, or Logistic Regression.

5. This dataset provides a robust foundation for learning signal processing, feature extraction, and machine learning techniques while addressing a real-world medical challenge in epilepsy detection.

This database, collected at the Children’s Hospital Boston, consists of EEG recordings from pediatric subjects with intractable seizures. Subjects were monitored for up to several days following withdrawal of anti-seizure medication in order to characterize their seizures and assess their candidacy for surgical intervention. The recordings are grouped into 23 cases and were collected from 22 subjects (5 males, ages 3–22; and 17 females, ages 1.5–19).

PCA

Can you use brainwave data to discern whether someone is feeling good?

Please cite the following if you are using this data

https://www.researchgate.net/publication/329403546_Mental_Emotional_Sentiment_Classification_with_an_EEG-based_Brain-machine_Interface

https://www.researchgate.net/publication/335173767_A_Deep_Evolutionary_Approach_to_Bioinspired_Classifier_Optimisation_for_Brain-Machine_Interaction

This is a dataset of EEG brainwave data that has been processed with our original strategy of statistical extraction (paper below)

The data was collected from two people (1 male, 1 female) for 3 minutes per state - positive, neutral, negative. We used a Muse EEG headband which recorded the TP9, AF7, AF8 and TP10 EEG placements via dry electrodes. Six minutes of resting neutral data is also recorded, the stimuli used to evoke the emotions are below

1 . Marley and Me - Negative (Twentieth Century Fox) Death Scene 2. Up - Negative (Walt Disney Pictures) Opening Death Scene 3. My Girl - Negative (Imagine Entertainment) Funeral Scene 4. La La Land - Positive (Summit Entertainment) Opening musical number 5. Slow Life - Positive (BioQuest Studios) Nature timelapse 6. Funny Dogs - Positive (MashupZone) Funny dog clips

Our method of statistical extraction resampled the data since waves must be mathematically described in a temporal fashion.

If you would like to use the data in research projects, please cite the following:

J. J. Bird, L. J. Manso, E. P. Ribiero, A. Ekart, and D. R. Faria, “A study on mental state classification using eeg-based brain-machine interface,”in 9th International Conference on Intelligent Systems, IEEE, 2018.

J. J. Bird, A. Ekart, C. D. Buckingham, and D. R. Faria, “Mental emotional sentiment classification with an eeg-based brain-machine interface,” in The International Conference on Digital Image and Signal Processing (DISP’19), Springer, 2019.

This research was part supported by the EIT Health GRaCE-AGE grant number 18429 awarded to C.D. Buckingham.

This is a dataset of EEG brainwave data that has been processed with our method of statistical feature extraction

Code for extraction of features - https://github.com/jordan-bird/eeg-feature-generation This dataset is the output of the above

The data was collected from four people (2 male, 2 female) for 60 seconds per state - relaxed, concentrating, neutral. We used a Muse EEG headband which recorded the TP9, AF7, AF8 and TP10 EEG placements via dry electrodes.

Our method of statistical extraction resampled the data since waves must be mathematically described in a temporal fashion.

If you would like to use the data in research projects, please cite the following:

J. J. Bird, L. J. Manso, E. P. Ribiero, A. Ekart, and D. R. Faria, “A study on mental state classification using eeg-based brain-machine interface,”in 9th International Conference on Intelligent Systems, IEEE, 2018.

If you would like more detail on the data itself and how this process was carried out, the research paper can be found here:

http://jordanjamesbird.com/mental-state-classification-using-eeg-based-brain-machine-interface/

For more applications, several of our research projects used this dataset for various reasons: https://scholar.google.co.uk/scholar?hl=en&as_sdt=0%2C5&q=Jordan+J.+Bird+EEG&btnG=

Description:
This dataset contains electroencephalography (EEG) signals recorded during an emotion classification experiment using two devices: a high-end professional EEG system (BrainVision) and a low-cost brain-computer interface (Emotiv EPOC+). Data were collected from 20 participants while they were exposed to visual stimuli from the International Affective Picture System (IAPS), designed to induce four emotional states based on Russell’s valence-arousal model:

• HVHA: High valence, high arousal
• HVLA: High valence, low arousal
• LVHA: Low valence, high arousal
• LVLA: Low valence, low arousal

The dataset includes raw EEG recordings, preprocessed signals, and extracted features for further analysis. Additionally, a README file provides detailed information on the data structure, device configurations, and emotional labels assigned to each signal segment.

Data Format:

• Raw EEG data: Original signal recordings (.edf, .csv, .mat).
• Preprocessed EEG: Filtered and normalized data (.csv, .mat).
• Extracted features: Set of statistical, spectral, and entropy-based features used in the study (.csv, .xlsx).
• Metadata: Participant information (anonymized), experimental details, and emotional condition labels (.txt, .json).

Usage and Applications:
This dataset can be used for research in neuroscience, emotion classification, artificial intelligence, machine learning, and EEG signal processing. It is particularly suitable for developing and validating machine learning and deep learning models applied to emotion recognition from brain signals.

License & Accessibility:
The dataset is publicly available under the Creative Commons Attribution (CC BY 4.0) license, allowing free use, distribution, and modification with proper attribution.

Recommended Citation:
If you use this dataset in your research, please cite the associated publication:

Sánchez-Reolid, R., Martínez-Sáez, M. C., García-Martínez, B., Fernández-Aguilar, L., Ros, L., Latorre, J. M., & Fernández-Caballero, A. (2022). Emotion classification from EEG with a low-cost BCI versus a high-end equipment. International Journal of Neural Systems, 32(10), 2250041. World Scientific. https://doi.org/10.1142/S0129065722500411

The datset is comprised of 46(22 commercial adertisement and 24 kannada Music clips) different subjcets EEG data recorded uisng 2 channel EEG device

The dataset folder contaions two sub folder 1. comercial advertisement 1.1 Channel_1(Ch_1) and Channel_2 (Ch_2) :Prefontal Cortex 2. Kannada Musical clips 2.1 channel_1(Ch_1) and Channel_2 (Ch_2) :left Brain

Excel file information : Each file column represneted as number of subjects and row is represnted as features per subjects There are totaly 12 excel files from two channels ( 6 for commercial advertisemnt and 6 for kannda Musical clips).

Subjective self-rating scale

Name
age Gender Have you ever had any health issues? YES NO Have you watched this song/advertisement before? YES NO Please let us know if this advertisement brings up any specific memories for you. YES NO Please Rate the following query from 1 to 10. How funny was the advertisement you watched How sad was the advertisement you watched How Horror was the advertisement you watched How relaxed was the Music you viewed with How Sad was the Music you viewed with How enjoyable was the Music you viewed with Do you think what you just watched was entertaining enough? If you have any comment please write here

Here is the website address for each stimulus that we considered:

ad1: https://www.youtube.com/watch?v=ZzG7duipQ7U&ab_channel=perfettiindia ad2: https://www.youtube.com/watch?v=SfAxUpeVhCg&ab_channel=bo0fhead ad3: https://www.youtube.com/watch?v=HqGsT6VM8Vg&ab_channel=kiddlestix song1: https://www.youtube.com/hashtag/kgfchapter2 song 2: https://www.youtube.com/watch?v=x43w4lLS9E0&ab_channel=AnandAudio Song 3: https://youtube.com/watch?v=Ysf4QRrcLGM&si=EnSIkaIECMiOmarE

For a more comprehensive understanding of the dataset and its background, we kindly ask researchers to refer to our associated manuscript titled:

Entertainment Based Database for Emotion Recognition from EEG Signals, the research article accepted at 3rd International Conference on Applied Intelligence and informatics (AII2023) held in Fostering reproducibility of research results right 29 -31 OCT 2023, DUBAI, UAE. (When utilizing this dataset in your research, please consider citing the following reference)

SAM 40: Dataset of 40 subject EEG recordings to monitor the induced-stress while performing Stroop color-word test, arithmetic task, and mirror image recognition task

presents a collection of electroencephalogram (EEG) data recorded from 40 subjects (female: 14, male: 26, mean age: 21.5 years). The dataset was recorded from the subjects while performing various tasks such as Stroop color-word test, solving arithmetic questions, identification of symmetric mirror images, and a state of relaxation. The experiment was primarily conducted to monitor the short-term stress elicited in an individual while performing the aforementioned cognitive tasks. The individual tasks were carried out for 25 s and were repeated to record three trials. The EEG was recorded using a 32-channel Emotiv Epoc Flex gel kit. The EEG data were then segmented into non-overlapping epochs of 25 s depending on the various tasks performed by the subjects. The EEG data were further processed to remove the baseline drifts by subtracting the average trend obtained using the Savitzky-Golay filter. Furthermore, the artifacts were also removed from the EEG data by applying wavelet thresholding. The dataset proposed in this paper can aid and support the research activities in the field of brain-computer interface and can also be used in the identification of patterns in the EEG data elicited due to stress.

This data set consists of over 240 two-minute EEG recordings obtained from 20 volunteers. Resting-state and auditory stimuli experiments are included in the data. The goal is to develop an EEG-based Biometric system.

The data includes resting-state EEG signals in both cases: eyes open and eyes closed. The auditory stimuli part consists of six experiments; Three with in-ear auditory stimuli and another three with bone-conducting auditory stimuli. The three stimuli for each case are a native song, a non-native song, and neutral music.

The Harvard EEG Database will encompass data gathered from four hospitals affiliated with Harvard University: Massachusetts General Hospital (MGH), Brigham and Women's Hospital (BWH), Beth Israel Deaconess Medical Center (BIDMC), and Boston Children's Hospital (BCH). The EEG data includes three types:

rEEG: "routine EEGs" recorded in the outpatient setting.
EMU: recordings obtained in the inpatient setting, within the Epilepsy Monitoring Unit (EMU).
ICU/LTM: recordings obtained from acutely and critically ill patients within the intensive care unit (ICU).

0. Sections

1. Project
2. Dataset
3. Terms of Use
4. Contents
5. Method and Processing

1. PROJECT

Title: Brain-Computer Music Interface for Monitoring and Inducing Affective States (BCMI-MIdAS)

Dates: 2012-2017

Funding organisation: Engineering and Physical Sciences Research Council (EPSRC)

Grant no.: EP/J003077/1 and EP/J002135/1.

2. DATASET

Title: EEG data investigating neural correlates of music-induced emotion.

Description: This dataset accompanies the publication by Daly et al. (2018) and has been analysed in Daly et al. (2014; 2015a; 2015b) (please see Section 5 for full references). The purpose of the research activity in which the data were collected was to investigate the EEG neural correlates of music-induced emotion. For this purpose 31 healthy adult participants listened to 40 music clips of 12 s duration each, targeting a range of emotional states. The music clips comprised excerpts from film scores spanning a range of styles and rated on induced emotion. The dataset contains unprocessed EEG data from all 31 participants (age range 18-66, 18 female) while listening to the music clips, together with the reported induced emotional responses . The paradigm involved 6 runs of EEG recordings. The first and last runs were resting state runs, during which participants were instructed to sit still and rest for 300 s. The other 4 runs each contained 10 music listening trials.

Publication Year: 2018

Creator: Nicoletta Nicolaou, Ian Daly.

Contributors: Isil Poyraz Bilgin, James Weaver, Asad Malik.

Principal Investigator: Slawomir Nasuto (EP/J003077/1).

Co-Investigator: Eduardo Miranda (EP/J002135/1).

Organisation: University of Reading

Rights-holders: University of Reading

Source: The musical stimuli were taken from Eerola & Vuoskoski, “A comparison of the discrete and dimensional models of emotion in music”, Psychol. Music, 39:18-49, 2010 (doi: 10.1177/0305735610362821).

3. TERMS OF USE

Copyright University of Reading, 2018. This dataset is licensed by the rights-holder(s) under a Creative Commons Attribution 4.0 International Licence: https://creativecommons.org/licenses/by/4.0/.

4. CONTENTS

BIDS File listing: The dataset comprises data from 31 participants, named using the convention: sub_s_number where: s_number is a random participant number from 1 to 31. For example: ‘sub-08’ contains data obtained from participant 8.

The data is BIDS format and contains EEG and associated meta data. The sampling rate is 1 kHz and the EEG corresponding to a music clip is 20 s long (the duration of the clips).

Each data folder contains the following data (please note that the number of runs varies between participants):

EEG data in .tsv format. Event codes (JSON) and timings (tsv). EEG channel information.

5. METHOD and PROCESSING

This information is available in the following publications:

[1] Daly, I., Nicolaou, N., Williams, D., Hwang, F., Kirke, A., Miranda, E., Nasuto, S.J., �Neural and physiological data from participants listening to affective music�, Scientific Data, 2018. [2] Daly, I., Malik, A., Hwang, F., Roesch, E., Weaver, J., Kirke, A., Williams, D., Miranda, E. R., Nasuto, S. J., �Neural correlates of emotional responses to music: an EEG study�, Neuroscience Letters, 573: 52-7, 2014; doi: 10.1016/j.neulet.2014.05.003. [3] Daly, I., Hallowell, J., Hwang, F., Kirke, A., Malik, A., Roesch, E., Weaver, J., Williams, D., Miranda, E., Nasuto, S.J., �Changes in music tempo entrain movement related brain activity�, Proc. IEEE EMBC 2014, pp.4595-8; doi: 10.1109/EMBC.2014.6944647 [4] Daly, I., Williams, D., Hallowell, J., Hwang, F., Kirke, A., Malik, A., Weaver, J., Miranda, E., Nasuto, S.J., �Music-induced emotions can be predicted from a combination of brain activity and acoustic features�, Brain and Cognition, 101:1-11, 2015b; doi: 10.1016/j.bandc.2015.08.003

Please cite these references if you use this dataset in your study.

Thank you for your interest in our work.

This dataset contains the EEG resting state-closed eyes recordings from 88 subjects in total. Participants: 36 of them were diagnosed with Alzheimer's disease (AD group), 23 were diagnosed with Frontotemporal Dementia (FTD group) and 29 were healthy subjects (CN group). Cognitive and neuropsychological state was evaluated by the international Mini-Mental State Examination (MMSE). MMSE score ranges from 0 to 30, with lower MMSE indicating more severe cognitive decline. The duration of the disease was measured in months and the median value was 25 with IQR range (Q1-Q3) being 24 - 28.5 months. Concerning the AD groups, no dementia-related comorbidities have been reported. The average MMSE for the AD group was 17.75 (sd=4.5), for the FTD group was 22.17 (sd=8.22) and for the CN group was 30. The mean age of the AD group was 66.4 (sd=7.9), for the FTD group was 63.6 (sd=8.2), and for the CN group was 67.9 (sd=5.4).

Recordings: Recordings were aquired from the 2nd Department of Neurology of AHEPA General Hispital of Thessaloniki by an experienced team of neurologists. For recording, a Nihon Kohden EEG 2100 clinical device was used, with 19 scalp electrodes (Fp1, Fp2, F7, F3, Fz, F4, F8, T3, C3, Cz, C4, T4, T5, P3, Pz, P4, T6, O1, and O2) according to the 10-20 international system and 2 reference electrodes (A1 and A2) placed on the mastoids for impendance check, according to the manual of the device. Each recording was performed according to the clinical protocol with participants being in a sitting position having their eyes closed. Before the initialization of each recording, the skin impedance value was ensured to be below 5k?. The sampling rate was 500 Hz with 10uV/mm resolution. The recording montages were anterior-posterior bipolar and referential montage using Cz as the common reference. The referential montage was included in this dataset. The recordings were received under the range of the following parameters of the amplifier: Sensitivity: 10uV/mm, time constant: 0.3s, and high frequency filter at 70 Hz. Each recording lasted approximately 13.5 minutes for AD group (min=5.1, max=21.3), 12 minutes for FTD group (min=7.9, max=16.9) and 13.8 for CN group (min=12.5, max=16.5). In total, 485.5 minutes of AD, 276.5 minutes of FTD and 402 minutes of CN recordings were collected and are included in the dataset.

Preprocessing: The EEG recordings were exported in .eeg format and are transformed to BIDS accepted .set format for the inclusion in the dataset. Automatic annotations of the Nihon Kohden EEG device marking artifacts (muscle activity, blinking, swallowing) have not been included for language compatibility purposes (If this is an issue, please use the preprocessed dataset in Folder: derivatives). The unprocessed EEG recordings are included in folders named: sub-0XX. Folders named sub-0XX in the subfolder derivatives contain the preprocessed and denoised EEG recordings. The preprocessing pipeline of the EEG signals is as follows. First, a Butterworth band-pass filter 0.5-45 Hz was applied and the signals were re-referenced to A1-A2. Then, the Artifact Subspace Reconstruction routine (ASR) which is an EEG artifact correction method included in the EEGLab Matlab software was applied to the signals, removing bad data periods which exceeded the max acceptable 0.5 second window standard deviation of 17, which is considered a conservative window. Next, the Independent Component Analysis (ICA) method (RunICA algorithm) was performed, transforming the 19 EEG signals to 19 ICA components. ICA components that were classified as “eye artifacts” or “jaw artifacts” by the automatic classification routine “ICLabel” in the EEGLAB platform were automatically rejected. It should be noted that, even though the recording was performed in a resting state, eyes-closed condition, eye artifacts of eye movement were still found at some EEG recordings.

A complete analysis of this dataset can be found in the published Data Descriptor paper "A Dataset of Scalp EEG Recordings of Alzheimer’s Disease, Frontotemporal Dementia and Healthy Subjects from Routine EEG", https://doi.org/10.3390/data8060095 *****Im not the original creator of this dataset it was published on https://openneuro.org/datasets/ds004504/versions/1.0.6 i just ported it here for ease of use *****

General information

The dataset provides resting-state EEG data (eyes open,partially eyes closed) from 71 participants who underwent two experiments involving normal sleep (NS---session1) and sleep deprivation(SD---session2) .The dataset also provides information on participants' sleepiness and mood states. （Please note here Session 1 (NS) and Session 2 (SD) is not the time order, the time order is counterbalanced across participants and is listed in metadata.）

Dataset

Presentation

The data collection was initiated in March 2019 and was terminated in December 2020. The detailed description of the dataset is currently under working by Chuqin Xiang,Xinrui Fan,Duo Bai,Ke Lv and Xu Lei, and will submit to Scientific Data for publication.

EEG acquisition

• EEG system (Brain Products GmbH, Steing- rabenstr, Germany, 61 electrodes)
• Sampling frequency: 500Hz
• Impedances were kept below 5k

Contact

 * If you have any questions or comments, please contact:
 * Xu Lei: xlei@swu.edu.cn   

Article

Xiang, C., Fan, X., Bai, D. et al. A resting-state EEG dataset for sleep deprivation. Sci Data 11, 427 (2024). https://doi.org/10.1038/s41597-024-03268-2

This dataset contains EEG recordings from 18 subjects listening to one of two competing speech audio streams. Continuous speech in trials of ~50 sec. was presented to normal hearing listeners in simulated rooms with different degrees of reverberation. Subjects were asked to attend one of two spatially separated speakers (one male, one female) and ignore the other. Repeated trials with presentation of a single talker were also recorded. The data were recorded in a double-walled soundproof booth at the Technical University of Denmark (DTU) using a 64-channel Biosemi system and digitized at a sampling rate of 512 Hz. Full details can be found in:

• Søren A. Fuglsang, Torsten Dau & Jens Hjortkjær (2017): Noise-robust cortical tracking of attended speech in real-life environments. NeuroImage, 156, 435-444

and

• Daniel D.E. Wong, Søren A. Fuglsang, Jens Hjortkjær, Enea Ceolini, Malcolm Slaney & Alain de Cheveigné: A Comparison of Temporal Response Function Estimation Methods for Auditory Attention Decoding. Frontiers in Neuroscience, https://doi.org/10.3389/fnins.2018.00531

The data is organized in format of the publicly available COCOHA Matlab Toolbox. The preproc_script.m demonstrates how to import and align the EEG and audio data. The script also demonstrates some EEG preprocessing steps as used the Wong et al. paper above. The AUDIO.zip contains wav-files with the speech audio used in the experiment. The EEG.zip contains MAT-files with the EEG/EOG data for each subject. The EEG/EOG data are found in data.eeg with the following channels:

• channels 1-64: scalp EEG electrodes
• channel 65: right mastoid electrode
• channel 66: left mastoid electrode
• channel 67: vertical EOG below right eye
• channel 68: horizontal EOG right eye
• channel 69: vertical EOG above right eye
• channel 70: vertical EOG below left eye
• channel 71: horizontal EOG left eye
• channel 72: vertical EOG above left eye

The expinfo table contains information about experimental conditions, including what what speaker the listener was attending to in different trials. The expinfo table contains the following information:

• attend_mf: attended speaker (1=male, 2=female)
• attend_lr: spatial position of the attended speaker (1=left, 2=right)
• acoustic_condition: type of acoustic room (1= anechoic, 2= mild reverberation, 3= high reverberation, see Fuglsang et al. for details)
• n_speakers: number of speakers presented (1 or 2)
• wavfile_male: name of presented audio wav-file for the male speaker
• wavfile_female: name of presented audio wav-file for the female speaker (if any)
• trigger: trigger event value for each trial also found in data.event.eeg.value

DATA_preproc.zip contains the preprocessed EEG and audio data as output from preproc_script.m.

The dataset was created within the COCOHA Project: Cognitive Control of a Hearing Aid

THINGS-EEG

This dataset is a processed version of THINGS-EEG, derived from the paper Bridging the Vision-Brain Gap with an Uncertainty-Aware Blur Prior (CVPR 2025). In this version, the EEG data is stored in float16 format, reducing the storage size by half. The original official dataset can be accessed from the OSF repository. Original official dataset:

A large and rich EEG dataset for modeling human visual object recognition [THINGS-EEG]

  Citation… See the full description on the dataset page: https://huggingface.co/datasets/Haitao999/things-eeg.

We used a high-density electroencephalography (HD-EEG) system, with 128 customized electrode locations, to record from 17 individuals with migraine (12 female) in the interictal period, and 18 age- and gender-matched healthy control subjects, during visual (vertical grating pattern) and auditory (modulated tone) stimulation which varied in temporal frequency (4 and 6Hz), and during rest. This dataset includes the EEG raw data related to the paper entitled Chamanzar, Haigh, Grover, and Behrmann (2020), Abnormalities in cortical pattern of coherence in migraine detected using ultra high-density EEG. The link to our paper will be made available as soon as it is published online.

This dataset contains 848,640 records with 17 columns, representing EEG (Electroencephalogram) signals recorded from multiple electrode positions on the scalp, along with a status label. The dataset is be related to the study of Alzheimer’s Disease (AD).

Features (16 continuous variables, float64): Each feature corresponds to the electrical activity recorded from standard EEG electrode placements based on the international 10-20 system:

Fp1, Fp2, F7, F3, Fz, F4, F8

T3, C3, Cz, C4, T4

T5, P3, Pz, P4

These channels measure brain activity in different cortical regions (frontal, temporal, central, and parietal lobes).

Target variable (1 categorical variable, int64):

status: Represents the condition or classification of the subject at the time of recording (e.g., patient vs. control, or stage of Alzheimer’s disease).

Size & Integrity:

Rows: 848,640 samples

Columns: 17 (16 EEG features + 1 status label)

Data types: 16 float features, 1 integer label

Missing values: None (clean dataset)

This dataset is suitable for machine learning and deep learning applications such as:

EEG signal classification (AD vs. healthy subjects)

Brain activity pattern recognition

Feature extraction and dimensionality reduction (e.g., PCA, wavelet transforms)

Time-series analysis of EEG recordings

This dataset is made by version 4 of my notebook here. An example how to use this dataset can be seen in my two starter notebooks here and here.

The folder EEG_Spectrograms contains one NumPy file per eeg id. The shape of the NumPy array is (128x256x4) which is (frequency, time, montage chain). The file eeg_specs.npy is a Python dictionary which contains all the NumPy array therein with eeg_id as key. Loading this single file is faster than loading 17089 individual NumPy files.

Experiment Details Electroencephalography recordings from 16 subjects to fast streams of gabor-like stimuli. Images were presented in rapid serial visual presentation streams at 6.67Hz and 20Hz rates. Participants performed an orthogonal fixation colour change detection task.

Experiment length: 1 hour Raw and preprocessed data are available online through openneuro: https://openneuro.org/datasets/ds004357. Supplementary Material and analysis scripts are available on github: https://github.com/Tijl/features-eeg

This is the raw EEG data for the study. Data is in BioSemi Data Format (BDF). Files with only "II" in the file name were recorded during the reported 1-Exemplar categorization task; "RB-II" files were recorded during the reported 2-Exemplar categorization task. "Resting" files were recorded during wakeful resting state data.