User behavior has a significant impact on household energy consumption. Though researchers use a variety of methods to investigate user behavior, the solutions for evaluating user behavior are limited. This article presents an open-access electroencephalography (EEG) dataset that contains EEG data from individuals stimulated by energy data visualizations. The dataset includes 28 healthy participants' 6-channel EEG recordings. A 32-channel EMOTIV EEG device is utilized to acquire EEG signals, and an international 10-20 electrode system is employed to place electrodes. The stimuli are created and presented using PsychoPy software. Through the use of a self-assessment manikin (SAM), participants rate the valence and arousal of each stimulus to determine their affective state for that stimulus. Additionally, three questions are asked for each stimulus. The dataset includes original data visualizations and ratings. To facilitate analysis, the raw EEG data is segmented into data visualizations and neutral images using event markers. Using the EMOTIVPro application, EEG recordings are directly saved, and the PsychoPy application is used to store subjective responses. This dataset suggests a novel application of EEG research and offers a helpful starting point for researchers in the fields of computer science, energy efficiency, artificial intelligence, brain-computer interfaces, and human-computer interaction.

EEG Spectrogram Dataset for Schizophrenia Detection (ASZED-derived)

This dataset is derived from the publicly available ASZED EEG dataset, reorganized and labeled for deep learning experiments focused on schizophrenia detection. It contains raw EEG files (.edf) and corresponding spectrogram images (.png) along with a metadata CSV (labels.csv).

⚠️ Note: The filename column in labels.csv uses .edf extensions. When working with the spectrogram images (e.g., during model training), you must replace .edf with .png in your code.

📂 Dataset Contents

• EEG_ASZED_ORGANIZED/ – Contains ~1800 reorganized EEG files in .edf format.
• EEG_IMAGES_VGG16/ – Contains 1,801 spectrogram images (.png) generated from the EEG data. Each corresponds to an .edf file, converted using MNE and Matplotlib.
• labels.csv – A metadata file with session info, diagnostic labels, and demographic details.

🧠 Labels and Metadata (labels.csv)

The CSV file includes the following columns:

🏷️ Label Description

• Control: EEG data recorded from healthy individuals without diagnosed schizophrenia.
• Patient: EEG data from individuals diagnosed with schizophrenia.

These labels are used as the target variable in classification tasks.

🧪 How to Use

1. Load labels.csv using pandas:

   import pandas as pd df = pd.read_csv("labels.csv")

2. Replace .edf with .png in the filename column if using spectrograms: df["filename"] = df["filename"].str.replace(".edf", ".png")

3. Use the label column as the classification target.

4. Optionally include age and gender as auxiliary features for demographic analysis.

🔗 Model Pipeline (VGG16-based)

To see how this dataset was used in a complete deep learning pipeline (including training, validation, evaluation, and visualization using VGG16), visit the accompanying GitHub repository:

👉 https://github.com/Ayushaote/EEG-schizophrenia-detection

📌 Citation & Attribution

The original EEG signals are from the ASZED dataset on PhysioNet, licensed for academic and research use.

This processed version adds value by:

Organizing EEG recordings by subject/session/phase

Curating labels.csv for supervised learning

Converting time-series EEG data to spectrograms for CNN models

📄 License

This dataset is shared under the Creative Commons Attribution 4.0 International (CC BY 4.0) license. You are free to use, share, and modify the dataset with proper credit to the author(s).

Description: This dataset consists of EEG recordings of five essential words commonly used in speech therapy for post-stroke patients. The data was collected from a single female participant using a NeuroSky Mindwave Mobile 2 headset in a controlled environment, ensuring minimal noise interference and high-quality signal acquisition.

Purpose: The dataset aims to facilitate research in neuroscience and brain-computer interface (BCI) development, specifically for post-stroke rehabilitation. It provides a foundation for creating machine learning models that decode EEG signals into meaningful linguistic outputs, offering potential breakthroughs in assistive technologies for individuals with speech and motor impairments.

Data Structure: EEG Signal Data: Captures brainwave patterns corresponding to five essential words. Participant: Post-stroke patients engaged in tasks designed to evoke EEG responses tied to the target words. Recording Settings: Standardized environment with participants focusing on auditory and visual stimuli associated with each word.

Applications: Development of classification algorithms for EEG signals linked to word recognition. Training BCIs to assist in real-time communication for post-stroke patients. Studying neural activity associated with speech therapy exercises.

Potential Use Cases: Creation of assistive communication devices for individuals with speech and motor challenges. Research into personalized EEG signal responses during language-based rehabilitation. Advancement of neurotechnology for targeted healthcare applications.

Dataset Features: High-quality EEG recordings of five essential rehabilitation words. Precise, noise-minimized data collection. Open-access format to encourage reproducibility and collaboration in EEG and healthcare research.

Overnight high-density EEG recording of a healthy young participant downsampled to 250Hz in fif format.

In addition, two text files:

• bad_channels.txt contains indexes of noisy channels
• annotations.txt contains the onset and duration of noisy temporal intervals

The package can be found on GitHub.

Summary of features provided by EPViz, as compared to existing EEG software.

This data contains a total of seven files.The first file is anonymised participants' behaviour, ET and EEG metrics when using the map task (raw data for statistical tests in the manuscript). Each row represents the results for one participant under one map trial. The ET and EEG data recordings failed for subject #1, and the EEG data recordings failed for subjects #17 and #26.The second file is the material (NASA-TLX scale and post-experiment questionnaire) that participants needed to make after completing the map task. All data were collected on paper, with two photographs for a sample of one participant.The third and fourth files are a sample of one participants' raw ET data (exported from Tobii pro) and EEG data (collected via the nic2 system).The fifth file is the stimulus material used in the experiment, of which only one trial is shown as a sample.The sixth file is the NASA-TLX and self-rated difficulty results.The last file is the python code for statistical analysis. It should be noted that visualization and EEG ERP results need the input of all sample raw data, and given the size of the data, the generation of these results is not shown in the code. Please contact the authors for more detailed requests.Please note that we have not disclosed all raw data given the volume of raw data and concerns about the privacy of participants. Please contact the authors at their email address for further enquiries.

The dataset contains each participant's event-related potential research data and electroencephalography brain data analysis. In addition, it contains the answer accuracy of experiment questions. The system contains two group files. Each group folder contains 26 participant files. Each participant folder contains one EEG file and one ERP file. The answer_summary_english_correct_formal_anonymity.xlsx contains all the subjective evaluation results and answer accuracy data in the folder. Participant number was matched between folders and files.

Human sleep architecture is structured with repeated episodes of rapid-eye-movement (REM) and non-rapid-eye-movement (NREM) sleep. An overnight sleep study facilitates identification of macro and micro changes in the pattern and duration of sleep stages associated with sleep disorders and other aspects of human mental and physical health. Overnight sleep studies record, in addition to electroencephalography (EEG) and other electro-physiological signals, a sequence of sleep-stage annotations. SSAVE, introduced here, is open-source software that takes sleep-stage annotations and EEG signals as input, identifies and characterizes periods of NREM and REM sleep, and produces a hypnogram and its time-matched EEG spectrogram. SSAVE fills an important gap for the rapidly growing field of sleep medicine by providing an easy-to-use tool for sleep-period identification and visualization. SSAVE can be used as a Python package, a desktop standalone tool or through a web portal. All versions of the SSAVE tool can be found on: https://manticore.niehs.nih.gov/ssave.

braindecode v0.7

Braindecode is an open-source Python toolbox for decoding raw electrophysiological brain data with deep learning models. It includes dataset fetchers, data preprocessing and visualization tools, as well as implementations of several deep learning architectures and data augmentations for analysis of EEG, ECoG and MEG.

For neuroscientists who want to work with deep learning and deep learning researchers who want to work with neurophysiological data.

soruce: https://braindecode.org/stable/index.html

Brain–computer interface (BCI) has developed rapidly over the past two decades, mainly due to advancements in machine learning. Subjects must learn to modulate their brain activities to ensure a successful BCI. Feedback training is a practical approach to this learning process; however, the commonly used classifier-dependent approaches have inherent limitations such as the need for calibration and a lack of continuous feedback over long periods of time. This paper proposes an online data visualization feedback protocol that intuitively reflects the EEG distribution in Riemannian geometry in real time. Rather than learning a hyperplane, the Riemannian geometry formulation allows iterative learning of prototypical covariance matrices that are translated into visualized feedback through diffusion map process. Ten subjects were recruited for MI-BCI (motor imagery-BCI) training experiments. The subjects learned to modulate their sensorimotor rhythm to centralize the points within one category and to separate points belonging to different categories. The results show favorable overall training effects in terms of the class distinctiveness and EEG feature discriminancy over a 3-day training with 30% learners. A steadily increased class distinctiveness in the last three sessions suggests that the advanced training protocol is effective. The optimal frequency band was consistent during the 3-day training, and the difference between subjects with good or low MI-BCI performance could be clearly observed. We believe that the proposed feedback protocol has promising application prospect.

This data package contains the slides, Matlab m files and a dataset for an ERP workshop I gave in Washington DC, Glasgow, Fribourg, Frankfurt & Berlin. The goal of the workshop is to use hands-on exercises to introduce the basic principles and the Matlab implementation of robust estimation, using resampling methods (bootstrap & permutation) in conjunction with robust estimators. The workshop covers why classic t-tests and ANOVAs on means are not necessarily the best options, and how robust approaches can help. In particular, it demonstrates techniques to compare entire distributions, how to build confidence intervals about any quantity using the bootstrap, and how to effectively control for multiple comparisons. The methods are applied to single-subject and group analyses, and examples are provided to integrate both levels into informative figures.

Neonatal brain monitoring in the neonatal intensive care units (NICU) requires a continuous review of the spontaneous cortical activity, i.e., the electroencephalograph (EEG) background activity. This needs development of bedside methods for an automated assessment of the EEG background activity. In this paper, we present development of the key components of a neonatal EEG background classifier, starting from the visual background scoring to classifier design, and finally to possible bedside visualization of the classifier results. A dataset with 13,200 5-minute EEG epochs (8–16 channels) from 27 infants with birth asphyxia was used for classifier training after scoring by two independent experts. We tested three classifier designs based on 98 computational features, and their performance was assessed with respect to scoring system, pre- and post-processing of labels and outputs, choice of channels, and visualization in monitor displays. The optimal solution achieved an overall classification accuracy of 97% with a range across subjects of 81–100%. We identified a set of 23 features that make the classifier highly robust to the choice of channels and missing data due to artefact rejection. Our results showed that an automated bedside classifier of EEG background is achievable, and we publish the full classifier algorithm to allow further clinical replication and validation studies.

Research data refers to all materials and datasets generated, analyzed, or used in your study that are necessary to validate your findings. This may include:

1. Raw and Processed Data

EEG brainwave recordings (raw and preprocessed signals)

Neurofeedback score datasets ( Neuron-Spectrum.NET )

Statistical analysis data (e.g., SPSS, MATLAB, or Python files)

Cognitive achievement test scores and student performance data

1. Supplementary Materials

Experimental protocols and study design details

Questionnaires, surveys, or rubrics used in the study

Educational materials related to HOTS-based mathematics tasks

1. Code and Algorithms (if applicable)

Scripts for EEG signal processing and analysis

Machine learning or statistical modeling scripts

Any software implementation used to analyze brainwave patterns

1. Figures, Graphs, and Visualizations

Plots of EEG data and neurofeedback trends

Correlations between cognitive achievement and brainwave activity

Unit testing code coverage for EPViz source files.

This dataset contains a selected subset of EEG signal recordings from the HMS – Harmful Brain Activity Classification competition (Kaggle 2024), originally published by Harvard Medical School and the Critical Care EEG Monitoring Research Consortium (CCEMRC).

No structural or semantic modifications were applied to the data. The original .parquet files were simply converted to .csv format using standard Python libraries (PyArrow and Pandas), to make them compatible with external symbolic and harmonic inference systems.

Only a few dozen .csv samples are included in this dataset for demonstration purposes. This subset will serve as input for S.O.M. – EEG, a harmonic model of neural pattern interpretation based on the theoretical framework of T-Physics.

This dataset is not intended to replace or reframe the original dataset. It exists solely to support visualization and inference demonstrations in a non-commercial, academic context.

In an EEG-based near real-time neurofeedback (NF) study in two parts using high immersive virtual reality (VR) we successfully trained healthy participants to downregulate their parietal alpha power, a neurophysiological correlate previously associated with enhanced sense of presence. The first part included n = 10 participants equipped with 128 and 64 channels gel-based active EEG electrodes in 10 sessions using standard bar feedback presented on a computer monitor. Nine participants were better than random at the 10th session and four improved over time. For the second part we reduced the electrode subset to 9 sponge-based active channels (2 frontal, 7 parietal around Pz) and a portable amplifier. Participants (n = 10) were trained each session within VR using bar feedback projected on a wall in the first 5 sessions and then controlling the flow of a water fountain. Participants were able to significantly downregulate their parietal alpha power after 5 sessions and learning occurred at the group level, with 7 participants showing both improvement over time and ability to modulate. However, these results were only shown during the fountain feedback and both ability and learning were non-significant in the VR projector condition. Based on self-reports, after excluding participants performing movements and closing their eyes, no particular mental strategy, such as relaxation, breathing or mental calculus was identified to help with alpha modulation. The hypothesized behavioral effect on sense of presence was not found nor any neurophysiological changes in fronto-parietal connectivity. While NF did not improve the sense of presence, we succeeded in adapting real-time NF training for high immersive VR technology via seamlessly embedded feedback in the form of a water fountain. The study showcases that NF is possible with sponge electrodes and portable EEG that would prove convenient in end-user (at home) or clinical setup. The dataset is publicly available on Openneuro.org.

Interictal spikes are electroencephalographic discharges that occur at or near brain regions that produce epileptic seizures. While their role in generating seizures is not well understood, spikes have profound effects on cognition and behavior, depending on where and when they occur. We previously demonstrated that spiking areas of the human neocortex show sustained MAPK activation in superficial cortical layers I-III and are associated with microlesions in deeper cortical areas characterized by reduced neuronal nuclear protein (NeuN) staining and increased microglial infiltration. Based on these findings, we chose to investigate additional neuronal populations within microlesions, specifically inhibitory interneurons. Additionally, we hypothesized that spiking would be sufficient to induce similar cytoarchitectonic changes within the rat cortex and that inhibition of MAPK signaling, using a MAP2K inhibitor, would not only inhibit spike formation but also reduce these cytoarchitectonic..., 40 two-month-old male Sprague-Dawley rats were utilized for this study. Briefly, rats were anesthetized and 7 electrode holes were drilled through the skull (3 left and 3 right electrode holes located at the following locations relative to bregma: AP +4 mm, ML 3.5 mm; AP -1 mm, ML 3.5 mm; AP -6 mm, ML 3.5 mm; 1 reference electrode hole above the nasal sinus: AP +10.5 mm, ML 0.5 mm left). Before electrode screw placement, rats received an injection of either 1 uL of sterile PBS alone (sham rats) or 80 ng of tetanus toxin (TeNT rats) in 1 uL of sterile PBS into the left somatosensory cortex (corresponding to the site of the left middle electrode: AP -1 mm, ML 3.5 mm left, DV -1.5 mm). Epidural electrode screws were then placed, and rats were fitted with head cap apparatuses. Beginning on postoperative day 5, electroencephalography (EEG) recordings were conducted every 5 days through postoperative day 35. From post-operative days 35-84, EEG recordings were conducted once weekly. After post..., EDF browser was used for data visualization and analysis. R or RStudio can be used to open the RDA file., # Spike-induced cytoarchitectonic changes in the epileptic human cortex are reduced via MAP2K inhibition

Description of the data and file structure

Variables in R Dataset (SpikeData_Cleaned_withRecTime.Rda):

• SpikeTimeSec: Identifies the time that a spike was observed on the EDF file, relative to the file start time.
• OspikeV: Maximum spike voltage (uV)
• Ldur2: Duration of the left half-spike (ms)
• Rdur2: Duration of the right half-spike (ms)
• Tdur2: Total spike duration (ms)
• OLslope2: Slope of the left half-spike
• ORslope2: Slope of the right half-spike
• OLamp2: Amplitude of the left half-spike (uV)
• ORamp2: Amplitude of the right half-spike (uV)
• CH: Corresponds to the electrode recording site. 1: right anterior electrode; 2: right middle electrode; 3: right posterior electrode; 4: left anterior electrode; 5: left middle electrode (site of TeNT or saline injection); 6: left posterior electrode
• Rat: Individual rat identification number
• ...

Electroencephalogram System (EEG) Market Outlook 2032

The global electroencephalogram system (EEG) market size was USD 1.03 Billion in 2023 and is projected to reach USD 1.78 Billion by 2032, expanding at a CAGR of 6.3% during 2024–2032. The market is driven by the increasing prevalence of neurological disorders and the advancements in EEG technology and software analytics.



Increasing consumer health awareness propels the demand for wearable EEG devices. These devices offer the convenience of monitoring brain activity in real-time, outside traditional clinical settings.



Recent launches by manufacturers focus on compact, user-friendly designs that integrate seamlessly with smartphones and other digital platforms for continuous monitoring. This trend is supported by investments in health technology startups, focusing on developing innovative wearable EEG solutions that cater to the growing consumer demand for personal health tracking.

• 
  

  In June 2023, Koneksa, a pioneer in evidence-based digital biomarkers, revealed a collaboration with Beacon Biosignals, a top entity in computational neurodiagnostics, to initiate a clinical trial exploring the incorporation of Beacon's at-home EEG technology into Koneksa's Neuroscience Solution Toolkit. This partnership leverages Beacon's platform to provide extended, at-home EEG monitoring, utilizing machine learning to enhance brain activity insights, and offering sponsors advanced data analysis and visualization tools.

  
  

Increasing application of EEG systems in cognitive research and neurotherapy marks a significant trend. Researchers and clinicians are leveraging EEG technology to understand brain functions and treat neurological conditions effectively.



This trend is driven by the growing body of research linking brainwave patterns to cognitive states and disorders, encouraging the use of EEG in therapeutic settings. Public and private sector investments in neuroscience research initiatives further fuel this trend, highlighting the expanding role of EEG in advancing brain science.</

Sleep-EDF Cassette Dataset

Overview

The Sleep-EDF Cassette Dataset is a comprehensive collection of sleep recordings from the PhysioBank's Sleep-EDF Database. This dataset includes 305 files that capture various aspects of sleep data, with each participant's data represented by a pair of files: one containing polysomnographic (PSG) recordings and the other containing the corresponding hypnogram annotations. The recordings are in EDF (European Data Format) and cover a wide range of sleep-related physiological parameters.

Dataset Structure

The dataset is organized into pairs of files for each subject: - PSG Files (*.edf): These files contain polysomnographic data, which include multi-channel recordings of brain activity (EEG), eye movements (EOG), muscle activity (EMG), heart rhythm (ECG), and other physiological signals collected during sleep. - Hypnogram Files (*-Hypnogram.edf): These files contain annotations of sleep stages, which are essential for sleep stage classification. They mark different stages of sleep such as Wake (W), Non-Rapid Eye Movement (NREM) sleep stages (N1, N2, N3), and Rapid Eye Movement (REM) sleep.

Dataset Information

• Dataset Name: Sleep Data EDF Files
• Dataset Visualization Tool: [Tool](https://www.physionet.org/lightwave/?db=sleep-edfx/1.0.0
• Description: This dataset contains sleep EEG data in EDF format.
• Total Files: 305
• File Format: EDF (European Data Format)

Data Sources

-**Sleep Cassette Study (SC)**: Data from a study on age effects on sleep in healthy individuals, recorded with a cassette-tape recorder. -**Sleep Telemetry Study (ST)**: Data from a study on temazepam effects on sleep, recorded with a telemetry system.

File Naming Convention

Each pair of files follows a structured naming convention: - Example: SC4001E0-PSG.edf and SC4001EC-Hypnogram.edf - SC4001E0: Subject identifier and session information. - PSG.edf: Indicates that the file contains polysomnographic data. - Hypnogram.edf: Indicates that the file contains the corresponding sleep stage annotations.

Applications

This dataset is highly valuable for research and development in the field of sleep medicine, particularly in: - Sleep Stage Classification: Using machine learning models to classify sleep stages based on PSG data. - Sleep Disorder Detection: Identifying and diagnosing sleep disorders such as sleep apnea, insomnia, etc. - Physiological Signal Analysis: Studying the physiological changes during sleep stages.

Usage Notes

• File Format: All files are in EDF format, a standard format for exchanging and storing medical time-series data.
• Annotations: Hypnogram files provide critical annotations for sleep stages, making them crucial for supervised learning tasks.
• Data Integrity: Ensure proper handling of the EDF format using appropriate libraries (e.g., mne, pyEDFlib).

Acknowledgments

This dataset is part of the PhysioBank Sleep-EDF Database. We acknowledge the creators and contributors of this database for making this valuable resource available to the research community.

Uploaded By

OM M PATEL

Links

• LinkedIn
• GitHub
• Portfolio