← LINI · UAM Iztapalapa Akimpech P300 Database  ·  Open Access

LINI · UAM Iztapalapa · Open-Access EEG Dataset

Akimpech
P300 Speller Database

A large open-access EEG database from first-time users of a P300 Brain-Computer Interface speller, recorded at the Neuroimaging Research Laboratory of UAM Iztapalapa.

⚡ 30 subjects 📁 4 sessions each 🧪 MATLAB format 🆓 Free download 📡 16-ch EEG · 256 Hz
30
Healthy subjects
(18M / 12F)
4
Sessions
per subject
16
EEG channels
g.tec gUSBamp
256
Hz sampling
rate
15
Epochs per
character

What is Akimpech?

The Akimpech dataset was created at the Laboratorio de Investigación en Neuroimagenología (LINI) of the Universidad Autónoma Metropolitana, Unidad Iztapalapa, to support open research in Brain-Computer Interfaces based on the P300 event-related potential.

The P300 Speller, originally proposed by Farwell and Donchin (1988), is one of the most widely studied BCI paradigms. It relies on the P300 component — a positive EEG deflection ~300 ms after a rare, attended stimulus — to allow users to select characters from a matrix by focusing attention on them while rows and columns are intensified in random order.

The database was recorded using the BCI2000 P300 Speller platform and is available in both BCI2000 and MATLAB formats, along with support functions for classifier design and testing.

Amplifier
g.tec gUSBamp
16 channels · 24-bit ADC
Sampling rate
256 Hz
10 channels available in dataset
Reference / Ground
Right ear / Right mastoid
Standard P300 montage
Bandpass filter
0.1 – 60 Hz
8th order + 60 Hz notch at recording
Stimulus duration
125 ms
ISI: 62.5 ms
Speller matrix
6 × 6
Characters: a–z, 1–9
Software
BCI2000
P300 Speller application
File format
MATLAB (.mat)
Also available in BCI2000 format

Recording sessions

Each of the 30 subjects completed 4 recording sessions. All sessions used 15 repetitions per character (except session 4 which could be reduced to 1).

1

Calibration / Copy-spelling

Subjects spelled three fixed Spanish words: calor, cariño and sushi. Used to calibrate the BCI classifier. Training set: 16 characters with 15 epochs each.

2

Copy-spelling · single word

Subjects spelled the word sushi. 15 repetitions per character.

3

Free-spelling

Subjects spelled any word of their choice. 15 repetitions per character. Commonly used as the test set in classifier evaluations.

4

Free-spelling · reduced iterations

Subjects spelled freely, with the number of repetitions reduced to as few as 1 per character, exploring speed vs. accuracy trade-offs.

📋 Typical experimental setup

Most published studies using Akimpech train on Session 1 and test on Session 3. The dataset has been used with LDA, SVM, CNN, capsule networks and unsupervised learning approaches, among others.

Download

The full dataset is freely available through the following mirrors. Choose whichever works best for you.

📦
✓ Available

Dropbox

Primary mirror. Full dataset including MATLAB files and support functions.

Download ↗
🖥️
✓ Available

Akimpech Server

Original LINI server at UAM Iztapalapa with dataset documentation.

Browse dataset ↓ Download ZIP ⬇
📊
⚠ Check availability

Kaggle

Community mirror on Kaggle. May require a free Kaggle account.

View on Kaggle ↗
📩 Access issues?

If you cannot access the data through any of the mirrors above, write directly to oyanez@izt.uam.mx and we will arrange access.

How to cite

If you use the Akimpech dataset in your research, please cite the original conference paper:

BibTeX @inproceedings{ledesma2010akimpech, title = {An Open-Access {P300} Speller Database}, author = {Ledesma-Ramirez, Claudia and Bojorges-Valdez, Erik and Y{\'a}{\~n}ez-Suarez, Oscar and Saavedra, Carolina and Bougrain, Laurent and Gentiletti, Gerardo Gabriel}, booktitle = {Fourth International Brain-Computer Interface Meeting}, address = {Monterey, CA, USA}, year = {2010} }

Plain text: Ledesma-Ramirez C., Bojorges-Valdez E., Yáñez-Suarez O., Saavedra C., Bougrain L., Gentiletti G.G. (2010). "An Open-Access P300 Speller Database." Fourth International Brain-Computer Interface Meeting, Monterey, CA, USA.

Authors

Claudia Ledesma-Ramírez
LINI · UAM Iztapalapa &
Universidad Iberoamericana
Erik Bojorges-Valdez
LINI · UAM Iztapalapa &
Universidad Iberoamericana
Oscar Yáñez Suárez
LINI · Depto. de Ingeniería Eléctrica
UAM Iztapalapa
Carolina Saavedra
CORTEX · INRIA Nancy –
Grand Est, France
Laurent Bougrain
CORTEX · INRIA Nancy –
Grand Est, France
Gerardo G. Gentiletti
LIRINS · Universidad Nacional
de Entre Ríos, Argentina

For enquiries about the dataset contact oyanez@izt.uam.mx or erik.bojorges@ibero.mx.

Subject browser

Browse and download individual files for each subject. Click a subject row to expand its sessions. Each session lists all available files — click any chip to download directly.

DAT BCI2000 raw recording MAT MATLAB format PRM BCI2000 parameters PNG Performance chart TXT Session summary ZIP Subject archive

Publications citing this dataset

The following is a selection of peer-reviewed publications that have used the Akimpech dataset for algorithm development, benchmarking, or analysis. If your work uses this dataset and is not listed, please contact us.

2025

Toward Lightweight, Efficient, and Explainable Deep Learning Models for P300 Detection

Liu M., Ahmad F., Beyette F.R. · In: Deep Learning Approaches for Brain-Computer Interfaces, Springer (2025)

2022

Merging Brain-Computer Interface P300 Speller Datasets: Perspectives and Pitfalls

Sosulski J., Tangermann M. · Frontiers in Neuroergonomics, 3, 1045653 (2022) · DOI ↗

2021

Improving P300 Speller Performance by Means of Optimization and Machine Learning

Cavrini F. et al. · Annals of Operations Research, 311, 775–798 (2021) · DOI ↗

Enhancing P300-Based Character Recognition Performance Using a Combination of Ensemble Classifiers and a Fuzzy Fusion Method

Jin J. et al. · Journal of Neuroscience Methods, 362, 109301 (2021) · DOI ↗

2020

Recurrence Analysis of the P300 Response During a BCI Spelling Task

Ledesma-Ramírez C., Bojorges-Valdez E., Yáñez-Suárez O. · Biomedical Signal Processing and Control, 57, 101747 (2020) · DOI ↗

2019

Wavelet-Based Semblance Methods to Enhance the Single-Trial Detection of Event-Related Potentials for a BCI Spelling System

Saavedra C., Bougrain L. · Computational Intelligence and Neuroscience, 2019, 8432953 (2019) · DOI ↗

A Comparison of Subject-Dependent and Subject-Independent Channel Selection Strategies for Single-Trial P300 Brain-Computer Interfaces

Sannelli C. et al. · Medical & Biological Engineering & Computing, 57 (2019) · DOI ↗

2016

P300 Detection Based on EEG Shape Features

Alvarado-González M. et al. · Computational and Mathematical Methods in Medicine, 2016, 2029791 (2016) · DOI ↗

2012

A Bayesian Model for Exploiting Application Constraints to Enable Unsupervised Training of a P300-based BCI

Kindermans P-J., Verstraeten D., Schrauwen B. · PLOS ONE, 7(4), e33758 (2012) · DOI ↗

Finally, What Is the Best Filter for P300 Detection?

Bougrain L., Saavedra C., Ranta R. · 4th International BCI Meeting, Asilomar, CA (2012)

A P300 BCI for the Masses: Prior Information Enables Automatic Language Model Based Unsupervised Adaptation

Kindermans P-J. et al. · Advances in Neural Information Processing Systems (NeurIPS 2012) · PDF ↗

📧 Add your paper

Used the Akimpech dataset in your research? Write to oyanez@izt.uam.mx or erik.bojorges@ibero.mx to have your publication listed here.