This dataset is associated with an IEEE journal submission titled: "Prediction of larynx function using multichannel surface EMG classification" by the associated authors. The dataset consists of surface electromyography (sEMG) signals recorded from 10 study participants (5 control, 5 laryngectomees), each undertaking 3 recording sessions.
During each session the following were recorded:
1 folder for each session: "P1_S1" = Participant 1 Session 1
1 .csv file exists for each recording. Each .csv file is structured as follows:
If there are 6 columns:
If there are 7 columns:
Hardware setup: Two submental electrodes (EL513, 10 mm diameter, BIOPAC Systems UK) were placed on the midline, posterior to the mental protuberance, with 20 mm interelectrode distance. Three electrodes (EL503, 11 mm diameter, BIOPAC) were placed on the right 9th/10th intercostal space close to the anterior axillary line, with 35 mm interelectrode distance. The posterior two electrodes formed the intercostal recording dipole. The anterior electrode and a single electrode placed on the left 9th/10th intercostal space formed the diaphragm recording dipole. Two reference electrodes (EL503) were placed on the midline over the sternum. Two wireless EMG recorders (BIOPAC BN-EMG2 BioNomadix, 2,000 Hz sampling rate, 2,000× gain, 5 to 500 Hz bandpass filter) were placed at the waist and on the head to minimise relative cable length and motion artefacts
See README.txt for additional information
Data consists of an EMG registry obtained with a hybrid electrostimulation and electromyography device. Electrodes were placed to record activity from the extensor muscle of the fingers while the subject was squeezing a hand gripper for 10 seconds and resting for another 10.
The dataset contains the signal recording acquired on vehicle (car) drivers (ten experienced drivers and ten learner drivers) on the same 28.7 km route in the Silesian Voivodeship (in Polish województwo śląskie) in southern Poland. Experienced drivers performed the tasks in their own cars whereas the learner drivers performed the tasks under a supervison of a driving instructor in a specially marked cars (with L sign).
This is the dataset associated with the IEEE-JBHI submission "Synthesizing Electrocardiograms With Atrial Fibrillation Characteristics Using Generative Adversarial Networks". This dataset contains 4,768 synthesized atrial fibrillation (AF)-like ECG signals stored in PhysioNet MAT/HEA format.
Music and animal's basic emotions associated with acoustic signals.
Files associated with animals’ sounds mainly were based on the records from Volodins Bioacoustic Group Homepage
Please contact the authors for all inquiries.
Ten volunteers were trained through a series of twelve daily lessons to type in a computer using the Colemak keyboard layout. During the fourth-, eight-, and eleventh-session, electroencephalography (EEG) measurements were acquired for the five trials each subject performed in the corresponding lesson. Electrocardiography (ECG) data at each of those trials were acquired as well. The purpose of this experiment is to aim in the development of different methods to assess the process of learning a new task.
Ten volunteers were trained through a series of twelve daily lessons to type in a computer using the Colemak keyboard layout, which is an alternative to the QWERTY and Dvorak layouts, and it is designed for efficient and ergonomic touch typing in English. Six of our volunteers were female, four male, all of them were right-handed, and their mean age was 29.3 years old with an standard deviation of 5.7 years. The lessons used during our experiment are available on-line at colemak.com/Typing_lessons. In our case, we asked the volunteers to repeat each of them five times (with resting intervals of 2 min in between). We
chose Colemak touch typing as the ability to learn because most people are unaware of its existence, then it is a good candidate for a truly new ability to learn. The training process always took place in a sound-proof cubicle in which the volunteers were isolated from distractions. Hence, the volunteers were sitting in front of the computer and were engaged entirely in the typing lesson. All the experiments were carried at the same hour of the day, and all volunteers were asked to refrain of doing any additional training anywhere else. For more details, see .
A Matlab-compatible file is provided for each subject. Each .mat file contains a cell array (named Cn) of size 15x10, which corresponds to the 15 trials and 10 channels, respectively. Trials are organized as follows: rows 1-5 correspond to the measurements during the fourth Colemak lesson, rows 6-10 during the eighth, and rows 11-15 during the eleventh. Channels are organized by columns in the following order: (1) ECG, (2) F3, (3) Fz, (4) F4, (5) C3, (6) Cz, (7) C4, (8) P3, (9) POz, and (10) P4. Each of the elements of Cn correspond to a vector containing the output (time samples acquired at 256 Hz sampling frequency) of each of those channels. The lenght of each of those vectors differ between subjects, as well as for each trial depending on the time it took the corresponging subject to complete the Colemak lesson. The units of all output signals are microVolts.
All data has been preprocessed with the automatic decontamination algorithms provided by the B-Alert Live Software (BLS): raw signals are processed to eliminate known artifacts. Particularly, the following actions are taken for different type of artifacts:
• Excursions and amplifier saturation – contaminated periods are replaced with zero values, starting and ending at zero crossing before and after each event.
• Spikes caused by artifact are identified and signal value is interpolated.
• Eye Blinks (EOG) – wavelet transforms deconstruct the signal and a regression equation is used to identify the EEG regions contaminated with eye blinks. Representative EEG preceding the eye blink is inserted in the contaminated region.
Aditionally, all data were detrended using Matlab's command detrend.
*How to acknowledge
We encourage researchers to use the published dataset freely and we ask that they cite the respective data sources as well as this paper:
 D. Gutiérrez y M. A. Ramírez-Moreno, “Assessing a Learning Process with Functional ANOVA Estimators of EEG Power Spectral Densities,” Cognitive Neurodynamics, vol. 10, no. 2, pp. 175-183, 2016. DOI: 10.1007/s11571-015-9368-7
All data were acquired in the Laboratory of Biomedical Signal Processing, Cinvestav Monterrey, in the context of M. A. Ramírez-Moreno's MSc thesis work under the advice of D. Gutiérrez.
This Dataset contains EEG recordings from epileptic rats. The genetic absence epilepsy rats (GAERS) are one of the best-established rodent models for generalized epilepsy. The rats show seizures with characteristic "spike and wave discharge" EEG patterns. Experiments were performed in accordance with the German law on animal protection and were approved by the Animal Care and Ethics Committee of the University of Kiel.
- Sample Frequency: 1600
- Day1 (18:23:57-16:35:56): Three animals (R1, R2, R3): Array (data points x channels (3))
- Day2 (16:42:53-16:52:06): Three animals (R1, R2, R3): Array (data points x channels (3))
- Day3 (17:32:19-10:25:19): Three animals (R1, R2, R3): Array (data points x channels (3))
- Day4 (10:26:40-14:46:13): Two animals (R1, R3): Array (data points x channels (3))
This data set includes continuous signals and isolated saccades recorded in an EOG experimentation. The horizontal saccades are recorded using an EOG signal acquisition setup implemented using an OpenBCI Cyton board.
The signals are processed using finite impulse response filters and Kalman filters. The results are provided in the excel file attached to the data set.
EEG signals of various subjects in text files are uploaded. It can be useful for various EEG signal processing algorithms- filtering, linear prediction, abnormality detection, PCA, ICA etc.
This dataset contains EEG signals from 73 subjects (42 healthy; 31 disabled) using an ERP-based speller to control different brain-computer interface (BCI) applications. The demographics of the dataset can be found in info.txt. Additionally, you will find the results of the original study broken down by subject, the code to build the deep-learning models used in  (i.e., EEG-Inception, EEGNet, DeepConvNet, CNN-BLSTM) and a script to load the dataset.