This dataset is in support of my research paper 'ElectroMagnetic Fields in Wireless Charging of Electric Vehicles '.

Preprint :

This is useful for industries, manufacturers,doctors,environmentalists, who are curious to see and know.


In this dataset, we performed a seven-day motor imagery (MI) based BCI experiment without feedback training on 20 healthy subjects. The MI tasks include left hand, right hand, feet and idle task.


20 healthy subjects (11 males, mean age: 23.2±1.47 years, all right-handed) participated in this study. The recruited subjects were asked to participate seven sessions within two weeks. Each session lasted around 40 minutes and was organized into 6 runs. Subjects could have a short break between runs. During each run, subjects had to perform 40 trials (4 different MI-tasks, 10 trials per task, presented in random order), each trial lasting 9s. The direction of the arrow informed the subjects which task to perform, i.e., the left arrow corresponding to MI of the left hand, the right arrow corresponding to MI of the right hand, down corresponding to MI of both feet, up corresponding to the idle task.


Electroretinography (ERG) has great potential in visual health detection in early diagnosis and intervention. To date, optical coherence tomography and other diagnostic tests are mainly used. Clinically used ERG is an important diagnostic assessment for various retinal diseases, such as hereditary diseases (retinitis pigmentosa, choroideremia, cone dystrophy, etc), diabetic retinopathies, glaucoma, macular degeneration, toxic retinopathies etc. A database of five types of adult and pediatric biomedical electroretinography signals is presented in this study.



1. A.E. Zhdanov, A.Yu. Dolganov, E. Lucian, X. Bao, V.I. Borisov, V.N. Kazajkin, V.O. Ponomarev, A.V. Lizunov, L.G. Dorosinskiy, "OculusGraphy: Ocular Examination for Toxicity Evaluation Based on Biomedical Signals," 2020 International Conference on e-Health and Bioengineering (EHB), IASI, 2020, pp. 1-6, doi: 10.1109/EHB50910.2020.9280291.
2. A.E. Zhdanov, A.Yu. Dolganov, V.N. Kazajkin, V.O. Ponomarev, A.V. Lizunov, V.I. Borisov, E. Lucian, X. Bao, L.G. Dorosinskiy, , "OculusGraphy: Literature Review on Electrophysiological Research Methods in Ophthalmology and Electroretinograms Processing Using Wavelet Transform," 2020 International Conference on e-Health and Bioengineering (EHB), IASI, 2020, pp. 1-6, doi: 10.1109/EHB50910.2020.9280221.


The file "00 Description of Research Protocols.pdf" contains a description of the protocols used in this study. The file "01 Appendix 1.xlsx" contains the resulting analysis data of 5 signal types. The file contains filtered signals and the following information: diagnosis, age, wave amplitude, wave latency. The file "02 Appendix 2.xlsx" contains a series of signals. The file contains the following information: patient number, signal.
For further questions please contact Mr. Aleksei E. Zhdanov (correspondence e-mail:


We express our most profound appreciation for cand. med. Oleg V. Shilovskikh CEO of IRTC Eye Microsurgery Ekaterinburg Center for the opportunity to publish the database and disseminate scientific knowledge. The ERG signals data decryption within the study was supported by RFBR, project number 20-07-00498, and 18-29-03088. The ERG signals data processing was supported by Act 211 Government of the Russian Federation, contract 02.A03.21.0006.


The world faces difficulties in terms of eye care, including treatment, quality of prevention, vision rehabilitation services, and scarcity of trained eye care experts. Early detection and diagnosis of ocular pathologies would enable forestall of visual impairment. One challenge that limits the adoption of computer-aided diagnosis tool by ophthalmologists is the number of sight-threatening rare pathologies, such as central retinal artery occlusion or anterior ischemic optic neuropathy, and others are usually ignored.


The dataset is divided into two parts:

A. RFMiD_All_Classes_Dataset: It consists of

1. Original color fundus images (3200 images divided into a training set (1920 images), validation (640 images), and testing set (640 images) - PNG Files)

2.  Groundtruth Labels for normal and abnormal (comprising of 45 different types of diseases/pathologies) categories (Divided into training, validation, and testing set - CSV Files)


B. RFMiD_Challenge_Dataset: It consists of

1. Original color fundus images (3200 images divided into a training set (1920 images), validation (640 images), and testing set (640 images) - PNG Files)

2. Groundtruth Labels for 28* different categories (Divided into training, validation, and testing set - CSV Files)


* The diseases having more than 10 images belong to an independent class and all other disease categories are merged and labeled as “OTHER”. This finally constitutes 28 classes for disease classification.


Detailed instructions about this dataset are available on the challenge website:


This dataset contains segmented data of nine human knees. For each of the knees, the surfaces (vertices and faces) of the following structures are provided: femur, tibia, fibula, patella, and the contrast solution that was injected into the knee joint representing the volume that is available for the manipulation of surgical instruments.


Instructions can be found in the README file.

  • See our next journal papers*.
  • *Suppl. to: Proc.
  •  XVI International Conference on Thermal Analysis and Calorimetry in Russia (RTAC-2020). July 6th , 2020, Moscow, Russia. Book of Abstracts. — Moscow. “Pero” Publisher, 2020. — 9 MB. [Electronic edition]. ISBN 978-5-00171-240-4

This heart disease dataset is curated by combining 5 popular heart disease datasets already available independently but not combined before. In this dataset, 5 heart datasets are combined over 11 common features which makes it the largest heart disease dataset available so far for research purposes. The five datasets used for its curation are:


This dataset can be used for building a predictive machine learning model for early-stage heart disease detection


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:

  • EMG-intercostal,EMG-submental,pneumotachometry,EMG-diaphragm,trigger,microphone
  • mV,mV,cmH20,mV,N/A,V

If there are 7 columns:

  • EMG-intercostal,EMG-submental,pneumotachometry,EMG-diaphragm,pressure,trigger,microphone
  • mV,mV,cmH20,mV,V,N/A,V


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


Dataset of fluorescent mice brain vessels Confocal 3D volumes aligned to Light-Field images.


  • Single volume dimension: 1287x1287x64.
  • Number of samples: 362
  • Voxel size: 0.086x0.086x0.9 um.
  • Objective: 40x/1.3 Oil.
  • Stain: tomato lectin (DyLight594 conjugated, DL-1177, Vector Laboratories).




This dataset contains the output from 3D gait analysis. Over a period of 3 months, between January 1st and March 31st in 2019, 5 children were familiarized with the Hibbot by using the walking aid for 30 minutes, twice a week, under the supervision of a physiotherapist.