Recent advances in computational power availibility and cloud computing has prompted extensive research in epileptic seizure detection and prediction. EEG (electroencephalogram) datasets from ‘Dept. of Epileptology, Univ. of Bonn’ and ‘CHB-MIT Scalp EEG Database’ are publically available datasets which are the most sought after amongst researchers. Bonn dataset is very small compared to CHB-MIT. But still researchers prefer Bonn as it is in simple '.txt' format. The dataset being published here is a preprocessed form of CHB-MIT. The dataset is available in '.csv' format.


Procedure :

  1. The tool used for preprocessing is Anaconda-Jupyter Notebook on Intel 8th gen i5 processor with 8GB RAM
  2. The dataset is prepared by extracting datapoints from '.edf' by using mne package in python. Equal amount of preictal and ictal data are extracted.
  3. A period of 4096 seconds (68 minutes) each of preictal and ictal data is extracted from the '.edf' files. All ictal periods for 24 patients annotated have been included in the dataset.
  4. Datapoints are loaded and preprocessed as dataframes by using pandas package in python.
  5. System RAM size should be available to the maximum possible extent as dataframes are large.
  6. The file chbmit_preprocessed_data.csv can be used as is for machine learning and deep learning models.

Data Availability :

The datset contains following files.

  • chbmit_ictal_raw_data.csv : This file contains only ictal data from all 24 patients. The channels vary largely and amount to 96 columns in this file.
  • chbmit_preictal_raw_data.csv : This file contains only preictal data from all 24 patients. The channels vary largely and amount to 96 columns in this file.
  • chbmit_preictal_23channels_data.csv :This file contains only preictal data from all 24 patients. Only 23 channels are retained and amount to 23 columns in this file.
  • chbmit_ictal_23channels_data.csv :This file contains only ictal data from all 24 patients. Only 23 channels are retained and amount to 23 columns in this file.
  • chbmit_preprocessed_data.csv :This file contains balanced preictal and ictal data from all 24 patients. Only 23 channels are retained, outcome column is added and amount to 24 columns in this file. In outcome column '0' indicates preictal and '1' indicates ictal.
  • 24 sheets (Seizures info: patient & file number, start-stop times, datapoints)
  • File 278 files (139 preictal+ 139 ictal) ptno_fileno_seizureORnoseizure.csv(Raw data)

This dataset is prepared with data reduction techniques. Data cleaning and data transformation need to be done as suitable for the application or model under development. 

Last 2 files can be used for accessing all raw data from 24 patients.

Original Data:


The original raw dataset in '.edf' is available at  and to be cited as 

Goldberger, A., Amaral, L., Glass, L., Hausdorff, J., Ivanov, P. C., Mark, R., ... & Stanley, H. E. (2000). PhysioBank, PhysioToolkit, and PhysioNet: Components of a new research resource for complex physiologic signals. Circulation [Online]. 101 (23), pp. e215–e220



This dataset contains video sequences and stereo reconstruction results supporting the IEEE Access contribution "Stereo laryngoscopic impact site prediction for droplet-based stimulation of the laryngeal adductor reflex" (J. F. Fast et al.).

See readme file for further information.


See provided readme file for instructions.


The MAUS dataset focused on collecting easy-acquired physiological signals under different mental demand conditions. We used the N-back task to stimuli different mental workload statuses. This dataset can help in developing a mental workload assessment system based on wearable device, especially for that PPG-based system. MAUS dataset provides ECG, Fingertip-PPG, Wrist-PPG, and GSR signal. User can make their own comparison between Fingertip-PPG and Wrist-PPG. Some study can be carried out in this dataset


The database is organized in 2 folders and documentation:
• Data – raw signal recordings for the individual participants, including extracted Inter-Beat-Interval sequence and participants’ respond in N-back task
• Subjective_rating – subjective rating of sleep quality and NASA-TLX
• MAUS_Documentation.pdf – documentation of dataset description and details.


This dataset has information of 83 patients from India. This dataset contains patients’ clinical history, histopathological features, and mammogram. The distinctive aspect of this dataset lies in its collection of mammograms that have benign tumors and used in subclassification of benign tumors. 


This datasest contains a zip folder of 80 mammograms and an excel file having mammographic features, histopathological features as well as clinical fatures of all the patients. 


The data acquisition process begins with capturing EEG signals from 20 healthy skilled volunteers who gave their written consent before performing the experiments. Each volunteer was asked to repeat an experiment for 10 times at different frequencies; each experiment was trigger by a visual stimulus.


Mother’s Significant Feature (MSF) Dataset has been designed to provide data to researchers working towards woman and child health betterment. MSF dataset records are collected from the Mumbai metropolitan region in Maharashtra, India. Women were interviewed just after childbirth between February 2018 to March 2021. MSF comprise of 450 records with a total of 130 attributes consisting of mother’s features, father’s features and health outcomes. A detailed dataset is created to understand the mother’s features spread across three phases of her reproductive age i.e.


We have provided the copy of forms used to collect data for datset and a read me guide to undertand the features provided in dataset along with the content of all the 6 dataset submitted in excel sheet format.


A wide range of wearable sensors exist on the market for continuous physiological health monitoring. The type and scope of health data that can be gathered is a function of the sensor modality. Blumio presents a dataset of synchronized data from a reference blood pressure device along with several wearable sensor types: PPG, applanation tonometry, and the Blumio millimeter-wave radar. Data collection was conducted under set protocol with subjects seated at rest. 115 study subjects were included (age range 20-67 years), resulting in over 19 hours of data acquired.



Participant Recruitment

Potential participants were informed of the study protocol prior to being enrolled. To be included in the study, subjects had to be over the age of 18 and under the age of 90. Informed consent was obtained from all participants. Personal data such as age, gender, height, and weight were collected prior to data collection and this information, along with collected sensor readings, was deidentified and stored in conformation with HIPAA.

Data Collection System

Blumio has conducted previous studies measuring arterial pulsations at the radial artery with millimeter-wave FMCW radar [1]. For this study, the developmental stage BGT60TR24B FMCW system (Infineon Technologies AG, Munich, Germany) was worn over the left wrist.

The data collection system also included the CNAP Monitor 500 (CNSystems Medizintechnik GmbH, Graz, Austria) worn on the left arm, a SPT-301 applanation tonometer (Millar Inc, Houston, USA) worn on the right wrist, and a SS4LA PPG transducer (BIOPAC Systems Inc, Goleta, USA) worn on the right hand’s middle digit.

Data Collection Procedures

Study protocol was approved by Western IRB prior to participant recruitment (Western IRB #20193057). All measurements were collected at the Blumio Office in San Mateo, CA. Measurements were performed according to a fixed protocol. Participants were seated at an appropriate height with both arms resting comfortably on a table in front of them. They were asked to rest quietly for 5 minutes in that position. Then, signals from the sensors were recorded simultaneously for a period of 10 minutes. During the signal acquisition period, the participant was asked to maintain a normal breathing frequency and to not speak or move.

Signal Processing

Following collection, the signals were first time-synchronized and then processed according to the steps described below.

The raw IF radar data output was processed utilizing two approaches. First, a standard phase transformation was used. This consisted of performing a Fast Fourier Transform (FFT) on the IF signal and extracting the phase from the appropriate range bin as described in our previous work. Secondly, a proprietary transformation created by Blumio was utilized. The algorithms employ a set of pre-processing and noise-reduction procedures, during which the radar signal is transformed into a univariate pulse waveform.

The auxiliary signals and the reference blood pressure data was extracted from the MP36R unit using the companion AcqKnowledge software (BIOPAC Systems Inc, Goleta, USA).

Dataset Description and Usage Notes

The entire dataset and associated participant health information are freely available for download as a ZIP file. All the sensor data is stored in CSV format. Each CSV file is named after the participant’s assigned identifier. The first column of the CSV contains the timestamp in seconds. For the sake of data analysis, all sensor channels have been time aligned in the included files. The second column includes the reference blood pressure in mmHg from the CNIBP monitor. The third column is data from the PPG sensor in mV. The fourth column includes the is the data from the applanation tonometer also in mV. The fifth column is the output from Blumio’s proprietary radar transform algorithm in arbitrary units. The sixth column is the output from the phase radar transformation algorithm in radians. Note that each file varies in length of time. Certain files have a truncated start due to the CNAP Monitor 500’s initialization period.

The included participant health information is available in a XSLX summary sheet. The information in the XSLX sheet is tabulated by participant study identifier.


The authors would like to thank the Silicon Valley Innovation Center (SVIC) and the Power & Sensor Systems (PSS) teams at Infineon Technologies AG for providing engineering support during our R&D process.


This work was supported by the Center for Disease Control under grant number 9679554 and Infineon Technologies AG.


[1] J. Johnson, C. Kim, and O. Shay, "Arterial Pulse Measurement with Wearable Millimeter Wave Device," in IEEE 16th International Conference on Wearable and Implantable Body Sensor Networks (BSN), 2019, pp. 1-4.


Real-time gesture recognition with bio-impedance measurement. Two videos , one for hand gesture, another for pinch gesture


It has been suggested that the wireless network evolution to smaller carrier wavelengths (from 2G to 5G) increases radio-frequency electromagnetic field (RF-EMF) absorption in Western Honey Bees (Apis mellifera). It is unknown whether the radiation performance of antennas is stable when an insect appears in their vicinity. In this research, the absorbed power in a worker honey bee and the influence of the bee's presence on antennas' radiation performance is investigated for the newly used frequencies in 5G networks, from 6-240 GHz.


The mean shift (MS) algorithm is a nonparametric method used to cluster sample points and find the local modes of kernel density estimates, using an idea based on iterative gradient ascent. In this paper we develop a mean-shift-inspired algorithm to estimate the modes of regression functions and partition the sample points in the input space. We prove convergence of the sequences generated by the algorithm and derive the non-asymptotic rates of convergence of the estimated local modes for the underlying regression model.


Biomolecular structure data analyzed in "Space Partitioning and Regression Mode Seeking via a Mean-Shift-Inspired Algorithm" by Wanli Qiao and Amarda Shehu.