Terms of use

The database is completely free and can be used for any purpose. However, we kindly ask to cite this publication if the database and / or its supplementary functions are used:

Structure

The database consists of records which represent one measurement each. That means, a record contains, for example, one measurement of one patient in case of the clinical study, or one driver driving in a specified scenario in case of the driving tests and so on. It should be pointed out that several records may exist for the same subject in the driving or lying in a bed scenario. However, these records are of course labeled with the same unique subject ID but different record IDs. The structure of each record in case of the MATLAB file is given in Table I.

The presented structure of one record is saved as a struct. Each record consists of several fields such as a unique id, the duration of the measurement, the measurement scenario measScenario, information about the subject and several channels containing the actual measurement data and annotations ann.

The field ann is an array of structs within each channel. It contains the class (e.g. peaks or rhythm), the subclass which may be event based (e.g. in case of the class peaks) or interval based (e.g. in case of the clinical study the clinicians analyzed an interval of 5 s), the source (e.g. manual by medical experts or automatic by the open source ECG detector OSEA [6]) and the location loc of the annotation in samples. The type of the annotation(s) depends on the annotation class and subclass and is further elucidated in Table II. This table also shows all currently available annotations. All datasets contain detected peaks from OSEA or by a medical expert. In case of the measurements from the clinical study, this dataset contains the following annotations for the cECG as well as for the reference ECG. The diagnosed rhythm and if extrasystoles extrasys or a bundle branch block bbb are present. If the two clinicians could not clearly identify a parameter or if their results differed, it is denoted with NaN or ’-2’. Furthermore, the heart rate and different time durations such as PQ, QRS and QT time are given. Here, the mean value of the two clinicians’ results and the relative difference are given. Again, if one parameter, e.g. the PQ time, could not be clearly estimated, it is denoted with NaN.

Download

The data can be downloaded here:

The supplementary MATLAB functions can be found here:

1.) A Synthesizer Framework for multimodal cardiorespiratory signals

In [7], our group has published a synthesizer for the generation of multimodal cardiorespiratory signals. Below, a MATLAB demonstration can be downloaded for free. This code was used to generate Figure 14 of the original publication. As the UnoViS database, this code is completely free but we kindly ask you to cite the original publication:

2.) Motion Artifact Quantification and Sensor Fusion for Unobtrusive Health Monitoring

A multisensor setup for unobtrusive vital sign estimation was published by our group in [8]. Here you can download the data of the “Motion Sequence” (UnoViS_motion2017) and the video sequence “Video Sequence” (UnoViS_video2017). The data format is the same as the UnoViS-database. We currently do not provide the data in WFDB format but we can convert it for you if necessary. As with the original database, the data is completely free but we kindly ask you to cite the original publication:

3.) Signal-Level Fusion with Convolutional Neural Networks for Capacitively Coupled ECG in the Car

In [9], we presented an algorithm for beat-detection in multi-channel capacitively coupled ECG. This algorithm is written in Python and makes use of the “Keras” as well as the “TensorFlow” package (among others). To use this demo, you also need to download the “UnoViS_auto2012” MAT-file you find above. As the UnoViS database, this code is completely free but we kindly ask you to cite the original publication:

4.) Heart Pacemaker spike can be detected in the capacitive ECG signal

In a clinical study [10], we tested our capacitive ECG car seat on patients with cardiac pacemakers. The multichannel cECG and accompanying reference ECG measurements are provided here in anonymous format for further research purposes. As the UnoViS database, the data and accompanying code is completely free but we kindly ask you to cite the original publication:

5.) A Portable Multi-Modal Cushion for Continuous Monitoring of a Driver’s Vital Signs

A multi-sensor setup for unobtrusive vital sign estimation was published by our group in [11]. The 4xU sensor data including capacitive ECG, magnetic inductance measurement, PPG and Seismocardiography accompanying the paper can be assessed here. As with the original database, the data is completely free but we kindly ask you to cite the original publication:

If you have any questions, please contact us at: unovis-support@hia.rwth-aachen.de

1. A. L. Goldberger, Amaral, L. A. N., L. Glass, J. M. Hausdorff, P. C. Ivanov, R. G. Mark, J. E. Mietus, G. B. Moody, C.-K. Peng, and H. E. Stanley, “PhysioBank, PhysioToolkit, and PhysioNet: Components of a New Research Resource for Complex Physiologic Signals,” Circulation 101(23):e215–e220, 2000, doi:https://doi.org/10.1161/01.CIR.101.23.e215
2. M. Czaplik, B. Eilebrecht, R. Walocha, M. Walter, P. Schauerte, S. Leonhardt, and R. Rossaint, “The reliability and accuracy of a noncontact electrocardiograph system for screening purposes,” Anesthesia and Analgesia, 114(2):322–327, 2012, doi: https://doi.org/10.1213/ane.0b013e31823f4182
3. B. Eilebrecht, T.Wartzek, J. Lem, R. Vogt, and S. Leonhardt, “Capacitive electrocardiogram mea­surement system in the driver seat,” Automobiltechnische Zeitschrift (ATZ), 113(3):232–237, 2011, doi: https://doi.org/10.1365/s38311-011-0034-3
4. T. Wartzek, B. Eilebrecht, J. Lem, H.-J. Lindner, S. Leonhardt, and M. Walter, “ECG on the Road: Robust and Unobtrusive Estimation of Heart Rate,” IEEE Transactions on Biomedical Engineering, 58(11):3112–3120, 2011, doi: https://doi.org/10.1109/TBME.2011.2163715
5. T. Wartzek, C. Brüser, T. Schlebusch, C. Brendle, S. Santos, A. Kerekes, K. Gerlach-Hahn, S. Weyer, K. Lunze, C. Hoog-Antink, and S. Leonhardt, “Modeling of Motion Artifacts in Contactless Heart Rate Measurements,” in 2013 Computing in Cardiology (CinC 2013), 22 - 25 Sep 2013.
6. P. S. Hamilton, "Open Source ECG Analysis Software Documentation," Computers in Cardiology, Memphis, TN, USA, 2002, pp. 101-104, 2002, doi: https://doi.org/10.1109/CIC.2002.1166717
7. C. Hoog Antink, S. Leonhardt, and M. Walter, “A Synthesizer Framework for Multimodal Car­dio­respiratory Signals”, Biomed. Phys. Eng. Express 3 (2017) 035028, doi: https://doi.org/10.1088/2057-1976/aa76ee.
8. C. Hoog Antink, F. Schulz, S. Leonhardt, and M. Walter, “Motion Artifact Quantification and Sensor Fusion for Unobtrusive Health Monitoring”, Sensors 2018, 18(1), 38, doi: https://doi.org/10.3390/s18010038
9. C. Hoog Antink, E. Breuer, D. U. Uguz, and S. Leonhardt, "Signal-Level Fusion with Convolutional Neural Networks for Capacitively Coupled ECG in the Car”, in 2018 Computing in Cardiology (CinC 2018);45, doi: https://doi.org/10.22489/CinC.2018.143
10. D. U. Uguz, R. Dettori, A. Napp, M. Walter, N. Marx, S. Leonhardt, C. Hoog Antink, "Car seats with capacitive ECG electrodes can detect cardiac pacemaker spikes“, Sensors 2020 (20), 6288, doi: https://doi.org/10.3390/s20216288
11. O. Linschmann, D.U. Uguz, B. Romanski, I. Baarlink, P. Gunaratne, S. Leonhardt, M. Walter, M. Lüken, „A Portable Multi-Modal Cushion for Continuous Monitoring of a Driver’s Vital Signs“, Sensors 23 (8), 4002, 2023, doi: https://doi.org/10.3390/s23084002.