PPGraw

PPGraw

The Quest for Raw Signals:
A Quality Review of Publicly Available Photoplethysmography Datasets

In this GitHub repository, we present an analytical tool for the quality review of raw photoplethysmography (PPG) signals, based on 7 multi-varied decision metrics. It has been applied in the review of 10 publicly available photoplethysmography datasets, referred below in Citation. Although all evaluated datasets were advertised to contain raw signals, the characteristics of the PPG data look quite diverse. Our developed tool enables to automatically analyze the suitability and applicability of datasets and helps to identify preprocessed and filtered signals with a limited evidence. The raw reference data, recorded with the MAX86140EVSYS# evaluation system, as well as the implemented Python tool, based on the presented 7 decision metrics, are available for download, to support the reproducibility and the review of new datasets.

Download

This GitHub repository provides the developed analytical tool PPGraw. The raw photoplethysmography reference signals can be downloaded via the following link: https://ubicomp.eti.uni-siegen.de/home/datasets/data20/index.html.en

Citation

“The Quest for Raw Signals: A Quality Review of Publicly Available Photoplethysmography Datasets”, Florian Wolling and Kristof Van Laerhoven. In DATA’20: Proceedings of the 3rd Workshop on Data Acquisition To Analysis, DATA 2020, Virtual Event, Japan, November 2020, ACM, 2020. https://doi.org/10.1145/3419016.3431485

Disclaimer

You may use the source code of the developed analytical tool PPGraw for scientific, non-commercial purposes, provided that you give credit to the owners when publishing any work based on it. We would also be very interested to hear back from you if you use our tool or metrics in any way and are happy to answer any questions or address any remarks related to it.

Presentation Video

Reference Data

REF: MAX86140EVSYS# [data]

Evaluated Datasets

The following figures show excerpts from the reviewed datasets: Short close-up of few pulses on the left, a 30-second window in the middle, and its respective frequency spectrum (FFT) on the right. Note that the PPG-BP dataset (S05) contains only snippets of 2.1 s length. Frequency bands: very low frequency (VLF, < 0.167 Hz, red), low frequency (LF, 0.167 to 0.667 Hz, orange), and intermediate frequency (IF, 0.5 to 3.0 Hz , green) while the high frequency (HF, > 3.0 Hz) noise and harmonics are clipped.

S01: MAXREFDES100# [Biagetti et al., data] S02: PPG-DaLiA [Reiss et al., data] S03: WESAD [Schmidt et al., data] S04: BloodLossSVM [Reljin et al., data] S05: PPG-BP [Liang et al., data] S06: BIDMC [Pimentel et al., data] S07: Wrist PPG During Exercise [Jarchi et al., data] S08: Cuff-Less Blood Pressure Estimation [Kachuee et al., data] S09: IEEE SPC 2015 (TROIKA) [Zhang et al., data] S10: IEEE SPC 2013 [Karlen et al., data]

References

S01: Giorgio Biagetti, Paolo Crippa, Laura Falaschetti, Leonardo Saraceni, AndreaTiranti, and Claudio Turchetti. 2020. “Dataset from PPG wireless sensor for activity monitoring”. Data in brief 29 (2020), 105044. https://doi.org/10.1016/j.dib.2019.105044

S02: Attila Reiss, Ina Indlekofer, Philip Schmidt, and Kristof Van Laerhoven. 2019. “DeepPPG: Large-Scale Heart Rate Estimation with Convolutional Neural Networks”. Sensors (Basel, Switzerland) 19, 14 (2019). https://doi.org/10.3390/s19143079

S03: Philip Schmidt, Attila Reiss, Robert Duerichen, Claus Marberger, and Kristof Van Laerhoven. 2018. “Introducing WESAD, a Multimodal Dataset for Wearable Stressand Affect Detection”. https://doi.org/10.1145/3242969.3242985

S04: Natasa Reljin, Gary Zimmer, Yelena Malyuta, Kirk Shelley, Yitzhak Mendel-son, David J. Blehar, Chad E. Darling, and Ki H. Chon. 2018. “Using support vector machines on photoplethysmographic signals to discriminate between hypovolemia and euvolemia”. PloS one 13, 3 (2018), e0195087. https://doi.org/10.1371/journal.pone.0195087

S05: Yongbo Liang, Zhencheng Chen, Guiyong Liu, and Mohamed Elgendi. 2018. “A new, short-recorded photoplethysmogram dataset for blood pressure monitoring in China”. Scientific Data 5, 1 (2018), 180020. https://doi.org/10.1038/sdata.2018.20

S06: Marco A. F. Pimentel, Alistair E. W. Johnson, Peter H. Charlton, Drew Birrenkott, Peter J. Watkinson, Lionel Tarassenko, and David A. Clifton. 2017. “Toward a Robust Estimation of Respiratory Rate From Pulse Oximeters”. IEEE transactions on bio-medical engineering 64, 8 (2017), 1914–1923. https://doi.org/10.1109/TBME.2016.2613124

S07: Delaram Jarchi and Alexander Casson. 2017. “Description of a Database Containing Wrist PPG Signals Recorded during Physical Exercise with Both Accelerometer and Gyroscope Measures of Motion”. Data 2, 1 (2017), 1. https://doi.org/10.3390/data2010001

S08: Mohamad Kachuee, Mohammad Mahdi Kiani, Hoda Mohammadzade, and Mahdi Shabany. 2015. “Cuff-less high-accuracy calibration-free blood pressure estimation using pulse transit time”. (2015), 1006–1009. https://doi.org/10.1109/ISCAS.2015.7168806

S09: Zhilin Zhang, Zhouyue Pi, and Benyuan Liu. 2015. “TROIKA: A General Framework for Heart Rate Monitoring Using Wrist-Type Photoplethysmographic Signals During Intensive Physical Exercise”. IEEE transactions on bio-medical engineering 62, 2 (2015), 522–531. https://doi.org/10.1109/TBME.2014.2359372

S10: Walter Karlen, Srinivas Raman, J. Mark Ansermino, and Guy A. Dumont. 2013. “Multiparameter Respiratory Rate Estimation from the Photoplethysmogram”. IEEE transactions on bio-medical engineering 60, 7 (2013), 1946–1953. https://doi.org/10.1109/TBME.2013.2246160