Dataset Open Access

IEEEPPG Dataset

Chang Wei Tan; Christoph Bergmeir; Francois Petitjean; Geoffrey I Webb

This dataset is part of the Monash, UEA & UCR time series regression repository. http://timeseriesregression.org/

The goal of this dataset is to estimate heart rate using PPG sensors. This dataset contains 3096, 5 dimensional time series obtained from the IEEE Signal Processing Cup 2015: Heart Rate Monitoring During Physical Exercise Using Wrist-Type Photoplethysmographic (PPG) Signals. Two-channel PPG signals, three-axis acceleration signals, and one-channel ECG signals were simultaneously recorded from subjects with age from 18 to 35. For each subject, the PPG signals were recorded from wrist by two pulse oximeters with green LEDs (wavelength: 515nm). Their distance (from center to center) was 2 cm. The acceleration signal was also recorded from wrist by a three-axis accelerometer. Both the pulse oximeter and the accelerometer were embedded in a wristband, which was comfortably worn. The ECG signal was recorded simultaneously from the chest using wet ECG sensors. All signals were sampled at 125 Hz and sent to a nearby computer via Bluetooth.

Please refer to https://sites.google.com/site/researchbyzhang/ieeespcup2015 for more details.

Copyright
All datasets have copyrights. But you can freely use them for the Signal Processing Cup or your own academic research, as long as you suitably cite the data in your works.

Citation request
Z. Zhang, Z. Pi, B. Liu, TROIKA: A general framework for heart rate monitoring using wrist-type photoplethysmographic signals during intensive physical exercise, IEEE Transactions on Biomedical Engineering, vol. 62, no. 2, pp. 522-531, February 2015, DOI: 10.1109/TBME.2014.2359372

Files (141.7 MB)
Name Size
IEEEPPG_TEST.ts
md5:723ba838cf50f0f07085fdc05130f094
60.2 MB Download
IEEEPPG_TRAIN.ts
md5:9e6a90b3ee7d58278ba4d99e542b755a
81.4 MB Download
169
67
views
downloads
All versions This version
Views 169169
Downloads 6767
Data volume 4.8 GB4.8 GB
Unique views 145145
Unique downloads 3737

Share

Cite as