Public PPG Datasets and Benchmarks for Research: A Comprehensive Guide
**Reproducible PPG research depends on standardized datasets and benchmarks, yet the landscape of publicly available PPG data remains fragmented acros...
- PPG & Signal Processing
Reproducible PPG research depends on standardized datasets and benchmarks, yet the landscape of publicly available PPG data remains fragmented across dozens of repositories with inconsistent formats, annotation quality, and documentation. This guide provides a comprehensive catalog of the most important public PPG datasets, organized by application domain, with practical guidance on their strengths, limitations, and appropriate use cases.
Access to high-quality annotated data is the single largest bottleneck in PPG algorithm development. While clinical data repositories like MIMIC contain massive volumes of waveform data, the annotation quality and demographic diversity often limit their utility for training robust models. Understanding which datasets are appropriate for which research questions, and how to properly benchmark against them, is essential for producing work that advances the field. For background on PPG signal characteristics and acquisition, see our introduction to PPG technology.
Heart Rate Estimation Datasets
Heart rate (HR) estimation from wrist-worn PPG during physical activity is the most extensively benchmarked PPG task, driven by commercial demand for accurate fitness tracking and by several organized competitions that produced standardized datasets.
IEEE Signal Processing Cup 2015
The IEEE SP Cup 2015 dataset, introduced with Zhang et al.'s TROIKA framework (2015), is one of the most widely used benchmarks for PPG heart rate estimation during motion (doi:10.1109/TBME.2014.2359372). Its training set contains wrist PPG recorded from 12 subjects during fast running at peak speeds of 15 km/h, together with three-axis accelerometer data and a simultaneous ECG reference.
The dataset's primary strength is its widespread adoption, enabling direct comparison across methods. Zhang's original TROIKA algorithm achieved mean absolute error (MAE) of 2.34 BPM on this dataset. Many later methods report lower errors. However, the dataset's limitations are significant: only 12 subjects, a fixed activity protocol, and recordings from a single device and body location. The small subject count means that leave-one-subject-out (LOSO) results have high variance, and reported average MAE values can be heavily influenced by one or two difficult subjects.
PPG-DaLiA (PPG Dataset for Daily Life Activities)
PPG-DaLiA, published by Reiss et al. (2019) from the German Research Center for Artificial Intelligence (DFKI), addresses many limitations of the IEEE SP Cup dataset (doi:10.3390/s19143079). It covers a wide range of activities performed under close to real-life conditions, such as sitting, climbing stairs, playing table soccer, cycling, driving, a lunch break, walking, and desk work. On this larger dataset, Reiss et al.'s CNN reduced mean absolute error by 31% compared with classical methods.
The sensor setup includes wrist PPG and a 3-axis accelerometer from an Empatica E4 wristband, with ECG from a RespiBAN chest strap providing the reference heart rate.
Errors on PPG-DaLiA are typically higher than on the IEEE SP Cup dataset. The higher error rates compared to the IEEE SP Cup dataset reflect the greater diversity and difficulty of the activities. This dataset is strongly recommended for evaluating motion artifact removal algorithms in realistic conditions.
WESAD (Wearable Stress and Affect Detection)
WESAD, also from DFKI (Schmidt et al., 2018), targets stress detection but is valuable for PPG heart rate research due to its multimodal sensor setup (doi:10.1145/3242969.3242985). It includes data from 15 subjects wearing both a wrist-worn Empatica E4 and a chest-worn RespiBAN Professional during a protocol designed to induce baseline, stress, and amusement states. The protocol uses the Trier Social Stress Test for stress induction and funny video clips for amusement.
Sensor data includes wrist PPG (64 Hz), wrist accelerometer (32 Hz), wrist EDA, wrist skin temperature, chest ECG (700 Hz), chest EMG, chest EDA, chest respiration, and chest temperature. Affect labels (baseline, stress, amusement, meditation) are provided. The dataset is publicly available.
Blood Pressure Estimation Datasets
PPG-based blood pressure estimation is one of the most active and challenging areas of PPG research, and the availability of paired PPG-BP data is critical for developing and validating cuffless blood pressure methods.
MIMIC-III Waveform Database
The MIMIC-III Waveform Database, part of the broader MIMIC-III Clinical Database maintained by the MIT Lab for Computational Physiology (Johnson et al., 2016; doi:10.1038/sdata.2016.35), is the largest publicly available source of continuous PPG waveforms with simultaneous arterial blood pressure (ABP). Its matched waveform records come from ICU patients at Beth Israel Deaconess Medical Center, with synchronized PPG, ABP, ECG, and other physiological signals.
The MIMIC-III database has been the foundation of hundreds of PPG-BP studies, including the influential work by Kachuee et al. (2017), who combined pulse arrival time with other ECG and PPG features and evaluated their regression models on about a thousand subjects; the method met the AAMI standard for diastolic and mean arterial pressure and reached BHS grade A for DBP (doi:10.1109/TBME.2016.2580904).
Critical limitations of MIMIC-III for BP research include: the ICU population is not representative of the general ambulatory population; many patients have arterial line damping artifacts that corrupt the ABP reference; the data is collected during critical illness, introducing pathological hemodynamics; and signal quality varies enormously across records. Researchers must implement careful quality screening (typically removing segments with ABP outside 40-200 mmHg systolic, PPG signal quality index below threshold, and records shorter than minimum duration) before using MIMIC data for model development.
Access requires completion of the CITI training program and a data use agreement through PhysioNet.
VitalDB
VitalDB (Lee et al., 2022; doi:10.1038/s41597-022-01411-5) is a large surgical vital signs database from Seoul National University Hospital containing high-resolution data from 6,388 cases, including 486,451 waveform and numeric tracks of 196 intraoperative monitoring parameters, such as continuous arterial blood pressure, PPG (pulse oximetry waveforms), and ECG.
The database is accessible through a web interface and Python API (vitaldb.net). For PPG-BP research, VitalDB offers several advantages over MIMIC: the data quality is generally higher because anesthesia records are carefully curated, the surgical population has a wider range of hemodynamic states (from induced hypotension to vasopressor-driven hypertension), and the API simplifies data extraction.
University of Queensland Vital Signs Dataset
The University of Queensland (UQ) Vital Signs Dataset (Liu et al., 2012; doi:10.1213/ANE.0b013e318241f7c0) contains high-resolution, multi-parameter monitoring data from 32 anesthesia cases recorded at the Royal Adelaide Hospital, synchronized from patient monitors and anesthesia machines at 10 ms resolution. Unlike ICU databases, it captures the more frequent and marked cardiovascular and respiratory changes seen in operating room patients.
Its manageable size (32 cases) makes it suitable for initial algorithm prototyping before scaling to larger databases.
Sensors PPG-BP Dataset
Liang et al. (2018) published a purpose-built PPG-BP dataset containing 657 short PPG segments from 219 subjects aged 20-89, including people with hypertension and diabetes, with paired cuff blood pressure values (doi:10.1038/sdata.2018.20).
While the dataset's strength is its broad age range and inclusion of hypertensive and diabetic subjects, its limitations are significant: very short recording duration per subject (limiting feature extraction), only cuff BP reference (no beat-to-beat reference), and the custom finger sensor that may not transfer to wrist-worn devices. Nevertheless, it has been widely used for PPG morphology-based BP estimation studies.
Atrial Fibrillation Detection Datasets
PPG-based atrial fibrillation (AF) detection is a rapidly growing research area, driven by the prevalence of wrist-worn devices capable of passive AF screening. For a clinical overview of AF detection capabilities, see our guide on wearable AF detection.
PhysioNet Databases
PhysioNet (Goldberger et al., 2000; doi:10.1161/01.CIR.101.23.e215) hosts several databases relevant to PPG-based AF research. The MIT-BIH Atrial Fibrillation Database contains 25 10-hour ECG recordings with rhythm annotations (AF, atrial flutter, junctional rhythm, other). While this is an ECG database, many PPG AF detection algorithms are initially validated on ECG-derived inter-beat intervals to isolate the rhythm analysis component from the PPG-specific signal quality challenges.
The 2017 PhysioNet/Computing in Cardiology Challenge dataset ("AF Classification from a Short Single Lead ECG Recording") contains 8,528 single-lead ECG recordings of 9-61 seconds duration, classified as normal, AF, other rhythm, or noisy. This dataset established the benchmark for short-duration arrhythmia classification, with the four winning teams achieving an equal F1 score of 0.83 averaged across all classes (Clifford et al., 2017; doi:10.22489/CinC.2017.065-469).
MIMIC-III for AF
By cross-referencing the MIMIC-III Waveform Database with the clinical database's diagnostic codes (ICD-9 code 427.31 for atrial fibrillation), researchers can identify PPG recordings from patients with confirmed AF diagnoses. Deep learning AF detectors from wearable PPG, such as Shashikumar et al. (2017), illustrate the kind of model such labeled data can support (doi:10.1109/BHI.2017.7897225).
The limitation of this approach is that ICD diagnostic codes indicate presence of AF during the hospitalization but do not provide beat-level or segment-level rhythm annotations. The patient may have been in sinus rhythm for much of the recording. Reliable use of MIMIC for AF research requires either manual rhythm annotation of PPG segments or the use of the simultaneous ECG channel to derive rhythm labels.
Signal Quality Assessment Datasets
Signal quality assessment (SQA) is critical for all PPG applications, as downstream algorithms produce unreliable results when applied to corrupted signals. Several datasets specifically target SQA development.
Wrist PPG Quality Assessment Dataset
Expert-annotated PPG quality datasets are small and scarce, and annotations are inherently somewhat subjective. Researchers often use quality annotations from respiratory or clinical datasets, such as those below, for SQA development.
CapnoBase
The CapnoBase IEEE TBME Benchmark Dataset (Karlen et al., 2013; doi:10.1109/TBME.2013.2246160) contains PPG, ECG, and capnography recordings from 42 surgical patients (29 children and 13 adults), with manual annotations of respiratory events and artifacts. While designed for respiratory rate estimation from PPG, its annotations also make it useful for SQA algorithm development.
Multi-Parameter and Specialized Datasets
BIDMC PPG and Respiration Dataset
The BIDMC dataset (Pimentel et al., 2017; doi:10.1109/TBME.2016.2613124) contains eight-minute recordings from critically ill patients, with PPG, ECG, impedance pneumography, and manual breath annotations, and is a common benchmark for PPG-derived respiratory rate estimation. Pimentel et al. tested their multiple-autoregressive-model method on 95 eight-minute recordings from two datasets, reporting median absolute errors of 1.5 and 4.0 breaths per minute (32-second windows) while keeping over 90% of the input data.
TROIKA Benchmark
Beyond the IEEE SP Cup 2015 dataset, the TROIKA algorithm framework (Zhang et al., 2015) established a complete benchmarking methodology for heart rate estimation: decompose the problem into signal decomposition, spectral peak tracking, and verification stages, and report per-recording absolute error against the ECG reference. This methodology is widely followed, and many later papers compare directly against TROIKA's results.
Best Practices for Using PPG Benchmarks
Subject-Level Splitting
The most critical methodological requirement when using PPG datasets is subject-level data splitting. PPG morphology carries strong individual signatures (related to vascular anatomy, skin properties, and sensor coupling), and models trained on random sample-level splits can achieve artificially high accuracy by memorizing subject-specific patterns. Always use LOSO or grouped k-fold cross-validation with subject-level grouping.
Slapnicar et al. (2019) illustrated the scale of the effect: personalized models performed substantially better than a general leave-one-subject-out model, so random splits that place the same subjects in training and test sets can greatly overstate accuracy (doi:10.3390/s19153420).
Reporting Standards
When benchmarking against public datasets, report results that enable direct comparison. At minimum, include: the exact dataset version and any preprocessing or filtering applied; the train/validation/test split strategy with subject IDs; per-subject metrics (not just population averages) to reveal inter-subject variability; the number of excluded segments and the exclusion criteria; and the reference signal processing used to derive ground truth labels.
Cross-Dataset Generalization
The ultimate test of a PPG algorithm is cross-dataset generalization: training on one dataset and evaluating on a completely different dataset collected with different hardware, subjects, and protocols. Most published PPG algorithms show significant performance degradation under cross-dataset evaluation, revealing overfitting to dataset-specific characteristics (sensor hardware, population demographics, activity patterns). Researchers should consider including cross-dataset evaluation as a standard validation step, training on the largest available dataset and evaluating on all others without fine-tuning.
For researchers implementing these datasets in complete analysis pipelines, our guides on PPG feature extraction and machine learning pipelines for PPG provide practical implementation guidance. Additional resources on PPG signal processing algorithms and the fundamentals of PPG technology are available in our learning center.
References
- Zhang, Z., Pi, Z., & Liu, B. (2015). TROIKA: A general framework for heart rate monitoring using wrist-type photoplethysmographic signals during intensive physical exercise. IEEE Transactions on Biomedical Engineering, 62(2), 522-531. https://doi.org/10.1109/TBME.2014.2359372
- Reiss, A., Indlekofer, I., Schmidt, P., & Van Laerhoven, K. (2019). Deep PPG: Large-scale heart rate estimation with convolutional neural networks. Sensors, 19(14), 3079. https://doi.org/10.3390/s19143079
- Schmidt, P., Reiss, A., Duerichen, R., Marberger, C., & Van Laerhoven, K. (2018). Introducing WESAD, a multimodal dataset for wearable stress and affect detection. Proceedings of the 20th ACM International Conference on Multimodal Interaction, 400-408. https://doi.org/10.1145/3242969.3242985
- Johnson, A. E. W., et al. (2016). MIMIC-III, a freely accessible critical care database. Scientific Data, 3, 160035. https://doi.org/10.1038/sdata.2016.35
- Kachuee, M., Kiani, M. M., Mohammadzade, H., & Shabany, M. (2017). Cuffless blood pressure estimation algorithms for continuous health-care monitoring. IEEE Transactions on Biomedical Engineering, 64(4), 859-869. https://doi.org/10.1109/TBME.2016.2580904
- Lee, H.-C., et al. (2022). VitalDB, a high-fidelity multi-parameter vital signs database in surgical patients. Scientific Data, 9, 279. https://doi.org/10.1038/s41597-022-01411-5
- Liu, D., Gorges, M., & Jenkins, S. A. (2012). University of Queensland vital signs dataset: development of an accessible repository of anesthesia patient monitoring data for research. Anesthesia & Analgesia, 114(3), 584-589. https://doi.org/10.1213/ANE.0b013e318241f7c0
- Liang, Y., Chen, Z., Liu, G., & Elgendi, M. (2018). A new, short-recorded photoplethysmogram dataset for blood pressure monitoring in China. Scientific Data, 5, 180020. https://doi.org/10.1038/sdata.2018.20
- Goldberger, A. L., et al. (2000). PhysioBank, PhysioToolkit, and PhysioNet. Circulation, 101(23), e215-e220. https://doi.org/10.1161/01.CIR.101.23.e215
- Clifford, G. D., et al. (2017). AF classification from a short single lead ECG recording: the PhysioNet/Computing in Cardiology Challenge 2017. Computing in Cardiology, 44. https://doi.org/10.22489/CinC.2017.065-469
- Shashikumar, S. P., Shah, A. J., Li, Q., Clifford, G. D., & Nemati, S. (2017). A deep learning approach to monitoring and detecting atrial fibrillation using wearable technology. 2017 IEEE EMBS International Conference on Biomedical & Health Informatics (BHI), 141-144. https://doi.org/10.1109/BHI.2017.7897225
- Karlen, W., Raman, S., Ansermino, J. M., & Dumont, G. A. (2013). Multiparameter respiratory rate estimation from the photoplethysmogram. IEEE Transactions on Biomedical Engineering, 60(7), 1946-1953. https://doi.org/10.1109/TBME.2013.2246160
- Pimentel, M. A. F., et al. (2017). Toward a robust estimation of respiratory rate from pulse oximeters. IEEE Transactions on Biomedical Engineering, 64(8), 1914-1923. https://doi.org/10.1109/TBME.2016.2613124
- Slapnicar, G., Mlakar, N., & Lustrek, M. (2019). Blood pressure estimation from photoplethysmogram using a spectro-temporal deep neural network. Sensors, 19(15), 3420. https://doi.org/10.3390/s19153420
Related articles
Photodetector Types and Technologies for PPG Sensing: A Comprehensive Guide
**The photodetector is the critical signal transduction element in every PPG system, converting optical information about pulsatile blood volume into ...
Driver Stress Detection with PPG: A Practical Guide for Automotive Monitoring
Learn how driver stress detection with PPG works in vehicles, from sensor placement and signal features to filtering noise, motion, and fatigue overlap.
Stress Tracker Accuracy Guide: What Wearables Actually Measure
Independent review of wearable stress tracker accuracy covering HRV methods, sensor limitations, and how to interpret stress scores from Garmin, Fitbit, and Apple Watch.
Neonatal Oxygen Monitoring Guide: SpO2 Targets, Sensors, and Clinical Protocols
Clinical guide to neonatal pulse oximetry covering SpO2 target ranges, sensor placement, alarm thresholds, and evidence-based monitoring protocols for preterm and term newborns.
PPG vs ECG Comprehensive
Photoplethysmography (PPG) and electrocardiography (ECG) are the two most widely deployed cardiac monitoring technologies in existence, yet they measu...
Devices in this article
Research records with the datasets, papers and published validation results for each device.