WildPPG: A Real-World PPG Dataset of Long Continuous Recordings

TL;DR

WildPPG provides a real-world, long-duration multimodal PPG dataset with ground-truth Lead-I ECG collected from 16 participants across four body sites and three wavelengths, plus accelerometer, temperature, and altitude data. The dataset captures diverse outdoor activities and environmental conditions, addressing the gap in in-the-wild HR estimation benchmarks. A broad set of baselines (heuristic and supervised) is evaluated, and a temperature-aware model, Temp-ResNet, is proposed to improve robustness in real-world scenarios. This resource enables more generalizable HR estimation and paves the way for multi-modal analyses of cardiovascular signals in wearable devices.

Abstract

Reflective photoplethysmography (PPG) has become the default sensing technique in wearable devices to monitor cardiac activity via a person's heart rate (HR). However, PPG-based HR estimates can be substantially impacted by factors such as the wearer's activities, sensor placement and resulting motion artifacts, as well as environmental characteristics such as temperature and ambient light. These and other factors can significantly impact and decrease HR prediction reliability. In this paper, we show that state-of-the-art HR estimation methods struggle when processing \emph{representative} data from everyday activities in outdoor environments, likely because they rely on existing datasets that captured controlled conditions. We introduce a novel multimodal dataset and benchmark results for continuous PPG recordings during outdoor activities from 16 participants over 13.5 hours, captured from four wearable sensors, each worn at a different location on the body, totaling 216\,hours. Our recordings include accelerometer, temperature, and altitude data, as well as a synchronized Lead I-based electrocardiogram for ground-truth HR references. Participants completed a round trip from Zurich to Jungfraujoch, a tall mountain in Switzerland over the course of one day. The trip included outdoor and indoor activities such as walking, hiking, stair climbing, eating, drinking, and resting at various temperatures and altitudes (up to 3,571\,m above sea level) as well as using cars, trains, cable cars, and lifts for transport -- all of which impacted participants' physiological dynamics. We also present a novel method that estimates HR values more robustly in such real-world scenarios than existing baselines.

Figures (6)

• Figure 1: WildPPG comprises multi-modal signals from wearable devices at four sites on the body. Each device continuously recorded synchronized signals from a 3-channel reflective photoplethysmogram (red, green, infrared PPG), 3-axis inertial sensor (accelerometer), temperature, and barometric altitude sensor. For reference, the sternum device continuously recorded a Lead-I electrocardiogram (ECG) from body-mounted gel electrodes to provide ground-truth heart rate (HR) estimates.
• Figure 2: WildPPG participants engaged in multiple forms of travel as well as indoor and outdoor activities with changing environmental conditions. No strict study protocol was enforced and participants completed the activities at their own preferred speed.
• Figure 3: The wearable devices used for the data recording were custom-built and are centered around a SoC to read and store all synchronized sensor data in on-board flash memory. (a) Devices were powered by a CR2032 coin cell batteries (runtime: 18 hours) inside a 3D-printed case with (b) a flexible and adjustable strap. (c) The sternum unit additionally connected to 3 gel-electrodes to obtain a continuous ECG recording for reference.
• Figure 4: Architecture of Temp-ResNet. The ResNet includes batch normalization and ReLU activations after each convolution.
• Figure 5: The error (blue) of 1D ResNet based on PPG from the wrist, dependent on the device temperature (left), and device motion (right). Inversely related is the computed SNR of the PPG signal (red).