Improving Heart Rate Estimation on Consumer Grade Wrist-Worn Device Using Post-Calibration Approach

Abstract

The technological advancement in wireless health monitoring allows the development of light-weight wrist-worn wearable devices to be equipped with different sensors. Although the equipped photoplethysmography (PPG) sensors can measure the changes in the blood volume directly through the contact with skin, the motion artifact (MA) is possible to occur during an intense exercise. In this study, we attempted to perform heart rate (HR) estimation by proposing a post-calibration approach during the three possible states of average daily activity (resting, sleeping, and intense treadmill activity states) in 29 participants (130 minutes/person) on four popular wearable devices: Fitbit Charge HR, Apple Watch Series 4, TicWatch Pro, and Empatica E4. In comparison to the HR provided by Fitbit Charge HR (HR Fitbit ) with the highest error of 3.26 ± 0.34 bpm in resting, 2.33 ± 0.23 bpm in sleeping, 9.53 ± 1.47 bpm in intense treadmill activity states, and 5.02 ± 0.64 bpm in all states combined, our improving HR estimation model with rolling windows as feature reduced the mean absolute error (MAE) for 33.44% in resting, 15.88% in sleeping, 9.55% in intense treadmill activity states, and 18.73% in all states combined. Four machine learning (ML) algorithms (support vector regression (SVR), random forest (RF), Gaussian process (GP), and artificial neural network (ANN)) were formulated and trained with the tuned hyperparameters. This demonstrates the feasibility of our proposed methods in order to correct and provide HR monitoring post-calibrated with high accuracy, raising further awareness of individual fitness in the daily application.

Fatigue Monitoring Through Wearables: A State-of-the-Art Review

“…Signal quality assessment was found to be the most neglected of the methodological aspects contemplated in the risk of bias assessment. Noise and artifacts arising from several sources have an influence on data quality and wearable systems are particularly susceptible to motion artifacts (Mihajlovic et al, 2015 ; Boudreaux et al, 2018 ; Choksatchawathi et al, 2020 ). While these facts are well known, only few studies ( n = 8) identified low-quality signal segments with the purpose of excluding those segments from further analysis or reconstructing them.…”

Potential Applications of Mobile and Wearable Devices for Psychological Support During the COVID-19 Pandemic: A Review

“…We have reviewed the accuracy of the previous generation smartwatches of these vendors; the accuracy of Apple Watch is the best compared to the other smartwatches, and, surprisingly, better than Empatica E4 [20], [150]. Additionally, Fitbit's and Samsung's smartwatch are comparable to Empatica E4 during the resting state [20], [150], [151]. Considering that all vendors upgrade their PPG technology in the new model smartwatches, higher PPG accuracy can be anticipated, although it has yet to be clarified.…”

“…Digital devices, especially mobile or wearable devices, are increasingly capable of capturing various sources of real-time behavioral, physiological, and psychosocial data in a precise and confidential manner [13]- [15]. Examples of these technologies include smartphones [16]- [18] and smartwatches [19], [20]. Interestingly, how we use these technologies to improve mental well-being or mitigate mental illness in terms of emerging uncertainties is opened to discussion.…”

Sensing Physiological Change and Mental Stress in Older Adults From Hot Weather

“…The continuous sensor measurement of heart rate also offered redundant information that provided a robust dataset to work with. There is a growing body of literature that shows mechanisms for improvement of heart rate datasets based on machine learning [27] and denoising algorithms [28]. We plan to use such algorithms in a larger study to improve the quality of the heart rate data.…”