Abstract

Real-time remote health monitoring is dramatically growing, revolutionizing healthcare delivery and outcome in everyday settings. Such remote services enable monitoring individuals anywhere and anytime, allowing diseases early detection and prevention. Photoplethysmography (PPG) is a non-invasive and convenient technique that enables tracking vital signs such as heart rate, heart rate variability, respiration rate, and blood oxygen saturation. PPG is broadly used in various clinical and commercial wearable devices, as it is easy-to-implement and low-cost. However, the technique is highly susceptible to motion artifacts and environmental noises, which distort the collected signals. Therefore, the signal quality needs to be investigated, and unreliable signals should be discarded. In the literature, rule-based and machine learning-based PPG quality assessment methods have been investigated in several studies. However, the rule-based methods are mostly inaccurate in remote health monitoring, where users engage in different physical activities. The supervised machine learning-based methods –including deep learning–are also infeasible for real-time monitoring applications since they are slow and are dependent on a massive pool of annotated data to train the model. In this paper, we introduce a PPG quality assessment method, enabled by an elliptical envelope, which requires low computational resources. The method clusters the PPG signals into two groups as “reliable” and “unreliable.” We also investigate various features extracted from the PPG signals. Five features with the highest scoring values are selected to be fed to the elliptical envelope model. Moreover, we assess the performance of the proposed method in terms of accuracy and execution time, using data collected in free-living conditions via an Internet-of-Things-based health monitoring system enabled by smart wristbands. The method is evaluated in comparison to a state-of-the-art PPG quality assessment method. We also provide the model implemented in Python for the community to be used in their solutions.

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.