Document Type
Dissertation
Date of Award
8-31-2024
Degree Name
Doctor of Philosophy in Electrical Engineering - (Ph.D.)
Department
Electrical and Computer Engineering
First Advisor
Moshe Kam
Second Advisor
Ali Abdi
Third Advisor
Edwin Hou
Fourth Advisor
Seyyedmohsen Azizi
Fifth Advisor
Leonid Hrebien
Abstract
In the rapidly advancing world of health technology, wearable devices are at the forefront, fundamentally changing how individuals monitor their health. The key to this transformation is photoplethysmography (PPG), a non-invasive optical method that measures blood flow variations through the skin by detecting changes in light absorption with each heartbeat. This capability makes PPG essential for monitoring vital signs such as heart rate and blood oxygen saturation(SpO2). Furthermore, the utility of PPG signals has been extended beyond traditional health metrics to include human activity classification, offering a holistic perspective on an individual's physical health and activity levels, in line with current wellness trends.
Despite its broad potential, PPG's effectiveness is curtailed by its vulnerability to motion-induced noise. Such noise can significantly distort the signal when the wearer moves, affecting the accuracy of essential health readings. This issue is particularly problematic in dynamic environments where movement is frequent, reducing the reliability of data critical for health decisions. The challenge posed by motion artifacts necessitates innovative signal processing solutions to achieve accurate and motion-resistant measurements.
This dissertation proposes techniques to address the challenges posed by motion noise in PPG signals. By combining signal processing methods with machine learning algorithms, this research aims to enhance the accuracy and reliability of heart rate and SpO2 measurements. In turn, these would improve human activity classification and the quality of wearable electronics.
Recommended Citation
Wang, Chizhong, "Estimation of SpO2 levels and heart rate from ppg signals in the presence of motion artifacts" (2024). Dissertations. 1781.
https://digitalcommons.njit.edu/dissertations/1781