Publication Type
PhD Dissertation
Version
publishedVersion
Publication Date
11-2024
Abstract
Human health and performance sensing has been extensively studied, from physiology to mental health and movement analytics. However, typical approaches rely on invasive and contact sensors or require professional practitioners, limiting their scalability. For example, the gold standard for measuring heart rate is through an electrocardiogram (ECG), which requires multiple probes attached to the skin and is impractical for individuals with skin issues. Additionally, it typically needs to be performed in a hospital setting under the supervision of a trained cardiac physiologist. Depression detection often relies on the expertise of psychologists or psychiatrists. However, there is a shortage of these professionals in many countries and areas. This scarcity poses a significant challenge in identifying and addressing depression. In the context of swimming, obtaining kinematic feedback from athletes often involves wearing inertial measurement units (IMUs), which is uncomfortable for the wearers and not legal to use during a competition. Recent studies have introduced innovative approaches that can sense and analyze human performance on a large scale and in a contactless manner. Nevertheless, each individual approach still faces challenges and trade-offs that need to be addressed. This thesis addresses these challenges through three integrative studies.
First, although acoustic waves are a recently developed method for contactless heart rate monitoring, they traditionally face limitations when users are close together. In this thesis, I develop an approach that can demonstrate high accuracy in various real-life scenarios, enabling simultaneous monitoring of multiple individuals in close proximity.
Second, I analyzed an app-based system that is employed to detect depression among middle-aged and elderly populations. Based on the collection of the demographics, health factors, levels of loneliness and daily activity duration, I identified key factors associated with geriatric depressive symptoms.
Third, to avoid the need for contact sensors in swimming, based on a drone-based system deployed by our collaborators that can capture swimmers’ strokes from an aerial view, I propose an approach to analyse the swimming parameters. Using video analysis, my approach can provide real-time feedback on stroke rate and swimming speed, potentially enhancing training and performance assessment.
Degree Awarded
PhD in Computer Science
Discipline
Health Information Technology | Software Engineering
Supervisor(s)
BALAN, Rajesh Krishna
First Page
1
Last Page
124
Publisher
Singapore Management University
City or Country
Singapore
Citation
TRAN, Ngoc Doan Thu.
Contactless and scalable approaches for human health and performance sensing. (2024). 1-124.
Available at: https://ink.library.smu.edu.sg/etd_coll/661
Copyright Owner and License
Author
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 4.0 International License.
