In this project, we investigate signal processing and machine learning techniques for cardiovascular and pulmonary health monitoring using multimodal sensors integrated into a wearable vest. The project involves prototyping, testing, and optimising the sensor’s performance to ensure its practicality and reliability for the intended application, as well as developing cutting-edge signal processing and machine learning algorithms for heart and lung health monitoring, disease detection and classification.
Throughout the project, the research student will have access to well-equipped laboratory facilities and receive guidance from knowledgeable mentors in both academia and industry. This project provides an enriching experience for a motivated student to contribute to the field of medical technologies and gain valuable skills in research and collaboration.
Aim
This project aims to develop new signal processing and machine learning-based classification algorithms for cardiovascular and pulmonary health monitoring using signals captured by multimodal sensors integrated into a wearable vest. Multimodal signal processing and machine learning algorithms will be designed to jointly process heart and lung signals from multiple sensors. Compared with the state-of-the-art approaches which are based on single-channel signal processing, a multimodal approach has an improved capability in extracting the features of abnormal heart and lung signals from various sensors (ECG, PCG, ultrasonic), leading to an increased pre-screening accuracy. The algorithms developed in this project are expected to greatly improve the accuracy of heart disease diagnosis and classification, not only under controlled clinical setting, but in general primary care and home environment.
Objectives
- Developing new algorithms for heart and lung cycle detection using signals captured from multiple sensors to perform a better segmentation of the heart and lung signals.
- Prototyping, testing, and optimising the performance of the sensors and the wearable vest.
- Designing effective machine learning architectures and optimising hyperparameters to improve the accuracy of heart and lung disease diagnosis and classification,.
- Testing and validating the performance of the algorithms proposed in this project using heart and lung signal data available in open access databases and data collected from the sensors and vest developed in the project.
Significance
Heart disease including coronary artery disease (CAD) and valvular heart disease (VHD) is the leading cause of mortality and morbidity in the world, leading to 31% of all global deaths. Early diagnosis of heart disease is important to prevent further development of the disease. Standard methods for diagnosis of CAD such as coronary angiography and myocardial perfusion imaging require specialised equipment and clinical expertise. Although these methods are effective in diagnosing CAD, they are highly costly and expose patients to radiation.
The wearable vest integrated with ECG, PCG and ultrasonic sensors developed in this project provides affordable diagnosis of heart diseases. The multimodal signal processing and machine learning algorithms developed in this project are expected to greatly improve the accuracy of heart disease diagnosis and classification. This project offers an excellent opportunity to explore the intersection of technology and healthcare.
Ideal Candidate
The HDR applicant should hold a first-class honour degree or above from a reputable institute. Preferably, the first degree of the applicant should be in electronics and signal processing engineering. Solid understanding of digital signal processing is required in this project. Experience with biomedical engineering is preferred, but not necessary. Additionally, the applicants should meet the eligibility criteria for entry into a PhD program at Curtin University.
This project is open to Domestic applicants only.
Internship
Through this project you will also have an internship opportunity. The supervisory team has strong ongoing collaborations with WA biomedical start-up companies, which provide internship opportunity for HDR students. These companies and the supervisory team are jointly supervising PhD students and honours final year projects. The supervisory team also has experience to supervise ICP internship students partnered with the Department of Health, where the students use machine learning for rare disease detection.
Scholarship
If you are identified as the preferred candidate for this project, you may be considered for an RTP scholarship.
Enquires and How to Apply
For enquires about this opportunity contact Professor Yue Rong at Y.Rong@curtin.edu.au
To formally apply submit an Expression of Interest to Professor Yue Rong during the Central Scholarship round (July 1st – July 31st 2026)