Research Assistant

Research assistant, Machine Learning for Acoustic-based automated obstructive sleep apnea detection method Obstructive Sleep Apnoea (OSA) is a prevalent sleep-related breathing disorder characterized by the partial or complete collapse of the upper airway during sleep. Although it primarily affects adult men with obesity, OSA can impact individuals of any age, gender, or body weight. A 2019 study, which analysed data from 17 studies across 16 countries, estimated that around 936 million adults aged 30 to 69 worldwide suffer from mild to severe OSA, with 425 million experiencing moderate to severe cases. China has the highest number of affected individuals (745 million), followed by the USA, Brazil, and India. Alarmingly, most cases remain undiagnosed. Given the significant global burden of OSA, particularly in China, there is an urgent need for effective and user‑friendly diagnostic methods to mitigate its health impacts. Polysomnography (PSG) is the gold standard for diagnosing OSA; however, its accessibility is often limited. PSG requires a healthcare professional to attach sensors, which can cause patient discomfort and potentially lead to test failure. Therefore, a more convenient, comfortable, and affordable screening method is essential. The proposed project is aimed to look for optimal acoustic feature set for OSA detection with the following objectives: Construct a dataset of 600 PSG tests paired with high‑fidelity sound recordings. Identify the best feature set using digital signal processing and artificial intelligence for automated OSA detection. Develop user‑friendly mobile applications for acoustics‑based OSA detection. Effective OSA detection systems rely on high‑quality training materials. Our target sample size is 600 from the United Christian Hospital (UCH) and the University of Hong Kong (HKU) along with collected 66 speech and snoring recordings paired with PSG from patients at HKU Dentistry and Queen Mary Hospital (QMH). HKU Dentistry ranked among the world’s top dental schools starting from 2018, ensures high‑quality patient records. United Christian Hospital, established in 1973, serves East Kowloon and sees over 600 OSA patients annually. These ensure the quality of data collection and ground truth development. By advancing these objectives, we aim to provide a more accessible and effective means of diagnosing and managing OSA, ultimately reducing its impact on public health. The Role The Research Assistant will be responsible for designing and implementing efficient and robust systems and applications for algorithms and methodologies based on state‑of‑the‑art research in machine learning, computer vision, acoustics, cloud and edge computing for biomedical engineering research. Responsibilities Design and write robust, readable, reproducible and reusable code components which can apply to implement state‑of‑the‑art research outcomes in machine learning, artificial intelligence, computer vision, acoustics and etc. Perform data collection, cleansing and processing for analysis of real‑world datasets. Develop mobile applications related to the project. Assist with the editing and preparation of manuscripts, reports and presentations. Participate in presentations and demos for exhibiting work at appropriate events. Other activities related to the research project. Requirements Bachelors or Masters in Computer Science or related disciplines with a focus in AI/Machine Learning/Acoustics/Big Data/Computer vision/Point cloud processing. Solid programming and application development skills with experience in Python. Mastery of programming languages such as C/C++/Java, Tensorflow and Android Studio. Ability to read and understand methodologies in research papers (good publication record is a plus). Fluent in English, (Cantonese, Mandarin is a plus) and good team‑player. Interested parties please send full resume with salary expectation and availability by clicking here to apply. Personal data provided by job applicants will be kept strictly confidential and used for employment related purpose. #J-18808-Ljbffr