Taiyu Zhu
BEng (Hons), MSc, PhD
NOVO NORDISK POSTDOCTORAL RESEARCH FELLOW
- Research Member of Common Room and College Advisor, Kellogg College, Oxford
Taiyu Zhu has completed his Ph.D. degree in Electrical and Electronic Engineering at Imperial College London in 2022. He received the First-Class B.Eng. degree (Hons) from Australian National University, in 2017, and the Distinction M.Sc. degree from Imperial College London, in 2018. He was a recipient of the President’s Ph.D. Scholarship and was awarded the Outstanding Achievement Award and the Stylianos Kalaitzis PhD Award, the most promising doctoral work, at Imperial College London.
His research interests include biomedical signal processing, data science, and artificial intelligence (AI), especially machine learning and deep learning, in healthcare, aiming to deliver cutting-edge biomedical applications and novel AI-powered technologies to improve the health and well-being for people with chronic cardiometabolic diseases.
He was awarded the Novo Nordisk Postdoctoral Research Fellowship, to work with Associate Prof Alejo Nevado-Holgado, Dr Joanna Howson, Dr Sile Hu, and Dr Robert Kitchen, starting in January 2023. His fellowship project, titled “Integrating genetics and deep neural networks to identify future drug targets for cardiometabolic disease”, aims to leverage AI techniques, especially deep learning, and large human genomic datasets to identify potential causal genes for cardiometabolic traits, assess their viability as potential therapeutic targets, and validate the hypothesised targets in phenotypic assays.
Recent publications
-
An automatic deep reinforcement learning bolus calculator for automated insulin delivery systems
Journal article
Ahmad S. et al, (2024), Scientific Reports, 14
-
Population-Specific Glucose Prediction in Diabetes Care With Transformer-Based Deep Learning on the Edge.
Journal article
Zhu T. et al, (2024), IEEE transactions on biomedical circuits and systems, PP
-
Offline Deep Reinforcement Learning and Off-Policy Evaluation for Personalized Basal Insulin Control in Type 1 Diabetes.
Journal article
Zhu T. et al, (2023), IEEE J Biomed Health Inform, PP
-
A Personalized and Adaptive Insulin Bolus Calculator Based on Double Deep Q-Learning to Improve Type 1 Diabetes Management
Journal article
Noaro G. et al, (2023), IEEE Journal of Biomedical and Health Informatics, 1 - 10
-
GluGAN: Generating Personalized Glucose Time Series Using Generative Adversarial Networks
Journal article
Zhu T. et al, (2023), IEEE Journal of Biomedical and Health Informatics, 1 - 12