INVITED SPEAKERS OF ICBEA 2027

 

Asst. Prof. Juexiao Zhou
The Chinese University of Hong Kong, Shenzhen, China

 

Juexiao Zhou has been a Tenure-Track Assistant Professor at the School of Data Science, The Chinese University of Hong Kong, Shenzhen, since 2025. He received his Bachelor of Science degree in Bioinformatics from the Southern University of Science and Technology (SUSTech) in 2020 and his Doctor of Philosophy (Ph.D.) degree in Computer Science from King Abdullah University of Science and Technology (KAUST) in 2025. His research spans the intersection of computer science and biomedicine, with a primary focus on AI-driven intelligent healthcare, bioinformatics, and ethical, trustworthy AI in clinical contexts. Juexiao develops cutting-edge deep learning models and large language models (LLMs) to facilitate disease detection, prognosis, and risk assessment across diverse clinical settings. He has authored over 40 publications in top-tier journals and conferences, including Nature Methods, Nature Machine Intelligence, Science Advances, Nature Computational Science, Nature Communications, The Lancet, Genome Research, Trends in Genetics, Bioinformatics, IEEE Transactions on Medical Imaging (IEEE TMI), and MICCAI. Among these, 11 are first-author papers, including contributions to Nature Methods (2026), Nature Communications (2023, 2023, 2024), and Science Advances (2023). Additionally, he holds editorial positions at BMC Bioinformatics, npj Artificial Intelligence, and Biomedical Informatics.

 

Speech Title: "Trustworthy, Explainable, and Ethical AI in Healthcare and Biomedicine"

 

 

Assoc. Prof. Ir. Dr. Rosmina Jaafar
Universiti Kebangsaan Malaysia, Malaysia

 

Associate Professor Ir. Dr. Rosmina Jaafar is an established lecturer and researcher in the Department of Electrical, Electronic & Systems Engineering, Faculty of Engineering and Built Environment at Universiti Kebangsaan Malaysia (UKM). She holds a B.Sc. in Biomedical Engineering from Case Western Reserve University (USA), an M.Sc. in Electronics (Medical Systems) from the University of Hertfordshire (UK), and a Ph.D. in Electrical, Electronic & Systems Engineering from UKM. With over three decades of academic, engineering, and clinical research leadership, Ir. Dr. Rosmina specializes in photoplethysmography (PPG), non-invasive cardiovascular diagnostics, EEG signal processing for automated epilepsy detection, and medical electronic instrumentation. She has led and co-investigated research projects totaling over RM2.5 million in grants, pioneering innovations in AI-powered coronary artery blockage detection, cuff-less blood pressure estimation, and IoT clinical decision support systems. Ir. Dr. Rosmina has authored over 100 peer-reviewed journal articles, conference papers, and books including the national 2025 award-winning medical book Jantung Tersumbat: Alternatif Pengesanan Melalui Teknik Pembelajaran Mesin. She actively serves as a Malaysian Qualifications Agency (MQA) assessor and reviewer for international biomedical engineering journals. As an invited speaker, Ir. Dr. Rosmina will showcase extensive academic leadership, advancing the translation of fundamental control theory and multi-modal biosensing into high-precision, point-of-care diagnostic tools that enhance patient monitoring.

 

Speech Title: "Biomedical framework of computational modeling for non-invasive bio-signals sensing and AI-driven diagnostics"

 

Abstract: Traditional clinical diagnostics often rely on invasive procedures or slow laboratory evaluations. This presentation introduces a unified biomedical engineering framework combining non-invasive biosensors, computational modeling, and artificial intelligence across cardiovascular, neurological, and respiratory domains. Initially, a closed-loop Simulink model simulates brainstem cardiorespiratory feedback dynamics. For cardiovascular health, optical photoplethysmography (PPG) and electrocardiography (ECG) enable continuous, cuff-less blood pressure monitoring. Synchronized ultrasound and PPG signal features evaluation assesses non-invasive endothelial dysfunction during reactive hyperemia. Dual-site PPG sensors achieve precise blood pressure tracking via pulse transit time (PTT), while merging synchronized ECG and PPG signals with an Artificial Neural Network detects severe coronary artery blockages with 95.83% accuracy. Furthermore, PPG waveform stability evaluation screens for atrial fibrillation (AF), wireless multi-site optical sensors track dengue vascular leakage with 89% accuracy. In neurological monitoring, electroencephalogram (EEG) signals undergo Discrete Wavelet Transform and Support Vector Machine classification, detecting epileptic discharges with 94% accuracy. Complementing this, the Computerized Recognition or Epileptic EEG Detection (CREED) hybrid algorithm matches expert neurologist seizure assessments. Together, these multi-modal technologies demonstrate how integrated biosensing and machine learning provide rapid, high-precision point-of-care clinical decision support.