Mr Shibo Jing

My research focuses on wearable sensing, machine learning, and physiological signal processing for real-world health monitoring. I am particularly interested in developing robust and generalisable models that can operate reliably under non-stationary conditions, such as sensor variability, placement changes, and long-term physiological drift.

My work explores:

• Wearable and multimodal physiological sensing
• Machine learning for non-stationary and real-world data
• Embedded and resource-constrained AI for deployable systems
• Robust modelling under distribution shifts and limited data
• Translational digital health technologies for infectious disease detection and monitoring

I am broadly interested in advancing wearable AI systems that enable early detection, continuous monitoring, and scalable healthcare solutions, particularly in resource-limited settings.

I received my PhD in Biomedical Engineering from Imperial College London, where my research centred on machine learning and signal processing methods for modelling physiological data from wearable sensors. My doctoral work addressed key challenges in real-world sensing, including non-stationarity, sensor variability, and robustness under distribution shifts, with a particular focus on human movement analysis.

My current work focuses on developing machine learning models and embedded AI solutions for wearable and handheld sensing platforms aimed at infectious disease detection and monitoring. I work closely with multidisciplinary teams across engineering, clinical research, and global health to translate methodological advances into practical healthcare technologies.

My research trajectory is centred on advancing wearable AI and physiological modelling to support scalable, data-driven healthcare systems, with an emphasis on early detection, longitudinal monitoring, and real-world deployment.