Public defence in Engineering Physics, M.Sc. Xichen Hu

Title of the thesis: Magnetic Sensing Supported by Machine Learning 

Thesis defender: Xichen Hu
Opponent: Associate Professor Benjamin Erne, Utrecht University, Netherlands
Custos: Professor Olli Ikkala, Aalto University School of Science

This doctoral research explores how magnetic materials can be combined with machine‑learning (ML) techniques to design smarter sensors. The goal was to establish sensing platforms based on magnetic materials—such as soft ferromagnetic nickel particles, flexible magnetic composites, and ferrofluids—and ML approaches, allowing sensors to be more adaptable and reliable in changing environments. Traditional sensors are often static, with fixed operating ranges, which limits their usefulness in applications such as soft robotics, where flexibility and adaptability are critical. By developing intelligent systems that allow self‑adjustment mimicking biological behaviour, this study bridges cutting‑edge materials science with modern artificial‑intelligence techniques.

In line with this vision, we developed different sensing techniques: magnetoelectric platforms for non‑visual shape detection; colloidal sensors for adaptive mechanosensing; a bioinspired method for magnetic information encryption; and a ferrofluid‑based magnetometer that uses image recognition for magnetic‑field measurements. These adaptive sensing systems can reconfigure themselves in real time, providing higher accuracy, wider range, and built‑in data security. Altogether, the work offers a fresh perspective on sensing—one that is not bound by static hardware constraints but is dynamically reconfigurable and guided by machine intelligence. This approach holds promise for a new generation of devices in areas such as soft robotics, wearable electronics, and security systems.

Key words: Magnetic Sensing, Machine Learning, Colloidal Assemblies, Bioinspired Materials

Thesis available for public display 10 days prior to the defence at Aaltodoc. 

Contact information: 

xichen.1.hu@aalto.fi 

Zoom passcode: hxc123