Analysis of real world walking

Wearable sensors technology based on inertial measurement units (IMUs) is leading the transition from laboratory-based gait analysis, to daily life gait monitoring. However, the validity of IMU-based methods for the characterization of real-world gait is still limited, especially in pathological populations. This is because measuring and interpreting real-world gait is far from simple or straightforward.

In this PhD project, co-supervised by Prof. Claudia Mazzà, Prof. Elizabeth Cross and Dr Tim Rogers at the University of Sheffield, you will collaborate on the development and validation of signal processing techniques for the extraction of gait digital mobility outcomes form data collected in real world scenarios. The PhD project will be part of Mobilise-D (www.mobilise-d.eu) a large five-years project that started in April 2019 as part of the Innovative Medicine Initiative (IMI).

As more data are collected, new challenges in the management and processing arise; the data science component of this project will focus on developing machine learning methodologies to maximise information gained. It is hoped that by harmonising established practice with these state-of-the-art techniques, current capabilities in diagnosis can be considerably improved.

We are looking for an excellent student with an Engineering, Mathematics or Physics background, ideally with previous expertise in signal processing, machine learning and inertial sensors.