Movement Data Science

Image

We have developed user-centred and low-cost technologies that are applicable in diverse clinical applications, e.g. monitoring movement or other biomarkers of people with neurodegenerative or musculoskeletal conditions, or their adherence to clinical intervention. These devices are built in-house and, as such, they can adapt to various user and/or clinical needs. 

The MoveR wearable is equipped with the most advanced sensors for longitudinal data collection combined with clinically validated digital biomarkers.

Sensors:

• Optical PPG (Photoplethysmogram)
• Ventral EDA (Electrodermal activity)
• Accelerometer and Gyroscope (6-axis)
• Body Temprature

Key features are:

• Long-term battery life, up to 30 days, depending on the specifications (e.g. sampling rate)
• Wireless connectivity to mobile phone via an app for data transfer and ecological momentary assessment (EMA)
• Remote connectivity to a safe data server benefiting from a lightweight and secure publish-subscribe messaging protocol
• Data analytics and advanced machine learning on the wearable and on the cloud (Microsoft Azure); enabling automated data analysis

If you are interested in using this platform in your research or commercialisation activity, please contact

Email Edinburgh MoveR

Image

In collaboration with Dr Niina Kolehmainen of Population Health Sciences Institute, Newcastle University, and as part of the ActiveCHILD project, we develop explainable machine learning models to analyse young children's physical activity data.

Two recent publications are:

• Physical activity in young children across developmental and health states: the ActiveCHILD study eClinicalMedicine 60:102008, 2023. PDF
• Using unsupervised machine learning to quantify physical activity from accelerometry in a diverse and rapidly changing population PLoS Digital Health 2(4): e0000220, 2023. PDF

In collaboration with Prof Abbasi of the Department of Sports Biomechanics, at Kharazmi University, Iran, we develop neural network based models of lower-limb movement.

• An efficient attention-driven deep neural network approach for continuous estimation of knee joint kinematics via sEMG signals during running Biomedical Signal Processing & Control, 86B:105103, 2023. PDF
• Lower-extremity intra-joint coordination and its variability between fallers and non-fallers during gait Applied Sciences 11(6):2840, 2021. PDF
• Estimation of lower limb kinematics during squat task in different loading using semg activity and deep recurrent neural networks Sensors 21(23):7773, 2021. PDF
• Intra-segment coordination variability in road cyclists during pedaling at different intensities Applied Sciences 10(24):8964, 2020. PDF
• A comparison of coordination and its variability in lower extremity segments during treadmill and overground running at different speeds Gait & posture 79:139-144, 2020. PDF