Using data science to promote a healthy life style
Movement behaviours, such as physical activity, sleep, and the amount of time we sit each day, impact our health. Recently, more researchers are looking at the influence of these behaviours combined, but this is a challenging task. For example, it is difficult to monitor in what way movement behaviours influence each other, as self-reported data is often inaccurate. To improve this, the project 'Learning Network for Advanced Behavioural Data' (LABDA) develops methods for analysing the data of movement-tracking wearables.
How can you create new methods to analyse the data of movement behaviour? And also, how can you examine to what extent this data can be useful for predicting health risks and whether this data can be applied in science, policy, and society? That’s the aim of LABDA, an EU-funded project that brings together researchers from different disciplines, such as epidemiology, data science, method development, and public health.
How can machine learning be used to understand data beter?
Throughout the project, 13 PhD students will study this problem each from a different angle. The PhD project at LIACS focuses on how machine learning techniques can be used to learn causal effects in the data. Furthermore, the project will identify what we can change in our daily activities to promote health. Involved LIACS researchers are Mitra Baratchi and Wessel Kraaij.
You can read more about LABDA on the project website.
Learning Network for Advanced Behavioural Data Analysis (LABDA) is a newly EU-funded Marie Skłodowska-Curie Actions (MSCA) doctoral network project under Horizon Europe.
This project is coordinated by Prof. Mai Chin A Paw at Amsterdam UMC. LABDA includes reseachers from the University of Southern Denmark, the Norwegian University of Science and Technology, Leiden University and many more.