Monday, 17 December, at 14:00, The Technical University of Denmark, Matematiktorvet/Asmussens Allé, Building 303 A, Aud 42.
Principal supervisor:
Associate Professor Jakob Eg Larsen
Co supervisor:
Professor Lars Kai Hansen
Examiners:
(Chairman) Associate professor Sune Lehmann Jørgensen, DTU Compute
Reader in Data Science Mirco Musolesi,University College London, United Kingdom
Professor Mikkel Baun Kjærsgaard, The University of Southern Denmark
Chairperson at defence:
Associate Professor Per Bækgaard, DTU Compute
Summary:
Increase of sedentary behaviour and obesity has been on the rise for a score of years or more, despite public information campaigns and even the incursion of the latest fad, fitness trackers. A reoccurring observation seem to be a misunderstanding of what drives human motivation and what it takes to change human behaviour with respect to physical activity. This misunderstanding, or naïvety, probably stems from conclusions that are drawn from data that are too thin to support them. We propose a paradigm that relies on massive amounts of data, pervasively sampled from smartphones.
We show that smartphone data is able to estimate plausible intervention effects from a randomized controlled trial, and through higher sampling frequency and additional modalities, is able to break up the estimated effects into contextual pieces that can be used to better understand behavioural aspects. We further show that by using a model that adapts to each individual, we can predict a persons total energy expenditure accurately from the same data.
A model is presented that from large complicated data, fully unsupervised is able to learn latent states that naturally decompose into static and dynamic representations. The static representations are learnt as a function that maps a high--dimensional observation into a low--dimensional code that is dependent on a structured prior distribution that governs the dynamical system.
READ MORE at orbit.dtu.dk
All are welcome!