We are looking for a highly motivated PhD candidate within the project Nightly dance – Dynamics of mother, father, and baby night interactions and sleep. This 4-year project is financed by ZonMw and focused on the transition to parenthood. The birth of a child is a period of adaptation for parents that mostly entails sleep disruptions. In this project we will follow couples from pregnancy until the baby is six months, using small wearable devices that automatically register nightly baby crying, parent-baby proximity, and parents’ sleep and stress. Are you our new PhD candidate?We will employ innovative machine learning and causal analyses to map night-time caregiving behavior, how it changes over time, and whether it predicts long term health problems. We will develop machine learning algorithms to understand these dynamics during the infant’s first six months, uncovering statistical associations and casual factors. To this end we will build on and extend state-of-the-art methods for detecting statistical associations (e.g., Bayesian timeseries models and recurrent neural networks). We will then probe the causal relations underlying these statistical associations using causal inference from time-series data (e.g. using Bayesian Constraint-Based Causal Discovery; BCCD and Partial Convergent Cross Mapping with Information Criteria; PCMCI) for causal discovery from time-series with latent confounders.
The project is a collaboration between Radboudumc, Radboud University, and University of Twente and this PhD project will be embedded within the groups of prof. Andre Marquand (Donders Institute for Brain, Cognition and Behaviour) and associate professor
Tom Claassen (Institute for Computing and Information Science, Faculty of Science). The broader team consists of senior researchers, a postdoc and two PhD students, as well as advisors from perinatal practice and parents. As a PhD you will be part of the wider research ecosystem at the
Donders Institute for Brain Cognition and Behaviour.
We offer a challenging position in an innovative project within a team of dedicated colleagues. Our collaboration is characterized by creativity, collegiality, teamwork, and responsibility. You are being part of dynamic, enthusiastic, collaborative, and ambitious research groups specialized in the development and application of advanced machine learning tools for biomedical data. See for more information our
webpage.