Are you the data scientist devoted to excellence in research and education in the field of Nutrition and Health? Do you want to increase the impact of Artificial Intelligence on the life sciences domain? Then we are looking for you!
As a data scientist within the division of Human Nutrition and Health of Wageningen University, you tackle complex issues concerning data processing in the field of dietary intake, lifestyle and health. We collect data in intake using apps and sensors, on physical activity using smartphones / GPS and on health using biomedical data and external records. So far the data analyses has been approached from a statistical angle, and training and education focused on biostatistics and epidemiology. But newer insights from data science and AI are still lacking.
With the rapidly increasing impact of Artificial Intelligence (AI)/Machine Learning on the life sciences domain we aim to modify our MSc program to include more data science. You develop the course Data Science and Health II for MSc students in Nutrition and Health, and you will organize this course and act as main lecturer. This course is part of a large set of new courses in data science at Wageningen University, so you will be part of a lager data science community.
Regarding the research component, it is your job to analyze and translate the data generated through our newly developed smart tools in one of our projects (BigO,
www.bigoprogramme.eu). This project aims to better understand factors affecting the prevalence of childhood obesity in different municipalities/countries. To this aim more than 1,500 children collected data by means of a citizen science approach, these (Big) data now need to be analyzed.
You are able to combine the right quantitative and qualitative sources into usable data. You build models, and you monitor and analyze and visualize data with tools such as SAS (Enterprise guide), R and Phyton. For the practical application you explore whether it is possible to integrate the data from different tools through machine learning techniques, and whether it is possible to provide the applications with personalized feedback mechanisms.