In large cities, health is poorer and life expectancy shorter than in rural environments. This is partly due to a lower physical activity of the residents. In this project we want to understand in more detail how the physical activity of city dwellers can be increased through the use of personalized app technology.

Up to now, existing health and exercise apps lack scientific substantiation. Different apps use different ways to encourage people to be physically active, such as feedback about physical activity, motivational messages or games. Whether a certain method of motivation works is very personal. This means that a good health app is tailored to, for example, current activity level, health, personality and environmental factors. But how the optimal alignment is found for each person is still unclear.

The aim of this project is to gain knowledge about this, by developing a motion app with different forms of feedback in which the optimum match between app and user is used. We will use the app to collect data about the physical activity and location of the user where very large data sets (big data) are collected. We will use data mining techniques to find out which app works best for different types of users. We then give each person his or her optimal app, and measure whether the physical activity continues to increase. Based on the data, we can determine the effect of different types of exercise apps, and which app is most suitable for a specific person.