Projektdetails

Physical activity is a major lifestyle factor affecting health, morbidity and mortality. The World Health Organization states lack of physical activity as the fourth leading risk factor for global mortality (according to the WHO. In recent years, 3D-accelerometer measurements have become current state-of-the-art for physical activity assessment also in large epidemiological cohorts. Accelerometers deliver so-called “objective” measurement points, and are thus free of any information bias.
The most commonly used approaches to analyze the data are far from making full use of the available data. In recent years, single attempts have been undertaken to use own algorithms on the data but there is still a large potential for further research. In particular, recent breakthroughs in machine learning for time series data could be exploited by adapting them to data analysis for physical activity assessment.
The main objective of this project is the development of open source software for accelerometer data analyses with high relevance to public health scientists that goes beyond the state-of the art of available software packages.