Sedentary workers recognition based on machine learning

Sedentary Behavior (SB) is one of the most frequent human behaviors and is associated with a multitude of extreme chronic lifestyle diseases and premature death. Office workers in particular are at an increased risk due to their extensive amounts of occupational sedentary behavior. There are currently several large data sets available which can be used to create long-term health risk prediction models. However, in many cases, the relation between physical activity and SB in work environment, is missing. The main objective of our study was to develop a method for the automatic classification of sedentary and non-sedentary workers in English Longitudinal Study of Ageing (ELSA) database.