ClimbTheWorld: Real-time stairstep counting to increase physical activity

Abstract

The increasing number of people that are overweight due to a sedentary life requires persuasive strategies to convince people to change their behaviors. In this paper, we present a machine learning based technique to recognize and count stairsteps when a person climbs or descends stairs. This technique has been used as part of ClimbTheWorld, a realtime smartphone application that aims at persuading people to use stairs instead of elevators or escalators, since an engaging activity has more chance to change people's life habits. We perform a fine-grained analysis by exploiting smartphone sensors to recognize single stairsteps. Datadependent sliding windows are used facilitating the learning process and reducing the computational cost. Finally, energy consumption is widely investigated to optimize the trade-off between classification precision and battery usage, to avoid exhausting smartphone battery.