Movement pattern recognition through smartphone's accelerometer

Abstract

Sensor-enabled smartphone's have become a mainstream platform for researchers due to their ability to collect and process large quantities of data, hence creating new opportunities for innovative applications. Yet, the limits in employing sensors to opportunistically detect human behaviors are not clear and deserve investigation. To this purpose, in this article, we discuss movement pattern recognition in day-by-day urban street behavior. As a case study, we restrict at recognizing situations when a pedestrian stops, crosses a street ruled by a traffic light; to do so we only use data coming from the accelerometer of the pedestrian's smartphone.