Decoded smartphone movements reveal transport mode

By Will Parker on November 13, 2013 in Computing & Electronics, News

Planes trains, and automobiles – scientists in Finland have worked out how to use accelerometer data from smartphones to reveal which mode of transport a subject is using. As well as applications in surveillance, the new technique could be used to reveal information about the user’s physical activity, personal CO₂ -footprint and preferred transit type.

On a larger scale, the information could be aggregated to discover information about the utilization of different transportation options to aid urban planning.

Lead researcher Samuli Hemminki (University of Helsinki) said the technique relied on extracting characteristic acceleration and braking patterns. These, he says, can be used as a signature to identify different vehicular transportation modes.

“Extracting vehicular movement information from smartphone accelerometers is challenging as the placement of the device can vary, users interact with the phone spontaneously, and the orientation of the phone can change dynamically,” Hemminki explained. “We overcame these challenges by developing novel algorithms for processing and analyzing accelerometer measurements.”

Experimental evaluations demonstrate that the technique can detect most common transportation types (bus, tram, subway, train, car, walking) with over 80 percent accuracy.

Hemminki said the benefits of the technique are particularly pronounced in daily monitoring as the system has low power consumption and works robustly in continuous detection tasks.

“Our work enables fine-grained modeling of human transportation behavior,” added co-researcher Petteri Nurmi. “The system enables a whole new breed of mobility-aware applications and services.”