Recognizing Falls and Surfaces Using Mobile Devices

Abstract

Mobile devices are getting much more relevance during the users' day, in a way that they are paying to increase device security and durability though external cases or insurance plans. However, these approaches are useless if the individuals does not properly take care of their devices. This paper describes an approach to monitor and classifies a surface where a smartphone falls, making possible to categorize this crash into a range of dangerousness. The authors collected empirical data from device falls to make possible the development of an optimal classifier. Our results reached up to 88% recognition rate of surfaces considering a specific features subset, letting us conclude that it is possible to infer user care level through the analysis of how a device is being treated.