In this article, we present an approach to determine stress level in a non-invasive way using a smartphone as the only and sufficient source of data. We also present the idea of how to partly transfer such approach to the determination of the driving style, as aggressive driving is one of the causes of car accidents. For determination of the driving style a variety of methods are used including the preparation movements before maneuvers, identification of steering wheel angle, accelerator and brake pedal pressures, glance locations, facial expressions, speed, medical examinations before driving as well as filling out of the questionnaires after the journey. In our paper we present a methodology for estimation of potentially unsafe driving (in the meaning of more intensive acceleration and braking compared to average driving) and discuss how to estimate such unsafe driving before it actually takes place. We present sensors and data which can be used for these purposes. Such data include heart rate variability from chest belt sensor, behavioral and contextual data from smartphone, STAI short questionnaire to assess personal anxiety and anxiety as a state at certain moment, and initial interaction with car during opening and closing of the car doors. To determine intensive acceleration and braking we analyzed GPS data like speed, acceleration and also data from accelerometer inside the car to avoid interference in GPS-signal. Actually, our long term goals are to provide feedback about potentially unsafe driving in advance and thus strengthening driver’s attention on the driving process before the start.

SYSOEV, Mikhail, KOS, Andrej, POGAČNIK, Matevž. Smart driving : influence of context and behavioral data on driving style. V: GALININA, Olga (ur.), BALANDIN, Sergey (ur.), KOUCHERYAVY, Yevgeni (ur.). Internet of things, smart spaces, and next generation networks and systems : proceedings, 16th International Conference, NEW2AN 2016, and 9th Conference, ruSMART 2016, St. Petersburg, Russia, September 26-28, 2016, (Lecture notes in computer science, ISSN 0302-9743, 9870). Cham: Springer. cop. 2016, str. 141-151, ilustr., doi: 10.1007/978-3-319-46301-8_12.