TY - GEN
T1 - Towards safer texting while driving through stop time prediction
AU - Li, Hongyu
AU - Liu, Luyang
AU - Karatas, Cagdas
AU - Liu, Jian
AU - Gruteser, Marco
AU - Chen, Yingying
AU - Wang, Yan
AU - Martin, Richard P.
AU - Yang, Jie
PY - 2016/10/3
Y1 - 2016/10/3
N2 - Driver distraction due to in-vehicle device use is an increasing concern and has led to national attention. We ask whether it is not more effective to channel the drivers’ device and information system use into safer periods, rather than attempt a complete prohibition of mobile device use. This paper aims to start the discussion by examining the feasibility of automatically identifying safer periods for operating mobile devices. We propose a movement-based architecture design to identify relatively safe periods, estimate the duration and safety level of each period, and delay notifications until a safer period arrives. To further explore the feasibility of such a system architecture, we design and implement a prediction algorithm for one safe period, long traffic signal stops, that relies on crowd sourced position data. Simulations and experimental evaluation show that the system can achieve a low prediction error and its converge and prediction accuracy increase proportionally to the availability of the amount of crowd-sourced data.
AB - Driver distraction due to in-vehicle device use is an increasing concern and has led to national attention. We ask whether it is not more effective to channel the drivers’ device and information system use into safer periods, rather than attempt a complete prohibition of mobile device use. This paper aims to start the discussion by examining the feasibility of automatically identifying safer periods for operating mobile devices. We propose a movement-based architecture design to identify relatively safe periods, estimate the duration and safety level of each period, and delay notifications until a safer period arrives. To further explore the feasibility of such a system architecture, we design and implement a prediction algorithm for one safe period, long traffic signal stops, that relies on crowd sourced position data. Simulations and experimental evaluation show that the system can achieve a low prediction error and its converge and prediction accuracy increase proportionally to the availability of the amount of crowd-sourced data.
KW - Safety aware notification
KW - Safety driving
KW - Smart phone application
UR - http://www.scopus.com/inward/record.url?scp=85026262091&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85026262091&partnerID=8YFLogxK
U2 - 10.1145/2980100.2980102
DO - 10.1145/2980100.2980102
M3 - Conference contribution
AN - SCOPUS:85026262091
SN - 9781450342506
T3 - Proceedings of the Annual International Conference on Mobile Computing and Networking, MOBICOM
SP - 14
EP - 21
BT - Proceedings of the 1st ACM International Workshop on Smart, Autonomous, and Connected Vehicular Systems and Services, CarSys 2016
PB - Association for Computing Machinery
T2 - 1st ACM International Workshop on Smart, Autonomous, and Connected Vehicular Systems and Services, CarSys 2016
Y2 - 3 October 2016 through 7 October 2016
ER -