The advantage of in-vehicle monitoring technology enables the collection of accurate and high resolution driving information. The availability of such large amount of information may open new possibilities to analyze behavior of small samples and even individual’s driving behavior in order to evaluate change over time, strengths and weaknesses which can be used to create personalized interventions and feedback massages. In this paper, the authors demonstrate how information from technology can be used for analyzing a single driver’s behavior. The authors analyzed individual driver’s information received from a novel in-vehicle technology, which identifies the occurrences of undesirable driving events such as extreme braking and accelerating, sharp cornering and sudden lane changing. During the three years measurement period, information about more than 5704 trips, 2107 driving hours and 6878 undesired driving events was recorded. The maximum likelihood estimation was used to fit the Negative-Binomial model for the events rate. Then, several negative binomial regression models were used to analyze how trip duration, daytime, and day of the week are linked to the rate of undesirable driving events. A generalized additive model (GAM) with the P-spline method for smoothing was used to evaluate how driving behavior changes over time, and a “before” and “after” study was performed to test the effect of providing feedback about driving behavior. Insurers and safety officers in commercial fleets can use driving information collected by technology to analyze trends in behavior and to evaluate the usefulness of intervention plans – even for a single driver.
[1]
A K Wagner,et al.
Segmented regression analysis of interrupted time series studies in medication use research
,
2002,
Journal of clinical pharmacy and therapeutics.
[2]
Carlo Giacomo Prato,et al.
Intrafamilial Transmission of Driving Behavior
,
2009
.
[3]
Hillel Bar-Gera,et al.
Electronic Records of Undesirable Driving Events
,
2010
.
[4]
Todd Litman.
Distance-Based Vehicle Insurance
,
2008
.
[5]
Tomer Toledo,et al.
In-Vehicle Data Recorder for Evaluation of Driving Behavior and Safety
,
2006
.
[6]
Todd Litman.
Pay-As-You-Drive Pricing For Insurance Affordability
,
2011
.
[7]
Tomer Toledo,et al.
In-vehicle data recorders for monitoring and feedback on drivers' behavior
,
2008
.
[8]
Jeroen Hogema,et al.
Effects of human-machine interface design for intelligent speed adaptation on driving behavior and acceptance
,
2005
.
[9]
Oren Musicant,et al.
When Technology Tells Novice Drivers how to Drive
,
2010
.
[10]
Tomer Toledo,et al.
Safety Correlation and Implications of In-Vehicle Data Recorder on Driver Behavior
,
2007
.
[11]
John D Lee,et al.
Technology and teen drivers.
,
2007,
Journal of safety research.
[12]
John D Lee,et al.
Extending parental mentoring using an event-triggered video intervention in rural teen drivers.
,
2007,
Journal of safety research.