Driving behavior and traffic safety: An acceleration-based safety evaluation procedure for smartphones

9 Pages·2014·1.717 MB·English

by  Vaiana R., Iuele T., Astarita V., Caruso M.V., Tassitani A., Zaffino C., Giofrè V.P.

Modern Applied Science; Vol. 8, No. 1; 2014
ISSN 1913-1844 E-ISSN 1913-1852
Published by Canadian Center of Science and Education
Driving Behavior and Traffic Safety: An Acceleration-Based Safety
Evaluation Procedure for Smartphones
Rosolino Vaiana1, Teresa Iuele1, Vittorio Astarita1, Maria Vittoria Caruso1, Antonio Tassitani1, Claudio Zaffino1
& Vincenzo Pasquale Giofrè1
1 Department of Civil Engineering, University of Calabria, Arcavacata di Rende, Cosenza, Italy
Correspondence: Teresa Iuele, Department of Civil Engineering, University of Calabria, Via P. Bucci, Cubo 46B,
87036, Arcavacata di Rende, Cosenza, Italy. Tel: [phone]. E-mail: [email protected]

Received: July 18, 2013 Accepted: December 3, 2013 Online Published: January 2, 2014
doi:10.5539/mas.v8n1p88 URL: http://dx.doi.org/10.5539/mas.v8n1p88

Abstract
Traffic safety and energy efficiency of vehicles are strictly related to driver’s behavior. The scientific literature
has investigated on some specific dynamic parameters that, among the others, can be used as a measure of unsafe
or aggressive driving style such as longitudinal and lateral acceleration of vehicle. Moreover, the use of modern
mobile devices (smartphones and tablets), and their internal sensors (GPS receivers, three-axes accelerometers),
allows road users to receive real time information and feedback that can be useful to increase awareness of
drivers and promote safety. This paper focuses on the development of a prototype mobile application that can
evaluate the grade of safety that drivers are keeping on the road by measuring of accelerations (longitudinal and
lateral) and warning for users when it can be convenient to correct their driving style. The aggressiveness is
evaluated by plotting vehicle’s acceleration on a g-g diagram specially studied and designed, where horizontal
and lateral acceleration is displayed inside areas of “Good Driving Style”. Several experimental tests were
carried out with different drivers and cars in order to estimate the system accuracy and the usability of the
application. This work is part of the wider research project M2M, Mobile to Mobility: Information and
communication technology systems for road traffic safety (PON National Operational Program for Research and
Competitiveness 2007-2013) which is based on the use of mobile sensor computing systems for giving real-time
information in order to reduce risks and to make the transportation system more safe and comfortable.
Keywords: driving behavior, vehicle accelerations, traffic safety, g-g diagram, GPS
1. Introduction
Traffic safety is strictly related to the behavior of each driver and to its individual variability associated to
several parameters such as: age, gender, geographic locations, and other factors. Moreover, driving behavior has
a great influence on energy efficiency: the difference in terms of fuel consumption and, consequently of gas
emissions, between a safe (or calm) driver and an aggressive one is estimated to be higher than 40%
(Alessandrini et al., 2012). For this reason, in order to reduce the environmental impact due to the road
transportation system, in the last few years the idea of educating drivers to adopt an eco-friendly driving style
has been promoted.
An eco-friendly and safe driving behavior could be achieved by reducing or avoiding sudden accelerations and
rapid brakings in both longitudinal direction and cornering maneuvers (Yamakado et al., 2009).
The evaluation of real driving scenarios is very complex because it’s reliant on many closely interconnected
variables depending not only on the different type of drivers, but also on the road environment, the traffic
characteristics and the categories of road infrastructure. However, driving behavior assessment has been
associated to two main dynamic parameters that, among the others, have been proposed in scientific literature as
the most significant for a quantitative evaluation of unsafe or aggressive driving style; these parameters are the
longitudinal and the lateral accelerations and decelerations (Shaout & Bodenmiller, 2011; Klauer et al., 2009;
Johnson et al., 2011; Paefgen et al., 2012).
By measuring the in-vehicle accelerations in the XY plane it is possible to categorize the driving behavior into
two main classes: aggressive drivers and non-aggressive or safe and expert drivers. The driving style of these last
ones, in particular, is characterized by the selection of smooth trajectories with a continuous adjustment of the
88
www.ccsennet.org/mas Modernn Applied Sciencce Vol. 8, No. 1;2014
acceleratioon levels in hharmony withh the operatioon of the steering wheel that contributte to a signifficant
improvemment of the ridee comfort for bboth drivers annd passengerss. Finally, expeert drivers are able to adequuately
decelerate passing from a straight lanne to a curve; iin this way, thhe front wheells are subject tto a higher vertical
load generrating more coornering force and a more efffective steerinng movement, reducing the eenergy loss and the
tire wear ddue to the rollinng resistance pphenomenon (YYamakado et aal., 2009).
The spreadd of modern teechnologies forr mobile devicces (smartphonnes, tablet, etc..), together witth the development
of several applications tto exploit theiir internal senssors (GPS recceivers, three-aaxes accelerommeters), allow road
users to reeceive real timme informatioon and feedbaack on their behavior that ccan be useful to increase ddivers
awareness and promotee safety. By pproviding thiss kind of inteerventions durring the guidee it is estimatted a
reduction oof about 20% iin the average estimated acccident number (Paefgen et al.., 2012).
In the ligght of the aboove mentionedd facts, this ppaper focuses on the deveelopment of aa prototype mmobile
applicationn through whicch vehicle dataa (position, speeed, longitudinnal and lateral accelerations)) are monitoredd and
recorded inn real time; fuurthermore it alllows to send aa warning for uusers when it ccan be convenient to correct their
driving styyle to be moree safe and lesss aggressive. Itt is noted that this project wwas run under the auspices oof the
research pproject “M2M – Mobile to Mobility: Infformation and communication technologyy systems for road
traffic safeety” (PON Naational Operatiional Programm for Researchh and Competitiveness 2007-2013, co-finaanced
by Europeean Regional Developmentt Fund, FESRR). The main objective of this project iis giving real--time
informatioon on road quaality to road ussers through mmobile sensor ccomputing systtems in order to reduce riskss and
to make thhe transportatioon system morre safe and commfortable.
The paperr is organized as follows: Section 2 preseents some prevvious studies about the asseessment of thee g-g
diagram uusability for driving style classificationn. Some detaails about thee used acceleerometer data and
experimenntal tests are allso specified inn Section 2. Section 3 contaains the resultss and a discusssion about obtaained
data; finallly, in Section 44 conclusions aand some futuure perspectives are carried out.
2. Methodd
2.1 Users DDriving Style: Safety Marginns in the g-g DDiagram
As stated iin the previouss paragraphs, bboth longitudinnal and lateral accelerations are significantt parameters foor the
evaluationn of drivers behhavior. The limmits of these aaccelerations aare related to thhe edges of the friction circlle (or
the ellipsee of adherencee) (Da Lio et aal., 2005) whicch depend on tire characteriistics and roadd surface conddition
(Vaiana ett al., 2012). Inn particular, veehicle stabilityy while cornerring depends oon the balancee of the centrifugal
force and tthe friction forrce that is deveeloped in the ccontact area between the wheeels and the paavement surface.

(a) (b)
Figuure 1. (a) Frictioon circle edge; (b) Area of eexperience andd inexperience

The frictioon force is coonventionally broken down into two commponents: longgitudinal fricttion and transvverse
friction. WWhen a vehiclee is travelling in a straight liine only the fiirst one is invoolved; on the contrary, when the
front wheeels are turnedd a transversse force occurrs. When botth longitudinaal and transveerse friction ooccur
simultaneoously, the resuultant force shhould not be hhigher than thee maximum frriction that is represented byy the
89
www.ccsennet.org/mas Modernn Applied Sciencce Vol. 8, No. 1;2014
edge of thee friction circlle for specific cconditions of ssurface (dry, wwet, icy) and tiire (see Figure 1a). On wet roads,
friction cann be reduced tto 30% comparred to dry condditions; the ratte of decrease reaches a valuue of about 90%% for
icy surfacees (Andersson et al., 2007). Moreover, thee way in whichh a driver takee a corner and the behavior in the
approachinng straight aree influenced byy the longituddinal acceleratiion or decelerration: each drriver can chooose to
take the coorner at a consstant speed or aaccelerating annd braking in pparticular sectiions of the patth, in relation tto the
perceived risk. Also thee experience oof each driver may be consiidered a key ffactor in longiitudinal and laateral
acceleratioons variation: the driver accquires capabiilities and skiills during driiving practice that determinnes a
learning efffect. Previouss researches (SSievert, 1994; LLamm et al., 11999) showed tthat it is possibble to single out an
area of driiving experience on the g-g ddiagram (see FFigure 1b): an uncommon phhysical behaviior is typical of this
area and itt is related to vvehicle-handlinng features (forrces, torques, eetc.).
Furthermoore, past studiees (Chen et all., 2013; Balddauf et al., 20009; Zhang et al., 2004) shoowed that vehiicle’s
speed andd acceleration are the most significant pparameters for the mental wworkload estimmation, amongg the
driving-peerformance feaatures. In particcular, the longgitudinal acceleeration of the ccar (increasingg and/or decreaasing
speed) is aan indicator off driving task difficulty. Whhen the mentaal workload beecomes too greeat and it is higher
than the drriver’s ability aan accident cann occur, affectting traffic saffeety.
Overlappinng the diagramm of the drivinng experiencee area and the friction circlee in an intermeediate conditioon of
constrain ((wet surface), a new area oof safe drivingg was identifieed in this studdy, (see Figuree 2a). Some deetails
about the edges of this area are also reported in Fiigure 2b. The new diagram has been nammed “Driving Style
Diagram” (DSD). In paarticular, the arrea has a limiit of 2.5 m/s2 for both longiitudinal and laateral acceleraations
(left/right turns); in the ccase of deceleration the limiit value is equual to 3.0 m/s2. In fact, apart from the tyre grip,
other limitting factors, suuch as the power of the enginne, come into pplay under forwward accelerattion.
The suitabbility of the “ssafe area” edgees (as it has bbeen defined) wwas evaluatedd by means of a dataset colleected
during the development of experimenttal phases of thhe M2M Project. This dataseet was developped consideringg two
different bbehaviors of a same professional driver; oonly the longittudinal accelerrations were ccalculated fromm the
GPS readinngs using the VVideo-Vbox innstrumentationn.
The differeences in termss of acceleratioon variability bbetween the agggressive and thhe safe drivingg were evaluatted in
many expeerimental tests, as shown in FFigure 3.

(a) ((b)
Figure 2. (a) Construction oof the new “safe area”; (b) DDriving Style DDiagram (DSD [a -a ])
x y
90
www.ccsennet.org/mas Modernn Applied Sciencce Vol. 8, No. 1;2014

Figure 3. Acceleratioon variations foor both safe annd aggressive ddriving behavioor

As it is poossible to obseerve in Figuree 3, the safe ddriving behavioor is characterrized by accelleration valuess that
range fromm about ±2 m/s2; on the conttrary, if the driiver has an agggressive behavvior this limitss are doubled. Data
were extraacted from a ddataset of 20 eexperimental teests carried ouut on a test sitte with a lengtth of about 122 km.
Results shhowed in Figurre 3 are cohereent with the mmethodology ddescribed beforre (see Figure 2a-2b), in ordder to
evaluate annd discriminatte different drivving styles.
2.2 Acceleerometer Data ffrom GPS
The GPS mmodule allowss to calculate bboth longitudinnal and lateral aaccelerations aas derived paraameters. Generrally,
GPS-basedd systems recoord satellite siggnal-derived sppeed readings once per seconnd. The longittudinal accelerration
can be calcculated from cconsecutive speed measuremments using thee backward diffference methood (Jun et al., 22006;
Tonzig, 20011):
(cid:1853)_(cid:1864)(cid:1867)(cid:1866)(cid:1866)(cid:1859)(cid:3404)∆(cid:1874)/∆(cid:1872) (1)
where ∆(cid:1874) is the speed variation (cid:4666)(cid:1874) (cid:3398)(cid:1874) ), while ∆∆(cid:1872) is the tempporal variationn. Moreover, since
(cid:3030)(cid:3030)(cid:3048)(cid:3045)(cid:3045)(cid:3032)(cid:3041)(cid:3047) (cid:3043)(cid:3045)(cid:3032)(cid:3049)(cid:3049)(cid:3036)(cid:3042)(cid:3048)(cid:3046)
the GPS hhas a samplinng frequency oof 1 Hz, ∆(cid:1872) iis equal to 1 sec. The laterral acceleratioon, instead, caan be
expressed as:
(cid:1853)_(cid:1864)(cid:1853)(cid:1872)(cid:1872)(cid:3404)(cid:1874)(cid:2870)/(cid:1844) (2)
where (cid:1874) iis the current speed value (mm/s), R is the turn radius (mm), which can be evaluate ussing the expression
specified bby (Abdulrahimm, 2006, Jocheem et al., 19955) (Equation 3)).
(cid:1844) (cid:3404)(cid:4666)180∙(cid:1874)(cid:4667)/(cid:4666)(cid:2024)∙∆(cid:1834)(cid:1857)(cid:1857)(cid:1853)(cid:1856)(cid:1861)(cid:1866)(cid:1859)(cid:4667) (3)
where (cid:1874) iis the current speed value (mm/s) and ∆(cid:1834)(cid:1857)(cid:1857)(cid:1853)(cid:1856)(cid:1861)(cid:1866)(cid:1859) is variiation of the hheading in the temporal unit. The
heading reepresents the current direction comparedd to the Northh direction, exxpressed as deegree with possitive
rotation wwith respect to the East. Morreover, the vallues of this vaariable is proviided directly bby the GPS. Inn this
study the EEquation (3) wwas used for thee calculation oof the instant raadius that has to be used in ((2), instead of other
relationshiip found in thee literature (Caarlson et al., 20005; Ibraheem & Janan, 20111).
Results wwere comparedd to acceleration data proviided by the VVideo-Vbox syystem, a high quality electronic
instrumentt that allows too evaluate speeed and both loongitudinal annd lateral accelleration from a GPS data logger.
The validaation proceduure was satisfaactory with diifferences lowwer than 1% bbetween the ttwo sets of values
(calculatedd/derived fromm the Video-Vbbox).
Another vvalidation proccedure was caarried out on sspeed data obtained from thhe GPS readinngs: derived sspeed
values werre compared too those red froom the Can network of vehiccle through thee OBD-II diaggnostic port (Figure
4a). Also iin this case results show a vvery high correlation coefficcient (R2 ≈ 0.99), as it is posssible to observe in
Figure 4b. Using accelerration data derrived from thee GPS readings allows the feeasibility of thhe applicationto be
independent from the poosition of the ddevice inside thhe vehicle, avooiding the probblems related tto the re-orienttation
of the acceelerometer in tthe x-y plane.
91
www.ccsennet.org/mas Modernn Applied Sciencce Vol. 8, No. 1;2014

(a) (b)
Figure 44. (a) Compariison between CCAN and GPSS speed; (b) Coorrelation betwween CAN and estimated speed

2.3 Researrch Design
All of experimental testss were carried out on two roaads in the distrrict of Cosenza, using one vvehicle (Fiat Dooblò)
and one smmartphone (a SSamsung Nextt with Androidd IO) because very low diffeerences, less thhan 5% in termms of
position daata, were founnd between maany devices in pprevious studiies (Astarita ett al., 2012). Thhe device was fixed
to the dashhboard of vehiccle through a rrubber and adhhesive support.
Five driveers with differeent driving behhavior were reecruited amonng students andd professors inn the Universiity of
Calabria (IItaly). Two paarticipants are young drivers with a drivingg license sincee 3-4 years, whhile the other three
are 45-50 years old withh many years of driving expperience. No iinformation abbout the devicce working feaatures
were givenn to the particcipants; howevver, each one oof them kneww the main aimm of the projecct in relation to the
monitoringg of driving beehavior.
To identifyy the aggressivve behavior, mmany potential ddangerous eveents were takenn into account:
 exxcessive speedds, higher thann the law limitss;
 suudden, intensse and repeaated brakings and accelerrations (detect consideringg the longitudinal
accceleration waaveform); aggrressive left andd right turns;
 agggressive U-tuurns and rounddabout crossingg ;
 agggressive lane changes.
The behavvior taken in alll these situatioons was agreeed as aggressivve drivers A, BB, D, and for aas safe behavioor the
remainders drivers (C annd E).
Moreover,, the experimeental plain inclluded two testt sites, both traaveled for twoo round trips ((Figure 5): thee first
has a lengtth of about 15 Km, while thee second has a length of 18 KKm; overall, a total of twentyy tests were caarried
out and abbout 330 Km of road travelled (Figure 5).

N
N

Figure 5. Test sites loocation and exxperimental plaan
92
www.ccsenet.org/mas Modern Applied Science Vol. 8, No. 1; 2014
3. Results and Discussion
The behavior of each driver was evaluated by calculating the percentage of points that are characterized by
values of accelerations higher than the limiting edges of the DSD area. In particular, the methodology proposed
in this study aims to the identification of a specific threshoold of this percentage that allows to differentiate an
aggressive driver from a safe one. In this way it is possible to use the proposed mobile application for collecting
GPS data, calculating the vehicle’s accelerations and giving real-time information to road users about their
driving style. In order to reach this purpose the application is set for a systematic control of the accelerations for
a specific period of time (i.e. 5 minutes); after this time the calculation restarts and new percentages of external
points are estimated with a continuous feedback given to drivers.
The results obtained for the twenty tests carried out in this research are reported in Table 1, in which the drivers,
the test sites and the percentage of accelerometer data which fall outside the DSD area are specified. The mean
value and the standard deviation of the percentage of external points for each driver were also calculated (Table
1).
Slight differences were found in the estimated percentages for the two tests sites; in particular for the test site
located in the city of Rende the aggressive driver is characterized by a mean value of external points of about
13.5, with a standard deviation of ±1.2%; the safe drivers registered a value of 5.7%. On the contrary, for the test
site located in Montalto, registered values are (11.9±1.1)% for the aggressive drivers and (6.1±0.5)% for the safe
ones.
The difference is probably related to the fact that the two tests site are quite different because the first one is
characterized by high traffic volumes and it is located in the centre of the city, whereas the other one can be
considered a suburban road (lower volumes of traffic, higher operative speeds, etc.).

Table 1. Internal and external percentages of accelerometer data in the DSD (* indicates the aggressive driver)
External
Test Internal Points EP - Mean EP - Standard
Driver Test Site Points
number IP [%] Value [%] Deviation [%]
EP [%]
1 84.7 15.3
Rende
2 86.0 14.0
A* 12.9 ±2.2
3 89.7 10.3
Montalto U.
4 88.0 12.0
5 87.5 12.5
Rende
6 88.0 12
B* 12.0 ±0.6
7 87.7 12.3
Montalto U.
8 88.9 11.1
9 94.5 5.5
Rende
10 95.6 4.4
C 5.5 ±0.8
11 93.7 6.3
Montalto U.
12 94.3 5.7
13 85.8 14.2
Rende
14 87 13.0
D* 13.2 ±0.9
15 86.5 13.5
Montalto U.
16 88.0 12.0
17 92.5 7.5
Rende
18 94.7 5.3
E 6.3 ±1.0
19 93.4 6.6
Montalto U.
20 94.3 5.7
93
www.ccsennet.org/mas Modernn Applied Sciencce Vol. 8, No. 1;2014
On the basis of the resuults summerizeed in Table 1,, for aggressivve drivers the mean value off external poinnts is
higher thaann 10%, whereeas the safe driivers registered a percentagee lower than 88%. For this reeason the thresshold
value for ddistinguishing between aggreessive and nonn-aggressive drrivers was set tto a value of 9%.

FFigure 6. Distriibution of poinnts in the DSD for an aggresssive driver (lefft) and a safe oone (right)

In Figure 66 it is possiblee to observe soome differencees between two DSD for an aggressive annd a safe driverr; the
percentagees of points belonging to the four external rregions of the diagram (E, FF, G, H) are shoown in Figure7.

Figurre 7. Percentagges of external points in the ddifferent regionns of the DSD

4. Conclussions
In this studdy a methodollogy for evaluaating driving bbehavior by meeans of an Anddroid applicatiion was develooped.
In particullar, the user’s driving style recognition wwas based on tthe acceleratioon values (botth longitudinall and
lateral) thhat are derivedd from GPS position data. The aggresssiveness was evaluated by plotting vehiicle’s
acceleratioons on a g-g ddiagram, wherre lateral accelleration is dispplayed on the horizontal axis and longitudinal
acceleratioon on the verrtical one. A ddetailed invesstigation on thhe safety marrgins to be seet for driving style
recognitionn was carriedd out. Overlappping the diaagram of drivving experiencce and the friiction circle iin an
intermediaate condition oof constrain (wwet surface), aa new diagramm was createdd, named Drivving Safe Diaggram,
DSD. The behavior of eaach driver wass evaluated by calculating the percentage oof points that aare characterizeed by
values of accelerations higher than thhe limiting eddges of the DSD area. The proposed proocedure alloweed to
establish aa specific thresshold for this ppercentage in order to createe a mobile appplication for a systematic coontrol
of vehicle accelerations during a speccific period of time with the possibility off giving a continuous feedback to
drivers. Thhe mobile appplication couldd be developedd recording thhe accelerationns by means of the GPS receiver
piggybackked on mobile devices. Drivvers can be infformed about the necessity of modifying their driving style
every “x” meters duringg the trip by ffollowing the proposed methhodology. Thee value of x ccould be calcuulated
starting froom the currentt driving speedd. Results showwed that the beest value for diiscriminating bbetween aggressive
94
www.ccsenet.org/mas Modern Applied Science Vol. 8, No. 1; 2014
and non-aggressive behavior can be set to 9% of external points. Outcomes of this study are expected to benefit
both practitioners and researchers. Moreover, further investigations on different types of roads with higher
operative speeds are needed in order to take into account other factors related to the features of the travelled
infrastructure. The results presented in this study represent the first prototype of the M2M project. At the end of
the project Authors expect a much broader data base that will allow to validate and improve further the results
presented in this study.
Acknowledgements
Authors wish to thank Eng. Francesco Diaz and Eng. Alfredo Imparato for have accommodated our equipment
inside the vehicles of FIAT Group S.p.a. (project partners) during certain project activities. Moreover, Authors
thank Eng. Francesco De Masi (chief technician of the Laboratory of Road Infrastructures and Materials,
Department of Civil Engineering) for the support during the experimental phases.
References
Abdulrahim, M. (2006). On the dynamic of automobile drifting. Society of automotive engineers 2006-01-1019
(pp. 168-178).
Alessandrini, A., Cattivera, A., Filippi, F., & Ortenzi, F. (2012). Driving style influence on car CO emissions. In
2
20th International Emission Inventory Conference - "Emission Inventories - Meeting the Challenges Posed
by Emerging Global, National, and Regional and Local Air Quality Issues". Tampa, Florida, August 13 –
16.
Andersson, M., Bruzelius, F., Casselgren, J., Gäfvert, M., Hjort, M., Hultén, J., ... Wälivaara, B. (2007). Road
friction estimation. Saab Automobile AB, Trollhättan, Sweden.
Astarita, V., Caruso, M. V., Danieli, G., Festa, D. C., Giofrè, V. P., Iuele, T., & Vaiana, R. (2012). A mobile
application for road surface quality control: UNIquALroad. Procedia: Social & Behavioral Sciences,
Elsevier, 54, 1135-1144. http://dx.doi.org/10.1016/j.sbspro.2012.09.828
Baldauf, D., Burgard, E., & Wittmann, M. (2009). Time perception as a workload measure in simulated car
driving. Applied Ergonomics, 40(5), 929-935.
Carlson, P. J., Burris, M., Black, K., & Rose, E. R. (2005). Comparison of radius-estimating techniques for
horizontal curves. In Transportation Research Record: Journal of the transportation research board, No
1918, TRB, Washington, D.C.
Chen, Z., Huang, Z., Wu, C., Lv, N., & Ma, J. (2013). Analysis on Vehicle Motion Parameters of Distracted
Driving. Improving Multimodal Transportation Systems-Information, Safety, and Integration (ICTIS 2013)
(pp. 1692-1697). http://dx.doi.org/0.1061/9780784413036.226
Da Lio, M., Biral, F., & Bertolazzi, E. (2005). Combining safety margins and user preferences into a driving
criterion for optimal control-based computation of reference maneuvers for an ADAS of the next generation.
Intelligent Vehicles Symposium. Las Vegas, USA, June 6-8.
Ibraheem, A., & Janan, F. (2011). Developing a computer program for the methods of radius-Estimating
techniques for horizontal curves. American Journal of Engineering and Applied Sciences, 4(2), 276-287.
Jochem, T., Pomerleau, D., Kumar, B., & Amstrong, J. (1995). PANS: A Portable Navigation Platform.
Symposium of Intelligent Vehicles. Detroid, Michigan, USA, September 25-26.
Johnson, D. A., & Trivedi, M. M. (2011). Driving Style Recognition Using a Smartphone as a Sensor Platform.
14th International IEEE Conference on Intelligent Transportation Systems. Washington, DC, USA, October
5-7.
Jun, J., Ko, J., Yoon, S., & Guensler, R. (2006). Impacts of Acceleration Calculation Methods on Onroad Vehicle
Engine Power Estimation. 99th Air & Waste Management Association Annual Meeting. New Orleans,
Louisiana, June 20-23.
Klauer, S. G., Dingus, T. A., Neale, V. L., Sudweeks, J. D., & Ramsey, D. J. (2009). Comparing Real-World
Behaviors of Drivers With High versus Low Rates of Crashes and Near-Crashes. NHTSA Final Letter
Report. Washington, DC, USA.
Lamm, R., Psarianos, B., & Mailaender, T. (1999). Highway Design and Traffic Safety Engineering Handbook.
McGraw-Hill.
Paefgen, J., Kehr, F., Zhai, Y., & Michahelles, F. (2012). Driving Behavior Analysis with Smartphones: Insights
95
www.ccsenet.org/mas Modern Applied Science Vol. 8, No. 1; 2014
from a Controlled Field Study. Proceedings of the 11th International Conference on mobile and ubiquitous
multimedia. Ulm, Germany, December 4-6.
Shaout, A. K., & Bodenmiller, A. E. (2011). A Mobile Application for Monitoring Inefficient and Unsafe Driving
Behaviour. International Arab Conference on Information Technology (ACIT 2011). Naif Arab University
for Security Sciences, Riyadh, Saudi Arabia, December 11-14.
Sievert, W. (1994). The Influence of Modern Electronic Systems in Motor Vehicles on Accident Statistics.
Journal for Traffic Safety, 2, 72-82.
Tonzig, G. (2011). Fondamenti di meccanica classica (3rd ed.). Maggioli Editore.
Vaiana R., Capiluppi G. F., Gallelli, V., Iuele, T., & Minani, V. (2012). Pavement surface performance evolution:
an experimental application. Procedia: Social & Behavioral Sciences, 53, 1150-1161.
http://dx.doi.org/10.1016/j.sbspro.2012.09.964
Yamakado, M., Takahashi, J., Saito, S., & Abe, M. (2009). G-Vectoring: New Vehicle Dynamics Control
Technology for Safe Driving. Industrial Systems, 58(7), December 2009.
Zhang, Y., Owechko, Y., & Zhang, J. (2004). Driver Cognitive Workload Estimation: A Data-driven Perspective.
2004 IEEE Intelligent Transportation Systems Conference, October 3-6. Washington, D.C., USA.

Copyrights
Copyright for this article is retained by the author(s), with first publication rights granted to the journal.
This is an open-access article distributed under the terms and conditions of the Creative Commons Attribution
license (http://creativecommons.org/licenses/by/3.0/).
96