@article{ac526159a15e47dbb81c626d23063763,
title = "Crash risk assessment of off-ramps, based on the gaussian mixture model using video trajectories",
abstract = "The focus of this paper is the crash risk assessment of off-ramps in Xi'an. The time-to-collision (TTC) is used for the measurement and cross-comparison of the crash risk of each location. Five sites from the urban expressway in Xi'an were selected to explore the TTC distribution. An unmanned aerial vehicle and a camera were used to collect traffic flow data for 20 min at each site. The parameters, including speed, deceleration rate, truck percentage, traffic volume, and vehicle trajectories, were extracted from video images. The TTCs were calculated for each vehicle. The Gaussian mixture model (GMM) was proposed to predict the TTC probability density functions (PDFs) and cumulative density functions (CDFs) for five sites. The Kolmogorov-Smirnov (K-S) test indicated that the samples followed the estimated GMM distribution. The relationship between the crash risk level and influencing factors was studied by an ordinal logistic regression model and a naive Bayesian model. The results showed that the naive Bayesian model had an accuracy of 86.71%, while the ordinal logistic regression model had an accuracy of 84.81%. The naive Bayesian model outperformed the ordinal logistic regression model, and it could be applied to the real-time collision warning system.",
keywords = "E-M algorithm, Gaussian mixture model, Naive bayesian, Ordinal logistic regression model, Risk assessment, Time-to-collision",
author = "Ting Xu and Yanjun Hao and Shichao Cui and Xingqi Wu and Zhishun Zhang and Chien, {Steven I.Jy} and Yulong He",
note = "Funding Information: This research was funded by the National Natural Science Foundation of China under Grant U1664264 and Grant No.51878066, Funds for Central Universities and Colleges of Chang'an University (No.300102229201 and No.300102220204), the Major scientific and technological innovation projects of Shandong Province under Grant No.2019JZZY020904, and Xi'an scientific and technological projects under Grant No.2019218514GXRC021CG022-GXYD21.5. Funding Information: Author Contributions: Conceptualization, T.X. and S.I.-J.C.; formal analysis, Y.H. (Yanjun Hao) and S.C.; iinnvveessttiiggaattiioonn,, SS.C.C.,.,XX.W.W. a.nadnZd.ZZ.;.Zm.;e tmhoedthoolodgoyl,oTg.yX,. aTn.Xd.Sa.In.-dJ. CS..;Is.-oJf.Ctw.;a sreo,ftYw.Ha.re(Y, aYn.jHun. H(Yaaon)juannd HS.aCo.); vaanlidd aSt.iCon.;, validation, T.X., Y.H. (Yulong He) and X.W.; writing, original draft, Y.H. (Yanjun Hao) and Z.Z.; writing, review T.X., Y.H. (Yanjun Hao) and Y.H. (Yulong He). All authors have read and agreed to the published version of and editing, T.X., Y.H. (Yanjun Hao) and Y.H. (Yulong He). the manuscript. Funding: This research was funded by the National Natural Science Foundation of China under Grant U1664264 Funding: This research was funded by the National Natural Science Foundation of China under Grant U1664264 and Grant No.51878066, Funds for Central Universities and Colleges of Chang{\textquoteright}an University a(Nndo .N30o0.1300202120922202102a0n4d),N thoe.3M00a1j0o2r2 s2c0i2e0n4ti)f,itch aenMd atjeocrhsncoielongtiifcicala inndnotevcahtnioonlo pgriocajelcitnsn oofv Sahtiaonndpornogje cPtrsoovfinSchea nudnodnegr Province under Grant No.2019JZZY020904, and Xi{\textquoteright}an scientific and technological projects under Grant No.2019218514GXRC021CG022-GXYD21.5. Publisher Copyright: {\textcopyright} 2020 by the authors.",
year = "2020",
month = apr,
day = "1",
doi = "10.3390/SU12083076",
language = "English (US)",
volume = "12",
pages = "3076",
journal = "Sustainability",
issn = "2071-1050",
publisher = "MDPI AG",
number = "8",
}