文档下载 文档下载导航
设为首页 | 加入收藏
搜索 请输入内容:  
 导航当前位置: 文档下载 > 所有分类 > 自然科学 > 数学 > 2104数学建模美赛A 交通流 安全性 参考资料 交通量
侵权投诉

2104数学建模美赛A 交通流 安全性 参考资料 交通量

2104数学建模美赛A 交通流 安全性 参考资料 交通量

Table1.AccidentCharacteristicsUsedintheAnalyses(N 1192)Variableandcategory

Collisiontype

SinglevehiclehitobjectoroverturnMultiplevehiclehitobjectoroverturnTwo-vehicleweavingaccidenta

Three-or-more-vehicleweavingaccidentaTwo-vehiclestraight-onrearend

Three-or-more-vehiclestraight-onrearendCollisionLocation

Off-road,driver’sleftLeftlane

Interiorlane s Rightlane

Offroad,driver’srightSeverity

PropertydamageonlyInjuryorfatalityb

Percentofsample14.25.919.35.533.821.313.825.832.719.38.371.928.1

Sideswipeorrear-endaccidentinvolvinglanechangeorotherturningmaneuver.b

Therewereonly vefatalaccidents.

Traf cFlowCharacteristics

Twelvevariableswerecomputedfromtheloopdetectordata.Thesewereorganizedintofourblocksofthreevariableseach onevariableforeachofthethreelanetypedesignations:left,interior,andright .Thefourblocksareasfollows:

The rstoftheseblocksisanindicatorofprevailingtraf cspeed.Thesethreevariablesmeasurethecentraltendencyoftheratioofvolumetooccupancy.Thisratioistypicallyas-sumedtobeproportionaltothespacemeanspeed.Forex-ample,underassumptionsofstationary ow,andanaveragevehiclelengthof5.49m 18ft ,avolume/occupancy V/O ratioof90wouldtranslatetoaspacemeanspeedestimateof49.2km/h 30.6mph .Median,ratherthanmean,isusedinordertoavoidthein uenceofoutlyingobservationsthatcanbeduetofailureoftheloopdetectors.

Thesecondblockrepresentsthetemporalvariationofthepre-vailingspeed.Becausewewishtominimizethein uenceofpotentiallyinvalidobservationsandtheeffectsofoutliers,weusethedifferenceofthe90thpercentileand50thpercentileofthedistributionofvolumeoveroccupancytocapturevariation. Thethirdblockmeasuresthecentraltendencyoftraf cvol-umeovertheperiod.Volumealoneisnotassensitivetoout-liersasistheratioofvolumetooccupancy,someanisused

Table2.BreakdownofSamplebyWeatherandAmbientLighting

Conditions

Weathera

Lighting

Daylight

DuskordawnDark—streetlightsDark—nostreetlightsTotalbyweathercondition

b

Dry78930951211,035

Wet1013b3220156

Totalbylighting890331271411,191

Basedonconditionoftheroadwaysurface wetordry .Eliminatedfromfurtheranalyses.

ratherthanmedian.Meanandmedianvaluesarequitesimilarforthesedata,soeithercanbeusedwithoutaffectingresults. Thefourthand nalblockmeasuresvariationinvolumeovertheperiod.Hereweusestandarddeviation,butthedifferencebetweenthe90thpercentileand50thpercentilescanbeusedwithoutaffectingtheresults.

Ourobjectiveistorelatethesetraf c owvariablestoacci-dentcharacteristics.However,werecognizethatthethreevari-ablesineachofthefourblocksmightbehighlycorrelatedifthe owcharacteristicbeingmeasuredisconsistentacrossthethreefreewaylanes;yet,itisnotknownhowwellspeedandvolumevariancesindifferentlanesarelinked.Tobetterunderstandthecorrelationstructureofthesetwelvevariables,andtoremoveun-necessaryredundancyfromthissetoftwelvevariablessothatwecaninterpretresultsaccurately,principalcomponentsanalysis PCA wasperformed.Theobjectivewastoextractarelativelylargenumberoffactorsinordertoidentifyindependenttraf c owvariableswhilesimultaneouslydiscardingaslittleoftheinformationintheoriginalvariablesaspossible.Sixfactorswerefoundtoaccountfor87.5%ofthevarianceintheoriginal12variables,andVarimaxrotationwasperformedtoaidininterpret-ingthefactors.Thefactorloadings,whicharethecorrelationsbetweentheoriginalvariablesandtherotatedfactors,arelistedinTable3,togetherwiththevariancesaccountedforbyeachrotatedfactor.Onevariablewasthenselectedtorepresenteachfactorinthesubsequentstagesoftheanalysis.

Factor1:Thefactorloadingsshowthatthecentraltendencyofspeed VariableBlock1 ishighlycorrelatedacrossallthreelanes.Thevariablechosentorepresentthiscentraltendencyofspeedfactoris‘‘medianvolume/occupancyintheinteriorlane.’’

Factor2:Asinglefactorencompassesthecentraltendencyofvolume VariableBlock3 inallthreelanes,butthefactorismorerepresentativeofvolumesintheleftandinteriorlanesthanintherightlane,aswitnessedbythelowercorrelationbetweenthisfactorandrightlanemeanvolume 0.742 .Al-thoughthefactorloadingfor‘‘meanvolumeintheinteriorlane’’isgreater,‘‘meanvolumeintheleftlane’’ischosentorepresentthisfactorinallfurtheranalysesbasedonitsconsis-tentlystrongloadingsonboththisfactorandFactor3 seebelow .

Factor3:Thethirdfactorrepresentsthetemporalvariationinvolumeintheleftandinteriorlanes.Variationinvolumeintherightlane,whichhasarelativelylowcorrelationof0.366withthisfactor,iscapturedbyaseparatefactor seeFactor6,below .Ourinterpretationisthattherightmostlanevolumeisin uencedsigni cantlybyfreewayon-andoff-ramps,whiletraf cintheleftandinteriorlanesisprincipallycomprisedofvehiclesthatarelessimpactedbyweavingtraf cinthevicin-ityoftheramps.‘‘Variationinvolumeintheleftlane’’ischosentorepresenttemporalvariationsinvolumesontheleftandinteriorlanes.

Factor4:Asinthecaseofthetemporalvariationinvolumes,thePCAresultsshowthattemporalvariationinspeedinthethreelanesalsoispartitionedintotwofactors.Hereagain,theimplicationisthatspeedintherightmostlane,whichhasadirectin uenceonthelevelofserviceinthevicinityoffree-wayon-andoff-ramps,variesoverrelativelyshortperiodsoftimeinadifferentwaythandoesmainlinefreewayspeeds.‘‘Variationinvolumeintheinteriorlane’’ischosentorepre-sentFactor4.

Factor5:‘‘Variationsinvolumetooccupancyratiointheright

344/JOURNALOFTRANSPORTATIONENGINEERING©ASCE/JULY/AUGUST2003

上一页第3页

你可能喜欢

  • 道路通行能力
  • 元胞自动机
  • 美国数学建模
  • 美赛论文
  • 数学建模美赛
  • 篮球教练
  • 交通安全

热门文档

相关文档

站点地图 | 文档上传 | 侵权投诉 | 手机版
本站所有资源均来自互联网,本站只负责收集和整理,均不承担任何法律责任,如有侵权等其它行为请联系我们.
文档下载 Copyright 2013 doc.guandang.net All Rights Reserved.  -  email