Skip to main content
Top
Published in: Arabian Journal for Science and Engineering 10/2020

22-05-2020 | Research Article-Civil Engineering

Estimation of Traffic Incident Duration: A Comparative Study of Decision Tree Models

Authors: Abdulsamet Saracoglu, Halit Ozen

Published in: Arabian Journal for Science and Engineering | Issue 10/2020

Log in

Activate our intelligent search to find suitable subject content or patents.

search-config
loading …

Abstract

Unexpected events such as crashes, disabled vehicles, flat tires and spilled loads cause traffic congestion or extend the duration of the traffic congestion on the roadways. It is possible to reduce the effects of such incidents by implementing intelligent transportation systems solutions that require the estimation of the incident duration to identify well-fitted strategies. This paper presents a methodology to establish incident duration estimation models by utilizing decision tree models of CHAID, CART, C4.5 and LMT. For this study, the data contained traffic incidents that occurred on the Istanbul Trans European Motorway were obtained and separated into three groups according to duration by utilizing some studies about classification of traffic incidents. By using classified data, decision tree models of CHAID, CART, C4.5 and LMT were established and validated to estimate the incident duration. According to the results, although the models used different variables, the decision tree models of CHAID, CART and C4.5 have nearly the same prediction accuracy which is approximately 74%. On the other hand, the prediction accuracy of decision tree model of LMT is 75.4% which is somewhat better than the others. However, C4.5 model required less number of parameters than the others, while its accuracy is the same with others.

Dont have a licence yet? Then find out more about our products and how to get one now:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

Literature
1.
go back to reference Chang, H.-L.; Chang, T.-P.: Prediction of freeway incident duration based on classification tree analysis. In: 10th EASTS Conference, 9–12 Sept 2013, Taipei (2013) Chang, H.-L.; Chang, T.-P.: Prediction of freeway incident duration based on classification tree analysis. In: 10th EASTS Conference, 9–12 Sept 2013, Taipei (2013)
2.
go back to reference Nam, D.; Mannering, F.: An exploratory hazard-based analysis of highway incident duration. Transp. Res. A 34, 85–102 (2000) Nam, D.; Mannering, F.: An exploratory hazard-based analysis of highway incident duration. Transp. Res. A 34, 85–102 (2000)
3.
go back to reference Chung, Y.: Development of an accident duration prediction model on the korean freeway systems. Accid. Anal. Prev. 42, 282–289 (2010)CrossRef Chung, Y.: Development of an accident duration prediction model on the korean freeway systems. Accid. Anal. Prev. 42, 282–289 (2010)CrossRef
4.
go back to reference Wei, C.-H.; Lee, Y.: Sequential forecast of incident duration using artificial neural network models. Accid. Anal. Prev. 39, 944–954 (2007)CrossRef Wei, C.-H.; Lee, Y.: Sequential forecast of incident duration using artificial neural network models. Accid. Anal. Prev. 39, 944–954 (2007)CrossRef
5.
go back to reference Shin, C.-H.: Development of freeway incident duration prediction models. J East Asia Soc Transp Stud 5, 1734–1744 (2003) Shin, C.-H.: Development of freeway incident duration prediction models. J East Asia Soc Transp Stud 5, 1734–1744 (2003)
6.
go back to reference Lopes, J.; Bento, J.; Pereira, F.C.; Ben-Akiva, M.: Dynamic forecast of incident clearance time using adaptive artificial neural network models. TRB 2013 Annual Meeting, 13–17 Jan 2013, Washington (2012) Lopes, J.; Bento, J.; Pereira, F.C.; Ben-Akiva, M.: Dynamic forecast of incident clearance time using adaptive artificial neural network models. TRB 2013 Annual Meeting, 13–17 Jan 2013, Washington (2012)
7.
go back to reference Wang, X.; Chen, S.; Zheng,W.: Analysis of regression method on traffic incident duration. In: ASCE 2013 International Conference on Transportation Information and Safety, 29 June–2 July 2013, Wuhan (2013) Wang, X.; Chen, S.; Zheng,W.: Analysis of regression method on traffic incident duration. In: ASCE 2013 International Conference on Transportation Information and Safety, 29 June–2 July 2013, Wuhan (2013)
8.
go back to reference Garib, A.; Radwan, E.; Al-Deek, H.: Estimating magnitude and duration of incident delays. J Transp Eng 123, 459–466 (1997)CrossRef Garib, A.; Radwan, E.; Al-Deek, H.: Estimating magnitude and duration of incident delays. J Transp Eng 123, 459–466 (1997)CrossRef
9.
go back to reference Sullivan, E.C.: New model for predicting freeway incidents and incident delays. J Transp Eng 123, 267–275 (1997)CrossRef Sullivan, E.C.: New model for predicting freeway incidents and incident delays. J Transp Eng 123, 267–275 (1997)CrossRef
10.
go back to reference Hojati, A.T.; Ferreira, L.; Washington, S.; Charles, P.; Shobeirinejad, A.: Modelling total duration of traffic incidents including incident detection and recovery time. Accid. Anal. Prev. 71, 296–305 (2014)CrossRef Hojati, A.T.; Ferreira, L.; Washington, S.; Charles, P.; Shobeirinejad, A.: Modelling total duration of traffic incidents including incident detection and recovery time. Accid. Anal. Prev. 71, 296–305 (2014)CrossRef
11.
go back to reference Lin, L.; Wang, Q.; Sadek, A.W.: A combined M5P tree and hazard-based duration model for predicting urban freeway traffic accident durations. Accid. Anal. Prev. 91(2016), 114–126 (2016)CrossRef Lin, L.; Wang, Q.; Sadek, A.W.: A combined M5P tree and hazard-based duration model for predicting urban freeway traffic accident durations. Accid. Anal. Prev. 91(2016), 114–126 (2016)CrossRef
12.
go back to reference Chimba, D.; Kutela, B.; Ogletree, G.; Horne, H.; Tugwell, M.: Impact of abandoned and disabled vehicles on freeway incident duration. J Transp Eng 140(3), 04013013(8) (2014)CrossRef Chimba, D.; Kutela, B.; Ogletree, G.; Horne, H.; Tugwell, M.: Impact of abandoned and disabled vehicles on freeway incident duration. J Transp Eng 140(3), 04013013(8) (2014)CrossRef
13.
go back to reference Wang, X.; Chen, S.; Gu, J.; Zhen, W.:. Traffic incident duration analysis based on cyclic subspace regression. In: ASCE 2013 Fourth International Conference on Transportation Engineering, 19–20 Oct 2013, Chengdu (2013) Wang, X.; Chen, S.; Gu, J.; Zhen, W.:. Traffic incident duration analysis based on cyclic subspace regression. In: ASCE 2013 Fourth International Conference on Transportation Engineering, 19–20 Oct 2013, Chengdu (2013)
14.
go back to reference Wu, W.; Chen, S.; Zheng, C.: Traffic incident duration prediction based on support vector regression. In: ASCE 2011 Eleventh International Conference of Chinese Transportation Professionals, 14–17 Aug 2011, Nanjing (2011) Wu, W.; Chen, S.; Zheng, C.: Traffic incident duration prediction based on support vector regression. In: ASCE 2011 Eleventh International Conference of Chinese Transportation Professionals, 14–17 Aug 2011, Nanjing (2011)
15.
go back to reference Wanga, X.; Chena, S.; Zheng, W.: Traffic incident duration prediction based on partial least squares regression. Procedia Soc Behav Sci 96, 425–432 (2013)CrossRef Wanga, X.; Chena, S.; Zheng, W.: Traffic incident duration prediction based on partial least squares regression. Procedia Soc Behav Sci 96, 425–432 (2013)CrossRef
16.
go back to reference Khattak, A.J.; Schofer, J.L.; Wang, M.-H.: A simple time sequential procedure for predicting freeway incident duration. IVHS J 2(2), 113–138 (1995) Khattak, A.J.; Schofer, J.L.; Wang, M.-H.: A simple time sequential procedure for predicting freeway incident duration. IVHS J 2(2), 113–138 (1995)
17.
go back to reference Wang, W.; Chen, H.; Bell, M.: A study of the characteristics of traffic incident duration on motorways. In: International Conference on Traffic and Transportation Studies (ICTTS), 23–25 July 2002, Guilin (2002) Wang, W.; Chen, H.; Bell, M.: A study of the characteristics of traffic incident duration on motorways. In: International Conference on Traffic and Transportation Studies (ICTTS), 23–25 July 2002, Guilin (2002)
18.
go back to reference Ozbay, K.; Noyan, N.: Estimation of incident clearance times using Bayesian networks approach. Accid. Anal. Prev. 38, 542–555 (2006)CrossRef Ozbay, K.; Noyan, N.: Estimation of incident clearance times using Bayesian networks approach. Accid. Anal. Prev. 38, 542–555 (2006)CrossRef
19.
go back to reference Park, H.; Zhang, X.; Haghani, A.: ATIS: interpretation of Bayesian neural network for predicting the duration of detected incidents. In: TRB 2013 Annual Meeting, 13–17 Jan 2013, Washington (2013) Park, H.; Zhang, X.; Haghani, A.: ATIS: interpretation of Bayesian neural network for predicting the duration of detected incidents. In: TRB 2013 Annual Meeting, 13–17 Jan 2013, Washington (2013)
20.
go back to reference Yang, B.J.; Zhang, X.; Sun, L.: Traffic incident duration prediction based on the Bayesian decision tree method. In: First International Symposium on Transportation and Development Innovative Best Practices, 24–26 Apr 2008, Beijing (2008) Yang, B.J.; Zhang, X.; Sun, L.: Traffic incident duration prediction based on the Bayesian decision tree method. In: First International Symposium on Transportation and Development Innovative Best Practices, 24–26 Apr 2008, Beijing (2008)
21.
go back to reference Li, R.; Pereira, F.C.; Ben-Akiva, M.E.: Competing risks mixture model for traffic incident duration prediction. Accid. Anal. Prev. 75(2015), 192–201 (2015)CrossRef Li, R.; Pereira, F.C.; Ben-Akiva, M.E.: Competing risks mixture model for traffic incident duration prediction. Accid. Anal. Prev. 75(2015), 192–201 (2015)CrossRef
22.
go back to reference Li, R.; Pereira, F.C.; Ben-Akiva, M.E.: Competing risk mixture model and text analysis for sequential incident duration prediction. Transp. Res. C 54(2015), 74–85 (2015)CrossRef Li, R.; Pereira, F.C.; Ben-Akiva, M.E.: Competing risk mixture model and text analysis for sequential incident duration prediction. Transp. Res. C 54(2015), 74–85 (2015)CrossRef
23.
go back to reference Ozen, H.; Saracoglu, A.: Multi-step approach to improving accuracy of incident duration estimation: case study of Istanbul. Tehnički vjesnik 26(6), 1777–1783 (2019) Ozen, H.; Saracoglu, A.: Multi-step approach to improving accuracy of incident duration estimation: case study of Istanbul. Tehnički vjesnik 26(6), 1777–1783 (2019)
24.
go back to reference Al-Ruzouq, R.; Hamad, K.; Dabous, S.A.; Zeiada, W.; Khalil, M.A.; Voigt, T.: Weighted multi-attribute framework to identify freeway incident hot spots in a spatiotemporal context. Arab J Sci Eng 44, 8205–8223 (2019)CrossRef Al-Ruzouq, R.; Hamad, K.; Dabous, S.A.; Zeiada, W.; Khalil, M.A.; Voigt, T.: Weighted multi-attribute framework to identify freeway incident hot spots in a spatiotemporal context. Arab J Sci Eng 44, 8205–8223 (2019)CrossRef
25.
go back to reference Zhang, H.; Zhang, Y.; Khattak, A.: Analysis of large-scale incidents on urban freeways. TRB 2012 Annual Meeting, 22-26 January 2012, Washington (2012) Zhang, H.; Zhang, Y.; Khattak, A.: Analysis of large-scale incidents on urban freeways. TRB 2012 Annual Meeting, 22-26 January 2012, Washington (2012)
26.
go back to reference Smith, K.W.; Smith, B.L.: Forecasting the clearance time of freeway accidents. Report No. UVACTS-15-0-35. Center for Transportation Studies. University of Virginia (2001) Smith, K.W.; Smith, B.L.: Forecasting the clearance time of freeway accidents. Report No. UVACTS-15-0-35. Center for Transportation Studies. University of Virginia (2001)
27.
go back to reference Lin, P.; Zou, N.; Chang, G.: Integration of a discrete choice model and a rule-based system for estimation for incident duration: a case study in MaryLand. In: TRB 83rd Annual Meeting, 11–15 Jan 2004, Washington (2004) Lin, P.; Zou, N.; Chang, G.: Integration of a discrete choice model and a rule-based system for estimation for incident duration: a case study in MaryLand. In: TRB 83rd Annual Meeting, 11–15 Jan 2004, Washington (2004)
28.
go back to reference Texas Department of Transportation: Texas Manual on Uniform Traffic Control Devices (TMUTCD), 2006 Edition, Revision 1, Texas (2006) Texas Department of Transportation: Texas Manual on Uniform Traffic Control Devices (TMUTCD), 2006 Edition, Revision 1, Texas (2006)
29.
go back to reference Federal Highway Administration (FWHA): Manual on Uniform Traffic Control Devices (MUTCD) for Streets and Highways, 2009 Edition, Washington (2009) Federal Highway Administration (FWHA): Manual on Uniform Traffic Control Devices (MUTCD) for Streets and Highways, 2009 Edition, Washington (2009)
30.
go back to reference Chattanooga-Hamilton County Regional Planning Agency and Transportation Planning Division: Chattanooga urban area highway incident management plan, Tennessee (2010) Chattanooga-Hamilton County Regional Planning Agency and Transportation Planning Division: Chattanooga urban area highway incident management plan, Tennessee (2010)
31.
go back to reference Istanbul Metropolitan Municipality Transportation Coordination Center (UKOME): Regulation#2005/2-5, Istanbul (2005) Istanbul Metropolitan Municipality Transportation Coordination Center (UKOME): Regulation#2005/2-5, Istanbul (2005)
32.
go back to reference Arguden, Y.; Ersahin, B.: Veri Madenciliği: Veriden Bilgiye, Masraftan Değere. ARGE Consulting Publications, Istanbul (2008) Arguden, Y.; Ersahin, B.: Veri Madenciliği: Veriden Bilgiye, Masraftan Değere. ARGE Consulting Publications, Istanbul (2008)
33.
go back to reference Tomei, L.A.: Encyclopedia of Information Technology Curriculum Integration”. IGI Global Information Science Reference, Hershey (2008)CrossRef Tomei, L.A.: Encyclopedia of Information Technology Curriculum Integration”. IGI Global Information Science Reference, Hershey (2008)CrossRef
34.
go back to reference Shmueli, G.; Patel, N.R.; Bruce, P.C.: Data Mining for Business Intelligence: Concepts, Techniques, and Applications in Microsoft Office Excel with XLMiner, 2nd edn. Wiley, New Jersey (2010) Shmueli, G.; Patel, N.R.; Bruce, P.C.: Data Mining for Business Intelligence: Concepts, Techniques, and Applications in Microsoft Office Excel with XLMiner, 2nd edn. Wiley, New Jersey (2010)
35.
go back to reference Chang, L.-Y.; Wang, H.-W.: Analysis of traffic injury severity: an application of non-parametric classification tree techniques. Accid. Anal. Prev. 38(5), 1019–1027 (2006)CrossRef Chang, L.-Y.; Wang, H.-W.: Analysis of traffic injury severity: an application of non-parametric classification tree techniques. Accid. Anal. Prev. 38(5), 1019–1027 (2006)CrossRef
36.
go back to reference Ruggieri, S.: Efficient C4.5 [classification algorithm]. IEEE Trans. Knowl. Data eng. 14(2), 438–444 (2002)CrossRef Ruggieri, S.: Efficient C4.5 [classification algorithm]. IEEE Trans. Knowl. Data eng. 14(2), 438–444 (2002)CrossRef
37.
go back to reference Landwehr, N.; Hall, M.; Frank, E.: Logistic model trees. Mach. Learn. 59(1–2), 161–205 (2005)CrossRef Landwehr, N.; Hall, M.; Frank, E.: Logistic model trees. Mach. Learn. 59(1–2), 161–205 (2005)CrossRef
Metadata
Title
Estimation of Traffic Incident Duration: A Comparative Study of Decision Tree Models
Authors
Abdulsamet Saracoglu
Halit Ozen
Publication date
22-05-2020
Publisher
Springer Berlin Heidelberg
Published in
Arabian Journal for Science and Engineering / Issue 10/2020
Print ISSN: 2193-567X
Electronic ISSN: 2191-4281
DOI
https://doi.org/10.1007/s13369-020-04615-2

Other articles of this Issue 10/2020

Arabian Journal for Science and Engineering 10/2020 Go to the issue

Premium Partners