Continuous risk profile and clustering-based method for investigating the effect of the automated enforcement system on urban traffic collisions

  • Shin Hyung Park
  • Shin Hyoung Park
  • Oh Hoon KwonEmail author
  • Yunsick Sung


The automated enforcement systems (AESs), which detect speeding vehicles or vehicles that violate traffic signals, are installed and operated on urban arterial roadways to prevent traffic collisions and reduce injury severity in case of a traffic collision. As it is expensive to install the AES, it will be installed at a site where it is expected to have a great effect. However, as there are no specific guidelines on where it should be installed, it has been installed arbitrarily in high collision concentration locations (HCCLs). The objective of this study is to contribute to the improvement in the efficiency of system operation and budget execution by identifying sites where the enforcement effect of the AES is high, and providing a road manager with the basis of decision-making on system installation. This study classified road sections into clusters based on road environment characteristics and spatial collision occurrence pattern, respectively, and compared collisions statistics and occurrence pattern before and after AES installation to analyze the effect of AES installation. As a result, the study verified that the number of collisions tends to decrease at HCCLs past enforcement sites, while the number of collisions tends to increase at sites where not only red light running but also speeding is enforced after AES installation. In addition, from the perspective of collision severity, it was observed that the severity of collisions was alleviated in most clusters after AES installation. This may be viewed as a positive effect caused by the decrease in vehicle speed due to speeding enforcement.


Automated enforcement system Red light running Continuous risk profile Clustering analysis Traffic collision 



This research was supported by a Grant (18RDRP-B076268-05) from the R&D program funded by the Ministry of Land, Infrastructure and Transport of the Korean government.


  1. 1.
    Gettman D, Head L (2003) Surrogate safety measures from traffic simulation models. Transp Res Rec J Transp Res Board 1840:104–115CrossRefGoogle Scholar
  2. 2.
    Hayward J C (1972) Near miss determination through use of a scale of danger. In: Highway Research Record 384Google Scholar
  3. 3.
    Garber NJ, Gadirau R (1988) Speed variance and its influence on accidents. In: AAA Foundation for Traffic SafetyGoogle Scholar
  4. 4.
    Taylor MC, Lynam DA, Baruya A (2000) The effects of drivers’ speed on the frequency of road accidents. Transport Research Laboratory, CrowthorneGoogle Scholar
  5. 5.
    Shen J, Gan A (2003) Development of crash reduction factors: methods, problems, and research needs. Transp Res Rec J Transp Res Board 1840:50–56CrossRefGoogle Scholar
  6. 6.
    Persaud BN (2001) Statistical methods in highway safety analysis. Transportation Research Board, Washington DCGoogle Scholar
  7. 7.
    Hauer E (1997) Observational before/after studies in road safety: Estimating the effect of highway and traffic engineering measures on road safety. Emerald Group Publishing, BingleyGoogle Scholar
  8. 8.
    Ko M, Geedipally SR, Walden TD, Wunderlich RC (2017) Effects of red light running camera systems installation and then deactivation on intersection safety. J Saf Res 62:117–126. CrossRefGoogle Scholar
  9. 9.
    Shin K, Washington S (2007) The impact of red light cameras on safety in Arizona. Accid Anal Prev 39(6):1212–1221. CrossRefGoogle Scholar
  10. 10.
    Lee Y, Li Z, Zhang S, Roshandeh AM, Patel H, Liu Y (2014) Safety impacts of red light running photo enforcement at urban signalized intersections. J Traffic Transp Eng (Engl Ed) 1(5):309–324. CrossRefGoogle Scholar
  11. 11.
    Erke A (2009) Red light for red-light cameras?: a meta-analysis of the effects of red-light cameras on crashes. Accid Anal Prev 41(5):897–905. CrossRefGoogle Scholar
  12. 12.
    Pulugurtha SS, Otturu R (2014) Effectiveness of red light running camera enforcement program in reducing crashes: evaluation using “before the installation”, “after the installation”, and “after the termination” data. Accid Anal Prev 64:9–17. CrossRefGoogle Scholar
  13. 13.
    Retting RA, Ferguson SA, Hakkert AS (2003) Effects of red light cameras on violations and crashes: a review of the international literature. Traffic Inj Prev 4(1):17–23. CrossRefGoogle Scholar
  14. 14.
    Shaaban K, Pande A (2018) Evaluation of red-light camera enforcement using traffic violations. J Traffic Transp Eng (Engl Ed) 5(1):66–72. CrossRefGoogle Scholar
  15. 15.
    Hu W, McCartt AT, Teoh ER (2011) Effects of red light camera enforcement on fatal crashes in large US cities. J Saf Res 42(4):277–282. CrossRefGoogle Scholar
  16. 16.
    Porter BE, Johnson KL, Bland JF (2013) Turning off the cameras: red light running characteristics and rates after photo enforcement legislation expired. Accid Anal Prev 50:1104–1111. CrossRefGoogle Scholar
  17. 17.
    Walden TD, Geedipally S, Ko M, Gillbert R, Perez M (2011) Evaluation of automated traffic Enforcement systems in Texas. Texas Transportation Institute, TexasGoogle Scholar
  18. 18.
    Andersson G, Larsson J (2005) Automatic speed cameras in Sweden 2002–2003. Statens väg-och transportforsknings-institut, LinköpingGoogle Scholar
  19. 19.
    Shim J, Park SH, Chung S, Jang K (2015) Enforcement avoidance behavior near automated speed enforcement areas in Korean expressways. Accid Anal Prev 80:57–66. CrossRefGoogle Scholar
  20. 20.
    Han J, Pei J, Kamber M (2011) Data mining: concepts and techniques. Elsevier, New YorkzbMATHGoogle Scholar
  21. 21.
    Warren Liao T (2005) Clustering of time series data—a survey. Pattern Recognit 38(11):1857–1874. CrossRefzbMATHGoogle Scholar
  22. 22.
    Kumar Y, Sahoo G (2017) An improved cat swarm optimization algorithm based on opposition-based learning and cauchy operator for clustering. J Inf Process Syst 13(4):1000–1013Google Scholar
  23. 23.
    Dadashova B, Ramírez BA, McWilliams JM, Izquierdo FA (2016) The identification of patterns of interurban road accident frequency and severity using road geometry and traffic indicators. Transp Res Proc 14:4122–4129CrossRefGoogle Scholar
  24. 24.
    Kononov J, Janson B (2002) Diagnostic methodology for the detection of safety problems at intersections. Transp Res Rec J Transp Res Board 1784:51–56CrossRefGoogle Scholar
  25. 25.
    Kumar S, Toshniwal D (2016) Analysis of hourly road accident counts using hierarchical clustering and cophenetic correlation coefficient (CPCC). J Big Data 3(1):13. CrossRefGoogle Scholar
  26. 26.
    Depaire B, Wets G, Vanhoof K (2008) Traffic accident segmentation by means of latent class clustering. Accid Anal Prev 40(4):1257–1266. CrossRefGoogle Scholar
  27. 27.
    Oates T, Firoiu L, Cohen PR (1999) Clustering time series with hidden markov models and dynamic time warping. In: Proceedings of the IJCAI-99 Workshop on Neural, Symbolic and Reinforcement Learning Methods for Sequence Learning, pp 17–21Google Scholar
  28. 28.
    Chung K, Jang K, Madanat S, Washington S (2011) Proactive detection of high collision concentration locations on highways. Transp Res Part A Policy Pract 45(9):927–934CrossRefGoogle Scholar
  29. 29.
    Wagstaff K, Cardie C, Rogers S, Schrödl S (2001) Constrained k-means clustering with background knowledge. In: ICLM, pp 577–584Google Scholar
  30. 30.
    Sriwanna K, Boongoen T, Iam-On N (2017) Graph clustering-based discretization of splitting and merging methods (GraphS and GraphM). Hum Centric Comput Inf Sci 7(1):21CrossRefGoogle Scholar
  31. 31.
    Karypis G, Han EH, Kumar V (1999) Chameleon: hierarchical clustering using dynamic modeling. Computer 32(8):68–75CrossRefGoogle Scholar
  32. 32.
    Székely GJ, Rizzo ML, Bakirov NK (2007) Measuring and testing dependence by correlation of distances. Ann Stat 35:2769–2794MathSciNetCrossRefzbMATHGoogle Scholar
  33. 33.
    Sarker MK, Song MK (2016) Segmentation and recognition of korean vehicle license plate characters based on the global threshold method and the cross-correlation matching algorithm. J Inf Process Syst 12(4):661–680. Google Scholar
  34. 34.
    Korea Ministry of Government Legislation (2018) National Land Planning and Utilization Act, South KoreaGoogle Scholar
  35. 35.
    Hair JF, Black WC, Babin BJ, Anderson RE, Tatham RL (1998) Multivariate data analysis, vol 5. Prentice hall Upper Saddle River, New JerseyGoogle Scholar
  36. 36.
    Park SH, Jang K, Kim DK, Kho SY, Kang S (2015) Spatial analysis methods for identifying hazardous locations on expressways in Korea. Sci Iran Trans B Mech Eng 22(4):1594Google Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2019

Authors and Affiliations

  1. 1.Department of Transportation EngineeringKeimyung UniversityDaeguRepublic of Korea
  2. 2.Department of Multimedia EngineeringDongguk University-SeoulSeoulRepublic of Korea

Personalised recommendations