Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Skip to main content

Advertisement

Springer Nature Link
Log in

Geospatial and machine learning techniques for wicked social science problems: analysis of crash severity on a regional highway corridor

  • Original Article
  • Published:
Journal of Geographical Systems Aims and scope Submit manuscript

Abstract

The contention of this paper is that many social science research problems are too “wicked” to be suitably studied using conventional statistical and regression-based methods of data analysis. This paper argues that an integrated geospatial approach based on methods of machine learning is well suited to this purpose. Recognizing the intrinsic wickedness of traffic safety issues, such approach is used to unravel the complexity of traffic crash severity on highway corridors as an example of such problems. The support vector machine (SVM) and coactive neuro-fuzzy inference system (CANFIS) algorithms are tested as inferential engines to predict crash severity and uncover spatial and non-spatial factors that systematically relate to crash severity, while a sensitivity analysis is conducted to determine the relative influence of crash severity factors. Different specifications of the two methods are implemented, trained, and evaluated against crash events recorded over a 4-year period on a regional highway corridor in Northern Iran. Overall, the SVM model outperforms CANFIS by a notable margin. The combined use of spatial analysis and artificial intelligence is effective at identifying leading factors of crash severity, while explicitly accounting for spatial dependence and spatial heterogeneity effects. Thanks to the demonstrated effectiveness of a sensitivity analysis, this approach produces comprehensive results that are consistent with existing traffic safety theories and supports the prioritization of effective safety measures that are geographically targeted and behaviorally sound on regional highway corridors.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10

Similar content being viewed by others

Notes

  1. This approach of using broad categories of crash severity is common in many earlier studies, such as Kashani and Mohaymany (2011), Mujalli and De Oña (2011), De Oña et al. (2013), Chiou et al. (2013), and Savolainen and Mannering (2007). This happens to be the case because of the way crash severity information is reported or to avoid the statistical issues that arise from having a very small number of crashes in more finely defined categories.

  2. For more information: (http://www.neurosolutions.com) (last accessed January 3, 2015).

  3. For more information: (http://eric.univ-lyon2.fr/~ricco/tanagra/en/tanagra.html) (last accessed January 5, 2015).

References

  • Abdel-Aty M (2003) Analysis of driver injury severity levels at multiple locations using ordered probit models. J Saf Res 34:597–603

    Article  Google Scholar 

  • Al-Ghamdi A (2002) Using logistic regression to estimate the influence of accident factors on accident severity. Accid Anal Prev 34(6):729–741

    Article  Google Scholar 

  • Anderson TK (2009) Kernel density estimation and K-means clustering to profile road accident hotspots. Accid Anal Prev 41(3):359–364

    Article  Google Scholar 

  • Anselin L (2010) Thirty years of spatial econometrics. Pap Reg Sci 89(1):3–25

    Article  Google Scholar 

  • Aworemi JR, Ibraheem Adegoke A, Segun Oluwaseun O (2010) Analytical study of the causal factors of road traffic crashes in southwestern Nigeria. Educ Res 1(4):118–124

    Google Scholar 

  • Binder S (2002) Injuries among older adults: the challenge of optimizing safety and minimizing unintended consequences. Inj Prev 8:2–4

    Article  Google Scholar 

  • Black W, Thomas I (1998) Accidents on Belgium’s motorways: a network autocorrelation analysis. J Transp Geogr 6(1):23–31

    Article  Google Scholar 

  • Chen SH (2010) Mining patterns and factors contributed to crash severity on road curves. Dissertation, Queensland University of Technology

  • Chiou YC, Lan LW, Chen WP (2013) A two-stage mining framework to explore key risk conditions on one-vehicle crash severity. Accid Anal Prev 50:405–415

    Article  Google Scholar 

  • Chowdhury M, Sadek A, Ma Y, Kanhere N, Bhavsar P (2006) Applications of artificial intelligence paradigms to decision support to real-time traffic management. Transp Res Rec 1968:92–98

    Article  Google Scholar 

  • Churchman CW (1967) Wicked problems. Manage Sci 14(4):B141–B142

    Article  Google Scholar 

  • Ciarapica FE, Giacchetta G (2009) Classification and prediction of occupational injury risk using soft computing techniques: an Italian study. Saf Sci 47(1):36–49

    Article  Google Scholar 

  • Conklin J (2006) Dialogue mapping: building shared understanding of wicked problems. Wiley, Chichester

    Google Scholar 

  • Corne S, Murray T, Openshaw S, See L, Turton I (1999) Using computational intelligence techniques to model subglacial water systems. J Geogr Syst 1(1):37–60

    Article  Google Scholar 

  • De Oña J, López G, Mujalli R, Calvo FJ (2013) Analysis of traffic accidents on rural highways using latent class clustering and Bayesian networks. Accid Anal Prev 51:1–10

    Article  Google Scholar 

  • Delen D, Sharda R, Bessonov M (2006) Identifying significant predictors of injury severity in traffic accidents using a series of artificial neural networks. Accid Anal Prev 38(3):434–444

    Article  Google Scholar 

  • Delmelle EC, Thill JC, Ha HH (2012) Spatial epidemiologic analysis of relative crash risk factors among urban bicyclists and pedestrians. Transportation 39(2):433–448

    Article  Google Scholar 

  • Eckley DC, Curtin KM (2012) Evaluating the spatiotemporal clustering of traffic incidents. Comput Environ Urban 37:70–81

    Article  Google Scholar 

  • Effati M, Rajabi MA, Samadzadegan F, Blais JA (2012) Developing a novel method for road hazardous segment identification based on fuzzy reasoning and GIS. J Transp Technol 2:32–40

    Article  Google Scholar 

  • FHWA (2012) FHWA safety program. http://safety.fhwa.dot.gov/

  • Fish KE, Blodgett JG (2003) A visual method for determining variable importance in an artificial neural network model: an empirical benchmark study. Target Meas Anal Mark 11(3):244–254

    Article  Google Scholar 

  • Fotheringham AS, Charlton ME, Brunsdon C (1998) Geographically weighted regression: a natural evolution of the expansion method for spatial data analysis. Environ Plan A 30(11):1905–1927

    Article  Google Scholar 

  • Garber NJ, Ehrhart AA (2000) Effect of speed, flow, and geometric characteristics on crash frequency for two-lane highways. Transp Res Rec 1717:76–83

    Article  Google Scholar 

  • Geurts K, Thomas I, Wets G (2005) Understanding spatial concentrations of road accidents using frequent item sets. Accid Anal Prev 37(4):787–799

    Article  Google Scholar 

  • Gray RC, Quddus MA, Evans A (2008) Injury severity analysis of accidents involving young male drivers in Great Britain. J Saf Res 39:483–495

    Article  Google Scholar 

  • Gundogdu IB (2010) Applying linear analysis methods to GIS-supported procedures for preventing traffic accidents: case study of Konya. Saf Sci 48:763–769

    Article  Google Scholar 

  • Ha HH, Thill JC (2011) Analysis of traffic hazard intensity: a spatial epidemiology case study of urban pedestrians. Comput Environ Urban 35:230–240

    Article  Google Scholar 

  • Hackney JK, Bernard M, Bindra S, Axhausen KW (2007) Predicting road system speeds using spatial structure variables and network characteristics. J Geogr Syst 9(4):397–417

    Article  Google Scholar 

  • Haining R (2009) The special nature of spatial data. In: Fotheringham AS, Rogerson PA (eds) The SAGE handbook of spatial analysis. Sage, Los Angeles, pp 5–23

    Chapter  Google Scholar 

  • Ishak S, Alecsandru C (2004) Optimizing traffic prediction performance of neural networks under various topological, input, and traffic condition settings. J Transp Eng 130:452–465

    Article  Google Scholar 

  • Jang JSR, Sun CT, Mizutani E (1997) Neuro-fuzzy and soft computing: a computational approach to learning and machine intelligence. Prentice-Hall, Englewood Cliffs, NJ

    Google Scholar 

  • Joshua SC, Garber N (1990) Estimating truck accident rate and involvements using linear and Poisson regression models. Transp Plan Tech 15:41–58

    Article  Google Scholar 

  • Kashani AT, Mohaymany AS (2011) Analysis of the traffic injury severity on two lane, two-way rural roads based on classification tree models. Saf Sci 49:1314–1320

    Article  Google Scholar 

  • Koetse MJ, Rietveld P (2009) The impact of climate change and weather on transport: an overview of empirical findings. Transp Res D-TR E 14(3):205–221

    Article  Google Scholar 

  • Kurtulus B, Razack M (2010) Modeling daily discharge responses of a large karstic aquifer using soft computing methods: artificial neural network and neuro-fuzzy. J Hydrol 381:101–111

    Article  Google Scholar 

  • Li X, Lord D, Zhang Y, Xie Y (2008) Predicting motor vehicle crashes using support vector machine models. Accid Anal Prev 40(4):1611–1618

    Article  Google Scholar 

  • Li Z, Liu P, Wang W, Xu C (2012) Using support vector machine models for crash injury severity analysis. Accid Anal Prev 45:478–486

    Article  Google Scholar 

  • Martin JL (2002) Relationship between crash rate and hourly traffic flow on interurban motorways. Accid Anal Prev 34(5):619–629

    Article  Google Scholar 

  • McCarthy PS (1999) Public policy and highway safety: a citywide perspective. Reg Sci Urban Econ 29(3):231–244

    Article  Google Scholar 

  • Miaou S, Lum H (1993) Modeling vehicle, accidents and highway geometric design relationships. Accid Anal Prev 256:689–709

    Article  Google Scholar 

  • Montella A, Aria M, D’Ambrosio A, Mauriello F (2012) Analysis of powered two-wheeler crashes in Italy by classification trees and rules discovery. Accid Anal Prev 49:58–72

    Article  Google Scholar 

  • Morgan A, Mannering F (2011) The effects of road-surface conditions, age, and gender on driver-injury severities. Accid Anal Prev 43(5):1852–1863

    Article  Google Scholar 

  • Mujalli RO, De Oña J (2011) A method for simplifying the analysis of traffic accidents injury severity on two-lane highways using Bayesian networks. J Saf Res 42:317–326

    Article  Google Scholar 

  • Okabe A, Satoh T (2006) Uniform network transformation for points pattern analysis on a non-uniform network. J Geogr Syst 8(1):25–37

    Article  Google Scholar 

  • Pai CW (2009) Motorcyclist injury severity in angle crashes at T-junctions: identifying significant factors and analysing what made motorists fail to yield to motorcycles. Saf Sci 47(8):1097–1106

    Article  Google Scholar 

  • Pakgohar A, Tabrizi RS, Khalilli M, Esmaeili A (2010) The role of human factor in incidence and severity of road crashes based on the CART and LR regression: a data mining approach. Procedia Comput Sci 3:764–769

    Article  Google Scholar 

  • Polat K, Durduran SS (2011) Subtractive clustering attribute weighting (SCAW) to discriminate the traffic accidents on Konya-Afyonkarahisar highway in Turkey with the help of GIS: a case study. Adv Eng Softw 42(7):491–500

    Article  Google Scholar 

  • Rittel HWJ, Webber MM (1973) Dilemmas in a general theory of planning. Policy Sci 4:155–169

    Article  Google Scholar 

  • Savolainen PT, Mannering FL (2007) Probabilistic models of motorcyclists’ injury severities in single- and multi-vehicle crashes. Accid Anal Prev 39(5):955–963

    Article  Google Scholar 

  • Savolainen P, Mannering F, Lord D, Quddus M (2011) The statistical analysis of crash-injury severities: a review and assessment of methodological alternatives. Accid Anal Prev 43(5):1666–1676

    Article  Google Scholar 

  • Shankar V, Mannering F, Barfield W (1995) Effect of roadway geometric and environment factors on rural freeway accident frequencies. Accid Anal Prev 27:11–23

    Article  Google Scholar 

  • Shekhar S, Vatsavai RR (2003) Mining geospatial data. In: Ye N (ed) The handbook of data mining. Lawrence Erlbaum, Mahwah, pp 519–547

    Google Scholar 

  • Siddiqui C, Abdel-Aty M, Huang H (2012) Aggregate nonparametric safety analysis of traffic zones. Accid Anal Prev 45:317–325

    Article  Google Scholar 

  • Steenberghen T, Dufays T, Thomas I, Flahaut B (2004) Intra-urban location and clustering of road accidents using GIS: a Belgian case. Int J Geogr Inf Sci 18(2):169–181

    Article  Google Scholar 

  • Tavris DR, Kuhn EM, Layde PM (2001) Age and gender patterns analysis accident in vehicle crash injuries: importance of type of crash and occupant role. Accid Anal Prev 33:167–172

    Article  Google Scholar 

  • The MathWorks, Inc. (2007) MATLAB programming. Natick, MA

  • Theofilatos A, Graham D, Yannis G (2012) Factors affecting accident severity inside and outside urban areas in Greece. Traffic Inj Prev 13(5):458–467

    Article  Google Scholar 

  • Vapnik VN (1995) The nature of statistical learning theory. Springer, New York

    Book  Google Scholar 

  • Veregin H (1995) Developing and testing of an error propagation model for GIS overlay operation. Int J Geogr Inf Sci 9:595–619

    Article  Google Scholar 

  • Wang X, Kockelman KM (2007) Specification and estimation of a spatially and temporally autocorrelated seemingly unrelated regression model: application to crash rates in China. Transportation 34(3):281–300

    Article  Google Scholar 

  • Yamada I, Thill JC (2007) Local indicators of network-constrained clusters in spatial point patterns. Geogr Anal 39(3):268–292

    Article  Google Scholar 

  • Yamada I, Thill JC (2010) Local indicators of network-constrained clusters in spatial patterns represented by a link attribute. Ann Assoc Am Geogr 100(2):1–17

    Article  Google Scholar 

  • Yannis G, Papadimitriou E, Dupont E, Martensen H (2010) Estimation of fatality and injury risk by means of in-depth fatal accident investigation data. Traffic Inj Prev 11(5):492–502

    Article  Google Scholar 

  • Yao X, Thill JC (2007) Neurofuzzy modeling of context-contingent proximity relations. Geogr Anal 39:169–194

    Article  Google Scholar 

  • Zhang J, Goodchild MF (2002) Uncertainty in geographical information. Taylor & Francis, New York

    Book  Google Scholar 

  • Zhou Z, Zhou LY (2010) An automatic incident of freeway detection algorithm based on support vector machine. In: 2010 International symposium on intelligence information processing and trusted computing. IEEE, Huanggang, pp 543–546

Download references

Author information

Authors and Affiliations

  1. Department of Civil Engineering, Faculty of Engineering, University of Guilan, Rasht, Iran

    Meysam Effati

  2. Department of Geography and Earth Sciences, University of North Carolina at Charlotte, Charlotte, NC, USA

    Jean-Claude Thill

  3. Department of Civil Engineering, Road and Transportation, North Tehran Center, Prayame Noor University (PNU), Tehran, Iran

    Shahin Shabani

Authors
  1. Meysam Effati
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Jean-Claude Thill
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Shahin Shabani
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Jean-Claude Thill.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Effati, M., Thill, JC. & Shabani, S. Geospatial and machine learning techniques for wicked social science problems: analysis of crash severity on a regional highway corridor. J Geogr Syst 17, 107–135 (2015). https://doi.org/10.1007/s10109-015-0210-x

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10109-015-0210-x

Keywords

JEL Classification

Search

Navigation