Skip to main content
Springer Nature Link
Log in

A hybrid system of neural networks and rough sets for road safety performance indicators

  • Focus
  • Published:
Soft Computing Aims and scope Submit manuscript

Abstract

Road safety performance indicators are comprehensible tools that provide a better understanding of current safety conditions and can be used to monitor the effect of policy interventions. New insights can be gained in case one road safety index is composed of all risk indicators. The overall safety performance can then be evaluated, and countries ranked. In this paper, a promising structure of neural networks based on decision rules generated by rough sets—is proposed to develop an overall road safety index. This novel hybrid system integrates the ability of neural networks on self-learning and that of rough sets on automatically transforming data into knowledge. By means of simulation, optimal weights are assigned to seven road safety performance indicators. The ranking of 21 European countries in terms of their road safety index scores is compared to a ranking based on the number of road fatalities per million inhabitants. Evaluation results imply the feasibility of this intelligent decision support system and valuable predictive power for the road safety indicators context.

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

Similar content being viewed by others

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

References

  • Atiya A, Ji CY (1997) How initial conditions affect generalization performance in large networks. IEEE Trans Neural Netw 8(2):448–451

    Article  Google Scholar 

  • Cao G, Shiu SCK, Wang X (2003) A fuzzy-rough approach for the maintenance of distributed case-based reasoning systems. Soft Comput 7(8):491–499

    MATH  Google Scholar 

  • European Transport Safety Council (2001) Transport Safety Performance Indicators, ETSC, Brussels

  • European Transport Safety Council (2008) Countdown to 2010, only two more years to act, 2nd Road Safety PIN Report ETSC, Brussels

  • European Commission (2001) White Paper European transport policy for 2010: time to decide, Commission of the European Communities, Brussels

  • Hagan MT, Menhaj MB (1994) Training feed forward network with the Marquardt algorithm. IEEE Trans Neural Netw 5(6):989–993

    Article  Google Scholar 

  • Haykin S (1999) Neural networks: a comprehensive foundation. Macmillan College Publishing Company, New York

    MATH  Google Scholar 

  • Hermans E (2009) A methodology for developing a composite road safety performance index for cross-country comparison. PhD Thesis, Hasselt university, Belgium

  • Hermans E, Ruan D, Brijs T, Wets G, Vanhoof K (2008a) Evaluation of road safety performance indicators using OWA operators. Comput Eng Inform Sci 1:695–700

    Google Scholar 

  • Hermans E, Van den Bossche F, Wets G (2008b) Combining road safety information in a performance index. Accid Anal Prev 40:1337–1344

    Article  Google Scholar 

  • Hornik K, Stinchcombe M, White H (1989) Multilayer feedforward networks are universal approximators. Neural Netw 2:359–366

    Article  Google Scholar 

  • Jiang Y, Zhang H, Xie J, Meng K (2006) An estimation model of research cost based on rough set and artificial neural network. LNAI 4114:766–771

    Google Scholar 

  • Li T, Ruan D, Wets G, Song J, Xu Y (2007) A rough sets based characteristic relation approach for dynamic attribute generalization in data mining. Knowl-Based Syst 20(5):485–494

    Article  Google Scholar 

  • Litman T (2007) Developing indicators for comprehensive and sustainable transport planning. Transportation Research Record 2017, Transportation Research Board, 10–15

  • Luo J, Shao H (2006) Developing soft sensors using hybrid soft computing methodology: a neurofuzzy system based on rough set theory and genetic algorithms. Soft Comput 10(1):54–60

    Article  Google Scholar 

  • Midelfart H, Komorowski HJ, Nørsett K, Yadetie F, Sandvik AK, Lægreid A (2002) Learning rough set classifiers from gene expressions and clinical data. Fundamenta Informaticae 53:155–183

    MathSciNet  Google Scholar 

  • Nardo M, Saisana M, Saltelli A, Tarantola S, Hoffman A, Giovannini E (2005) Handbook on constructing composite indicators: methodology and user guide. OECD Statistics Working Papers, Organisation for Economic Cooperation and Development, Paris

  • Øhrn A, Komorowski J, Skowron A, Synak P (1998) The design and implementation of a knowledge discovery toolkit based on rough sets: the ROSETTA system. In: Polkowski L, Skowron A (eds) Rough sets in knowledge discovery. 1. Methodoloy and applications. Studies in fuzziness and soft computing, vol 18. Physica-Verlag, Heidelberg, pp 376–399

  • Pawlak Z (1991) Rough sets. Theoretical aspects of reasoning about data. Kluwer Academic Publishers, Boston

    MATH  Google Scholar 

  • Pawlak Z, Polkowski L, Skowron A (2005) Rough sets. In: Rivero LC, Doorn JH, Ferragine VE (eds) Encyclopedia of database technologies and applications, Idea Group Reference, pp 575–580

  • Pawlak Z, Skowron A (2007) Rudiments of rough sets. Inform Sci 177(1):3–40

    Article  MATH  MathSciNet  Google Scholar 

  • Peters JF, Skowron A (2002) A rough set approach to knowledge discovery. Int J Intell Syst 17(2):109–112

    Article  Google Scholar 

  • Reich Y, Baraib SV (2000) A methodology for building neural networks models from empirical engineering data. Eng Appl Artif Intell 13:685–694

    Article  Google Scholar 

  • Rumelhart DE, Hinton GE, Wiliams RJ (1986) Learning representations by back-propagating errors. Nature 323:533–536

    Article  Google Scholar 

  • SafetyNet Work Package 3 (2005) State-of-the-art Report on Road Safety Performance Indicators, SafetyNet

  • SARTRE 3 Report (2004) European Drivers and Road Risk, SARTRE

  • Shen Y, Hermans E, Ruan D, Wets G, Vanhoof K, Brijs T (2008) Development of a composite road safety performance index based on neural networks. In: Proceedings of 2008 international conference on intelligent systems and knowledge engineering, Xiamen, IEEE Press 2:901–906

  • Skowron A (1995) Extracting laws from decision tables: a rough set approach. Comput Intell 11:371–388

    Article  MathSciNet  Google Scholar 

  • Swiniarski RW (2001) Rough set methods in feature reduction and classification. Int J Appl Math Comput Sci 11(3):565–582

    MathSciNet  Google Scholar 

  • Swiniarski RW, Skowron A (2003) Rough set methods in feature selection and recognition. Pattern Recognit Lett 24(6):833–849

    Article  MATH  Google Scholar 

  • Wegman F, Commandeur J, Doveh E, Eksler V, Gitelman V, Hakkert S, Lynam D, Oppe S (2008) SUNflowerNext: towards a composite road safety performance index, Deliverable D6.16 of the EU FP6 project SafetyNet

  • Werbos PJ (1988) Back-propagation: past and future. In: Proceeding of international conference on neural networks, San Diego, CA, 1:343–354

  • Witten IH, Frank E (2005) Data mining: practical machine learning tools and techniques, 2nd edn. Morgan Kaufmann, San Francisco

    Google Scholar 

  • Xiang C, Ding SQ, Lee TH (2005) Geometrical interpretation and architecture selection of MLP. IEEE Trans Neural Netw 16(1):84–96

    Article  Google Scholar 

  • Xiao Z, Ye S, Zhong B, Sun C (2009) BP neural network with rough set for short term load forecasting. Expert Syst Appl 36:273–279

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Transportation Research Institute, Hasselt University, Wetenschapspark 5 bus 6, 3590, Diepenbeek, Belgium

    Yongjun Shen, Elke Hermans, Da Ruan, Geert Wets, Koen Vanhoof & Tom Brijs

  2. School of Information Science and Technology, Southwest Jiaotong University, Chengdu, 610031, People’s Republic of China

    Tianrui Li

  3. Belgian Nuclear Research Centre (SCK CEN), Boeretang 200, 2400, Mol, Belgium

    Da Ruan

Authors
  1. Yongjun Shen
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Tianrui Li
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. Elke Hermans
    View author publications

    You can also search for this author inPubMed Google Scholar

  4. Da Ruan
    View author publications

    You can also search for this author inPubMed Google Scholar

  5. Geert Wets
    View author publications

    You can also search for this author inPubMed Google Scholar

  6. Koen Vanhoof
    View author publications

    You can also search for this author inPubMed Google Scholar

  7. Tom Brijs
    View author publications

    You can also search for this author inPubMed Google Scholar

Corresponding author

Correspondence to Yongjun Shen.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Shen, Y., Li, T., Hermans, E. et al. A hybrid system of neural networks and rough sets for road safety performance indicators. Soft Comput 14, 1255–1263 (2010). https://doi.org/10.1007/s00500-009-0492-3

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00500-009-0492-3

Keywords