Traffic Accidents Analysis using Self-Organizing Maps and Association Rules for Improved Tourist Safety

Andreas Gregoriades, Andreas Christodoulides

2017

Abstract

Traffic accidents is the most common cause of injury among tourists. This paper presents a method and a tool for analysing historical traffic accident records using data mining techniques for the development of an application that warns tourist drivers of possible accident risks. The knowledge necessary for the specification of the application is based on patterns distilled from spatiotemporal analysis of historical accidents records. Raw accident obtained from Police records, underwent pre-processing and subsequently was integrated with secondary traffic-flow data from a mesoscopic simulation. Two data mining techniques were applied on the resulting dataset, namely, clustering with self-organizing maps (SOM) and association rules. The former was used to identify accident black spots, while the latter was applied in the clusters that emerged from SOM to identify causes of accidents in each black spot. Identified patterns were utilized to develop a software application to alert travellers of imminent accident risks, using characteristics of drivers along with real-time feeds of drivers’ geolocation and environmental conditions.

References

  1. Anderberg M. Cluster analysis for applications, 1973, Academic Press.
  2. Gregoriades A, Mouskos K, 2013. Black spots identification through a Bayesian Networks quantification of accident risk index. Transportation Research Part C 28, 28-43.
  3. Bayardo Jr, Roberto J. (1998). Efficiently mining long patterns from databases. ACM SIGMOD, 27 (2).
  4. Bentley et al., 2001, Recreational tourism injuries among visitors to New Zealand: an exploratory analysis using hospital discharge data, Tourism Management, 22 (2001), pp. 373-381.
  5. Berry MJA, Linoff G. Data Mining Techniques: For Marketing, Sales, and Customer Support. New York, NY, USA: Wiley, 1997. 2135 DOGRU and SUBAS¸I/Turk J Elec Eng & Comp Sci.
  6. Chen, W. and Jovanis P. (2002) Method for identifying factors contributing to driver-injury severity in traffic crashes, Transportation Research Record 1717 1-9.
  7. Depaire B, Wets G, Vanhoof K. Traffic accident segmentation by means of latent class clustering. Accident Anal Prev 2008; 40: 1257-1266.
  8. Frawley, W. J., Piatetsky-Shapiro, G., Matheus, C. J., Knowledge Discovery in Databases, AAAI/MIT Press, 1-27(1991).
  9. Howard, 2009, Risky business? Asking tourists what hazards they actually encountered in Thailand, Tourism Management, 30 (2009), pp. 359-365.
  10. Sun J, Jian Sun, 2015. A dynamic Bayesian network model for real-time crash prediction using traffic speed conditions data. Transportation Research Part C 54, 176-186.
  11. Kassawat S., Sunya S, Vatanavongs R, 2015. Integration of Spatial Models for Web-based Risk Assessment of Road Accident. Engineering and Physical Sciences 8, 671.
  12. Lee, C., Saccomanno, F. and Hellinga B. (2002). Analysis of Crash Precursors on Instrumented Freeways, Proceedings of the Transportation Research Board, Washington D.C.
  13. Liu, Y, Kiang, M., Brusco, M. (2012). A unified framework for market segmentation and its applications, Expert Systems with Applications, 39, (11), 1 September, 10292-10302.
  14. Mahdi A., Ali N, 2013. Presentation of clusteringclassification heuristic method for improvement accuracy in classification of severity of road accidents in Iran. Safety Science 60, 142-150.
  15. Miao Chong, Ajith Abraham and Marcin Paprzycki, 2005. Traffic Accident Data Mining Using Machine Learning Paradigms. Informatica 29, 89-98.
  16. Kwon H, Wonjong Rheeb, Yoonjin Yoona, 2015. Application of classification algorithms for analysis of road safety risk factor dependencies. Accident Analysis and Prevention 75, 1-15.
  17. Page, Meyer, 1996, Tourist accidents an exploratory analysis, Annals of Tourism Research, 23 (3) (1996), pp. 666-690.
  18. Liu P, 2009. A self-organizing feature maps and data mining based decision support system for liability authentications of traffic crashes. Neurocomputing 72, 2902-2908.
  19. Rossello, Jaume, Saenz-de-Miera, 2011, Road accidents and tourism: The case of the Balearic Islands (Spain), Accident Analysis and Prevention. 43(3),675-683.
  20. Smith, W. R. (1956). Product differentiation and market segmentation as alternative marketing strategies. The Journal of Marketing, 21(1), 3-8.
  21. Tambouratzis T, Souliou D, Chalikias M and Gregoriades A., Combining probabilistic neural networks and decision trees for maximally accurate and efficient accident prediction, IJCNN, Barcelona, 2010, pp. 1-8.
  22. WHO. Global Status Report on Road Safety 2015.
  23. Yiannis G, , Golias J, Eleonora Papadimitriou, 2007, Accident risk of foreign drivers in various road environments, Journal of Safety Research, Vol 38,4, pp471-480.
Download


Paper Citation


in Harvard Style

Gregoriades A. and Christodoulides A. (2017). Traffic Accidents Analysis using Self-Organizing Maps and Association Rules for Improved Tourist Safety . In Proceedings of the 19th International Conference on Enterprise Information Systems - Volume 1: ICEIS, ISBN 978-989-758-247-9, pages 452-459. DOI: 10.5220/0006356204520459


in Bibtex Style

@conference{iceis17,
author={Andreas Gregoriades and Andreas Christodoulides},
title={Traffic Accidents Analysis using Self-Organizing Maps and Association Rules for Improved Tourist Safety},
booktitle={Proceedings of the 19th International Conference on Enterprise Information Systems - Volume 1: ICEIS,},
year={2017},
pages={452-459},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006356204520459},
isbn={978-989-758-247-9},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 19th International Conference on Enterprise Information Systems - Volume 1: ICEIS,
TI - Traffic Accidents Analysis using Self-Organizing Maps and Association Rules for Improved Tourist Safety
SN - 978-989-758-247-9
AU - Gregoriades A.
AU - Christodoulides A.
PY - 2017
SP - 452
EP - 459
DO - 10.5220/0006356204520459