Abstract
Road asset managers are overwhelmed with a high volume of raw data which they need to process and utilize in supporting their decision making. This paper presents a method that processes road-crash data of a whole road network and exposes hidden value inherent in the data by deploying the clustering data mining method. The goal of this method is to partition the road network into a set of groups (classes) based on common data and characterize the crash types to produce a crash profile for each cluster. By comparing similar road classes with differing crash types and rates, insight can be gained into these differences that are caused by the particular characteristics of their roads. These differences can be used as evidence in knowledge development and decision support.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
World Health Organization (2002) Global health: today’s challenges. The World Health Organization. Available from: http://www.who.int/whr/2003/en/Chapter1.pdf. Cited 11 Feb 2011
Queensland-Fire-and-Rescue-Service (2002) Firefighters called to record number of road crashes. Queensland Fire and Rescue Service, Queensland Government (Brisbane) [serial online]. 18 Nov 2002. Available from: http://www.fire.qld.gov.au/news/view.asp?id=207. Cited 2008 October
Queensland Department of Transport Main Roads (2011) Road planning and design manual, design philosophy. Queensland Government, Transport and Main Roads (Brisbane) [serial online]. 11 Feb 2011. Available from http://www.tmr.qld.gov.au/Business-and-industry/Technical-standards-and-publications/Road-planning-and-design-manual.aspx. Cited 02 Aug 2010
Huang H, Chin H, Haque M (2009) Empirical evaluation of alternative approaches in identifying crash hot spots. Trans Res Rec: J Trans Res Board 32–41
ARRB Group (2011) Tools for improving road safety. ARRB Group. Available from: http://www.arrb.com.au/Safe-Systems/Tools-for-improving-road-safety.aspx. Cited 1 Sept 2001
Depaire B, Wets G, Vanhoof K (2008) Traffic accident segmentation by means of latent class clustering. Accid Anal Prev 40(4):1257–1266
Alzghoul A, Löfstrand M (2011) Increasing availability of industrial systems through data stream mining. Comput Ind Eng 60(2):195–205
Pande A, Abdel-Aty M (2009) Market basket analysis of crash data from large jurisdictions and its potential as a decision support tool. Saf Sci 47(1):145–154
Zhao Z, Jin X, Cao Y, Wang J (2010) Data mining application on crash simulation data of occupant restraint system. Expert Syst Appl 37(8):5788–5794
Anderson TK (2009) Kernel density estimation and K-means clustering to profile road accident hotspots. Accid Anal Prev 41(3):359–364
Emerson D, Nayak R, Weligamage J (2011) Using data mining to predict road crash count with a focus on skid resistance values. In: Proceedings of the 3rd international surface friction conference. Gold Coast, p 18
Qin X, Ivan JN, Ravishanker N (2004) Selecting exposure measures in crash rate prediction for two-lane highway segments. Accid Anal Prev 36(2):183–191
Nayak R, Emerson D, Weligamage J, Piyatrapoomi (2011) Road crash proneness prediction using data mining. In: Proceedings of the extending database technology. Uppsala, Sweden. p 521–526
Nayak R, Emerson D, Weligamage J, Piyatrapoomi N (2010) Using data mining on road asset management data in analysing road crashes. Proceedings of the 16th Annual TMR Engineering and Technology Forum, Brisbane
Emerson D, Nayak R, Weligamage J, Piyatrapoomi N (2010) Identifying differences in wet and dry road crashes using data mining. Proceedings of the Fifth World Congress on Engineering Asset Management, Brisbane
Acknowledgments
This paper was developed within the CRC for Infrastructure and Engineering Asset Management (CIEAM), established and supported under the Australian Government’s Cooperative Research Centres Programme. The authors gratefully acknowledge the financial support provided by CIEAM. This CIEAM study is a component of a project involving QUT and QDTMR in the development of a skid resistance decision support system for road asset management [11, 13–15]. Queensland Department of Transport and Main Roads provided the road and crash datasets. Data mining operations and presentations were performed in the WEKA and SAS platforms, and substantial computer processing was performed on the QUT High Performance Computing facility (HPC). The views presented in this paper are of the authors and not necessarily the views of the organizations.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Appendix 1
Appendix 1
Rights and permissions
Copyright information
© 2014 Springer-Verlag London
About this paper
Cite this paper
Emerson, D., Nayak, R., Weligamage, J. (2014). Identifying Differences in Safe Roads and Crash Prone Roads Using Clustering Data Mining. In: Lee, J., Ni, J., Sarangapani, J., Mathew, J. (eds) Engineering Asset Management 2011. Lecture Notes in Mechanical Engineering. Springer, London. https://doi.org/10.1007/978-1-4471-4993-4_10
Download citation
DOI: https://doi.org/10.1007/978-1-4471-4993-4_10
Published:
Publisher Name: Springer, London
Print ISBN: 978-1-4471-4992-7
Online ISBN: 978-1-4471-4993-4
eBook Packages: EngineeringEngineering (R0)