Extended Traffic Crash Modelling through Precision and Response Time Using Fuzzy Clustering Algorithms Compared with Multi-layer Perceptron
Abstract
This paper compares two fuzzy clustering algorithms – fuzzy subtractive clustering and fuzzy C-means clustering – to a multi-layer perceptron neural network for their ability to predict the severity of crash injuries and to estimate the response time on the traffic crash data. Four clustering algorithms – hierarchical, K-means, subtractive clustering, and fuzzy C-means clustering – were used to obtain the optimum number of clusters based on the mean silhouette coefficient and R-value before applying the fuzzy clustering algorithms. The best-fit algorithms were selected according to two criteria: precision (root mean square, R-value, mean absolute errors, and sum of square error) and response time (t). The highest R-value was obtained for the multi-layer perceptron (0.89), demonstrating that the multi-layer perceptron had a high precision in traffic crash prediction among the prediction models, and that it was stable even in the presence of outliers and overlapping data. Meanwhile, in comparison with other prediction models, fuzzy subtractive clustering provided the lowest value for response time (0.284 second), 9.28 times faster than the time of multi-layer perceptron, meaning that it could lead to developing an on-line system for processing data from detectors and/or a real-time traffic database. The model can be extended through improvements based on additional data through induction procedure.References
Donnell, E.T., Mason Jr. J.M. Predicting the frequency of median barrier crashes on Pennsylvania Interstate Highways. accident Analysis & Prevention 2006;38 (3):590–599.
Lord, D. Methodology for estimating the variance and confidence intervals of the estimate of the product of baseline models and AMFs. Accident Analysis & Prevention 2008;40 (3):1013–1017.
Mussone, L., Ferrari, A. and Oneta, M. An analysis of urban collisions using an artificial intelligence model. Accident Analysis and Prevention, 1999;31 (6):705–718.
Zhang, J., Lindsay, J., Clarke, K., Robbins, G. and Mao, Y. Factors affecting the severity of motor vehicle traffic crashes involving elderly drivers in Ontario. Accident Anal. Prev. 2000;32 (1):117–125.
Valent, F., Schiava, F., Savonitto, C., Gallo, T., Brusaferro, S. and Barbone, F. Risk factors for fatal road accidents in Udine, Italy. Accident Analysis and Prevention 2002;34 (1):71–84.
Yin, H., Wong, S.C., Xu, J. and Wong, C.K. Urban traffic flow prediction using fuzzy-neural network, Transportation Research Part C 2002;10 (2):85–98.
Zhong, M., Lingras, P., Sharma, S. Estimation of missing traffic counts using factor, genetic, neural and regression techniques. Transportation Research Part C 2004;12 (2):139–166.
Tong, H.Y. and Hung, W.T. Neural network modelling of vehicle discharge headway at signalized intersection: model descriptions and the results, Transportation Research Part A 2002;36 (1):17–40.
Jin, X., Cheu, R.L. and Dipti, S. Development and adaptation of constructive probabilistic neural network
in freeway incident detection. Transportation Research Part C 2002;10 (2):121–147.
Yuan, F. and Cheu, R.L. Incident detection using support vector machines, Transportation Research Part C 2003;11 (3-4):309–328.
Subba Rao, P.V., Sikdar, P.K. and Krishna Rao, K.V. Another insight into artificial neural networks through behavioral analysis of access mode choice, Computers, Environment and Urban Systems 1998;22 (5):485–496.
Hensher, D.A. and Ton, T.T. A comparison of the predictive potential of artificial neural networks and nested logit models for commuter mode choice. Transportation Research Part E 2000;36 (3):155–172.
Vythoulkas, P.C. and Koutsopoulos, H.N. Modelling discrete choice behavior using concepts from fuzzy set theory, approximate reasoning and neural networks, Transportation Research Part C 2003;11 (1):51–73.
Mussone, L., Rinelli, S., Reitani, G. Estimating the accident probability of a vehicular flow by means of an artificial neural network. Environment and Planning B: Planning and Design, 1996;23(6):667–675.
Sohn, S. and Lee, S. Data fusion, ensemble and clustering to improve the classification accuracy for the severity of road traffic accident in Korea, Safety Science 2003;41(1):1–14.
Abdel-Aty, M., Pande, A.. Identifying crash propensity using traffic speed conditions. Journal of Safety Research 2005;36 (1): 97–108.
Abdelwahab, H.T., Abdel-Aty, M.A.. Development of artificial neural network models to predict driver injury severity in traffic accidents at signalizes intersection. Transportation Research Record 1746, Paper No. 01- 2234, 2001;6–13.
Kunt, M.M., Aghayan, I. and Noii, N. Prediction the traffic accident severity: comparing the artificial neural network, genetic algorithm, combined genetic algorithm and pattern search methods. Transport 2011; 26(4): 353-366.
Zadeh, L. Fuzzy sets. Information and Control 1965;8:338-353.
Akiyama, T., Sho, C. F. Fuzzy mathematical programming for traffic safety planning on an urban expressway. Transportation Planning and Technology 1993;17:179-190.
Hadji Hosseinlou, M. and Aghayan, I. Prediction of traffic accident severity based on fuzzy logic, 8th International Congress on Civil Engineering, Shiraz, Iran. 2009;65p.
Kamijo, S., Matsushita, Y., Ikeuchi, K., Sakauchi, M. Traffic monitoring and accident detection at intersections. IEEE Transactions on Intelligent Transportation Systems 2000;1 (2):108–118.
Mussa, R.N. and Upchurch, J.E. Simulator evaluation of incident detection by transponder-equipped vehicles. Transportation, 2002;29 (3):287–305.
Lanser, S.H. and Hoogendoorn, S. A fuzzy genetic approach to travel choice behavior in public transport networks. CD-ROM Proc., Transportation Research Board 79th Annual Meeting, TRB, Washington, DC. 2000.
Niitymaki, J. General fuzzy rule base for isolated traffic signal control: rule formulation. Transporation Planning and Technology, 2001;24 (3):237–247.
Ishak, S.S. and Al-Deek, H.M. Fuzzy art neural network model for automated detection of freeway incidents. 1998;Transportation Research Record 1634:56–63.
Ruspini, E. H. A new approach to clustering, Information and Control, 1969;15(1):22-32.
Dunn, J.C. A fuzzy relative of the ISODATA process and its use in detecting compact, well-separated clusters. J. Cybernet, 1974;3:32–57.
Bezdek, J. Pattern Recognition with Fuzzy Objective Function Algorithms, New York: Plenum Press;1981.
Sugeno M. and Yasukawa T. A fuzzy-logic-based approach to qualitative modelling. IEEE Trans Fuzzy Syst 1993;1:7–31.
Chen JQ, Xi YG, Zhang Z.J., A clustering algorithm for fuzzy model identification. Fuzzy Sets Syst 1998;98:319–29.
Wang, X., Wang, Y. and Wang, L. Improving fuzzy Cmeans clustering based on feature-weight learning. Pattern Recognition Letters 2004;25:1123–1132.
Frigui, H. and Nasraoui, O. Unsupervised learning of prototypes and attribute weights. Pattern Recognition, 2004;37:567–581.
Chiu, S.L. Fuzzy model identification based on cluster estimation. Journal of Intelligent & Fuzzy System, 1994;2 (3).
Yager, R.R. and Filev, D.P. Approximate clustering via the mountain method. IEEE Trans. Systems, Man, Cybernet. 1994;24 (8):1279–1284.
Hayajneh M. and Hassan A. Modelling the machinability of self-lubricated aluminium/alumina/graphite hybrid composites synthesized by the powder metallurgy method using a fuzzy subtractive clustering-based system identification method. International Journal of Machining and Machinability of Materials 2008;3(3-4): 252–271.
MacQueen, J.B. Some methods for classification and analysis of multivariate observations. Proceedings of Fifth Berkeley Symposium on Mathematical Statistics and Probability, 1967;(1):281–297, Berkeley: University of California Press.
Fukunaga, K. Introduction to Statistical Pattern Recognition. San Diego: Academic Press. 1990.
Pena, J.M., Lozano, J.A., Larranaga, P. An empirical comparison of four initialization methods for the K-means algorithm. Pattern Recognition Letters, 1999;20:1027–1040.
Khan, S. and Ahmad, A. Cluster centre initialization algorithm for K-means clustering. Pattern Recognition Letters 2004;25 (11):1293–1302.
Redmond, S.J. and Heneghan, C. A method for initializing the K-means clustering algorithm using kd-trees. Pattern Recognition Letters 2007;28:965–973.
Sneath, P.H. and Sokal, R.R. Numerical Taxonomy. London, UK:Freeman;1973.
King, B. Step-wise clustering procedures. Journal of the American Statistical Association, 1967;69:86–101.
Guha, S., Rastogi, R. and Shim, K. CURE: An efficient clustering algorithm for large databases. In Proc. of 1998 ACM-SIGMOD Int. Conf. on Management of Data, 1998;73–84.
Guha, S., Rastogi, R. and Shim, K. ROCK: A robust clustering algorithm for categorical attributes. In Proc. of the 15th Int’l Conf. on Data Eng., 1999;512–521.
Karypis, G., Han, E.H., and Kumar, V. Chameleon: A hierarchical clustering algorithm using dynamic modelling. IEEE Computer, 1999;32(8):68–75.
Wang, X.-Y., Garibaldi, J. M., Bird, B. and George, M. W. Novel Developments in Fuzzy Clustering for the Classification of Cancerous Cells Using FTIR Spectroscopy. In: Valente de Oliveira, J. and Pedrycz, W., editors. Advances in Fuzzy Clustering and its Applications, John Wiley & Sons, Ltd, Chichester, UK. 2007
Hammouda, K. and Fakhreddine, K. A Comparative study of data clustering techniques, SYDE 625: Tools of Intelligent Systems Design. Course Project. University of Waterloo, Ontario, Canada. 2002.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
