No Access

SETTING UP A PROBABILISTIC NEURAL NETWORK FOR CLASSIFICATION OF HIGHWAY VEHICLES

Department of Mechanical and Applied Mechanics, North Dakota State University, 205 Dolve Hall, Fargo, North Dakota, 58105, USA

Search for more papers by this author

VALERIAN KWIGIZILE

Department of Civil and Environmental Engineering, University of Nevada, Las Vegas, Nevada, USA

Search for more papers by this author

, and

RENATUS N. MUSSA

Department of Civil and Environmental Engineering, Florida A&M University — Florida State University, Florida, USA

Search for more papers by this author

https://doi.org/10.1142/S1469026805001702Cited by:5 (Source: Crossref)

Abstract

Many neural network methods used for efficient classification of populations work only when the population is globally separable. In situ classification of highway vehicles is one of the problems with globally nonseparable populations. This paper presents a systematic procedure for setting up a probabilistic neural network that can classify the globally nonseparable population of highway vehicles. The method is based on a simple concept that any set of classifiable data can be broken down to subclasses of locally separable data. Hence, if these locally separable data can be identified, then the classification problem can be carried out in two hierarchical steps; step one classifies the data according to the local subclasses, and step two classifies the local subclasses into the global classes. The proposed approach was tested on the problem of classifying highway vehicles according to the US Federal Highway Administration standard, which is normally handled by decision tree methods that use vehicle axle information and a set of IF-THEN rules. By using a sample of 3326 vehicles, the proposed method showed improved classification results with an overall misclassification rate of only 2.9% compared to 9.7% of the decision tree methods. A similar setup can be used with different neural networks such as recurrent neural networks, but they were not tested in this study especially since the focus was for in situ applications where a high learning rate is desired.

Keywords:

Remember to check out the Most Cited Articles!
Check out these titles in artificial intelligence!

References

FHWA , Traffic Monitoring Guide, Section 4: Vehicle Classification Monitoring ( Office of Highway Policy Information , 2001 ) . Google Scholar
J. H. Wyman, G. A. Braley and R. I. Stephens, Field evaluation of FHWA vehicle classification categories, Maine Department of Transportation, Final Report for Contract DTFH-71-80-54-ME-03 for US Department of Transportation, FHWA, Office of Planning (January 1985) . Google Scholar
P. Davies, Information Technology Applications in Transport, ser. Topics in Transportation, eds. M. Bell and P. Bonsall (VNU Science Press, Haarlem, the Netherlands, 1986) pp. 11–40. Google Scholar
D. Beymeret al., A real time computer vision system for measuring traffic parameters, Proc. IEEE Conf. Computer Vision and Pattern Recognition (1997) pp. 495–501, DOI: 10.1109/CVPR.1997.609371. Google Scholar
M. J. J. Burden and M. G. H. Bell, Image classification using stereo vision, Proc. 6th Int. Conf. Image Proc. Its Appl.2 (1997) pp. 881–887. Google Scholar
G. D. Sullivanet al., Image Vision Comput. 15, 649 (1997), DOI: 10.1016/S0262-8856(97)00009-7. Crossref, Google Scholar
S. Gupteet al., IEEE Trans. Intell. Trans. Syst. 3(1), 37 (2002), DOI: 10.1109/6979.994794. Crossref, Google Scholar
T. Cherrett, H. Bell and M. McDonald, Trans. Res. Rec. 1719, 112 (2000). Crossref, Google Scholar
S. Cheung et al. , Traffic measurement and vehicle classification with a single magnetic sensor , Compendium of Papers Presented at the TRB 84th Annual Meeting ( 2005 ) . Google Scholar
C. Sun, An investigation in the use of inductive loop signatures for vehicle classification, California PATH, Research Report UCB-ITS-PRR-2002-4 (2000) . Google Scholar
D. Michie , D. J. Spiegelhalter and C. C. Taylor , Machine Learning, Neural and Statistical Classification ( Ellis Horwood , 1994 ) , http://citeseer.ist.psu.edu/michie94machine.html . Google Scholar
L. H. Tsoukalas and R. E. Uhrig , Fuzzy and Neural Approaches in Enegineering ( John Willey , 1997 ) . Google Scholar
G. A. Albanis and R. A. Batchelor , Using probabilistic neural networks and rule induction to predict bond ratings , Proc. 5th Ann. Conf. Inf. Syst. Anal. Synthesis , ed. M. Torres ( 1999 ) . Google Scholar
D. F. Specht, Neural Networks 3(1), 109 (1990), DOI: 10.1016/0893-6080(90)90049-Q. Crossref, Google Scholar
D. F. Specht, IEEE Trans. Neural Networks 1(1), 111 (1990), DOI: 10.1109/72.80210. Crossref, Google Scholar
E. Parzen, Ann. Math. Statist. 33, 1065 (1962). Crossref, Google Scholar
V. K. Murthy, Ann. Math. Statist. 36, 1027 (1965). Crossref, Google Scholar
V. K. Murthy , Multivariate Analysis , ed. P. R. Krishnaiah ( Academic Press , New York , 1966 ) . Google Scholar
R. Cacoullous, Ann. Inst. Statist. Math. (Tokyo) 18(2), 179 (1966). Crossref, Google Scholar
D. Li, M. Azimi-Sadjadi and M. Robinson, IEEE Trans. Neural Networks 15(1), 189 (2004), DOI: 10.1109/TNN.2003.820621. Crossref, Google Scholar