Assessment of Relative Contribution of Input Variables to Pavement Performance Prediction by Artificial Neural Networks

Abstract

Neural networks can be quite efficient at classification, pattern recognition, and prediction. However, the knowledge embedded in the neural network is opaque; that is, it is difficult to understand how neural networks arrive at the results. Here three explanatory mechanisms (attempts to explain the knowledge) are reviewed from the literature. Neural networks are trained to predict the present serviceability rating (PSR) of pavements with structural number, age, and cumulative equivalent single-axle loads as input variables. To determine the relative contribution of each input variable to the prediction of PSR, the method of partitioning of connection weights is employed. Neural networks are also trained with a few connection weights pruned, and the relative contribution of the input variables to the prediction of PSR is assessed. Apart from the three input variables mentioned above, another input variable, random numbers, is introduced. Its contribution to the prediction of PSR is found to be minimal.

Get full access to this article

View all access options for this article.

References

Eliot

L. B.

Ruling Neural Networks. Al Expert, Feb. 1995, pp. 8–10.

Smith

B. L.

, and Demetsky

M. J.

. Short-Term Traffic Flow Prediction: Neural Network Approach. In Transportation Research Record 1453, TRB, National Research Council, Washington, D.C., 1994, pp. 98–104.

Hecht-Nielsen

Kolmogorov’s Mapping Neural Network Existence Theorem. In IEEE First International Conference on Neural Networks, IEEE Press, New York, 1987, pp. II-19–II-32.

Garson

D. G.

Interpreting Neural-Network Connection Weights. Al Expert, April 1991, pp. 47–51.

Rule Generation from Neural Networks. IEEE Transactions on Systems, Man, and Cybernetics, Vol. 24, No. 8, Aug. 1994, pp. 1114–1124.

Narazaki

Reorganizing Knowledge in Neural Networks: An Explanatory Mechanism for Neural Networks in Data Classification Problems. IEEE Transactions on Systems, Man, and Cybernetics, Vol. 26, No. 1, Feb. 1996.

Lee

Y. H.

, Mohseni

, and Darter

M. I.

. Simplified Pavement Performance Models. In Transportation Research Record 1397, TRB, National Research Council, Washington, D.C., 1993, pp. 7–14.

Guide for the Design of Pavement Structures. American Association of State Highway and Transportation Officials, Washington, D.C., 1993.

Hornik

, Stinchcombe

, and White

. Multilayer Feedforward Networks Are Universal Approximators. Neural Networks, Vol. 2, 1989, pp. 359–366.

10.

Dorsey

R. E.

, Johnson

J. D.

, and Mayer

W. J.

. A Genetic Algorithm for the Training of Feedforward Neural Networks. In Advances in Artificial Intelligence in Economics, Financing, and Management, Jai Press Inc., Greenwich, Conn., Vol. 1, 1994, pp. 93–111.

11.

Shekharan

A. R.

Effect of Noisy Data on Pavement Performance Prediction by Artificial Neural Networks. In Transportation Research Record 1643, TRB, National Research Council, Washington, D.C., 1998, pp. 7–13.