Combined Forecasting Model on Automotive Logistics Demand Based on RBF Neural Network

Abstract:

This paper establishes a combination forecasting model based on Radia Basis Function Neural Network (RBFNN). It puts forward a seeking optimum parameters method by searching optimal solution for two-dimensional space (goal, spread) in a certain range, and realizes the combination forecasting of logistics demand, and improves the stability of network and the precision of prediction in RBFNN. An instance is presented to realize the model by MATLAB. The results showed that a good fitting precision and a high forecasting precision are reached in the application of the logistics demand forecasting by the designed forecasting model.

• Periodical: Advanced Materials Research (Volumes 148-149)
• Pages: 515-518
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.148-149.515
• Online since: October 2010
• Authors: Fei Fei Gao, Ji Chen Fang, Qiang Zhang, Qin Zhang, Zhan Gen Wang, Meng Zhu Shi
• Keywords: Automobile Logistics, Logistics Demand Forecasting, Neural Network (NN), Seeking Optimum Parameters in RBF

References

[1] Li Shi, G. Q. Cai. Logistics Technology, vol. 27, pp.160-162, (2008).

[2] Y. C. Feng, L.R. Peng. Communications Standardization, pp.110-113, June (2007).

[3] L. B Wu, Q. P Yan. Transportation Engineering and Information Technology, vol. 6, pp.65-68, (2008).

[4] X. F. Ji, L. B. Meng. Adaptive multi-step prediction PID control based on RBF neural network. Gansu Science and Technology, vol. 15, (2003).

[5] S.R. Gutierreza, A.O. Solisb, S. Mukhopadhyay, Lumpy Demand Forecasting Using Neural Networks, Int. J. Production Economics, (2007).