Application of an improved artificial neural network in battlefield ammunition consumption prediction

被引：0

作者：

Cui, YQ ^{[1
]}

Li, ZB ^{[1
]}

机构：

[1] Shandong Univ, Sch Math & Syst Sci, Jinan 250100, Peoples R China

来源：

Proceedings of the 2005 International Conference on Management Science & Engineering (12th), Vols 1- 3 | 2005年

关键词：

artificial neural network; ammunition consumption; predict; principle components; correlation; scatter;

D O I：

暂无

中图分类号：

F [经济];

学科分类号：

02 ;

摘要：

In this paper one improved artificial neural network (ANN) method is used to predict the battlefield ammunition consumption. There are so many factors affecting the ammunition consumption that the input nodes number is large. In order to reduce the input nodes, the factors that affect the ammunition consumption are standardized firstly. Then they are reduced using the principle components analysis method. For hidden nodes, their number is firstly limited to less than the square root of product of input nodes number and output nodes number. Then the correlation coefficients between different hidden nodes in same layer are calculated. Lastly the hidden nodes are merged or deleted according to correlation coefficients. The structure of ANN is optimized by above method. The prediction result of the battlefield ammunition consumption using the improved ANN is shown to be satisfying.

引用

页码：182 / 186

页数：5