Tax prediction by a hybrid model of RBF neural network and particle swarm optimization algorithm

摘要：

Tax prediction is very significant to make up the economy policy and adjust the structure of economy.A hybrid model of RBF neural network and particle swarm optimization algorithm is proposed to predict tax in the paper.The connection weights which are connected hidden layer and output layer,and the centers and the widths of radial basis function in hidden layer are selected by particle swarm optimization to solve the influence of them on prediction ability of RBF neural network.The error of tax prediction between PSO-RBFNN and RBFNN is computed,which illustrates that the tax prediction ability of PSO-RBFNN is better than that of RBFNN.

关键词： tax prediction optimization algorithm neural network particle swarm optimization prediction technology

作者: He Yong-mei Guo Qin

作者单位: Jilin University of Finance and Economics Changchun 130117,China Jilin University of Finance and Economics Changchun 130U7,China

会议类型: 国际会议

会议名称: 2010 4th International Conference on Intelligent Information Techonlogy Application(第四届智能信息技术应用国际学术研讨会 IITA 2010)

会议地点: 秦皇岛

会议语种:英文

页码: 147-150

在线出版日期: 2010-11-05（万方平台首次上网日期，不代表论文的发表时间）