基于遗传算法优化的BP神经网络的组合预测模型方法研究

doi:10.3864/j.issn.0578-1752.2012.23.020

摘要/Abstract

摘要： 【目的】提出以传统猪瘟发病率为对象的组合预测模型。【方法】利用ARIMA模型以及灰色模型GM(1,1)进行数据初始化处理，将初步处理结果作为优化后的BP神经网络输入构建组合模型。【结果】利用组合模型对2000年到2009年的月度发病数据进行实例分析，结果表明预测数据精度达到97.379%，较ARIMA模型，灰色模型、BP神经网络模型分别提高了5.469%、3.499%、1.188%，模型平稳性增强，预测结果良好。【结论】本研究为动物疫情测报提供了有效的分析手段，验证了组合模型在动物疫情研究中的可行性，并可为其它动物疫病提供借鉴和参考。

关键词: 组合模型 , ARIMA , GM(1 , 1) , 遗传算法 , BP神经网络

Abstract: 【Objective】 The combined forecasting model for studying the classic swine fever morbidity was proposed.【Method】The data was processed by ARIMA and GM(1,1) initially, then the results were used as the inputs of the majorizing BP neural network.【Result】The combined model was used to analyze the monthly data from 2000/01 to 2008/05, and the accuracy of the forecasting results from 2008/06 to 2009/06 was 97.379%. The prediction accuracy of the combined model increased by 5.469%, 3.499%, and 1.188%, respectively, compared with BP neural network, ARIMA, GM(1,1), which suggest that the combined model is more steady than traditional methods.【Conclusion】This research has supplied an efficient analytical tool for animals diseases forecasting work, verified the feasibility of the combined model in animal diseases forecasting research, and also has provided references to other animal diseases.

Key words: combined model , ARIMA , GM (1 , 1) , genetic algorithm , BP neural network

梁毅, 刘世洪. 基于遗传算法优化的BP神经网络的组合预测模型方法研究[J]. 中国农业科学, 2012, 45(23): 4924-4930.

LIANG Yi, LIU Shi-Hong. Research on the Combined Forecast Model Method Based on BP Neural Network Improved by Genetic Algorithm[J]. Scientia Agricultura Sinica, 2012, 45(23): 4924-4930.

0
/ / 推荐

导出引用管理器 EndNote|Reference Manager|ProCite|BibTeX|RefWorks

链接本文: https://www.chinaagrisci.com/CN/10.3864/j.issn.0578-1752.2012.23.020

https://www.chinaagrisci.com/CN/Y2012/V45/I23/4924

参考文献

[1]陶玉顺, 黄涛, 袁东波, 徐健. 目前我国猪瘟的流行现状及防控策略. 畜牧与兽医, 2008, 40(8): 90-94.

Tao Y S, Huang T, Yuan D B, Xu J. Current situation and preventive and control strategy of classic swine fever in China. Animal Husbandry and Veterinary Medicine, 2008, 40(8): 90-94. (in Chinese)

[2]许丹宁, 王洪斌, 肖建华. 基于ARIMA的猪瘟发病率预测模型的建立. 中国预防兽医学报, 2009(5): 352-355.

Xu D N, Wang H B, Xiao J H. Construction of an ARI MA model for prediction of the incidence of classical swine fever. Chinese Journal of Preventive Veterinary Medicine, 2009(5): 352-355. (in Chinese)

[3]Guan P, Huang D S，Zhou B S. Forecasting model for the incidence of hepatitis A based on artificial neural network. World Journal of Gastroenterology, 2004, 10(24): 3579-3582.

[4]邓奎, 李龙国, 伍仪保. 组合模型在农业用水量预测中的应用. 安徽农业科学, 2011, (4):1902-1903.

Deng K, Li L G, Wu Y B. Application of combined model in the prediction of agricultural water consumption. Journal of Anhui Agricultural Science, 2011, (4):1902-1903. (in Chinese)

[5]徐聪. 数据挖掘方法在传统预测模型中的应用. 河北工业科技, 2009, 26(4)：280-283.

Xü C. Application of data mining methods to traditional prediction mathematical models. Hebei Journal of Industrial Science and Technology, 2009, 26(4)：280-283. (in Chinese)

[6]田富鹏, 马亮亮. 应用ARIMA模型预测青海海西州地区肺心病的发病率. 中国组织工程研究与临床康复, 2010(14): 6243-6246.

Tian F P, Ma L L. Application of ARIMA model in estimation of pulmonary heart disease in Qinghai Haixizhou region. Journal of Clinical Rehabilitative Tissue Engineering Research, 2010(14): 6243-6246. (in Chinese)

[7]王洪斌, 许丹宁, 李静. 基于时间序列模型的猪瘟月发病率的分析. 中国畜牧兽医学会信息技术分会2008年会学术研讨会论文集, 2008.

Wang H B, Xu D N, Li J. The analysis of class swine fever monthly morbidity based on time series model. 2008 Annual Academic Meeting of Information Technology Branch of Chinese Association of Animal & Veterinary Science, 2008. (in Chinese)

[8]迟道才, 唐延芳, 顾拓, 于森, 李峥, 马宗正. 灌溉用水量的并联型灰色神经网络预测. 农业工程学报, 2009, 25(5): 26-29.

Chi D C, Tang Y F, Gu T, Yu S, Li Z, Ma Z Z. Predication of irrigation water use using parallel gray neural network. Transactions of the Chinese Society of Agricultural Engineering, 2009, 25(5):26-29. (in Chinese)

[9]丛爽. 面向MATLAB工具箱的神经网络理论与应用. 合肥:中国科学技术大学出版社, 2009.

Cong S. Neural Network Theory and Application Based on MATLAB Toolbox. Hefei: Press of University of Science and Technology of China, 2009. (in Chinese)

[10]张立明. 人工神经网络的模型以及应用. 上海:复旦大学出版社, 1993.

Zhang L M. Models and Applications of Artificial Neural Networks. Shanghai: Fudan University Press, 1993. (in Chinese)

[11]Watrous R L. Learning Algorithms for Connectionist Network: Applied Gradient Methods of Nonlinear Optimization. New York: IEEE Press. 1990.

[12]Zhou J H, Shen G L, Ding X L, Yang T. BP neural network in analysis of disease influential factors. Journal of Clinical Rehabilitative Tissue Engineering Research, 2011(15): 1702-1705.

[13]MATLAB中文论坛. MATLAB神经网络30个案例分析. 北京:北京航空航天大学出版社, 2010: 286.

MATLAB Chinese Forum. 30 case studies of MATLAB neural network. Beijing: Beihang University Press, 2010: 286. (in Chinese)

[14]张长胜, 欧阳丹彤, 岳娜, 张永刚. 一种基于遗传算法和LM算法的混合学习算法. 吉林大学学报. 理学版, 2008(46):675-680.

Zhang C S, Ouyang D T, Yue N, Zhang Y G. A hybrid algorithm based on genetic algorithm and levenberg-marquardt. Journal of Jilin University: Science Edition, 2008(46):675-680. (in Chinese)

[15]Sam R. Levenberg-marquardt Optimization. http://media.cs.ohiou.edu/ teaching/cs641/week3/LMA.pdf.

[16]张栋，蔡开元. 基于遗传算法的神经网络两阶段学习方案. 系统仿真学报, 2003(8):1088-1090.

Zhang D, Cai K Y. A genetic-algorithm-based two-stage learning scheme for neural networks. Journal of System Simulation, 2003(8): 1088-1090. (in Chinese)

[17]毛开翼. 关于组合预测中的权重确定及应用[D]. 成都：成都理工大学, 2007.

Mao K Y. Combination forecast in weight determination and application[D]. Chengdu: Chengdu University of Technology, 2007. (in Chinese)

[18]刘晓东. ARIMA模型与GM组合模型预测中国人口死亡率的研究[D]. 潍坊: 潍坊医学院, 2009.

Liu X D. Study on combination model of ARIMA and GM in forecasting population mortality rate of China[D]. Weifang: Weifang Medical University, 2009. (in Chinese)

[19]郑玉胜, 黄介生. 基于神经网络的灌溉用水量预测. 灌溉排水学报, 2004, 23(2):59-61.

Zheng Y S, Huang J S. Forecast of irrigation water use based on neural network. Journal of Irrigation and Drainage, 2004, 23(2): 59-61. (in Chinese)

[20]孟博, 李荣冰, 刘建业, 李睿佳. 基于改进反向传播算法的跨音速攻角补偿修正研究, 系统工程与电子技术, 2010, 32(12): 2681-2685.

Meng B, Li R B, Liu J Y, Li R J. Research on compensation- correction of transonic angle-of-attack based on improved back-propagation algorithm. Systems Engineering and Electronics, 2010, 32(12): 2681-2685. (in Chinese)

[21]张爱兵, 陈建, 王正军, 李典谟, 田洁. BP网络模型和LOGIT模型在森林害虫测报上的应用初报——以安徽省潜山县马尾松毛虫为例. 生态学报, 2001, 21(12) :2159-2165.

Zhang A B, Chen J, Wang Z J, Li D M, Tian J. The application of BP model and logit model to prediction of forest insect pests. Acta Ecologica Sinica, 2001,21(12):2159-2165. (in Chinese)

[22]刘宁. 基于组合模型的交通流量预测方法[D]. 上海：华东理工大学, 2010.

Liu N. Traffic flow forecasting method based on combination mode[D]. Shanghai: East China University of Science and Technology, 2010. (in Chinese)

[23]崔吉峰, 乞建勋, 杨尚东. 基于粒子群改进BP神经网络的组合预测模型及其应用, 中南大学学报: 自然科学版, 2009(40): 190-194.

Cui J F, Qi J X, Yang S D. Combined forecasting model based on BP improved by PSO and its application. Journal of Central South University: Science and Technology, 2009(40): 190-194. (in Chinese)

[24]蔡立, 徐鑫. MATLAB 神经网络工具箱在非线性系统建模中的应用. 机电工程技术, 2008(37):82-84.

Cai L, Xü X, The application of MATLAB neural network toolbox on non-liner system modeling. Mechanical and Electrical Engineering Technology, 2008(37):82-84. (in Chinese)

[25]Eric M, Barend M, Katie A, Sarah C. Animal movements and the spread of infectious diseases. Trends in Microbiology, 2006(14): 125-131.