[1]WU Jian-sheng.Study on the shorttime rainfall prediction model of neural ensemble based on PSO algorithms[J].CAAI Transactions on Intelligent Systems,2006,1(2):67-73.
Copy

Study on the shorttime rainfall prediction model of neural ensemble based on PSO algorithms

CAAI Transactions on Intelligent Systems[ISSN 1673-4785/CN 23-1538/TP] Volume: 1 Number of periods: 2006 2 Page number: 67-73 Column: 学术论文—机器学习 Public date: 2006-10-25
Title:
Study on the shorttime rainfall prediction model of neural ensemble based on PSO algorithms
Author(s):
WU Jian-sheng
Department of Mathematics and Computer Science, Liuzhou Teache rs College, Liuzhou 545004，China
Keywords:
neural network ensemble;  particle swarm optimization;  quadratic program
CLC:
TP183
DOI:
-
Abstract:
This paper presents the evolving neural network architecture and connection weig hts based on Diversityguided Particle Swarm Optimization algorithms. The ensem ble strategy is carried out by using the quadratic programming to calculate the best nonnegative weights. The weighted coefficient of each ensemble individual is o b tained. This method can be used to establish the forecast model of the shortti m e rainfall. The applied example is built with the monthly mean rainfall in the w hole area of Guangxi. The result shows that this method can effectively increase the generalization ability of neural network. 
References:
［1］ DEAN A, ANDREW R, BRIAN H. Forecasting warmseason burn o ff low clouds at the San Francisco international airport using linear regression a nd a neural network ［J］. Apply Meteor, 2002, 41(6): 629-639.
［2］HSIEH W W. Nonlinear canonical correlation analysis of the tropical pacifi c climate variability using neural network approach［J］. Apply Meteor,2001,14(12) : 2528-2539. 
［3］GRIORGIO CORANI, GIOGIO GUARIO. Coupling fuzzy modeling and neural network s for river flood prediction ［J］. IEEE Transactions on Systems, Man, And Cyber neticPart C: Applications and Reviews, 2005, 25(3): 382-388.
［4］吴建生,金 龙, 农吉夫. 基于遗传算法的神经网络建模研究［J］. 数学的实践与认识, 2005, 35(1): 83-88.
?WU Jiansheng,JIN long,LONG Jifu. Study on model of neural network based on genet ic algorithm［J］.Mathematics in Practic and theory,2005,35(1):83-88.
［5］SOLLICH P, KROGH A. Learning with ensembles: how overfitting can be usef ul［A］. In Proceeding of Advances in Neural Information Processing Systems 8［C ］. Cambridge, MA: MIT Press, 1996.
［6］HANSEN L K, SALAMON P. Neural network ensembles ［J］. IEEE Transaction s on Pattern Analysis and Machine Intelligence, 1990,12(10): 993-1001.
［7］周志华, 陈世福. 神经网络集成［J］. 计算机学报, 2002, 25(1): 1-8. ZHOU Zhihua,CHEN Shifu. Neural nctwork ensemble［J］.Chinese Journal of Computer , 2002,25(1):1-8.
［8］MAO J. A case study on bagging boosting and basic ensembles of neur al networks for OCR［A］. In Proceedings of International Joint conference on Ne ural Networks 1998［C］. Anchorage, AK, 1998:1828-1833.
［9］GUTTA S, WECHSLER H. Face recognition using hybrid classifier systems［A ］. In Proceedings of International Conference Neural Network 1996［C］. Washin gton, DC, 1996：1017-1022.
［10］SOLLICH P, INTRATOR N. Classification of seismic signals by integrating ensembles of neural networks ［J］. IEEE Transactions Signal Processing,1998, 46(5):1194-1021.
［11］BONABEAU E, DORIGO M, G THERAULAZ. Inspiration for optimization from s ocial insect behavior ［J］. Nature, 2000, 406(6):39-42.
［12］KENNEDY J, EBERHART R C. Swarm intelligence［M］. San Francisco: Morgan K aufmann Publishers,2001.
［13］高海兵,高 亮,周 驰，等. 基于粒子群优化的神经网络训练算法研究［J］ . 电子学报, 2004, 32(9): 1572-1574.
GAO Haibing, GAO Liang, ZHOU Chi,et al. Particle swarm optimization based algori thm for neural network learning［J］.Acta Electronic Sinica,2004，32(9)；1572-15 74.
［14］RUMLHART D E, HINTON G E, WILLIAMS R J. Learning representations by back propagating errors. Nature, 1986, 323(11):456-466.
［15］REED R. Pruning algorithms—a survey［J］. IEEE Transactions on Neur al Net works, 1993(4): 740-747.
［16］JACQUES RIGET, JAKOB VESTERSTR.A Diversityguided Particle Swarm Op timiz erthe ARPSO［A］. Development and Practice of Artificial Intelligence Techniqu es［C］. Durban, South Africa, 1999,41-45.
［17］KENNEDY J, SPEARS W. Matching algorithms to problems: an experimental tes t of the particle swarm and some genetic algorithms on the multimode problem gen erator［A］. In Proceedings of IEEE International Conference on Evolutionary Com putation［C］. Anchorage, Alaska, USA, 1998.
［18］马永开, 唐小我, 杨桂元. 非负权重最优组合预测方法的基本理论研究［J］. 运筹与管理, 1997, 6(2): 1-8.
MA Yongkai, TANG Xiaowo.YANG Guiyuan. A study on basic theory of the optimal com binated prediction method of non negative weights［J］.Operations Research and M anagement Science, 1997,6(2):1-8.
［19］马振华. 运筹学与最优化理论［M］. 北京:清华大学出版社，1998.
［20］VAUTARD. SSA: a toolkit for noisy chaotic signals ［J］. Physica D, 1992, 58: 95-126.
［21］魏凤英, 曹鸿兴. 长期预测的数学模型及应用［M］.北京:气象出版社, 1990.
［22］王惠文. 偏最小二乘回归方法及其应用［M］.北京:国防工业出版社,1999. 
［23］金 龙.神经网络气象预报建模理论方法与应用［M］. 北京: 气象出版社, 2004.
Similar References:

Memo

-

Last Update: 2009-05-05

Copyright © CAAI Transactions on Intelligent Systems