Abstract
The paper researches on the behavior of particles in the PSO, and improves the situation of easily falling into local optimum by the right combination of simulated annealing and PSO. In the paper, the author compared the original PSO and the improved SAPSO algorithms in neural network training. The empirical research shows that the improved algorithm performed better than the PSO algorithm in global search ability, and the prediction accuracy is greatly increased.
Publisher
Trans Tech Publications, Ltd.
Reference10 articles.
1. Li M, Lin S. Several Problems of Exchange Rate Forecasting Using Neural Network. International Symposium on Intelligent Information Systems and Applications, OCT 28-30, 2009 Qingdao, PEOPLES R CHINA.
2. Wolfgang Polasek and Lei Ren. A multivariate GARCH - M model for exchange rates in the US, Germany and Japan [M]. Institute of Statistics and Econometrics University of Basel, (1999).
3. Jerry Coakley and Ana - Maria Fuertes. Nonparametric cointegration analysis of real exchange rate [J]. Applied Financial Economics, 2001, (11): 1 - 8.
4. Guoqiang Zhang, Eddy Patuwo, Michael Hu. Forecasting with artificial neural networks: The state of the art [J]. International Journal of Forecasting, 1998, 14: 35 - 62.
5. Y Shi, RC Eberhart. A modified swarm optimizer [A]. IEEE International Conference of Evolutionary Computation [C]. Anchorage, Alaska: IEEE Press, May, (1998).