收稿日期: 2013-10-16
修回日期: 2014-07-28
网络出版日期: 2015-05-15
基金资助
国家自然科学基金(51374242)资助
BP neural network optimized with QPSO algorithm improved by DELTA potential trough and its application
Received date: 2013-10-16
Revised date: 2014-07-28
Online published: 2015-05-15
于凤玲 , 周扬 , 陈建宏 , 周汉陵 . DELTA势阱改进QPSO优化BP算法及其应用[J]. 中国科学院大学学报, 2015 , 32(3) : 416 -421 . DOI: 10.7523/j.issn.2095-6134.2015.03.019
To improve the generalization ability of BP network for prediction, a BP neural network optimized with QPSO is proposed. This model uses the QPSO improved by δ potential trough to optimize the initial values of weights and thresholds of BP network. Then the data of each year's GDP are selected in training and prediction. The experiments show that the QPSO-BP network optimized by using δ potential trough produces stable prediction results. Compared with the prediction models of PSO-BP and BP, the proposed model has a better generalization ability and a higher accuracy. In addition, the calculation results of the improved QPSO-BP optimization algorithm model have smaller relative errors and average errors compared with the results of the models in the literature.
Key words： back-propagation neural network; PSO model; QPSO model; δ potential trough; GDP
[1] Yu Z F, Li J W, Liu K. Radar emitter recognition based on PSO-BP network[J]. AASRI Procedia, 2012(1):213-219.
[2] Ismail A, Jeng D S, Zhang L L. An optimised product-unit neural network with a novel PSO-BP hybrid training algorithm: applications to load-deformation analysis of axially loaded piles[J]. Engineering Applications of Artificial Intelligence, 2013, 26(10): 2 305-2 314.
[3] 王亮, 张宏伟, 岳琳, 等. PSO-BP 模型在城市用水量短期预测中的应用[J]. 系统工程理论与实践, 2007, 27(9): 165-170.
[4] Liu K, Guo W Y, Shen X L, et al. Research on the forecast model of electricity power industry loan based on GA-BP neural network[J]. Energy Procedia, 2012, 14: 1 918-1 924.
[5] 王德明, 王莉, 张广明. 基于遗传 BP 神经网络的短期风速预测模型[J]. 浙江大学学报: 工学版, 2012, 46(5): 837-841.
[6] Huang J, Luo H, Wang H, et al. Prediction of time sequence based on GA-BP neural net[J]. Journal of University of Electronic Science and Technology of China, 2009, 5:29.
[7] Liu Y P, Wu M G, Qian J X. Predicting coal ash fusion temperature based on its chemical composition using ACO-BP neural network[J]. Thermochimica acta, 2007, 454(1): 64-68.
[8] Kennedy J, Eberhart R C. Particle swarm optimization[C]//Proceedings of IEEE International Conference on Neural Networks, Piscataway, NJ: IEEE Press, 1995(4): 1 942-1 948.
[9] 曾建潮, 介婧, 崔志华. 微粒群算法[M]. 北京: 科学出版社, 2004: 1-23, 116-139.
[10] Sun J, Feng B, Xu W. Particle swarm optimization with particles having quantum behavior[C]//Congress on Evolutionary Computation. 2004, 325-331.
[11] Clerc M,Kennedy J. The partiele swarm: explosion,stability and convergence in a muli-dimensional complex space[J]. IEEE Transactions on Evolutionary Computation, 2002, 6: 58-73.
[12] Sun J. Adaptive parameter control for quantum-behaved particle swarm optimization on individual level[C]//IEEE International Conference on Systems, Man and Cybernetics, 2005: 3 049-3 054.
[13] 喻胜华, 邓娟.基于主成分分析和贝叶斯正则化BP神经网络的GDP预测[J].湖南大学学报:社科版,2011, 25(6): 42-45.
[14] 向平, 张蒙, 张智, 等. 基于BP神经网络的城市时用水量分时段预测模型[J]. 中南大学学报:自然科学版, 2012,43(8): 3 320-3 324.
[15] Majhi R, Panda G, Sahoo G. Efficient prediction of exchange rates with low complexity artificial neural network models[J]. Expert System with Applications, 2009,36: 181-189.
[16] 王鹏, 刘渊.基于改进的QPSQ训练BP网络的网络流量预测[J].计算机应用研究, 2009, 26(1): 299-301.
[17] Baffigi A, Golinelli R, Parigi G. Bridge models to forecast the euro area GDP[J]. International Journal of Forecasting, 2004, 20: 447-460.
[18] Zukime M, Junoh H M, Universiti K, et al. Predicting GDP growth in Malaysia using knowledge-based economy indicators: a comparison between neural network and econometric approaches[J]. Sunway College Journal, 2004(1):39-50.
[19] 熊志斌.基于ARIMA与神经网络集成的GDP时间序列预测研究[J].数理统计与管理,2011, 30(2): 306-314.
[20] 桂文林, 韩兆洲.基于状态空间模型的中国季度GDP季节调整(1996—2009年)[J].数量经济技术经济研究, 2011(7): 77-89.
[21] 何新易.基于时间序列模型的中国GDP增长预测分析[J].财经理论与实践,2012, 33(4): 96-99.
/
| 〈 |
|
〉 |
