正在加载图片...
·408· 智能系统学报 第11卷 能力均有较强的优势。 [7]ZHAO Huasheng,JIN Long,HUANG Ying,et al.An ob- 对3组不同类型和不同复杂度的真实降水数据 jective prediction model for typhoon rainstorm using particle 集的拟合和预测的对比实验结果表明,本文BS_ swarm optimization:neural network ensemble[J].Natural GEP算法对降雨时间序列数据的建模和预测结果 hazards,2014,73(2):427-437. 比传统GEP及其改进算法ADF_GEP、常用的BP和 [8]HE Suhong,FENG Taichen,GONG Yanchun,et al.Pre- dicting extreme rainfall over eastern Asia by using complex NAR神经网络自动建和预测算法的效果好,模型具 networks[J].Chinese physics B,2014,23(5):059202. 有一定的适用性,同时由于该算法模型对资料要求 [9]WU Jiansheng,LONG Jin,LIU Mingzhe.Evolving RBF 比较单一,只需降水历史数据,因而具有广泛的应 neural networks for rainfall prediction using hybrid particle 用价值。 swarm optimization and genetic algorithm[J].Neurocomput- 总之,BIS_GEP的改进是有效的,并为气象时 ing,2015,148:136-142. 间序列预测建模提供了一种切实可行的方法。下一 [10]DHANYA C T,KUMAR D N.Data mining for evolving 步工作是进一步研究和修改BIS_GEP算法,并将其 fuzzy association rules for predicting monsoon rainfall of In- 应用于高维多要素气象预测建模的研究和应用中。 dia[J].Journal of intelligent systems,2009.18(3):193- 另外,该方法若在实际业务中大规模推广应用还有 210. 若干问题有待解决,如海量高维气象数据建模的适 [11]TERZI O.Monthly rainfall estimation using data-mining process[J].Applied computational intelligence and soft 应性和稳定性问题等,都有待进一步研究。 computing,2012,2012:698071. 参考文献: [12]BERNARD E,NAVEAU P,VRAC M,et al.Clustering of maxima:spatial dependencies among heavy rainfall in [1]彭显忠,王谦,元昌安,等.数据挖掘技术在气象预报 France[J].Journal of climate,2013,26(20):7929- 研究中的应用J].干旱气象,2015,33(1):19-27. 7937. PENG Yuzhong,WANG Qian,YUAN Chang'an,et al. [13]TENG Shaohua,FAN Jihui,ZHU Haibin,et al.A cooper- Review of research on data mining in application of meteoro- ative multi-classifier method for local area meteorological logical forecasting[J].Journal of arid meteorology,2015, data mining[C]//Proceedings of the 18th IEEE Interna- 33(1):19-27. tional Conference on Computer Supported Cooperative [2]金龙,吴建生,林开平,等.基于遗传算法的神经网络 Work in Design.Hsinchu,Taiwan,China,2014:435- 短期气候预测模型[J].高原气象,2005,24(6):981- 440. 987 [14]FERREIRA C.Gene expression programming:mathemati- JIN Long,WU Jiansheng,LIN Kaiping,et al.Short-term cal modeling by artificial intelligence[M].Portugal:Angra climate prediction model of neural network based on genetic do Heroismo,2002:1-15. algorithms[J].Plateau meteorology,2005,24(6):981- [15]胡建军,唐常杰,段磊,等.基因表达式编程初始种群 987 的多样化策略[J].计算机学报,2007,30(2):305- [3]EL-SHAFIE A,JAAFER O,AKRAMI S A.Adaptive neu- 310. ro-fuzzy inference system based model for rainfall forecas- HU Jianjun,TANG Changiie,DUAN Lei,et al.The strat- ting in Klang River,Malaysia[J].International journal of egy for diversifying initial population of gene expression the physical sciences,2011,6(12):2875-2885 programming[J].Chinese journal of computers,2007,30 [4]GOSAV S,TIRON G.Artificial neural networks built for the (2):305-310. rainfall estimation using a concatenated database[J].Envi- [16]李太勇,唐常杰,吴江,等.基因表达式编程种群多样 ronmental engineering and management journal,2012,11 性自适应调控算法[J].电子科技大学学报,2010,39 (8):1383-1388. (2):279-283. [5]VENKADESH S,HOOGENBOOM G,POTTER W,et al. LI Taiyong,TANG Changjie,WU Jiang,et al.Adaptive A genetic algorithm to refine input data selection for air tem- population diversity tuning algorithm for gene expression perature prediction using artificial neural networks[J].Ap- programming[].Journal of university of electronic science plied soft computing,2013,13(5):2253-2260. and technology of China,2010,39(2):279-283. [6]RAHMAN M,SAIFUL ISLAM A H M,NADVI S Y M,et [17]宣士斌,刘怡光.基于混合差异度控制的基因表达式编 al.Comparative study of ANFIS and ARIMA model for 程[J].模式识别与人工智能,2012,25(2):186-194. weather forecasting in Dhaka[C]//Proceedings of IEEE in- XUAN Shibin,LIU Yiguang.GEP evolution algorithm ternational conference on informatics,electronics vision. based on control of mixed diversity degree[J].Pattern rec- Dhaka,Bangladesh,2013:1-6. ognition artificial intelligence,2012,25(2):186-194.能力均有较强的优势。 对 3 组不同类型和不同复杂度的真实降水数据 集的拟合和预测的对比实验结果表明,本文 BIS _ GEP 算法对降雨时间序列数据的建模和预测结果 比传统 GEP 及其改进算法 ADF_GEP、常用的 BP 和 NAR 神经网络自动建和预测算法的效果好,模型具 有一定的适用性,同时由于该算法模型对资料要求 比较单一, 只需降水历史数据, 因而具有广泛的应 用价值。 总之,BIS_GEP 的改进是有效的,并为气象时 间序列预测建模提供了一种切实可行的方法。 下一 步工作是进一步研究和修改 BIS_GEP 算法,并将其 应用于高维多要素气象预测建模的研究和应用中。 另外,该方法若在实际业务中大规模推广应用还有 若干问题有待解决,如海量高维气象数据建模的适 应性和稳定性问题等,都有待进一步研究。 参考文献: [1]彭昱忠, 王谦, 元昌安, 等. 数据挖掘技术在气象预报 研究中的应用[J]. 干旱气象, 2015, 33(1): 19⁃27. PENG Yuzhong, WANG Qian, YUAN Chang’ an, et al. Review of research on data mining in application of meteoro⁃ logical forecasting[ J]. Journal of arid meteorology, 2015, 33(1): 19⁃27. [2]金龙, 吴建生, 林开平, 等. 基于遗传算法的神经网络 短期气候预测模型[ J]. 高原气象, 2005, 24( 6): 981⁃ 987. JIN Long, WU Jiansheng, LIN Kaiping, et al. Short⁃term climate prediction model of neural network based on genetic algorithms[ J]. Plateau meteorology, 2005, 24 ( 6): 981⁃ 987 . [3]EL⁃SHAFIE A, JAAFER O, AKRAMI S A. Adaptive neu⁃ ro⁃fuzzy inference system based model for rainfall forecas⁃ ting in Klang River, Malaysia[J]. International journal of the physical sciences, 2011, 6(12): 2875⁃2885. [4]GOSAV S, TIRON G. Artificial neural networks built for the rainfall estimation using a concatenated database[ J]. Envi⁃ ronmental engineering and management journal, 2012, 11 (8): 1383⁃1388. [5] VENKADESH S, HOOGENBOOM G, POTTER W, et al. A genetic algorithm to refine input data selection for air tem⁃ perature prediction using artificial neural networks[ J]. Ap⁃ plied soft computing, 2013, 13(5): 2253⁃2260. [6]RAHMAN M, SAIFUL ISLAM A H M, NADVI S Y M, et al. Comparative study of ANFIS and ARIMA model for weather forecasting in Dhaka[C] / / Proceedings of IEEE in⁃ ternational conference on informatics, electronics & vision. Dhaka, Bangladesh, 2013: 1⁃6. [7]ZHAO Huasheng, JIN Long, HUANG Ying, et al. An ob⁃ jective prediction model for typhoon rainstorm using particle swarm optimization: neural network ensemble [ J]. Natural hazards, 2014, 73(2): 427⁃437. [8]HE Suhong, FENG Taichen, GONG Yanchun, et al. Pre⁃ dicting extreme rainfall over eastern Asia by using complex networks[J]. Chinese physics B, 2014, 23(5): 059202. [9] WU Jiansheng, LONG Jin, LIU Mingzhe. Evolving RBF neural networks for rainfall prediction using hybrid particle swarm optimization and genetic algorithm[J]. Neurocomput⁃ ing, 2015, 148: 136⁃142. [10] DHANYA C T, KUMAR D N. Data mining for evolving fuzzy association rules for predicting monsoon rainfall of In⁃ dia[J]. Journal of intelligent systems, 2009, 18(3): 193⁃ 210. [11] TERZI O. Monthly rainfall estimation using data⁃mining process[ J]. Applied computational intelligence and soft computing, 2012, 2012: 698071. [12]BERNARD E, NAVEAU P, VRAC M, et al. Clustering of maxima: spatial dependencies among heavy rainfall in France[ J]. Journal of climate, 2013, 26 ( 20): 7929⁃ 7937. [13]TENG Shaohua, FAN Jihui, ZHU Haibin, et al. A cooper⁃ ative multi⁃classifier method for local area meteorological data mining[C] / / Proceedings of the 18th IEEE Interna⁃ tional Conference on Computer Supported Cooperative Work in Design. Hsinchu, Taiwan, China, 2014: 435⁃ 440. [14]FERREIRA C. Gene expression programming: mathemati⁃ cal modeling by artificial intelligence[M]. Portugal: Angra do Heroismo, 2002: 1⁃15. [15]胡建军, 唐常杰, 段磊, 等. 基因表达式编程初始种群 的多样化策略[ J]. 计算机学报, 2007, 30 ( 2): 305⁃ 310. HU Jianjun, TANG Changjie, DUAN Lei, et al. The strat⁃ egy for diversifying initial population of gene expression programming[J]. Chinese journal of computers, 2007, 30 (2): 305⁃310. [16]李太勇, 唐常杰, 吴江, 等. 基因表达式编程种群多样 性自适应调控算法[ J]. 电子科技大学学报, 2010, 39 (2): 279⁃283. LI Taiyong, TANG Changjie, WU Jiang, et al. Adaptive population diversity tuning algorithm for gene expression programming[J]. Journal of university of electronic science and technology of China, 2010, 39(2): 279⁃283. [17]宣士斌, 刘怡光. 基于混合差异度控制的基因表达式编 程[J]. 模式识别与人工智能, 2012, 25(2): 186⁃194. XUAN Shibin, LIU Yiguang. GEP evolution algorithm based on control of mixed diversity degree[J]. Pattern rec⁃ ognition & artificial intelligence, 2012, 25(2): 186⁃194. ·408· 智 能 系 统 学 报 第 11 卷
<<向上翻页向下翻页>>
©2008-现在 cucdc.com 高等教育资讯网 版权所有