基于过程神经元网络的时序预测模型研究
|
摘要
时间序列预测是用被预测事物过去和现在的观测数据,构造依时间变化的序列模型,借助其反映出来的发展过程、方向和趋势,进行外推或延伸,从而预测下一段时间可能达到的状态和水平,是预测领域的重要组成部分,在工程领域和科学研究中具有重要意义。过程神经元网络可以同时表达系统多输入时变信号的空间聚合作用和时间过程的累积效应,能够直接处理过程式数据,且具有在时变函数空间上的连续性和对满足Lipschitz条件泛函的逼近能力,以及与Turing机等价的计算能力,这使过程神经元网络在解决实际问题中有着广泛的适应性和灵活性。
论文对已有的用于时序预测问题研究的理论、方法、模型进行归纳总结,对目前方法存在的问题和困难进行了分析,并基于时序预测模型及径向基过程神经网络,提出了一种新的非线性组合预测方法。该方法将单一预测方法得出的预测结果,作为RBFPNN的输入,而实际的历史数据值作为网络的期望输出,这样避免了一般线性组合预测方法中确定各个权重的复杂计算,又可涵盖实际问题的线性与非线性两方面,综合地利用各种单一预测方法提供的信息,提高了预测精度。最后将这种预测方法应用在航空公司的旅客数量预测中,取得了满意的结果。
针对非线性时间序列中的混沌时间序列分析问题,论文从重构相空间理论出发,探讨确定相空间嵌入维数和延迟时间各种不同的方法。对时间序列混沌特性的识别方法,及混沌相空间预测模型进行了详细讨论,并根据相空间重构技术和过程神经网络的技术原理,寻求二者的结合点,从而提出了一种相空间重构与过程神经网络相结合的混沌时间序列预测方法。并以太阳黑子数预测为例验证了算法的有效性。
针对时序预测中的Markov链状态转移预测问题,提出了一种基于离散过程神经元网络(DPNN)的等效状态转移预测方法和模型,探讨了DPNN与Markov模型在一定条件下对于系统状态转移问题描述的等价关系。对于任意的Markov链,本文给出了与之等效DPNN的构建方法和Markov链状态转移概率条件约束下的网络权值矩阵求解算法,仿真实验结果验证了方法的有效性。
Time series prediction is forecast to be things of the past and present observational data, structural changes in the time-series model and use it to reflect in the development process, the direction and trends, extrapolation or extended, which is expected to predict a period of time , the forecast is an important component of the field, in engineering and scientific research. Process neural networks expression system can be more time-varying input signals in the polymerization of space and time course of the cumulative effect, it can directly process data, and has a time-varying function in the continuity of space and to meet Lipschitz condition functional approaching capacity, as well as the Turing machine equivalent computing power, which makes the process neural network in the solution of practical problems of a wide range of adaptability and flexibility.
This paper has been forecast for timing problems with the theories, methods, models summary, the present method of the problems and difficulties of the analysis, and forecasting model based on the timing and process of RBF neural network, a combination of new nonlinear forecasting methods. The method means that the forecast results of a single forecast, as RBFPNN input, the actual value of the historical data network as the expectations of output, so to avoid a general linear combination of forecasting methods identified in the various weight of the complex, could cover the practical problems of both linear and non-linear, integrated use of a single prediction method to provide the information and improve the prediction accuracy. Finally, the methods used in this projection airline forecast in the number of passengers, and achieved satisfactory results.
Nonlinear time series against the chaotic time series, the paper from the reconstruction phase space theory, determine the phase space of embedding dimension and a variety of time delay methods. Chaos on the time sequence of the identification method, and chaotic phase space forecasting model were discussed in detail, and in accordance with phase space reconstruction process neural network technology and the technical principles for the combination of the two, and thus proposed a phase-space neural network structure and the process of combining chaotic time series forecasting methods. And the sunspot forecasting as an example verifies the effectiveness of the algorithm.
Against the prediction of the state Markov chain prediction transfer, a process based on discrete neural network (DPNN) transfer the equivalent state forecasting methods and models were created, this paper explored the DPNN Markov model under certain conditions for the transfer of state system Description of equivalence relations. For arbitrary Markov chain, this paper proposed the equivalent DPNN Construction methods and state Markov chain transition probability under the conditions of the network-weight-matrix algorithm, the simulation results demonstrate the effectiveness of the method.
论文对已有的用于时序预测问题研究的理论、方法、模型进行归纳总结,对目前方法存在的问题和困难进行了分析,并基于时序预测模型及径向基过程神经网络,提出了一种新的非线性组合预测方法。该方法将单一预测方法得出的预测结果,作为RBFPNN的输入,而实际的历史数据值作为网络的期望输出,这样避免了一般线性组合预测方法中确定各个权重的复杂计算,又可涵盖实际问题的线性与非线性两方面,综合地利用各种单一预测方法提供的信息,提高了预测精度。最后将这种预测方法应用在航空公司的旅客数量预测中,取得了满意的结果。
针对非线性时间序列中的混沌时间序列分析问题,论文从重构相空间理论出发,探讨确定相空间嵌入维数和延迟时间各种不同的方法。对时间序列混沌特性的识别方法,及混沌相空间预测模型进行了详细讨论,并根据相空间重构技术和过程神经网络的技术原理,寻求二者的结合点,从而提出了一种相空间重构与过程神经网络相结合的混沌时间序列预测方法。并以太阳黑子数预测为例验证了算法的有效性。
针对时序预测中的Markov链状态转移预测问题,提出了一种基于离散过程神经元网络(DPNN)的等效状态转移预测方法和模型,探讨了DPNN与Markov模型在一定条件下对于系统状态转移问题描述的等价关系。对于任意的Markov链,本文给出了与之等效DPNN的构建方法和Markov链状态转移概率条件约束下的网络权值矩阵求解算法,仿真实验结果验证了方法的有效性。
Time series prediction is forecast to be things of the past and present observational data, structural changes in the time-series model and use it to reflect in the development process, the direction and trends, extrapolation or extended, which is expected to predict a period of time , the forecast is an important component of the field, in engineering and scientific research. Process neural networks expression system can be more time-varying input signals in the polymerization of space and time course of the cumulative effect, it can directly process data, and has a time-varying function in the continuity of space and to meet Lipschitz condition functional approaching capacity, as well as the Turing machine equivalent computing power, which makes the process neural network in the solution of practical problems of a wide range of adaptability and flexibility.
This paper has been forecast for timing problems with the theories, methods, models summary, the present method of the problems and difficulties of the analysis, and forecasting model based on the timing and process of RBF neural network, a combination of new nonlinear forecasting methods. The method means that the forecast results of a single forecast, as RBFPNN input, the actual value of the historical data network as the expectations of output, so to avoid a general linear combination of forecasting methods identified in the various weight of the complex, could cover the practical problems of both linear and non-linear, integrated use of a single prediction method to provide the information and improve the prediction accuracy. Finally, the methods used in this projection airline forecast in the number of passengers, and achieved satisfactory results.
Nonlinear time series against the chaotic time series, the paper from the reconstruction phase space theory, determine the phase space of embedding dimension and a variety of time delay methods. Chaos on the time sequence of the identification method, and chaotic phase space forecasting model were discussed in detail, and in accordance with phase space reconstruction process neural network technology and the technical principles for the combination of the two, and thus proposed a phase-space neural network structure and the process of combining chaotic time series forecasting methods. And the sunspot forecasting as an example verifies the effectiveness of the algorithm.
Against the prediction of the state Markov chain prediction transfer, a process based on discrete neural network (DPNN) transfer the equivalent state forecasting methods and models were created, this paper explored the DPNN Markov model under certain conditions for the transfer of state system Description of equivalence relations. For arbitrary Markov chain, this paper proposed the equivalent DPNN Construction methods and state Markov chain transition probability under the conditions of the network-weight-matrix algorithm, the simulation results demonstrate the effectiveness of the method.
引文
[1]吴怀宇.时间序列分析与综合[M].武汉:武汉大学出版社,2004.
[2]张树京,齐立心.时间序列分析简明教程[M].北京:清华大学出版社,2003.
[3]阮晓钢.神经计算科学.北京:国防工业出版社,2006.
[4]柯莱蒙兹,韩德瑞,陆懋祖.预测经济时间序列.北京:北京大学出版社,2006.
[5] J.P.Marques de Sa.Pattern Recognition.北京:清华大学出版社,2002.
[6]何新贵,许少华.过程神经元网络.北京:科学技术出版社,2007
[7]何新贵,梁久祯.过程神经元网络的若干理论问题.中国工程科学,2000, 2(12):40-44.
[8]王海燕,卢山著.非线性时间序列分析及应用[M].北京:科学出版社,2006.
[9] Box G E P and Jenk ngs GM 1 Time Series Analysis forecasing and control Oak land, CA: Holded Day, 1976.
[10]丁刚.面向状态预报的过程神经网络模型及其应用研究[D].哈尔滨:哈尔滨工业大学,2006.
[12] A.Lapedes R.Farber.Nonlinear Signal Prediction and System Modeling.Los Alamos National Laboratory Technical eport,LA-UR-87-2662,1987.
[13] P.J.Werbos.Generalization of Backpropagation with Application to a Recurrent Market Model.Neural Networks,1988,339~356.
[14] W.Halbert.Economic Prediction Using neural Networks:The Case of IBM Daily Stock Returns.Proceedings of the IEEE International Conference on Neural Networks,New York:IEEE,1988,451~459.
[15] B.E.Ydsite.Forecasting and Control Using Adaptive Connectionist Networks.Computer and Chemical Engineering, 1990, 14:583~589.
[16] K.Hornik M.Stinchcombe H.White.Multilayer Feedforward Networks Are Universal Approximators.Neural Networks,1989,2(5):359~366.
[17] K.Funahashi.On The Approximate Realization of Continuous Mappings by Neural Networks.Neural Networks,1989, 2(3):183~192.
[18]秦大建,李志蜀.基于神经网络的时间序列组合预测模型研究及应用.计算机应用,2006,26.
[19]赵海青.神经网络优选组合预测模型在电力负荷预测中的应用.
[20]刘豹,胡代平.神经网络在预测中的一些应用研究[J].系统工程学报,1999,14(4)
[21]文新辉,牛明杰.神经网络与预测方法研究[J].预测与控制,1992(4)
[22]司昕.预测方法中的神经网络模型.预测, 1998, 2: 32~35
[23] He Xin-Gui, Liang Jiu-Zhen.Process neural networks.World ComputerCongress 2000, Proceedings of Conference on Intelligent Information Processing.Beijing , 2000:143-146.
[24]何新贵,许少华.输入输出均为时变函数的过程神经网络及应用.软件学报,2003,14(4):764-769.
[25]张希,吴志真,雷勇.航空发动机试车中转子故障诊断.计算机测量与控制,2005,13(11):1182~1185
[26]许少华,何新贵.基于函数正交基展开的双隐层过程神经元网络及其应用.控制与决策,2004,19(1):36-39.
[27] Bates.J.N Granger.C.W.J.Combined Forecasting.Jornal of Operational Research,1969,(20):451-68.
[28]文新辉,牛明杰.一种新的基于神经网络的非线性组合预测方法[J].系统工程理论与实践,1994,12.
[28]文新辉,陈开周.一种新的最优组合预测方法及其应用[J].西安电子科技大学学报,1994,21(3).
[29]赵海清.神经网络优选组合预测模型在电力负荷预测中的应用.运筹与管理,2005,14(1).
[30] Volker Tresp and Reimar Hofmann Siemens AG.Nonlinear Time-Series Pridiction with Missing and Noisy Data.Corporate Technology Department Information and Communications,1997.
[31]韩冬梅,牛文清,杨荣.线性与非线性最优组合预测方法的比较研究[J].情报科学,2007,25(11).
[32]徐兵,王丽华.GM(1,1)模型的一类性质研究[J].系统工程与电子技术,2000,22(5).
[33]严修红,许伦辉.基于神经网络实现的改进灰色组合预测及应用[J].交通与计算机2006,24(6).
[34]王霜,殷国富,罗中先,廖敏.基于GM(1,1)模型的用电量灰预测方法[J].西华大学学报(自然科学版),2007,26(1).
[35]杭力,韩直,杜益文.BP神经网络和GM(1,1)灰色模型在公路客运量预测中的应用[J].公路交通技术,2006(4).
[36]姚志学,孙慧钧.时间数列回归与相关分析中的自相关问题[J].东北财经大学学报,2003,6(30).
[37]许少华何新贵.径向基过程神经网络及其应用研究.北京航空航天大学学报, 2004,30(1):14-17.
[38]韩敏.混沌时间序列预测理论与方法.北京:北京水利水电出版社,2007.
[39]刘士达,梁福明.混沌时间序列预测理论与方法北京:北京大学出版社,2003.
[40] Peter D W.The use of fast Fourier Transform for the estimation of power spectra:a methord based on time averaging over short,modified periodograms.IEEE Transactions on Audio and Electroacoustics,1967,15(2):70~73.
[41]顾圣士,王志谦,程极泰.太阳黑子数时间序列的分形研究及预测[J].应用数学和力学,1999,20(1).
[42]徐自励,王一扬,周激流.估计非线性时间序列嵌入延迟时间和延迟时间窗的C-C平均方法.四川大学学报(工程科学版),2007,39(1).
[43]李天舒.混沌时间序列分析方法研究及其应用[D].哈尔滨:哈尔滨工业大学,2006.
[44]陈铿,韩伯棠.混沌时间序列分析中的相空间重构技术综述[J].计算机科学,2005,32(4)。
[45]杨绍清,贾传荧.两种实用的相空间重构方法[J].物理学报.2002,51(11).
[46]肖方红,阎桂荣,韩宇航.混沌时序相空间重构参数确定的信息论方法[J].物理学报.2005,54(2).
[47]丁晶,王文圣,赵永龙.以互信息为基础的广义相关系数.四川大学学报(工程科学版).2002,34(3).
[48]吕小青,曹彪,曾敏.确定延迟时间互信息法的一种算法.计算物理,2002,23(2).
[49]王海燕,盛昭瀚.混沌时间序列相空间重构参数的选取方法.东南大学学报(自然科学版),2000,30(5).
[50]杨志安,王光瑞.用等间距分格子法计算互信息函数确定延迟时间.计算物理,1995,12(4).
[51]向小东,郭耀煌.混沌时间序列最大Lyapunov指数的计算[J].预测,2001,20(5)
[52]丁刚,钟诗胜.基于时变阈值过程神经网络的太阳黑子数预测[J].物理学报,2007,56(2).
[53]张亚光,梁静国,宋艳.相空间重构与神经网络相结合的预测方法研究.经济师,2005(1).
[54]谭文,王耀南,刘祖润,周少武.非线性系统混沌运动的神经网络控制[J].物理学报,2002,51(11).
[55] WANG Zhaoxia,ZHEN Zengqiang.Study of Predicting Combined Chaotic Time Series Using Neural Networks[J].Jurnal of Optoelectronics·Laser,200415(10).
[56]蒋传文,权先璋,张勇传,混沌理论在电力负荷预测中的应用[J].武汉交通科技大学学报.1999, 23 (6) :6082611
[57]李军,刘君华.一种新型广义RBF神经网络在混沌时间序列预测中的研究.物理学报.2005.54(10).
[58]杜彦巍,周锋,何潇.应用相空间重构理论分析电力负荷时间序列.电气应用,2006,25(3).
[58]杨杰,卢凌.基于RBF径向基神经网络的混沌时间序列预测.交通与计算机,1999,17(1).
[60] De Falco,A.Della Cioppa,A.Iazzetta .Optimizing Neural Networks for Time Series Prediction.National Research Council of Italy[J].1997.
[61]李冬梅,王正欧.基于RBF神经网络的混沌时间序列预测.模式识别与人工智能,2001,14(2).
[62]李冬梅,王正欧.基于RBF网络的混沌时间序列的建模与多步预测.系统工程与电子技术,2002,24(6).
[63]简相超,政君里,混沌神经网络预测算法评价准则与性能分析.清华大学学报(自然科学版),2001,41(7).
[64]刘次华.随机过程.武汉:华中科技大学出版社,2001
[65]戴葵,仇广煜,胡守仁.一种基于离散马尔可夫模型的神经网络可靠性设计方法.计算机工程与科学,1999,21(3):10-14.
[66]刘兴坡,周玉文.污水流量序列随机模拟的马尔可夫链模型.哈尔滨工业大学学报,2005,35(5):93-101.
[67]金子.神经网络的Hopfield异步动力学模型及其应用.工程数学,2000,16(4).
[68]严姝娜,韦思滢.改进权马尔可夫链实现对相依随机变量序列的预测.管理学报,2005,2(1).combined model time series and
[69] Zhan-Qian Lu.Markov Switching Time Series Models with Application to a Daily Runoff Series.Water Resources Research.1998.
[70]王兴富,谷红伟,戴学丰.马尔可夫链在离散事件系统中的应用.自动化技术与应用,2000,19(3).
[71] He Xin-Gui, Liang Jiu-Zhen.Process neural networks.World Computer Congress 2000, Proceedings of Conference on Intelligent Information Processing.Beijing , 2000:143-146.
[72]陈继光,祝令德.基于神经网络的马尔可夫预测模型.计算机工程与应用,2006(06).
[2]张树京,齐立心.时间序列分析简明教程[M].北京:清华大学出版社,2003.
[3]阮晓钢.神经计算科学.北京:国防工业出版社,2006.
[4]柯莱蒙兹,韩德瑞,陆懋祖.预测经济时间序列.北京:北京大学出版社,2006.
[5] J.P.Marques de Sa.Pattern Recognition.北京:清华大学出版社,2002.
[6]何新贵,许少华.过程神经元网络.北京:科学技术出版社,2007
[7]何新贵,梁久祯.过程神经元网络的若干理论问题.中国工程科学,2000, 2(12):40-44.
[8]王海燕,卢山著.非线性时间序列分析及应用[M].北京:科学出版社,2006.
[9] Box G E P and Jenk ngs GM 1 Time Series Analysis forecasing and control Oak land, CA: Holded Day, 1976.
[10]丁刚.面向状态预报的过程神经网络模型及其应用研究[D].哈尔滨:哈尔滨工业大学,2006.
[12] A.Lapedes R.Farber.Nonlinear Signal Prediction and System Modeling.Los Alamos National Laboratory Technical eport,LA-UR-87-2662,1987.
[13] P.J.Werbos.Generalization of Backpropagation with Application to a Recurrent Market Model.Neural Networks,1988,339~356.
[14] W.Halbert.Economic Prediction Using neural Networks:The Case of IBM Daily Stock Returns.Proceedings of the IEEE International Conference on Neural Networks,New York:IEEE,1988,451~459.
[15] B.E.Ydsite.Forecasting and Control Using Adaptive Connectionist Networks.Computer and Chemical Engineering, 1990, 14:583~589.
[16] K.Hornik M.Stinchcombe H.White.Multilayer Feedforward Networks Are Universal Approximators.Neural Networks,1989,2(5):359~366.
[17] K.Funahashi.On The Approximate Realization of Continuous Mappings by Neural Networks.Neural Networks,1989, 2(3):183~192.
[18]秦大建,李志蜀.基于神经网络的时间序列组合预测模型研究及应用.计算机应用,2006,26.
[19]赵海青.神经网络优选组合预测模型在电力负荷预测中的应用.
[20]刘豹,胡代平.神经网络在预测中的一些应用研究[J].系统工程学报,1999,14(4)
[21]文新辉,牛明杰.神经网络与预测方法研究[J].预测与控制,1992(4)
[22]司昕.预测方法中的神经网络模型.预测, 1998, 2: 32~35
[23] He Xin-Gui, Liang Jiu-Zhen.Process neural networks.World ComputerCongress 2000, Proceedings of Conference on Intelligent Information Processing.Beijing , 2000:143-146.
[24]何新贵,许少华.输入输出均为时变函数的过程神经网络及应用.软件学报,2003,14(4):764-769.
[25]张希,吴志真,雷勇.航空发动机试车中转子故障诊断.计算机测量与控制,2005,13(11):1182~1185
[26]许少华,何新贵.基于函数正交基展开的双隐层过程神经元网络及其应用.控制与决策,2004,19(1):36-39.
[27] Bates.J.N Granger.C.W.J.Combined Forecasting.Jornal of Operational Research,1969,(20):451-68.
[28]文新辉,牛明杰.一种新的基于神经网络的非线性组合预测方法[J].系统工程理论与实践,1994,12.
[28]文新辉,陈开周.一种新的最优组合预测方法及其应用[J].西安电子科技大学学报,1994,21(3).
[29]赵海清.神经网络优选组合预测模型在电力负荷预测中的应用.运筹与管理,2005,14(1).
[30] Volker Tresp and Reimar Hofmann Siemens AG.Nonlinear Time-Series Pridiction with Missing and Noisy Data.Corporate Technology Department Information and Communications,1997.
[31]韩冬梅,牛文清,杨荣.线性与非线性最优组合预测方法的比较研究[J].情报科学,2007,25(11).
[32]徐兵,王丽华.GM(1,1)模型的一类性质研究[J].系统工程与电子技术,2000,22(5).
[33]严修红,许伦辉.基于神经网络实现的改进灰色组合预测及应用[J].交通与计算机2006,24(6).
[34]王霜,殷国富,罗中先,廖敏.基于GM(1,1)模型的用电量灰预测方法[J].西华大学学报(自然科学版),2007,26(1).
[35]杭力,韩直,杜益文.BP神经网络和GM(1,1)灰色模型在公路客运量预测中的应用[J].公路交通技术,2006(4).
[36]姚志学,孙慧钧.时间数列回归与相关分析中的自相关问题[J].东北财经大学学报,2003,6(30).
[37]许少华何新贵.径向基过程神经网络及其应用研究.北京航空航天大学学报, 2004,30(1):14-17.
[38]韩敏.混沌时间序列预测理论与方法.北京:北京水利水电出版社,2007.
[39]刘士达,梁福明.混沌时间序列预测理论与方法北京:北京大学出版社,2003.
[40] Peter D W.The use of fast Fourier Transform for the estimation of power spectra:a methord based on time averaging over short,modified periodograms.IEEE Transactions on Audio and Electroacoustics,1967,15(2):70~73.
[41]顾圣士,王志谦,程极泰.太阳黑子数时间序列的分形研究及预测[J].应用数学和力学,1999,20(1).
[42]徐自励,王一扬,周激流.估计非线性时间序列嵌入延迟时间和延迟时间窗的C-C平均方法.四川大学学报(工程科学版),2007,39(1).
[43]李天舒.混沌时间序列分析方法研究及其应用[D].哈尔滨:哈尔滨工业大学,2006.
[44]陈铿,韩伯棠.混沌时间序列分析中的相空间重构技术综述[J].计算机科学,2005,32(4)。
[45]杨绍清,贾传荧.两种实用的相空间重构方法[J].物理学报.2002,51(11).
[46]肖方红,阎桂荣,韩宇航.混沌时序相空间重构参数确定的信息论方法[J].物理学报.2005,54(2).
[47]丁晶,王文圣,赵永龙.以互信息为基础的广义相关系数.四川大学学报(工程科学版).2002,34(3).
[48]吕小青,曹彪,曾敏.确定延迟时间互信息法的一种算法.计算物理,2002,23(2).
[49]王海燕,盛昭瀚.混沌时间序列相空间重构参数的选取方法.东南大学学报(自然科学版),2000,30(5).
[50]杨志安,王光瑞.用等间距分格子法计算互信息函数确定延迟时间.计算物理,1995,12(4).
[51]向小东,郭耀煌.混沌时间序列最大Lyapunov指数的计算[J].预测,2001,20(5)
[52]丁刚,钟诗胜.基于时变阈值过程神经网络的太阳黑子数预测[J].物理学报,2007,56(2).
[53]张亚光,梁静国,宋艳.相空间重构与神经网络相结合的预测方法研究.经济师,2005(1).
[54]谭文,王耀南,刘祖润,周少武.非线性系统混沌运动的神经网络控制[J].物理学报,2002,51(11).
[55] WANG Zhaoxia,ZHEN Zengqiang.Study of Predicting Combined Chaotic Time Series Using Neural Networks[J].Jurnal of Optoelectronics·Laser,200415(10).
[56]蒋传文,权先璋,张勇传,混沌理论在电力负荷预测中的应用[J].武汉交通科技大学学报.1999, 23 (6) :6082611
[57]李军,刘君华.一种新型广义RBF神经网络在混沌时间序列预测中的研究.物理学报.2005.54(10).
[58]杜彦巍,周锋,何潇.应用相空间重构理论分析电力负荷时间序列.电气应用,2006,25(3).
[58]杨杰,卢凌.基于RBF径向基神经网络的混沌时间序列预测.交通与计算机,1999,17(1).
[60] De Falco,A.Della Cioppa,A.Iazzetta .Optimizing Neural Networks for Time Series Prediction.National Research Council of Italy[J].1997.
[61]李冬梅,王正欧.基于RBF神经网络的混沌时间序列预测.模式识别与人工智能,2001,14(2).
[62]李冬梅,王正欧.基于RBF网络的混沌时间序列的建模与多步预测.系统工程与电子技术,2002,24(6).
[63]简相超,政君里,混沌神经网络预测算法评价准则与性能分析.清华大学学报(自然科学版),2001,41(7).
[64]刘次华.随机过程.武汉:华中科技大学出版社,2001
[65]戴葵,仇广煜,胡守仁.一种基于离散马尔可夫模型的神经网络可靠性设计方法.计算机工程与科学,1999,21(3):10-14.
[66]刘兴坡,周玉文.污水流量序列随机模拟的马尔可夫链模型.哈尔滨工业大学学报,2005,35(5):93-101.
[67]金子.神经网络的Hopfield异步动力学模型及其应用.工程数学,2000,16(4).
[68]严姝娜,韦思滢.改进权马尔可夫链实现对相依随机变量序列的预测.管理学报,2005,2(1).combined model time series and
[69] Zhan-Qian Lu.Markov Switching Time Series Models with Application to a Daily Runoff Series.Water Resources Research.1998.
[70]王兴富,谷红伟,戴学丰.马尔可夫链在离散事件系统中的应用.自动化技术与应用,2000,19(3).
[71] He Xin-Gui, Liang Jiu-Zhen.Process neural networks.World Computer Congress 2000, Proceedings of Conference on Intelligent Information Processing.Beijing , 2000:143-146.
[72]陈继光,祝令德.基于神经网络的马尔可夫预测模型.计算机工程与应用,2006(06).