基于过程神经网络的时序数据挖掘研究
|
摘要
关于时间序列的问题涉及经济、气象、水利、林业等多个领域，目前对于时序数据的挖掘是数据挖掘研究的热点之一，具有很强的理论意义和实际应用意义。而由于时序数据挖掘的应用背景广泛，同时时序数据具有时变性、高维性、噪声干扰及波动性等复杂特点，时序数据挖掘一直是数据挖掘领域的研究难点之一。过程神经网络是传统神经网络在时间域上的拓展，其过程式输入放宽了传统神经元网络模型对于输入的同步瞬时限制，是更一般化的人工神经元网络模型，在处理与时间相关的问题上，具有自身独特的优势。本文将过程神经网络引入时序数据挖掘中，结合小波多分辨分析等相关技术，对时序背景下的聚类、分类、预测等问题展开深入地研究。
首先，针对时序背景下的聚类问题，提出一种基于小波和改进自组织过程神经网络的时序聚类方法，应用小波变换对原时序数据进行小波分解，在保留相关聚类特征的原则下，对信号进行重构。然后将重构信号拟合为时变函数作为过程神经网络的输入，应用改进的竞争算法训练自组织过程神经网络，利用过程神经网络输入为时变函数的特点，将经小波处理后的时序信号特征充分纳入到聚类分析中，网络提取输入函数隐含的过程式模式特征并进行自组织，给出了改进的竞争学习算法。最后应用UCI数据集进行仿真实验结果表明，该方法能有效应用于时序聚类中。
其次，针对时序分类问题，提出一种竞争型径向基过程神经网络时序分类器。首先给出了竞争型径向基过程神经网络的拓扑结构，引入复合竞争过程神经元隐层，将连续时间点上的离散数据拟合为时变函数作为网络的输入，突破了时序数据不等长的限制，由复合竞争过程神经元单元完成对过程式输入信息的模式匹配和时空聚合运算，省去了输出层线性连接权的计算，简化了网络结构和训练过程。然后针对各聚类大小及网络训练结果，采用不同的聚类系数，提高了分类器的泛化能力，给出了具体的学习算法。最后以多变量时序分类仿真数据验证了分类器的性能和有效性。
再次，在时序预测方面，提出两种用于预测的过程神经网络模型。一是遗传过程神经网络模型，在将输入数据表示成一组正交基展开式的基础上，引入移民算子，应用改进的遗传算法优化遗传过程神经网络的训练过程，应用人均GDP预测问题和对比分析验证了模型的预测精度和泛化性能。二是提出一种改进的前馈过程神经网络模型，给出了组合式过程神经网络学习算法并应用于CPI预测研究中，结果表明，该模型的预测精度明显高于传统神经网络模型。
最后，针对时序背景下的控制问题，提出一种基于前馈过程神经网络的时序控制和非线性系统辨识方法。首先基于时序控制问题的时变性特点及复杂非线性特征，将前馈双隐层过程神经网络引入到时序控制和非线性系统辨识当中，利用过程神经网络处理时变特征问题的优势，将时变和非线性特征充分纳入到时序控制中，并说明了该模型应用于时序控制的优势。然后针对具体木材干燥过程控制的特点，应用改进的学习算法训练过程神经网络，得到两种水曲柳木材干燥控制模型。两种模型与传统神经网络模型比较分析结果表明，过程神经网络模型具备更好的预测精度和泛化能力，其性能优于传统BP神经网络模型，过程神经网络应用于时序控制和非线性系统辨识问题是可行的。
本文工作围绕时序数据挖掘的若干问题展开，其中涉及到聚类、分类和预测的若干方法和模型，并通过实验、实例验证和比较分析的方式验证了方法和模型的性能和有效性，其中时序聚类和时序分类器的研究为进一步时序数据挖掘研究的拓展提供了较好的理论基础和思路。
Time series problem involves several fields, such as economy, meteorology, waterconservancy, forestry etc. At present, time series data mining has been the focus of datamining, which has strong theoretical and practical significance. Because of some complexcharacteristics of time series data, for example, time variation, high dimension, noise jammingand volatility, time series data mining is always one of the difficulties in data mining research.Process neural network (PNN) is a development of traditional neural network in the timedomain. Process input of PNN relax synchronization instantaneous limit on inputs intraditional neural network models, and is more general artificial neural network model. It hasits own unique advantages in dealing with time related problems. In this thesis, process neuralnetworks is introduced into time series data mining to deeply studying on clustering,classification and prediction problems, combining with wavelet multi-resolution analysis andrelated technologies.
Firstly, a time series clustering method is proposed base on wavelet and improvedself-organization process neural network for time series clustering problem. Original timeseries data is decomposed by wavelet. Under the principle of reserving clusteringcharacteristics, the signal is reconstructed. And then reconstructed signal which has beenfitted into time-varying functions is used as the input of process neural network.Self-organization PNN is trained by improved competition algorithm. Making use oftime-varying input characteristic of PNN, the timing signal characteristics processed bywavelet is considered adequately in clustering analysis. Network extracts implicit processmode characteristics of input function to self-organize. The improved competition learningalgorithm is given. Finally, clustering result of UCI datasets shows that the proposed approachcan be applied to timing clustering effectively.
Secondly, a time series classifier is proposed based on competitive radial basis processneural network for time series classification. First, the topology of competitive radial basisprocess neural network is given. The compound competition process neuron hidden layer isadded to network. Discrete data in continues time points are fitted to time-varied functions asnetwork input. The classifier breaks through time series data unequal length restriction.Pattern matching and temporal aggregation operation of time-varied input is achieved bycompetition process neuron units. The linear connection weights calculation in the outputlayer is omitted to simplify network structure and training process. Then generalization ability of classifier is improved by using different clustering coefficient for each clustering sizes andnetwork training results. Learning algorithm is given. Finally performance and effectivenessof classifier are proved by multivariable time series classification simulation data.
Thirdly, two process neural network models are proposed for time series prediction. Oneis genetic process neural network model. After input data are represented as a set oforthogonal basis expansions, using improved genetic algorithm to optimize genetic processneural network training process by introducing immigration operator. Prediction accuracy andgeneralization performance of the model is verified by per capita GDP prediction problem andcontrast analysis. The second model is an improved feed forward process neural network,giving combined process neural network algorithm and applying to CPI prediction. The resultshows that this model’s prediction accuracy is obviously higher than traditional neuralnetwork model.
Lastly, a time series control and system identification method based on PNN is proposedfor control problem in time series context.First, based on time-varying feature and complexnonlinear characteristic of time series control problem, double hidden layer process neuralnetwork is introduced into time series control and system identification. Nonlinear andtime-varying characteristics are taken into the consideration of time series control for theadvantage of processing time-varying problem using PNN, and analyzed the model advantageused in time series control.Then, two wood drying control models are built by PNN trained byimproved learning algorithm for the characteristics of wood drying process control. Twomodels’ analysis results compared to traditional neural network models show that processneural network model has better prediction control precision and generalization ability, theperformance is superior to the traditional neural network model, PNN applied in time seriescontrol and nonlinear system identification problem is feasible.
This thesis is mainly carried on some problems of tine series data mining, which involvesin some methods and models of clustering, classification and prediction. The performance andeffectiveness of these methods and models are verified by experiments, example validationsand comparative analysis. The research on time series clustering and time series classifierprovides a good theoretical basis and ideas for further time series data mining research.
首先，针对时序背景下的聚类问题，提出一种基于小波和改进自组织过程神经网络的时序聚类方法，应用小波变换对原时序数据进行小波分解，在保留相关聚类特征的原则下，对信号进行重构。然后将重构信号拟合为时变函数作为过程神经网络的输入，应用改进的竞争算法训练自组织过程神经网络，利用过程神经网络输入为时变函数的特点，将经小波处理后的时序信号特征充分纳入到聚类分析中，网络提取输入函数隐含的过程式模式特征并进行自组织，给出了改进的竞争学习算法。最后应用UCI数据集进行仿真实验结果表明，该方法能有效应用于时序聚类中。
其次，针对时序分类问题，提出一种竞争型径向基过程神经网络时序分类器。首先给出了竞争型径向基过程神经网络的拓扑结构，引入复合竞争过程神经元隐层，将连续时间点上的离散数据拟合为时变函数作为网络的输入，突破了时序数据不等长的限制，由复合竞争过程神经元单元完成对过程式输入信息的模式匹配和时空聚合运算，省去了输出层线性连接权的计算，简化了网络结构和训练过程。然后针对各聚类大小及网络训练结果，采用不同的聚类系数，提高了分类器的泛化能力，给出了具体的学习算法。最后以多变量时序分类仿真数据验证了分类器的性能和有效性。
再次，在时序预测方面，提出两种用于预测的过程神经网络模型。一是遗传过程神经网络模型，在将输入数据表示成一组正交基展开式的基础上，引入移民算子，应用改进的遗传算法优化遗传过程神经网络的训练过程，应用人均GDP预测问题和对比分析验证了模型的预测精度和泛化性能。二是提出一种改进的前馈过程神经网络模型，给出了组合式过程神经网络学习算法并应用于CPI预测研究中，结果表明，该模型的预测精度明显高于传统神经网络模型。
最后，针对时序背景下的控制问题，提出一种基于前馈过程神经网络的时序控制和非线性系统辨识方法。首先基于时序控制问题的时变性特点及复杂非线性特征，将前馈双隐层过程神经网络引入到时序控制和非线性系统辨识当中，利用过程神经网络处理时变特征问题的优势，将时变和非线性特征充分纳入到时序控制中，并说明了该模型应用于时序控制的优势。然后针对具体木材干燥过程控制的特点，应用改进的学习算法训练过程神经网络，得到两种水曲柳木材干燥控制模型。两种模型与传统神经网络模型比较分析结果表明，过程神经网络模型具备更好的预测精度和泛化能力，其性能优于传统BP神经网络模型，过程神经网络应用于时序控制和非线性系统辨识问题是可行的。
本文工作围绕时序数据挖掘的若干问题展开，其中涉及到聚类、分类和预测的若干方法和模型，并通过实验、实例验证和比较分析的方式验证了方法和模型的性能和有效性，其中时序聚类和时序分类器的研究为进一步时序数据挖掘研究的拓展提供了较好的理论基础和思路。
Time series problem involves several fields, such as economy, meteorology, waterconservancy, forestry etc. At present, time series data mining has been the focus of datamining, which has strong theoretical and practical significance. Because of some complexcharacteristics of time series data, for example, time variation, high dimension, noise jammingand volatility, time series data mining is always one of the difficulties in data mining research.Process neural network (PNN) is a development of traditional neural network in the timedomain. Process input of PNN relax synchronization instantaneous limit on inputs intraditional neural network models, and is more general artificial neural network model. It hasits own unique advantages in dealing with time related problems. In this thesis, process neuralnetworks is introduced into time series data mining to deeply studying on clustering,classification and prediction problems, combining with wavelet multi-resolution analysis andrelated technologies.
Firstly, a time series clustering method is proposed base on wavelet and improvedself-organization process neural network for time series clustering problem. Original timeseries data is decomposed by wavelet. Under the principle of reserving clusteringcharacteristics, the signal is reconstructed. And then reconstructed signal which has beenfitted into time-varying functions is used as the input of process neural network.Self-organization PNN is trained by improved competition algorithm. Making use oftime-varying input characteristic of PNN, the timing signal characteristics processed bywavelet is considered adequately in clustering analysis. Network extracts implicit processmode characteristics of input function to self-organize. The improved competition learningalgorithm is given. Finally, clustering result of UCI datasets shows that the proposed approachcan be applied to timing clustering effectively.
Secondly, a time series classifier is proposed based on competitive radial basis processneural network for time series classification. First, the topology of competitive radial basisprocess neural network is given. The compound competition process neuron hidden layer isadded to network. Discrete data in continues time points are fitted to time-varied functions asnetwork input. The classifier breaks through time series data unequal length restriction.Pattern matching and temporal aggregation operation of time-varied input is achieved bycompetition process neuron units. The linear connection weights calculation in the outputlayer is omitted to simplify network structure and training process. Then generalization ability of classifier is improved by using different clustering coefficient for each clustering sizes andnetwork training results. Learning algorithm is given. Finally performance and effectivenessof classifier are proved by multivariable time series classification simulation data.
Thirdly, two process neural network models are proposed for time series prediction. Oneis genetic process neural network model. After input data are represented as a set oforthogonal basis expansions, using improved genetic algorithm to optimize genetic processneural network training process by introducing immigration operator. Prediction accuracy andgeneralization performance of the model is verified by per capita GDP prediction problem andcontrast analysis. The second model is an improved feed forward process neural network,giving combined process neural network algorithm and applying to CPI prediction. The resultshows that this model’s prediction accuracy is obviously higher than traditional neuralnetwork model.
Lastly, a time series control and system identification method based on PNN is proposedfor control problem in time series context.First, based on time-varying feature and complexnonlinear characteristic of time series control problem, double hidden layer process neuralnetwork is introduced into time series control and system identification. Nonlinear andtime-varying characteristics are taken into the consideration of time series control for theadvantage of processing time-varying problem using PNN, and analyzed the model advantageused in time series control.Then, two wood drying control models are built by PNN trained byimproved learning algorithm for the characteristics of wood drying process control. Twomodels’ analysis results compared to traditional neural network models show that processneural network model has better prediction control precision and generalization ability, theperformance is superior to the traditional neural network model, PNN applied in time seriescontrol and nonlinear system identification problem is feasible.
This thesis is mainly carried on some problems of tine series data mining, which involvesin some methods and models of clustering, classification and prediction. The performance andeffectiveness of these methods and models are verified by experiments, example validationsand comparative analysis. The research on time series clustering and time series classifierprovides a good theoretical basis and ideas for further time series data mining research.
引文
[1] Massimo Panella.Advances in biological time series prediction by neuralnetworks. Biomedical Signal Processing and Control,2011,6(2):112-120P.
[2] Ashu Jain,Avadhnam Madhav Kumar.Hybrid neural network models for hydrologic time series forecasting.Applied Soft Computing,2007,7(2):585-592P.
[3] FangMei Tseng, HsiaCheng Yu, GwoHsiung Tzeng.Combining neural network modelwith seasonal time series ARIMA model. Technological Forecasting and SocialChange,2002,69(1):71-87P.
[4] G.Peter Zhang. An investigation of neural networks for linear time-series forecasting.Computers&Operations Research.2001,28(12):183-1202P.
[5] Mohammad Assaad, Romuald Bone, Hubert Cardot.A new boosting algorithm forimproved time-series forecasting with recurrent neural networks. Information Fusion,2008,9(1):41-55P.
[6] Sven F. Crone, Nikolaos Kourentzes.Feature selection for time series prediction–Acombined filter and wrapper approach for neural networks. Neurocomputing,2010,73(10-12):1923-1936P.
[7] Thomas J. Glezakos,Theodore A. Tsiligiridis,Lazaros S. Iliadis,Constantine P.Yialouris, Fotis P. Maris, Konstantinos P. Ferentinos.Feature extraction for time-seriesdata: An artificial neural network evolutionary training model for the management ofmountainous watersheds. Neurocomputing,2009,73(1-3):49-59P.
[8] D. Gao, Y. Kinouchi, K. Ito, X. Zhao. Neural networks for event extraction from timeseries: a back propagation algorithm approach.Future Generation Computer Systems,2005,21(7):1096-1105P.
[9] ArdalaniFarsa Muhammad, Zolfaghari Saeed.Chaotic time series prediction withresidual analysis method using hybrid Elman–NARX neural networks.Neurocomputing,2010,73(13-15):2540-2553P.
[10]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):41-44P.
[11]何新贵,梁久祯,许少华.过程神经元网络的训练及其应用.中国工程科学,2001(3):31-35P.
[12]许少华,何新贵,王兵.一种分式过程神经元网络及其应用研究.计算机研究与发展,2006,12(2):2088-2094P.
[13]丁刚,钟诗胜.具有时变输入输出函数的反馈过程神经元网络及应用.控制与决策,2007,11(1):91-94P.
[14]许少华,何新贵.多聚合过程神经元网络及其学习算法研究.计算机学报,2007,8(1):48-56P.
[15]钟诗胜,朴树学,丁刚.改进BP算法在过程神经元网络中的应用.哈尔滨工业大学学报,2006,11(6):840-842P.
[16]许少华,何新贵,刘坤,王兵.关于连续过程神经元网络的一些理论问题.电子学报,2006,15(10):1838-1841P.
[17]王丹丹,刘显德.一种基于自组织过程神经网络的动态样本半监督学习算法.智能计算机与应用,2011,1(3):88-90P.
[18]孟庆德.基于过程神经元网络的市场评价.技术经济,2006,10(7):71-73P.
[19]杨晓龙,刘希宋.基于过程神经元网络的中国油气资源可持续发展能力评价.哈尔滨工业大学学报,2006,11(5):58-63P.
[20]丁刚,钟诗胜.基于时变阈值过程神经元网络的太阳黑子数预测.物理学报,2007,10(2):1224-1230P.
[21]付旭云,丁刚,钟诗胜,边旭.基于双隐层径向基过程神经网络的润滑油金属含量预测.润滑于密封,2009,34(2):18-21P.
[22]钟诗胜,李洋.基于小波过程神经元网络的飞机发动机状态监视.航空学报,2007,20(1):68-71P.
[23]何新贵,许少华.过程神经元网络及其在时变信息处理中的应用.智能系统学报,2006,9(1):1-8P.
[24]钟诗胜,栾圣罡,丁刚.基于过程神经元网络与气动热力参数的航空发动机状态监视.南京理工大学学报,2006,12(5):533-541P.
[25]许少华,刘扬,何新贵.基于过程神经元网络的水淹层自动识别系统.石油学报,2004,10(4):54-57P.
[26]葛利,陈广胜.基于过程神经网络的木材生长轮密度预测.林业科学,2008,11(1):63-65P.
[27]葛利.一种基于混合遗传算法学习的过程神经网络.哈尔滨工业大学学报,2005,17(7):986-989P.
[28] E.Keogh Data mining and machine learning in time series database[C].Proc of the5thIndustrial Conference on Data Mining (ICDM). Leipzig:[s. n.],2005.
[29] R.Agrawal, C.Faloutsos, A.Swami. Efficient similarity Search in sequencedatabases[C].Proc of the4th InternationalConference on Foundations of DataOrganization and Algorithms.London:Springer-Verlag,1993:69-84P.
[30] C.Faloutsos, M.Ranganathan, Y.Manolopoulos. Fast Subsequence matching in timeseries databases[C].Proc of the ACM SIGMOD International Conference onManagement of Data.Mineapolis: ACM Press,1994:419-429P.
[31] E.Keogh, S.Chu,D.Hart,M.Pazzani.Segmenting time series:A survey and Novelapproach. In M.Last,A.Kandel,H.Bunke,eds, Data Mining In Time-series Databases,World Seientific,2004:1-22P.
[32] C.S.M ller-Levet,F.Klawonn,K.-H.Cho,O.Wolkenhauer,Fuzzy clustering of shorttime series and unevenly distributed sampling points[C].Proeeedings of the5thInternational symposium on Intelligent Data Analysis,Berli,Germany,2003:330-340P.
[33] T.Oates,M.D.Schmill,P.R.Cohen.A Method for Clustering the Experiences of aMobile Robot that Accords with Human Judgments[C].Proc.of the17th NationalConference on Artificial Intelligence,2000:846-851P.
[34] R.Agrawal,C.Faloutsos,A.Swami.Effieient similarity search in sequenecedatabases[C].FODO-Foundations of Data Organization and Algorithms Proeeedings，1993:69-84P.
[35] Z.Struzik, A.Sibe.Measuring Time Series Similarity Through Large Singular FeaturesRevealed with Wavelet Transformation.In Proc.ofthe10th Int. Workshop on Databaseand Expert Systems Application,1999:162-166P.
[36] M.Gavrilov,D.Angnelov,P.Indyk,R.Motwani.Mining the stock market:which measureis best?[C].In proceedings of the6th ACM Int.Conference on Knowledge Diseoveryand DataMining.Boston,MA,2000:487-496P.
[37] Christian Dose, Silvano Cincotti.Clustering of financial time series with application toindex and enhanced index tracking portfolio. http://www.elsevier.com/locate/physa,Physica A2005:145–151P.
[38] A.M. Alonso, J.R. Berrendero, A. Hernández, A. Justel.Time series clustering basedon forecast densities. Computational Statistics&Data Analysis2006(51):762-776P.
[39] P. Cheeseman, J. Stutz. Bayesian classification (AutoClass):theory and results. In:U.M. Fayyard, G. Piatetsky-Shapiro,P. Smyth, R. Uthurusamy (Eds.), Advances inKnowledge Discovery and Data Mining, AAAI/MIT Press, Cambridge,MA,1996.
[40] M.Corduas, D.Piccolo.Time series clustering and classification by the autoregressivemetric.Computational Statistics&Data Analysis.2008,(52):1860-1872P.
[41] KuoChin Hsu,ShengTun Li.Clustering spatial–temporal precipitation data usingwavelet transform and self-organizing map neural network. Advances in WaterResources.2010(33):190–200P.
[42] Yiin Xiong, DitYan Yeung.Time series clustering with ARMA mixtures. PatternRecognition2004,(37):1675-1689P.
[43] Lian Liu, Lihong Huanga, Mingyong Lai, Chaoqun Mac.Projective ART with buffersfor the high dimensional space clusteringand an application to discover stockassociations. Neurocomputing2009(72):1283–1295P.
[44] Aymen Cherif, Hubert Cardot, Romuald Bone.SOM time series clustering andprediction with recurrent neural networks. Neurocomputing,2011(74):1936–1944P.
[45] A. Meyer-B se, A. Saalbach, O. Lange, A. Wismüer.Unsupervised clustering of fMRIand MRI time series.Biomedical Signal Processing and Control2007(2):295–310P.
[46] T W Liao.Clustering of time series data. Pattern Recognition.2005(38):1857-1874P.
[47] E.Keogh, S.Kasetty. On the need for time series data mining benchmarks:a survey andempirical demonstration.Data mining and knowledge discovery.2003(7):349-371P.
[48] P. D’Urso. Fuzzy clustering for data time array with inlier and outlier time trajectories.IEEE Transactions on Fuzzy Systems.2005,13(5):583–604P.
[49] C S M ller-Levet, F Klawonn, K Cho et al. Clustering of unevenly sampled geneexpressiontime-series data. Fuzzy Sets and Systems.2005,152(1):49–66P.
[50] T W Liao, F.Tang, J.Qu et al. Grinding wheel condition monitoring with boostedminimum distanceVclassifiers. Mechanical Systems and Signal Processing.2008(22):217–232P.
[51] P.D’Urso, E A Maharaj. Autocorrelation-based fuzzy clustering of time series. FuzzySets and Systems.2009(160):3565–3589P.
[52] L A Garcia-Escudero, A. Gordaliza. A proposal for robust curve clustering. Journal ofClassification.2005(22):185-201P.
[53] E A Maharaj. Comparison of non-stationary time series in the frequency domain.ComputationalStatistics&Data Analysis.2002(40):131-141P.
[54] D.Piccolo. A distance measure for classifying ARIMA models. Journal of Time SeriesAnalysis.1990,11(2):153-164P.
[55] E A Maharaj. Using wavelets to compare time series patterns. Wavelets,Multiresolution and Information Processing.2005,3(4):511-521P.
[56] J. Caiado, N.Crato, D.Pena. A periodogram-based metric for time series classification.Computational Statistics&Data Analysis.2006(50):2668-2684P.
[57] A M Alonso, J R Berrendero, A.Hernández et al. Time series clustering based onforecast density.Computational Statistics&Data Analysis.2006,51(2):762-776P.
[58] T.Warren Liao.Clustering of time series data—a survey.Pattern Reeognition.2005(38):1857-1874P.
[59] E.Keogh,K.Chakrabarti,M.Pazzani,P.Mehrotra.Dimensionality Reduetion for FastSimilarity Search in Large Time Series Databases.Journal of Knowledge andInformation Systems.2001(3):263-286P.
[60]杨一鸣,潘嵘,潘嘉林,杨强,李磊.时间序列分类问题的算法比较.计算机学报,2007,30(8):1260-1263P.
[61] YoungSeon Jeong,Myong K. Jeong,Olufemi A.Omitaomu.Weighted dynamic timewarping for time series classification.Pattern Recognition,2011(44):2231–2240P.
[62] E.Keogh, S.Kasetty. On the need for time series data mining benchmarks: A surveyand empirical demonstration.Proceedings of the8th ACM SIGKDD InternationalConferenceon Knowledge Discovery and Data Mining. Edmonton, Alberta, Canada,2002:102-111P.
[63] A.NanoPoulos,R.Aleoek Y,Manolo Poulos.Feature-based Classification of Time SeriesData.International Journal of Computer Research.NY:Nova Seienee Publisher.2001:49-61P.
[64] Eiekeler,S.Kosmala,A.Rigoll G.Hidden Markov Model based continuous online gesture recognition.In IEEE Proc.Internat Conf.on Pattern Recognition.1998(2):1206-1208P.
[65] K.N. Plataniotis, D. Androutsos, A.N. Venetsanopoulos, D.G.Lainiotis.A newtime series classification approach. Signal Processing.1996(54):191-199P.
[66] Jorge Caiado, Nuno Crato, Daniel Pe a.A periodogram-based metric for time seriesclassification.Computational Statistics&Data Analysis2006(50):2668-2684P.
[67] Xiaoqing Weng,Junyi Shen.Classification of multivariate time series using localitypreserving projections.Knowledge-Based Systems2008(21):581-587P.
[68] Xiaoqing Weng,Junyi Shen.Classification of multivariate time series usingtwo-dimensional singular value decomposition.Knowledge-Based Systems2008(21):535-539P.
[69] Ahlame Douzal-Chouakria,Cécile Amblard. Classification trees for time series.PatternRecognition.2011.
[70] C. Orsenigo, C. Vercellis.Combining discrete SVM and fixed cardinality warpingdistances for multivariate time series classification. Pattern Recognition2010(43):3787-3794P.
[71] Raquel Pradoa, Francisco Molina,Gabriel Huerta.Multivariate time series modelingand classification via hierarchical VAR mixtures. Computational Statistics&DataAnalysis2006(51):1445-462P.
[72] Friedhelm Schwenker, Christian Dietrich,Hans A. Kestler,Klaus Riede,Günther Palm.Radial basis function neural networks and temporal fusion for the classification ofbioacoustic time series.Neurocomputing2003(51):265-275P.
[73] Michael Hüsken, Peter Stagge.Recurrent neural networks for time seriesclassication.Neurocomputing2003(50):223-235P.
[74] Juan José,Rodrígueza,Carlos J. Alonso,José A. Maestrob.Support vector machines ofinterval-based featuresfor time series classification. Knowledge-Based Systems2005(18):171-178P.
[75] YoungSeon Jeong,Myong K. Jeong,Olufemi A. Omitaomu.Weighted dynamic timewarping for time series classification. Pattern Recognition2011(44):2231-2240P.
[76] Marcella Corduas, Domenico Piccolo.Time series clustering and classification bythe autoregressive metric.Computational Statistics&Data Analysis2008(52):1860-1872P.
[77] Steinn Gudmundsson, Thomas Philip Runarsson, Sven Sigurdsson.Test–retestreliability and feature selection in physiological time series classification. computermethods and programs in biomedicine2010.
[78] eljko Jagnji,Nikola Bogunovi,Ivanka Pi eta,Franjo Jovi.Time series classificationbased on qualitative space fragmentation. Advanced Engineering Informatics2009(23):116-129P.
[79] G.E.P.Box,G.M.Jenkins.Time series analysis:foreeasting and control[M].San Fransisco,CA:Holden-Day.1976.
[80]邓聚龙.灰色控制系统.华中工业大学学报.1982,10(6):10-18P.
[81] F.Takens. Detecting strange attractors in turbulence[C]. Dynamical systems andturbulence, lecture notes in mathematics. New York: Springer-Verlag,1981,336-381P.
[82]张志华,郑南宁,郑海兵.径向基函数神经网络(RBF)的一种极大熵学习算法.计算机学报,2001,24(5):474-479P.
[83]陈哲,冯天瑾,张海燕.基于小波神经网络的混沌时间序列分析与相空间重构.计算机研究与发展,2001,38(5):591-596P.
[84] Kunhuang Huarng, Tiffany Hui-Kuang Yu. The application of neural networks toforecast fuzzy time series.Available online at www.sciencedirect.com,Physica A2006(363):481–491P.
[85] Zarita Zainuddin, Ong Pauline. Modified wavelet neural network in functionapproximation and its application in prediction of time-series pollution data. AppliedSoft Computing,2011,11(8):4866-4874P.
[86] Muhammad Ardalani-Farsa, Saeed Zolfaghari. Chaotic time series prediction withresidual analysis method using hybrid Elman–NARX neuralnetworks.Neurocomputing,2010,73(13–15):2540-2553P.
[87] Cyril Voyant,Marc Muselli,Christophe Paoli,Marie-Laure Nivet Optimization of anartificial neural network dedicated to the multivariate forecasting of daily globalradiation. Energy,2011,36(1):348-359P.
[88] Tiffany Hui-Kuang Yu,Kun-Huang Huarng,A bivariate fuzzy time series model toforecast the TAIEX.Expert Systems with Applications2008(34):2945-2952P.
[89] Jo o Victor Issler,Luiz Renato Lima.A panel data approach to economic forecasting:The bias-corrected average forecast. Journal of Econometrics2009(152):153-164P.
[90] Sandy D.Balkin.A Statistcal Implementation of Feedforward Neural Networks forUnivariate Time Series Forecasting. In UMI.2000.
[91] Léonar Studer,Francesco Masulli.Building a neuro-fuzzy system toefficiently forecast chaotic time series. Nuclear Instruments and Methodsin Physics Research A1997(389):264-267P.
[92] Lei Hong. Decomposition and Forecast for Financial Time Series withHigh-frequency Based on Empirical Mode Decomposition. Energy Procedia2011(5)1333-1340P.
[93] Susan Colvin White.Forecasting bussiness time series with radial funtionnetworks.Texas A&M University.1994.
[94] Vasudev Rangadass.Nonlinear Time Series Forecasting:A Recurrent Neural NetworkApproach.The University of Texas at Arlington.1996.
[95]蒋嵘,李德毅.基于形态表示的时间序列相似性搜索.计算机研究与发展,2000,37(5):601-608P.
[96]李爱国.时间序列数据分割与时态模式挖掘研究[D].西安交通大学博士论文,2003.
[97] Stephen G. Hall, James Mitchell.Combining Density forecasts. International Journal ofForecasting2007(23):1-13P.
[98] Massimo Guidolin,Allan Timmermannc.Forecasts of US short-term interest rates: Aflexible forecast combination approach. Journal of Econometrics2009(150):297-311P.
[99] U.M.Fayyad,G.Piatetsky-ShaPerio,P.Smyth,R.Uthurusamy.Advances in KnowledgeDiscovery and Data Mining[M].AAAI/MITPress,1996.
[100] W.Frawley,G.Piatetsky-ShaPiro,C.Matheus.Knowledge discovery in databases:Anoverview.AlMagazine.1992,13(3):57-70P.
[101] R.Agrawal, H.Mamnila,R.Srikant,et al.Fast Discovery of Association Rules.In:Fayyad M,Piatetshy-ShaPiro G,SmythPeds.Advanees in Knowledge Discovery andData Mining,Menlo Park,California:AAAI/MITPress,1996.
[102] Yong Joon Leea, Jun Wook Leea, Duck Jin Chaib, Bu Hyun Hwangc, Keun HoRyub.Mining temporal interval relational rules from temporal ata.Journal of Systemsand Software,2009,8(1),155–167P.
[103]张保稳.时间序列数据挖掘研究[D].西北工业大学博士论文.2002.
[104] E.Keogh, M.Pazzani.An enhanced representation of time series which allows fast andaccurate classification, clustering and relevance feedback[C].In proceedings of the4thInt.Conference on Knowledge Discovery and Data Mining.NewYork,NY,1998.
[105] Michael T.Rosenstein, Paul R.Cohen,Concepts from Time Series.In Proeeedings ofthe Fifteenth National Conference on Artifieial Intelligenee,2001,739-745P.
[106] G.Das,K.Lin,H.Mannila,G.Renganathan,P.Smyth:Rule diseovery from timeseries,Proeeedings of the Fourth International Conference on Knowledge Discoveryand DataMining,1998.
[107] R.J Povinelli, X.Feng.Temporal Pattem Identifieation of time Series Data UsingPattem Wavelets and Genetie Algorithms,Artifical neural Networks in Engineering，St.Louis,issouri,2007,691-696P.
[108] R.J Povinelli.Time Series Data Mining:Ideniifying Temporal Pattems forCharacterization and Prediction of Time Series Events,PhD Dissertation,MarquetteUniversity,Milwaukee,1999.
[109]许少华,何新贵,尚福华.基于基函数展开的双隐层过程神经元网络及其应用.控制与决策,2004,12(1):36-48P.
[110]何新贵,许少华.输入输出均为时变函数的过程神经元网络及应用.软件学报,200314(4):764-769P.
[111]何新贵,许少华.一类反馈过程神经元网络模型及其学习算法.自动化学报,2004,11(6):801-806P.
[112]柳重堪.正交基函数及其应用[M].国防工业出版社.1982.
[113]许少华,何新贵,李盼池.自组织过程神经元网络及其应用研究.计算机研究与发展,2003,40(11):1613-1615P.
[114]郑纪安.基于小波分析和神经网络的金融时间序列预测研究[D].厦门大学硕士学位论文.2009.
[115] Holger Kantz,Thomas Schreiber.Nonlinear time series analysis[M].Cambridge:Cambridge University Press,2004.
[116]李智.小波理论与经济金融时序应用研究[D].厦门大学博士学位论文.2007.
[117] C K Chui. An introduction to wavelets[M]. NewYork: Academic Press,Inc.,1992.
[118] I.Daubechies.Ten lectures on wavelets[M].Vermont: Capital City Press,1992.
[119] E.Hernadez, G.Weiss. A first course on wavelets[M]. New York:CRC Press,1996.
[120]倪布喜,章丽芙,姚敏.基于SOFM网络的聚类分析.计算机工程与设计.2006,27(5):855-858P.
[121] Kwang Bo Cho, Bo Hyeun Wang.Radial basis function based adaptive fuzzysystems and their applications to system identification and prediction.Fuzzy Sets and Systems,1996(83):325-339P.
[122] Asim Roy,Sandeep Govil,Raymond Miranda.An Algorithm to Generate Radial BasisFunction (RBF)-Like Nets for Classification Problems.Neural Networks,1995(8):179-201P.
[123] M.S.Sánchez,H. Swierenga, L.A.Sarabia, E.Derks, L.Buydens. Performance of multilayer feedforward and radial base function neural networks in classification andmodelling.Chemometrics and Intelligent Laboratory Systems,1996(33):101-119P.
[124]许少华,何新贵.径向基过程神经元网络及其应用研究.北京航空航天大学学报,2004,25(1):14-17P.
[125]黄国宏,刘刚.新的C-RBF神经网络分类器的设计与实现.计算机应用研究,2008,3(25):709-711P.
[126]周明,孙树栋.遗传算法原理及其应用[M].北京:国防工业出版社,1999.
[127]张铃,张拔.遗传算法机理的研究.软件学报,2000,11(7):945-952P.
[128]韩力群.人工神经网络的理论、设计及应用[M].北京:化工出版社,2002.
[129] Xiangyang Zhao, Kangsheng Lai, Dongming Dai.An Improved BP Algorithm and ItsApplication in Classification of Surface Defects of Steel Plate.Journal of Iron andSteel Research,2007,14(2),52-55P.
[130] Weisheng Chen, Wei Li, Qiguang Miao. Backstepping control for periodicallytime-varying systems using high-order neural network and Fourier series expansion.ISA Transactions,2010,49(3):283-292P.
[131] Ralph Linsker.Neural network learning of optimal Kalman prediction andcontrol.Neural Networks,2008,21(9):1328-1343P.
[132] Draguna Vrabie, Frank Lewis.Neural network approach to continuous-time directadaptive optimal control for partially unknown nonlinear systems. Neural Networks,2009,22(3):237-246P.
[133] R.K. Al Seyab, Y. Cao. Nonlinear system identification for predictive control usingcontinuous time recurrent neural networks and automatic differentiation. Journal ofProcess Control,2008,18(6):568-581P.
[134] Paisan Kittisupakorn, Piyanuch Thitiyasook, M.A. Hussain, Wachira Daosud. Neuralnetwork based model predictive control for a steel pickling process. Journal of ProcessControl,2009,19(4):579-590P.
[135] Sj berg J,Zhang Q H,Ljung L,et al.Nonlinear black-box modeling in systemidentification:A unified overview.Automatica,1995,31(12):1691-1724P.
[136]高齐圣,张纪,张嗣滚.基于时间序列模型的统计质量控制研究.2004中国控制与决策学术年会论文集.2004,695-699P.
[137]贺诗波,刘祥官,郜传厚,黄丽英,黄雅彬.高炉硅含量预测控制的时间序列混合建模.浙江大学学报,2009,41(10):1740-1744P.
[138] Dongyan,Zhang Liping Sun, Jun Cao.Modeling of temperature-humidity for wooddrying based on time-delay Neural network. Journal of Forestry Research.2006,17(2):41–144P.
[139]张延林,宋文龙,朱小利.神经网络在木材干燥过程中建模的应用.东北林业大学学报,2009,l37(8):51-55P.
[140]胡昆仑,曹军,孙丽萍.基于时延神经网络的木材干燥模型辨识研究.林业科技,2004,4(29):41-45P.
[141]袁晓磊.基于遗传编程的系统辨识研究[D].华北电力大学博士论文.2010.
[142] Ieroham S. Baruch, Rafael Beltran Lopez, Jose-Luis Olivares Guzman, Jose MartinFlores.A fuzzy-neural multi-model for nonlinear systems identification and control.Fuzzy Sets and Systems,2008,159(20),2650-2667P.
[143] Huaqing Li,Xiaofeng Liao,Chuandong Li,Chaojie Li.Chaos control andsynchronization via a novel chatter free sliding mode controlstrategy. Neurocomputing,2011,74(17):3212-3222P.
[144] Ivan Zelinka.Real-time deterministic chaos control by means of selected evolutionarytechniques.Engineering Applications of Artificial Intelligence,2009,22(2):283-297P.
[145]郝华涛.木材干燥技术[M].北京:高等教育出版社,2002.
[146] Peter Carlsson,J Arfvidsson.Optimized wood drying.Drying Technology,2000,18(8):1779-1796P.
[147] Peter Carlsson,Mats Tinnsten.Optimization of drying sehedules adated of a mixture ofboards with distribution of sapwood and heartwood.DryingTechnology,2002,20(2):403-418P.
[148] K Cronin,P Buaeou,K Abodayeh.et al.Probabilistic analysis of timber dyringsehedules.Dyring Technology,2003,21(8):1433-1456P.
[149] Y Fortin,M Defo,M Nabhani etal.A Simulation tool for the optimization of lmuberdyring sehedules.DryingTeehnolog2004,22(5):963-953P.
[150]胡慕伊.木材干燥基准数学模型的研究与应用.林产工业.1997,24(6):4-6P.
[151]杨甲沛,李锵,刘郑,袁晓琳.基于自适应学习速率的改进型BP算法研究.计算机工程及应用,2009,45(11),56-59P.
[2] Ashu Jain,Avadhnam Madhav Kumar.Hybrid neural network models for hydrologic time series forecasting.Applied Soft Computing,2007,7(2):585-592P.
[3] FangMei Tseng, HsiaCheng Yu, GwoHsiung Tzeng.Combining neural network modelwith seasonal time series ARIMA model. Technological Forecasting and SocialChange,2002,69(1):71-87P.
[4] G.Peter Zhang. An investigation of neural networks for linear time-series forecasting.Computers&Operations Research.2001,28(12):183-1202P.
[5] Mohammad Assaad, Romuald Bone, Hubert Cardot.A new boosting algorithm forimproved time-series forecasting with recurrent neural networks. Information Fusion,2008,9(1):41-55P.
[6] Sven F. Crone, Nikolaos Kourentzes.Feature selection for time series prediction–Acombined filter and wrapper approach for neural networks. Neurocomputing,2010,73(10-12):1923-1936P.
[7] Thomas J. Glezakos,Theodore A. Tsiligiridis,Lazaros S. Iliadis,Constantine P.Yialouris, Fotis P. Maris, Konstantinos P. Ferentinos.Feature extraction for time-seriesdata: An artificial neural network evolutionary training model for the management ofmountainous watersheds. Neurocomputing,2009,73(1-3):49-59P.
[8] D. Gao, Y. Kinouchi, K. Ito, X. Zhao. Neural networks for event extraction from timeseries: a back propagation algorithm approach.Future Generation Computer Systems,2005,21(7):1096-1105P.
[9] ArdalaniFarsa Muhammad, Zolfaghari Saeed.Chaotic time series prediction withresidual analysis method using hybrid Elman–NARX neural networks.Neurocomputing,2010,73(13-15):2540-2553P.
[10]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):41-44P.
[11]何新贵,梁久祯,许少华.过程神经元网络的训练及其应用.中国工程科学,2001(3):31-35P.
[12]许少华,何新贵,王兵.一种分式过程神经元网络及其应用研究.计算机研究与发展,2006,12(2):2088-2094P.
[13]丁刚,钟诗胜.具有时变输入输出函数的反馈过程神经元网络及应用.控制与决策,2007,11(1):91-94P.
[14]许少华,何新贵.多聚合过程神经元网络及其学习算法研究.计算机学报,2007,8(1):48-56P.
[15]钟诗胜,朴树学,丁刚.改进BP算法在过程神经元网络中的应用.哈尔滨工业大学学报,2006,11(6):840-842P.
[16]许少华,何新贵,刘坤,王兵.关于连续过程神经元网络的一些理论问题.电子学报,2006,15(10):1838-1841P.
[17]王丹丹,刘显德.一种基于自组织过程神经网络的动态样本半监督学习算法.智能计算机与应用,2011,1(3):88-90P.
[18]孟庆德.基于过程神经元网络的市场评价.技术经济,2006,10(7):71-73P.
[19]杨晓龙,刘希宋.基于过程神经元网络的中国油气资源可持续发展能力评价.哈尔滨工业大学学报,2006,11(5):58-63P.
[20]丁刚,钟诗胜.基于时变阈值过程神经元网络的太阳黑子数预测.物理学报,2007,10(2):1224-1230P.
[21]付旭云,丁刚,钟诗胜,边旭.基于双隐层径向基过程神经网络的润滑油金属含量预测.润滑于密封,2009,34(2):18-21P.
[22]钟诗胜,李洋.基于小波过程神经元网络的飞机发动机状态监视.航空学报,2007,20(1):68-71P.
[23]何新贵,许少华.过程神经元网络及其在时变信息处理中的应用.智能系统学报,2006,9(1):1-8P.
[24]钟诗胜,栾圣罡,丁刚.基于过程神经元网络与气动热力参数的航空发动机状态监视.南京理工大学学报,2006,12(5):533-541P.
[25]许少华,刘扬,何新贵.基于过程神经元网络的水淹层自动识别系统.石油学报,2004,10(4):54-57P.
[26]葛利,陈广胜.基于过程神经网络的木材生长轮密度预测.林业科学,2008,11(1):63-65P.
[27]葛利.一种基于混合遗传算法学习的过程神经网络.哈尔滨工业大学学报,2005,17(7):986-989P.
[28] E.Keogh Data mining and machine learning in time series database[C].Proc of the5thIndustrial Conference on Data Mining (ICDM). Leipzig:[s. n.],2005.
[29] R.Agrawal, C.Faloutsos, A.Swami. Efficient similarity Search in sequencedatabases[C].Proc of the4th InternationalConference on Foundations of DataOrganization and Algorithms.London:Springer-Verlag,1993:69-84P.
[30] C.Faloutsos, M.Ranganathan, Y.Manolopoulos. Fast Subsequence matching in timeseries databases[C].Proc of the ACM SIGMOD International Conference onManagement of Data.Mineapolis: ACM Press,1994:419-429P.
[31] E.Keogh, S.Chu,D.Hart,M.Pazzani.Segmenting time series:A survey and Novelapproach. In M.Last,A.Kandel,H.Bunke,eds, Data Mining In Time-series Databases,World Seientific,2004:1-22P.
[32] C.S.M ller-Levet,F.Klawonn,K.-H.Cho,O.Wolkenhauer,Fuzzy clustering of shorttime series and unevenly distributed sampling points[C].Proeeedings of the5thInternational symposium on Intelligent Data Analysis,Berli,Germany,2003:330-340P.
[33] T.Oates,M.D.Schmill,P.R.Cohen.A Method for Clustering the Experiences of aMobile Robot that Accords with Human Judgments[C].Proc.of the17th NationalConference on Artificial Intelligence,2000:846-851P.
[34] R.Agrawal,C.Faloutsos,A.Swami.Effieient similarity search in sequenecedatabases[C].FODO-Foundations of Data Organization and Algorithms Proeeedings，1993:69-84P.
[35] Z.Struzik, A.Sibe.Measuring Time Series Similarity Through Large Singular FeaturesRevealed with Wavelet Transformation.In Proc.ofthe10th Int. Workshop on Databaseand Expert Systems Application,1999:162-166P.
[36] M.Gavrilov,D.Angnelov,P.Indyk,R.Motwani.Mining the stock market:which measureis best?[C].In proceedings of the6th ACM Int.Conference on Knowledge Diseoveryand DataMining.Boston,MA,2000:487-496P.
[37] Christian Dose, Silvano Cincotti.Clustering of financial time series with application toindex and enhanced index tracking portfolio. http://www.elsevier.com/locate/physa,Physica A2005:145–151P.
[38] A.M. Alonso, J.R. Berrendero, A. Hernández, A. Justel.Time series clustering basedon forecast densities. Computational Statistics&Data Analysis2006(51):762-776P.
[39] P. Cheeseman, J. Stutz. Bayesian classification (AutoClass):theory and results. In:U.M. Fayyard, G. Piatetsky-Shapiro,P. Smyth, R. Uthurusamy (Eds.), Advances inKnowledge Discovery and Data Mining, AAAI/MIT Press, Cambridge,MA,1996.
[40] M.Corduas, D.Piccolo.Time series clustering and classification by the autoregressivemetric.Computational Statistics&Data Analysis.2008,(52):1860-1872P.
[41] KuoChin Hsu,ShengTun Li.Clustering spatial–temporal precipitation data usingwavelet transform and self-organizing map neural network. Advances in WaterResources.2010(33):190–200P.
[42] Yiin Xiong, DitYan Yeung.Time series clustering with ARMA mixtures. PatternRecognition2004,(37):1675-1689P.
[43] Lian Liu, Lihong Huanga, Mingyong Lai, Chaoqun Mac.Projective ART with buffersfor the high dimensional space clusteringand an application to discover stockassociations. Neurocomputing2009(72):1283–1295P.
[44] Aymen Cherif, Hubert Cardot, Romuald Bone.SOM time series clustering andprediction with recurrent neural networks. Neurocomputing,2011(74):1936–1944P.
[45] A. Meyer-B se, A. Saalbach, O. Lange, A. Wismüer.Unsupervised clustering of fMRIand MRI time series.Biomedical Signal Processing and Control2007(2):295–310P.
[46] T W Liao.Clustering of time series data. Pattern Recognition.2005(38):1857-1874P.
[47] E.Keogh, S.Kasetty. On the need for time series data mining benchmarks:a survey andempirical demonstration.Data mining and knowledge discovery.2003(7):349-371P.
[48] P. D’Urso. Fuzzy clustering for data time array with inlier and outlier time trajectories.IEEE Transactions on Fuzzy Systems.2005,13(5):583–604P.
[49] C S M ller-Levet, F Klawonn, K Cho et al. Clustering of unevenly sampled geneexpressiontime-series data. Fuzzy Sets and Systems.2005,152(1):49–66P.
[50] T W Liao, F.Tang, J.Qu et al. Grinding wheel condition monitoring with boostedminimum distanceVclassifiers. Mechanical Systems and Signal Processing.2008(22):217–232P.
[51] P.D’Urso, E A Maharaj. Autocorrelation-based fuzzy clustering of time series. FuzzySets and Systems.2009(160):3565–3589P.
[52] L A Garcia-Escudero, A. Gordaliza. A proposal for robust curve clustering. Journal ofClassification.2005(22):185-201P.
[53] E A Maharaj. Comparison of non-stationary time series in the frequency domain.ComputationalStatistics&Data Analysis.2002(40):131-141P.
[54] D.Piccolo. A distance measure for classifying ARIMA models. Journal of Time SeriesAnalysis.1990,11(2):153-164P.
[55] E A Maharaj. Using wavelets to compare time series patterns. Wavelets,Multiresolution and Information Processing.2005,3(4):511-521P.
[56] J. Caiado, N.Crato, D.Pena. A periodogram-based metric for time series classification.Computational Statistics&Data Analysis.2006(50):2668-2684P.
[57] A M Alonso, J R Berrendero, A.Hernández et al. Time series clustering based onforecast density.Computational Statistics&Data Analysis.2006,51(2):762-776P.
[58] T.Warren Liao.Clustering of time series data—a survey.Pattern Reeognition.2005(38):1857-1874P.
[59] E.Keogh,K.Chakrabarti,M.Pazzani,P.Mehrotra.Dimensionality Reduetion for FastSimilarity Search in Large Time Series Databases.Journal of Knowledge andInformation Systems.2001(3):263-286P.
[60]杨一鸣,潘嵘,潘嘉林,杨强,李磊.时间序列分类问题的算法比较.计算机学报,2007,30(8):1260-1263P.
[61] YoungSeon Jeong,Myong K. Jeong,Olufemi A.Omitaomu.Weighted dynamic timewarping for time series classification.Pattern Recognition,2011(44):2231–2240P.
[62] E.Keogh, S.Kasetty. On the need for time series data mining benchmarks: A surveyand empirical demonstration.Proceedings of the8th ACM SIGKDD InternationalConferenceon Knowledge Discovery and Data Mining. Edmonton, Alberta, Canada,2002:102-111P.
[63] A.NanoPoulos,R.Aleoek Y,Manolo Poulos.Feature-based Classification of Time SeriesData.International Journal of Computer Research.NY:Nova Seienee Publisher.2001:49-61P.
[64] Eiekeler,S.Kosmala,A.Rigoll G.Hidden Markov Model based continuous online gesture recognition.In IEEE Proc.Internat Conf.on Pattern Recognition.1998(2):1206-1208P.
[65] K.N. Plataniotis, D. Androutsos, A.N. Venetsanopoulos, D.G.Lainiotis.A newtime series classification approach. Signal Processing.1996(54):191-199P.
[66] Jorge Caiado, Nuno Crato, Daniel Pe a.A periodogram-based metric for time seriesclassification.Computational Statistics&Data Analysis2006(50):2668-2684P.
[67] Xiaoqing Weng,Junyi Shen.Classification of multivariate time series using localitypreserving projections.Knowledge-Based Systems2008(21):581-587P.
[68] Xiaoqing Weng,Junyi Shen.Classification of multivariate time series usingtwo-dimensional singular value decomposition.Knowledge-Based Systems2008(21):535-539P.
[69] Ahlame Douzal-Chouakria,Cécile Amblard. Classification trees for time series.PatternRecognition.2011.
[70] C. Orsenigo, C. Vercellis.Combining discrete SVM and fixed cardinality warpingdistances for multivariate time series classification. Pattern Recognition2010(43):3787-3794P.
[71] Raquel Pradoa, Francisco Molina,Gabriel Huerta.Multivariate time series modelingand classification via hierarchical VAR mixtures. Computational Statistics&DataAnalysis2006(51):1445-462P.
[72] Friedhelm Schwenker, Christian Dietrich,Hans A. Kestler,Klaus Riede,Günther Palm.Radial basis function neural networks and temporal fusion for the classification ofbioacoustic time series.Neurocomputing2003(51):265-275P.
[73] Michael Hüsken, Peter Stagge.Recurrent neural networks for time seriesclassication.Neurocomputing2003(50):223-235P.
[74] Juan José,Rodrígueza,Carlos J. Alonso,José A. Maestrob.Support vector machines ofinterval-based featuresfor time series classification. Knowledge-Based Systems2005(18):171-178P.
[75] YoungSeon Jeong,Myong K. Jeong,Olufemi A. Omitaomu.Weighted dynamic timewarping for time series classification. Pattern Recognition2011(44):2231-2240P.
[76] Marcella Corduas, Domenico Piccolo.Time series clustering and classification bythe autoregressive metric.Computational Statistics&Data Analysis2008(52):1860-1872P.
[77] Steinn Gudmundsson, Thomas Philip Runarsson, Sven Sigurdsson.Test–retestreliability and feature selection in physiological time series classification. computermethods and programs in biomedicine2010.
[78] eljko Jagnji,Nikola Bogunovi,Ivanka Pi eta,Franjo Jovi.Time series classificationbased on qualitative space fragmentation. Advanced Engineering Informatics2009(23):116-129P.
[79] G.E.P.Box,G.M.Jenkins.Time series analysis:foreeasting and control[M].San Fransisco,CA:Holden-Day.1976.
[80]邓聚龙.灰色控制系统.华中工业大学学报.1982,10(6):10-18P.
[81] F.Takens. Detecting strange attractors in turbulence[C]. Dynamical systems andturbulence, lecture notes in mathematics. New York: Springer-Verlag,1981,336-381P.
[82]张志华,郑南宁,郑海兵.径向基函数神经网络(RBF)的一种极大熵学习算法.计算机学报,2001,24(5):474-479P.
[83]陈哲,冯天瑾,张海燕.基于小波神经网络的混沌时间序列分析与相空间重构.计算机研究与发展,2001,38(5):591-596P.
[84] Kunhuang Huarng, Tiffany Hui-Kuang Yu. The application of neural networks toforecast fuzzy time series.Available online at www.sciencedirect.com,Physica A2006(363):481–491P.
[85] Zarita Zainuddin, Ong Pauline. Modified wavelet neural network in functionapproximation and its application in prediction of time-series pollution data. AppliedSoft Computing,2011,11(8):4866-4874P.
[86] Muhammad Ardalani-Farsa, Saeed Zolfaghari. Chaotic time series prediction withresidual analysis method using hybrid Elman–NARX neuralnetworks.Neurocomputing,2010,73(13–15):2540-2553P.
[87] Cyril Voyant,Marc Muselli,Christophe Paoli,Marie-Laure Nivet Optimization of anartificial neural network dedicated to the multivariate forecasting of daily globalradiation. Energy,2011,36(1):348-359P.
[88] Tiffany Hui-Kuang Yu,Kun-Huang Huarng,A bivariate fuzzy time series model toforecast the TAIEX.Expert Systems with Applications2008(34):2945-2952P.
[89] Jo o Victor Issler,Luiz Renato Lima.A panel data approach to economic forecasting:The bias-corrected average forecast. Journal of Econometrics2009(152):153-164P.
[90] Sandy D.Balkin.A Statistcal Implementation of Feedforward Neural Networks forUnivariate Time Series Forecasting. In UMI.2000.
[91] Léonar Studer,Francesco Masulli.Building a neuro-fuzzy system toefficiently forecast chaotic time series. Nuclear Instruments and Methodsin Physics Research A1997(389):264-267P.
[92] Lei Hong. Decomposition and Forecast for Financial Time Series withHigh-frequency Based on Empirical Mode Decomposition. Energy Procedia2011(5)1333-1340P.
[93] Susan Colvin White.Forecasting bussiness time series with radial funtionnetworks.Texas A&M University.1994.
[94] Vasudev Rangadass.Nonlinear Time Series Forecasting:A Recurrent Neural NetworkApproach.The University of Texas at Arlington.1996.
[95]蒋嵘,李德毅.基于形态表示的时间序列相似性搜索.计算机研究与发展,2000,37(5):601-608P.
[96]李爱国.时间序列数据分割与时态模式挖掘研究[D].西安交通大学博士论文,2003.
[97] Stephen G. Hall, James Mitchell.Combining Density forecasts. International Journal ofForecasting2007(23):1-13P.
[98] Massimo Guidolin,Allan Timmermannc.Forecasts of US short-term interest rates: Aflexible forecast combination approach. Journal of Econometrics2009(150):297-311P.
[99] U.M.Fayyad,G.Piatetsky-ShaPerio,P.Smyth,R.Uthurusamy.Advances in KnowledgeDiscovery and Data Mining[M].AAAI/MITPress,1996.
[100] W.Frawley,G.Piatetsky-ShaPiro,C.Matheus.Knowledge discovery in databases:Anoverview.AlMagazine.1992,13(3):57-70P.
[101] R.Agrawal, H.Mamnila,R.Srikant,et al.Fast Discovery of Association Rules.In:Fayyad M,Piatetshy-ShaPiro G,SmythPeds.Advanees in Knowledge Discovery andData Mining,Menlo Park,California:AAAI/MITPress,1996.
[102] Yong Joon Leea, Jun Wook Leea, Duck Jin Chaib, Bu Hyun Hwangc, Keun HoRyub.Mining temporal interval relational rules from temporal ata.Journal of Systemsand Software,2009,8(1),155–167P.
[103]张保稳.时间序列数据挖掘研究[D].西北工业大学博士论文.2002.
[104] E.Keogh, M.Pazzani.An enhanced representation of time series which allows fast andaccurate classification, clustering and relevance feedback[C].In proceedings of the4thInt.Conference on Knowledge Discovery and Data Mining.NewYork,NY,1998.
[105] Michael T.Rosenstein, Paul R.Cohen,Concepts from Time Series.In Proeeedings ofthe Fifteenth National Conference on Artifieial Intelligenee,2001,739-745P.
[106] G.Das,K.Lin,H.Mannila,G.Renganathan,P.Smyth:Rule diseovery from timeseries,Proeeedings of the Fourth International Conference on Knowledge Discoveryand DataMining,1998.
[107] R.J Povinelli, X.Feng.Temporal Pattem Identifieation of time Series Data UsingPattem Wavelets and Genetie Algorithms,Artifical neural Networks in Engineering，St.Louis,issouri,2007,691-696P.
[108] R.J Povinelli.Time Series Data Mining:Ideniifying Temporal Pattems forCharacterization and Prediction of Time Series Events,PhD Dissertation,MarquetteUniversity,Milwaukee,1999.
[109]许少华,何新贵,尚福华.基于基函数展开的双隐层过程神经元网络及其应用.控制与决策,2004,12(1):36-48P.
[110]何新贵,许少华.输入输出均为时变函数的过程神经元网络及应用.软件学报,200314(4):764-769P.
[111]何新贵,许少华.一类反馈过程神经元网络模型及其学习算法.自动化学报,2004,11(6):801-806P.
[112]柳重堪.正交基函数及其应用[M].国防工业出版社.1982.
[113]许少华,何新贵,李盼池.自组织过程神经元网络及其应用研究.计算机研究与发展,2003,40(11):1613-1615P.
[114]郑纪安.基于小波分析和神经网络的金融时间序列预测研究[D].厦门大学硕士学位论文.2009.
[115] Holger Kantz,Thomas Schreiber.Nonlinear time series analysis[M].Cambridge:Cambridge University Press,2004.
[116]李智.小波理论与经济金融时序应用研究[D].厦门大学博士学位论文.2007.
[117] C K Chui. An introduction to wavelets[M]. NewYork: Academic Press,Inc.,1992.
[118] I.Daubechies.Ten lectures on wavelets[M].Vermont: Capital City Press,1992.
[119] E.Hernadez, G.Weiss. A first course on wavelets[M]. New York:CRC Press,1996.
[120]倪布喜,章丽芙,姚敏.基于SOFM网络的聚类分析.计算机工程与设计.2006,27(5):855-858P.
[121] Kwang Bo Cho, Bo Hyeun Wang.Radial basis function based adaptive fuzzysystems and their applications to system identification and prediction.Fuzzy Sets and Systems,1996(83):325-339P.
[122] Asim Roy,Sandeep Govil,Raymond Miranda.An Algorithm to Generate Radial BasisFunction (RBF)-Like Nets for Classification Problems.Neural Networks,1995(8):179-201P.
[123] M.S.Sánchez,H. Swierenga, L.A.Sarabia, E.Derks, L.Buydens. Performance of multilayer feedforward and radial base function neural networks in classification andmodelling.Chemometrics and Intelligent Laboratory Systems,1996(33):101-119P.
[124]许少华,何新贵.径向基过程神经元网络及其应用研究.北京航空航天大学学报,2004,25(1):14-17P.
[125]黄国宏,刘刚.新的C-RBF神经网络分类器的设计与实现.计算机应用研究,2008,3(25):709-711P.
[126]周明,孙树栋.遗传算法原理及其应用[M].北京:国防工业出版社,1999.
[127]张铃,张拔.遗传算法机理的研究.软件学报,2000,11(7):945-952P.
[128]韩力群.人工神经网络的理论、设计及应用[M].北京:化工出版社,2002.
[129] Xiangyang Zhao, Kangsheng Lai, Dongming Dai.An Improved BP Algorithm and ItsApplication in Classification of Surface Defects of Steel Plate.Journal of Iron andSteel Research,2007,14(2),52-55P.
[130] Weisheng Chen, Wei Li, Qiguang Miao. Backstepping control for periodicallytime-varying systems using high-order neural network and Fourier series expansion.ISA Transactions,2010,49(3):283-292P.
[131] Ralph Linsker.Neural network learning of optimal Kalman prediction andcontrol.Neural Networks,2008,21(9):1328-1343P.
[132] Draguna Vrabie, Frank Lewis.Neural network approach to continuous-time directadaptive optimal control for partially unknown nonlinear systems. Neural Networks,2009,22(3):237-246P.
[133] R.K. Al Seyab, Y. Cao. Nonlinear system identification for predictive control usingcontinuous time recurrent neural networks and automatic differentiation. Journal ofProcess Control,2008,18(6):568-581P.
[134] Paisan Kittisupakorn, Piyanuch Thitiyasook, M.A. Hussain, Wachira Daosud. Neuralnetwork based model predictive control for a steel pickling process. Journal of ProcessControl,2009,19(4):579-590P.
[135] Sj berg J,Zhang Q H,Ljung L,et al.Nonlinear black-box modeling in systemidentification:A unified overview.Automatica,1995,31(12):1691-1724P.
[136]高齐圣,张纪,张嗣滚.基于时间序列模型的统计质量控制研究.2004中国控制与决策学术年会论文集.2004,695-699P.
[137]贺诗波,刘祥官,郜传厚,黄丽英,黄雅彬.高炉硅含量预测控制的时间序列混合建模.浙江大学学报,2009,41(10):1740-1744P.
[138] Dongyan,Zhang Liping Sun, Jun Cao.Modeling of temperature-humidity for wooddrying based on time-delay Neural network. Journal of Forestry Research.2006,17(2):41–144P.
[139]张延林,宋文龙,朱小利.神经网络在木材干燥过程中建模的应用.东北林业大学学报,2009,l37(8):51-55P.
[140]胡昆仑,曹军,孙丽萍.基于时延神经网络的木材干燥模型辨识研究.林业科技,2004,4(29):41-45P.
[141]袁晓磊.基于遗传编程的系统辨识研究[D].华北电力大学博士论文.2010.
[142] Ieroham S. Baruch, Rafael Beltran Lopez, Jose-Luis Olivares Guzman, Jose MartinFlores.A fuzzy-neural multi-model for nonlinear systems identification and control.Fuzzy Sets and Systems,2008,159(20),2650-2667P.
[143] Huaqing Li,Xiaofeng Liao,Chuandong Li,Chaojie Li.Chaos control andsynchronization via a novel chatter free sliding mode controlstrategy. Neurocomputing,2011,74(17):3212-3222P.
[144] Ivan Zelinka.Real-time deterministic chaos control by means of selected evolutionarytechniques.Engineering Applications of Artificial Intelligence,2009,22(2):283-297P.
[145]郝华涛.木材干燥技术[M].北京:高等教育出版社,2002.
[146] Peter Carlsson,J Arfvidsson.Optimized wood drying.Drying Technology,2000,18(8):1779-1796P.
[147] Peter Carlsson,Mats Tinnsten.Optimization of drying sehedules adated of a mixture ofboards with distribution of sapwood and heartwood.DryingTechnology,2002,20(2):403-418P.
[148] K Cronin,P Buaeou,K Abodayeh.et al.Probabilistic analysis of timber dyringsehedules.Dyring Technology,2003,21(8):1433-1456P.
[149] Y Fortin,M Defo,M Nabhani etal.A Simulation tool for the optimization of lmuberdyring sehedules.DryingTeehnolog2004,22(5):963-953P.
[150]胡慕伊.木材干燥基准数学模型的研究与应用.林产工业.1997,24(6):4-6P.
[151]杨甲沛,李锵,刘郑,袁晓琳.基于自适应学习速率的改进型BP算法研究.计算机工程及应用,2009,45(11),56-59P.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |