基于谱聚类的高阶模糊时序自适应预测方法

doi:10.11959/j.issn.1000-436x.2016036

摘要/Abstract

摘要：

结合数据特征及分布特点提出一种基于谱聚类的模糊时间序列自适应预测方法。首先基于谱聚类的思想，根据样本数据特征获取其所属论域的个数及范围，实现向模糊时间序列的自适应转化；然后基于 Markov 概率模型表示模糊时间序列中的模糊关系，从而对多步模糊关系、高阶模糊关系及模糊关系的稳态进行求解；最后获取预测值的可能模糊状态，进而利用去模糊化方法将其还原为预测值。在真实以及人工时间序列数据上的实验表明了所提方法的合理性与有效性。

关键词: 模糊时间序列, 谱聚类, 论域划分, Markov概率模型, 模糊关系

Abstract:

A fuzzy time series self-adaption prediction method based on spectral clusterin and data characteristics was proposed. First, based on spectral clustering and the racteristics of data, the number and scope of the discourses was obtained to convert into fuzzy time series self-adaptively. Then, fuzzy relationships based on Markov probability model was presented, and the multi-steps, high-order and steady fuzzy relationship are gotten.Finally, proposed meted obtained the probable fuzzy states, and got its predicted values based on defuzzification methods. Experiments on real-world and synthetic time series data indicate the rationality and effectiveness of the proposed method.

Key words: fuzzy time series, spectral clustering, discourse partition, Markov probability model, fuzzy relationship

周春楠,黄少滨,迟荣华,李雅,郎大鹏. 基于谱聚类的高阶模糊时序自适应预测方法[J]. 通信学报, 2016, 37(2): 107-115.

Chun-nan ZHOU,Shao-bin HUANG,Rong-hua CHI,Ya LI,Da-peng LANG. High-order fuzzy time series self-adaption prediction method based on spectral clustering[J]. Journal on Communications, 2016, 37(2): 107-115.

图/表 8

图1

图2

图3

图4

图5

图6

图7

图8

参考文献 1

[1]	SONG Q , CHISSOM B S . Fuzzy time series and its models[J]. Fuzzy Sets System, 1993, 54(3): 269-277.
[2]	SONG Q , CHISSOM B S . Forecasting enrollments with fuzzy time series[J]. Part I Fuzzy Sets System, 1993, 54(1): 1-9.
[3]	SONG Q , CHISSOM B S . Forecasting enrollments with fuzzy time series[J]. Part II Fuzzy Sets System, 1994, 62(1): 1-8.
[4]	LEE L W , WANG L H , CHEN S M . Temperature prediction and TAIEX forecasting based on high-order fuzzy logical relationships and genetic simulated annealing techniques[J]. Expert Systems with Applications, 2008(34): 328-336.
[5]	CHEN S M , HWANG J R . Temperature prediction using fuzzy time series[J]. IEEE Transactions on Systems, Man, Cybernetics-Part B:Cybernetics, 2000, 30(2): 263-275.
[6]	王兆霞, 孙雨耕 . 基于模糊神经网络的网络业务量预测研究[J]. 通信学报， 2005, 26(3): 136-140. WANG Z X , SUN Y G . Study of predicting network traffic using fuzzy neural networks[J]. Journal on Communications, 2005, 26(3): 136-140.
[7]	YU H K . Weighted fuzzy time-series models for TAIEX forecasting[J]. Physical A, 2004(349): 609-624.
[8]	张韬, 冯子健 . 模糊时间序列分析在肾综合征出血热发病率预测的应用初探[J]. 中国卫生统计， 2011, 2: 146-150. ZHANG T , FENG Z J . Application of fuzzy time series analysis in in-cidence of hemorrhagic fever with renal syndrome prediction[J]. China Health Statistics, 2011, 2: 146-150.
[9]	倪明 . 模糊时间序列预测模型研究及其在污水处理上的应用[D]. 西南石油大学， 2012. NI M . Fuzzy time series forecasting model and its application in wastewater treatment[D]. Southwest Petroleum University, 2012.
[10]	ALADAG C H , EGRIOGLU E . A high order seasonal fuzzy time series model and application to international tourism demand of turkey[J]. Applications in Engineering and Technology, 2014, 26(1): 295-302.
[11]	HUARNG K . Effective lengths of intervals to improve forecasting in fuzzy time series[J]. Fuzzy Sets and Systems, 2001, 123(3): 387-394.
[12]	LI S T , CHEN Y P . A high order seasonal fuzzy time series model and application to international tourism demand of turkey[C]// /The IEEE International Conference on Fuzzy Systems Budapest. Hungary, c2004: 25-29.
[13]	CHEN S M , HSU C C . A new method to forecast enrollments using fuzzy time series[J]. International Journal of Applied Science and Engineering, 2004, 2(3): 234-244.
[14]	TRAN T N , WEHRENS R , BUYDENS L . KNN-kernel density-based clustering for high-dimensional multivariate data[J]. Computational Statistics and Data Analysis, 2006, 51(2): 513-525.
[15]	CHENG C H , CHANG J R , YEH C A . Entropy-based and trapezoid fuzzification-based fuzzy time series approaches for forecasting IT project cost[J]. Technological Forecasting and Social Change, 2006, 73(5): 524-542.
[16]	HUARNG K , YU T H . Ratio-based lengths of intervals to improve fuzzy time series forecasting[J]. IEEE Transactions on Systems,Man, and Cybernetics-Part B: Cybernetics, 2006, 36(2): 328-340.
[17]	LEE L W , WANG L H , CHEN S M . Temperature prediction and TAI-FEX forecasting based on fuzzy logical relationships a netic algo-rithms[J]. Expert Systems with Applications, 2007, (33): 539-550.
[18]	CHENG C H , CHENG G W , WANG J W . Multi-attribute fuzzy time series method based on fuzzy clustering[J]. Expert Systems with Applications, 2008, 34(2): 1235-1242.
[19]	YOLCU U , EGRIOGLU E , USLU V R . A new approach for determining the length of intervals for fuzzy time series[J]. Applied Soft Computing, 2009, 9(2): 647-651.
[20]	EGRIOGLU E , ALADAG C H . Fuzzy time series forecasting ith a novel hybrid approach combining fuzzy c-means and neural networks[J]. Expert Systems with Application, 2013, 40(3): 854-857.
[21]	KHASHEI M . Fuzzy artificial neural network p, d, q model for incomplete financial time series forecasting[J]. Applications in Engineering and Technology, 2014, 26(2): 831-845.
[22]	CHEN S M , KAO P Y . TAIEX forecasting based on fuzzy ti series, particle swarm optimization techniques and support vec ma-chines[J]. Information Sciences, 2013, 247(15): 62-71.
[23]	BAS E , USLU V R , YOLCU U . A modified genetic algorithm for forecasting fuzzy time series[J]. Applied Intelligence, 2014, 41(2): 453-463.
[24]	曹盼盼, 阎春宁 . 人类通信模式的幂律分布和Zipf定律[J]．复杂系统与复杂科学, 2009, 6(4): 51-56. CAO P P , YAN C N . The power law and Zipf's law in huma mmu-nication patterns[J]. Complex Systems and Complexity Science, 2009, 6(4): 51-56.
[25]	CHEN S M , WANG N Y , PAN J S . Forecasting enrollments using automatic clustering techniques and fuzzy logical relationship[J]. Expert Systems with Applications, 2009, 36(8): 11070-11076.
[26]	CHEN S M , TANUWIJAYA K . Multivariate fuzzy forecasting based on fuzzy time series and automatic clustering techniques[J]. Expert Systems with Applications, 2011, 38(8): 10594-10605.
[27]	MILLS T C . Time series techniques for economists[J]. Cambridge: Cambridge University Press 1990.
[28]	LI S T , KUO S C , CHENG Y C , et al. A vector forecastin model for fuzzy time series[J]. Applied Soft Computing, 2011, 11(3): 3125-3134.
[29]	WANG W , LIU X . Fuzzy forecasting based on automatic cl stering and axiomatic fuzzy set classification[J]. Information Sciences, 2015, 294(294): 78-94.
[30]	NG A Y , JORDAN M I , WEISS Y . On spectral clustering: analysis and an algorithm[J]. Advances in Neural Information Processing Systems, 2002, 2(8): 849-856.
[31]	LUXBURG U V . A tutorial on spectral clustering[J]. Statistics and Computing, 2007, 17(4): 395-416.
[32]	LI M , LI Y C , LENG J X . Powertype functions of prediction error of sea le-vel time series[J]. Entropy, 2015, 17(7): 4809-4837.
[1]	LI M , LI J Y . On the predictability of long-range dependent series[J/OL]. Mathematical Problems in Engineering, 2010, article ID 397454..