基于极端积算子的LL型模糊数的最小一乘回归

doi:10.12005/orms.2016.0019

摘要/Abstract

摘要： 针对模糊输入和模糊输出数据系统中的回归分析问题,考虑到系统中依赖关系不确定性特点以及模型稳健性和求解准确性等需求,建立一个模糊最小一乘优化模型。首先利用能诱导出LL型模糊数乘法保形运算的唯一T-模,即极端积算子,结合扩张原理,给出LL型模糊数间加法和乘法的运算规则。其次,基于LL型模糊数间的完备距离,得到模糊线性回归模型的参数估计,由此给出考虑清晰参数或清晰输入的两个简约模型及相应参数估计。通过计算Kim & Bishu测度、贴近测度和输出展形差异测度,比较与其他7种回归方法的优劣,并由模型的敏感性分析,充分说明本文算法的有效性和稳健性。

关键词: 极端积算子, LL型模糊数, 扩张原理, 最小一乘法, 模糊线性回归

Abstract: Fuzzy least-absolutes regression is developed by considering uncertain dependence,model robustness and exact solutions in the system with fuzzy inputs and fuzzy output. Firstly,Tw based addition and multiplication properties for LL type of fuzzy number are derived using the extension principle, where TW is also called drastic product,which is the only T norm inducing a shape preserving multiplication of LL type of fuzzy number.Secondly, fuzzy parameters are determined based on a complete metric on LL type of fuzzy number and then two particular cases of the general model are discussed.Finally,the potential of the proposed model with regard to other regression approaches is illustrated by some experiments and sensitivity analysis by adopting several measures, which turns out that the proposed model has good prediction accuracy and resistant power against outliers.

Key words: drastic product, LL type of fuzzy number, extension principle, least-absolutes method, fuzzy linear regression

中图分类号:

O159
O212.1

王宁, 陆秋君. 基于极端积算子的LL型模糊数的最小一乘回归[J]. 运筹与管理, 2016, 25(1): 145-153.

WANG Ning, LU Qiu-jun. Least-absolutes Regression Using LL Type of Fuzzy Number Operations Based on Drastic Product[J]. Operations Research and Management Science, 2016, 25(1): 145-153.

参考文献

[1] Montgonmery D C,Peck E A, Vinning G. Introduction to linear regression analysis[M] .4th Edition.New York:Wiley- Interscience, 2006.
[2] 靳云江,金赛男等.高级计量经济学(上册)[M] .北京:北京大学出版社,2007.
[3] Tanaka H, Uejima S, Asai K. Linear regression analysis with fuzzy model[J]. IEEE Transactions on Systems,Man and Cybernetics, 1982, 12: 903-907.
[4] Taheri S M, Kelkinnama M. Fuzzy linear regression based on least absolutes deviations[J] . Iranian Journal of Fuzzy Systems, 2012, 9: 121-140.
[5] Diamond P. Fuzzy least squares[J]. Information Sciences,1988, 46: 141-157.
[6] Chen L H, Hsueh C C, Chang C J. A two-stage approach for formulating fuzzy regression models[J]. Knowledge-Based Systems, 2013, 52: 302-310.
[7] Pourahmad S, Ayatollahi S M T, Taheri S M. Fuzzy logistic regression:a new possibilistic model and its application in clinical vague status[J]. Iranian Journal of Fuzzy Systems, 2011, 8: 1-17.
[8] Shakouri G H, Nadimi R. Outlier detection in fuzzy linear regression with crisp input-output by linguistic variable view[J]. Applied Soft Computing, 2013, 13: 734-742.
[9] Bisserier A, Boukezzoula R, Galichet S. A revisited approach to linear fuzzy regression using trapezoidal fuzzy intervals[J]. Information Sciences, 2010, 180: 3653-3673.
[10] Chan K Y, Kwong C K, Fogarty T C. Modeling manufacturing processes using a genetic programming based fuzzy regression with detection of outliers[J]. Information Sciences, 2010, 180: 506-518.
[11] Wu H C. The construction of fuzzy least squares estimators in fuzzy linear regression model[J]. Expert Systems with Applications, 2011, 11: 13632-13640.
[12] D’Urso P, Massari R, Santoro A. Robust fuzzy regression analysis[J]. Information Sciences, 2011, 181: 454- 474.
[13] Chen Y Q. Least squares support vector fuzzy regression[J].EnergyProcedia, 2012, 17: 711-716.
[14] Su Z G, Wang P H, Song Z L. Kernel based nonlinear fuzzy regression model[J]. Engineering Applications of Artificial Intelligence, 2013, 26, 724-738.
[15] Roh S B, Ahn T C, Pedrycz W. Fuzzy linear regression based on polynomial neural networks[J]. Expert Systems with Applications, 2012, 39: 8909- 8928.
[16] Hong D H, Song L K, Do H Y. Fuzzy least-squares linear regression analysis using shape preserving operations[J]. Information Sciences, 2001, 138: 185-193.
[17] Yang M S, Lin T S. Fuzzy least-squares linear regression analysis for fuzzy input-output data[J]. Fuzzy Sets and Systems, 2002, 126: 389-399.
[18] Choi S H, Buckley J J. Fuzzy regression using least absolute deviation estimators[J].Soft Computing, 2008, Y12: 257-263.
[19] Chen L H, Hsueh C C. Fuzzy regression models using the least-squares method based on the concept of distance[J]. IEEE Transactions on Fuzzy Systems, 2009, 6: 1259-1272.
[20] Hassanpour H, Maleki H R, Yaghoobi M A. Fuzzy linear regression model with crisp coefficients: a goal programming approach[J]. Iranian Journal of Fuzzy Systems, 2010, 7: 19-39.
[21] Hojati M, Bector C R, Smimou K. A simple method for computation for fuzzy linear regression[J]. European Journal of Operational Research, 2005, 166: 172-184.
[22] Hong D H. Shape preserving multiplication of fuzzy numbers[J]. Fuzzy Sets and Systems, 2001, 123: 81- 84.
[23] Hong D H, Lee S, Do H Y. Fuzzy linear regression analysis for fuzzy input-output data using shape-preserving operations[J]. Fuzzy Sets and Systems, 2001, 122: 513-526.
[24] 胡宝清.模糊理论基础(第二版)[M].武汉:武汉大学出版社,2010.
[25] Mesiar R. Shape preserving additions of fuzzy interval[J]. Fuzzy Sets and Systems, 1997, 86: 73-78.
[26] Hong D H, Do H Y. Fuzzy system reliability analysis by the use TW(the weakest T-norm)on the fuzzy number arithmetic operations[J]. Fuzzy Sets and Systems, 1997, 90: 307-316.
[27] Yang M S, Ko C H. On clusterwise fuzzy regression analysis[J]. IEEE Transactions on Systems, Man and Cybernetics,1997, 27:1-13.
[28] Kim B, Bishu R R. Evaluation of fuzzy linear regression models by comparing membership functions[J] . Fuzzy Sets and Systems, 1998, 100: 343-352.
[29] Rezaei H, Emoto M, Mukaidono M. New similarity measure between two fuzzy sets[J]. Journal of Advanced Computational Intelligence and Intelligent Informatics, 2006, 10: 946-953.
[30] Chang P T, Lee E S. Fuzzy linear regression with spreads unrestricted in sign[J]. Computers and Mathematics with Applications, 1994, 4: 61-70.
[31] D’Urso P. Linear regression analysis for fuzzy/crisp input and fuzzy/crisp output data[J]. Computational Statistics and Data Analysis, 2003, 42: 47-72.
[32] Coppi R, D’Urso P, Giordani P et al. Least squares estimation of linear regression model with LR fuzzy response[J]. Computational Statistics and Data Analysis, 2006, 51: 267-268.