A comparative assessment of fuzzy regression models: the case of oil consumption estimation

The objective of this study is to examine the most well-known FR approaches with respect to oil consumption estimation. Furthermore, there is no clear cut as to which approach is superior for oil consumption estimation. The economic indicators used in this paper are population, cost of crude oil, gross domestic production and annual oil production. The data for oil consumption in Canada, USA, Japan and Australia from 1990 to 2005 are considered. The input data are divided into train and test data. The FR models have been tuned for all their parameters according to the train data and the best coefficients are identified. Three popular defuzzification methods for defuzzifying outputs are applied. For determining the rate of error of FR models estimations, mean absolute percentage error is calculated. This study reveals that there is no best FR model unlike previous studies which claim to have developed the most efficient FR models.

[1]  Bilal M. Ayyub,et al.  Fuzzy regression methods - a comparative assessment , 2001, Fuzzy Sets Syst..

[2]  Ning Wang,et al.  Fuzzy nonparametric regression based on local linear smoothing technique , 2007, Inf. Sci..

[3]  Pradip Kumar Ray,et al.  Non-contact estimation of surface roughness in turning using computer vision and Artificial Neural Networks , 2009 .

[4]  C. R. Bector,et al.  A simple method for computation of fuzzy linear regression , 2005, Eur. J. Oper. Res..

[5]  Lotfi A. Zadeh,et al.  The Concepts of a Linguistic Variable and its Application to Approximate Reasoning , 1975 .

[6]  Hsiao-Fan Wang,et al.  Insight of a fuzzy regression model , 2000, Fuzzy Sets Syst..

[7]  Miao-Ling Wang,et al.  To construct a monitoring mechanism of production loss by using Fuzzy Delphi method and fuzzy regression technique - A case study of IC package testing company , 2008, Expert Syst. Appl..

[8]  Ebrahim Nasrabadi,et al.  Fuzzy linear regression analysis: a multi-objective programming approach , 2005, Appl. Math. Comput..

[9]  H. Moskowitz,et al.  Fuzzy versus statistical linear regression , 1996 .

[10]  Phil Diamond,et al.  Fuzzy least squares , 1988, Inf. Sci..

[11]  Chuck Zhang,et al.  Feature-based cost estimation for composite structures with Fuzzy Multi-Attribute Utility Theory , 2006 .

[12]  J. Watada,et al.  Possibilistic linear systems and their application to the linear regression model , 1988 .

[13]  Shing I. Chang,et al.  A fuzzy approach for multiresponse optimization: An off-line quality engineering problem , 1994 .

[14]  T. Ross.  Fuzzy Logic with Engineering Applications , 1994 .

[15]  E. Stanley Lee,et al.  Modeling of thermal comfort in air conditioned rooms by fuzzy regression analysis , 2006, Math. Comput. Model..

[16]  H. Tanka.  Fuzzy data analysis by possibilistic linear models , 1987 .

[17]  Hsiao-Fan Wang,et al.  Resolution of fuzzy regression model , 2000, Eur. J. Oper. Res..

[18]  A. Celmins.  Least squares model fitting to fuzzy vector data , 1987 .

[19]  Ram R. Bishu,et al.  Evaluation of fuzzy linear regression models by comparing membership functions , 1998, Fuzzy Sets Syst..

[20]  Georg Peters.  Fuzzy linear regression with fuzzy intervals , 1994 .

[21]  M. Saberi,et al.  Improved Estimation of Electricity Demand Function by Integration of Fuzzy System and Data Mining Approach , 2006, 2006 IEEE International Conference on Industrial Technology.

[22]  Ping-Teng Chang,et al.  A generalized fuzzy weighted least-squares regression , 1996, Fuzzy Sets Syst..

[23]  Hsien-Chung Wu,et al.  Fuzzy estimates of regression parameters in linear regression models for imprecise input and output data , 2003, Comput. Stat. Data Anal..

[24]  A. Gil,et al.  Forecasting of electricity prices with neural networks , 2006 .

[25]  Junzo Watada,et al.  Possibilistic linear regression analysis for fuzzy data , 1989 .

[26]  William H. Woodall,et al.  Further examination of fuzzy linear regression , 1996, Fuzzy Sets Syst..

[27]  Sándor József.  On the effect of linear data transformations in possibilistic fuzzy linear regression , 1992 .

[28]  Ali Azadeh,et al.  An integrated GA-time series algorithm for forecasting oil production estimation: USA, Russia, India, and Brazil , 2009 .

[29]  Lucien Duckstein,et al.  Multi-objective fuzzy regression: a general framework , 2000, Comput. Oper. Res..

[30]  A. Kandel,et al.  Fuzzy linear regression and its applications to forecasting in uncertain environment , 1985 .