Adjusting Membership Functions and Generating TSK Fuzzy Systems from Numerical Data: Application to a Medical Case

0*, Raouf Ketata**, Imed Maaloul***, Chtourou M****, Mounir Ben Jemaa*****
* ,** Research unit on Intelligent Control, Design and Optimization of Complex Systems (lCOS), National School of Engg of SfaxTunisia.
*** Department of infectious diseases, Hedi Chaker University Hospital, Sf Tunisia
**** Research unit on Intelligent Control, Design and Optimization of ComplexSystems(ICOS), National School of Engineers of Sf Sfax Tunisia.
*****Department of infectious diseases, Hedi Chaker UnNersify Hospital, Sfax. Tunisia.
Periodicity:July - September'2007
DOI : https://doi.org/10.26634/jse.2.1.670

Abstract

This paper presents a new algorithm for generating fuzzy rule base from numerical data. The algorithm is based on different concepts: First, the Mendel Wang generating method for constructing rules premises. Second, the gradient descent method for the identification of Takagi—Sugeno—Kang (TSK) parameters. Third, the similarity measure between fuzzy sets premises and TSK parameters. The principal idea consists in the adjustment of membership function if similarity exists using initial numerical values. The benefits consist in a better fuzzy sets definition without reducing fuzzy rule bases or losing precision. This paper focuses on the application of this approach to the non linear function and a medical problem.

Keywords

Generating Fuzzy Rules, Gradient Descent Method, Merging Fuzzy Sets and Similarity

How to Cite this Article?

Hatem Bellaaj, Raouf Ketata, Imed Maaloul, Chtourou M and Mounir Ben Jemaa (2007). Adjusting Membership Functions and Generating TSK Fuzzy Systems from Numerical Data: Application to a Medical Case.i-manager’s Journal on Software Engineering, 2(1),10-23. https://doi.org/10.26634/jse.2.1.670

References

[I ]. L.-X.Wong et J. M. Mendel, Generating fuzzy ru\es by learning from exampies, IEEE Trons. Syst., Mon, Cybern,, voL 22, pp. 14141427, Nov,/Dec. 1992.
[2]. Robert 8obusko, Construction of Fuzzy Systems, lnterplOy between Precision ond Tronsporency Control Lob, Foc. ITS, Delft Univ. of Technology
[3]. Serge Guilloume, Design\ng Fuzzy \nference Systems from Data: An \nterpretabillfy-Or\ented Revlew, IEEE Trons. Fuzzy Syst., Vol, . 9, NO. 3, JUNE 2001
[4]. Sontiogo Ajo-Fernandez ond Corlos Alberolo-L6pez, Fast Inference in SAM Fuzzy Systems Using Transition Matrices, IEEE Trons. Fuzzy Syst., VoI., VOL. 12, NO, 2, APRIL 2004
[5]. R. Alcol6, J. Cosillos, O. Cord6n, F. Herrero, ond S. Zwir, Know\edge engineering Systems techniques and applications, in Techniques for Looming ond Tuning Fuzzy Rule-Hosed Systems for Linguistic Modeling ond Their Applicotion. NewYork: Acodemic, I 999 .
[6]. E. Momdoni, App/ication of fuzzy algorithms for control of slmp\e dynamic plant, Proc. Inst. Elect. Eng,: Control Science, vol. I 21, pp. 15851588, Dec. 1974.
[7]. 8. Kosko, Fuzzy Engineering. Upper Soddle River, NJ: Prentice-HoIL 1997.
[8]. M~ 8oczynski, On a class of distrlbuHve implications, Inf, J. Uncertointy Knowledge-Bosed Syst. , voL 9, no. 2, pp, 229238, 2001 IEEE Trons. Fuzzy Syst., VoI. I 2, NO. 2, APRIL 2004
[9]. T. Tokogi ond M. Sugeno, Fuzzy \dent/flcation of systems and its applications to modeling and control, IEEE Trons. Syst~, Mon, Cybern., voL SMC- I 5, pp. I I 6 I 32, JOn. 1985.
[10]. O. Cordon, F. Herrero, I. Zwir, A hierarchical know\edge-based environment for linguistic mode\Ing: modeis and iteratlve methodology, Fuzzy Sets ond Systems (2003) 307341
[ I I ]. J. Espinoso ond J. VOndewOllfe, Constructing Fuzzy Models with Linguistic \ntegrity from Numerlcal Data- AFRELI Algorithm, IEEE Trons, Fuzzy Syst,, VoI, 8, No, 5, pp, 59 I -600, 2000.
[ I 2]. C.-C. Wong ond C.-C. Chen, A Hybrid Clustering and Gradient Descent Approach for Fuzzy Mode\Ing, IEEE Trons. Syst., Mon, ond Cybern. B, VoI. 29, No. 6, pp. 686-693, 1999.
[ I 3]. J. Espinoso ond J. VOndewOllfe, Constructing Fuzzy Models with Linguistic \ntegrity from Numerical Data- AFRELI Algorithm, IEEE Trons. Fuzzy Syst., Vol. 8, No, 5, pp, 59 I -600, 2000.
[ I 4]. O.Cordon, F.Herrero ond oil. Genetic fuzzy systems.' evolutionary tuning and \earnlng of fuzzy know\edge bases, World Scientific, Singopore, New Jersey, London, Hong Kong, 200 I , 462 pp~
[ I 5]. A.E. G owedo, ond J.M. Zurodo, Doto-Driven linguistic Modeling Using Relotionol Fuzzy Rules IEEE Trons. Fuzzy Syst., VoI. . 11, NO. I , FEBRUARY 2003 I 21
[ I 6]. J.-S. R. Jong, C..-T. Sun, ond E. Mizutoni, Neuro-Fuzzy and Soft-Computing. Upper Soddle River, NJ: Prentice- HolL I 997~
[ I 7]. Y.Tong, W.J.Wong, ond Y.A.Liou. GA-Hosed Fuzzy Modeling with on Exponentiol-Portitioned Structure \nternationa\ Journal of Fuzzy Systems, Vo\, 4, No, 4, December2OO2 .
[18]. R J. Bentley. Evolving Fuzzy Detectives: An Investlgotion into the Evolution of Fuzzy Rules Deportment of Computer Science, University College London, Gower Street, London WCIE 68T, UK
[ I 9]. D. E. Gustofson ond W C. Kessei, Fuzzy c\ustering with a fuzzy covar\ance matrix In Proc~ IEEE Cont, Decision Control, Son Diego, CA, 1979, pp. 761 766 .
[20]. J. Fon ondW. Xie, Distance measure and \nduced fuzzy entropy, Fuzzy Sets Syst., vol. 104, pp. 305314, 1999.
[2 I ]. 8. 8. Choudhuri ond A. Rosenfeld, On a metr\c d\stance between fuzzy sets, Pottern Recogn. Left,, vol, 17, pp. I 1571160, 1996.
[22]. 8. 8. Choudhuri ond A. Rosenfeld, A modif\ed hausdorff d\stance between fuzzy sets, Inform. Sci., vol, 118, pp. 15917 I , 1999.
[23]. R. Lowen ond W Peelers, Distance between fuzzy sets representing grey level Images, Fuzzy Sets Syst., vol, 99, pp~ I 35149, 1998 ,
[24]. L. Koczy ond K. Hiroto, Ordering, distance and c\oseness of fuzzy sets, Fuzzy Sets Syst., Vol. 59, pp. 281293, 1993.
[25]. S.Guilloume ond 8.Chornomordic, Generating an \nterpretab\e Family of Fuzzy Part\fions From Data, IEEE Trons. Fuzzy Systems I 2, June 2004.
[26]. J.-S.R. Jong, Se\f-\earning fuzzy contro\\ers based on tempora\ backpropagation, IEEE Trons. Neurol Networks (1992) 714723.
[27]. G.C. Mouzouris, J.M. Mendel, Dynamic non- slngleton fuzzy \ogic systems for non\\near mode\\ng, IEEE Trons. Fuzzy Systems 5 (1997) 199208.
[28]. J.8.Theochoris, G. Vochtsevonos, Recurs\ve learning algorithms for training fuzzy recurrent mode\s, Internet. J, InteII, Syst. 1 I (1996) 10591098 ,
[29]. T. Tokogi, M. Sugeno, Fuzzy ident\:cation ofsystems and \ts app\ications, IEEE Trons. Systems, Mon, Cybernet, 15 (1985) I I 6132.
[30]. C.-H. Lee, C.-C. Tong, Ident\fication and contro\ of dynamic systems using recurrent fuzzy neural networks, IEEE Trons. Fuzzy Systems 8 (2000) 349366 ,
[32]. A. Mostorocostos, John 8. Theochoris, An orthogonal least-squares method for recurrent fuzzy- neural modelling, Fuzzy Sets ond Systems 140 (2003) 285300
[33]. M"8etnes, R.8obuisko, U.Koymok, ond H.R.Nouto Lemke: Similarity Measures In Fuzzy Rule Base Slmplification, IEEE Trons. Systems Mon Cybernet. Port B, vol. 28, June 1998
[34]. D.F. Li ond C.T. Cheng, New similarity measures of intuifionistic fuzzy sets and app\ication to pattern recognifion, Pottern Recognition Letters 23, 221-225, (2002).
[35]. RR Angelov, Evolving Rule-Dosed Models: A Tool for Design of Flexible Adoptive Systems, Physico-Verlog, Springer, Heidelberg, 2002.
[36]. R Angeiov, R. Guthke, A GA-bosed opprooch to optimizotion of bioprocesses described by fuzzy rules, J. 8loprocess Eng. 1 6 (1997) 299301 .
[37]. 8. Corse, TC. Fogorty, A. Munro, Evolving fuzzy rule- Dosed controllers using GA, Fuzzy Sets ond Systems 80 (1996) 273294,
[38]. Plomen R Angelov, An evolutionary approach to fuzzy ru\e-based model synthesis using indices for ru\es, Fuzzy Sets ond Systems I 37 (2003) 325338
[39]. I.Rojos, H.Pomores, J.Ortega ond A.Prieto. Self- Orgonized Fuzzy System Generotion from Troining Exomples. IEEE TrOns, Fuzzy Syst, , Vol.. 8, NO, I , FEBRUARY 2000 23
[40]. F.Y.Cheng, 8.8. MocDonold, ond oil. A Prospect\ve Mu\ticenter Study of Staphy\ococcus aureus Bacteremia \ncidence of Endocard\tis, RiskFactors for Mortaii\y and C\\nica\ \mpact of Methici\\in Resistance Medicine _ Volume 82, Number 5, September 2003
[41]. S.H.Kiml, W.8.Porkl, ond oil. Outcome of inoppropriote initiol ontimlcrobiol treotment in potients with methicillin-resistont Stophylococcus oureus
[42]. F.Aversa, E.Gronda, S.Piuuti and C.Aragno. A Fuzzy Logic Approach to Decision Support in Medicine KeII s.r.I., ViaE.Q. Visconti, 8 00193 Rome Italy.
[43]. Le Conseil medical du Canada. Analyses de lab orat oireVal eurs d e referenc e . www. m cc , ca/ Objectives online/objectives,pl?lang=french&loc=valu
[44]. M.Y. Chen, D.A. Linkens RuIe-base self-generation and simplification for data-dri\/en fuzzy models Fuzzy Sets and Systems 142 (2004) 243265
[45]. A.E. Gaweda,, and J.M. Zurada, Data-Driven Linguistic Modeling Using Relational Fuzzy Rules IEEE Trans. Fuzzy Syst., Vol, . 11, NO. I ,pp I 21, February 2003
If you have access to this article please login to view the article or kindly login to purchase the article

Purchase Instant Access

Single Article

North Americas,UK,
Middle East,Europe
India Rest of world
USD EUR INR USD-ROW
Pdf 35 35 200 20
Online 35 35 200 15
Pdf & Online 35 35 400 25

Options for accessing this content:
  • If you would like institutional access to this content, please recommend the title to your librarian.
    Library Recommendation Form
  • If you already have i-manager's user account: Login above and proceed to purchase the article.
  • New Users: Please register, then proceed to purchase the article.