Software Implementation Issues of Existing and New Defuzzification Methods

This paper discusses software implementation issues of different defuzzification procedures in fuzzy systems. Three new defuzzification methods are introduced which are suitable for efficient software and also hardware implementations. A set of seven important existing defuzzification methods are reviewed and compared with these new methods for different software implementation approaches. The C models of all methods are prepared to perform a comprehensive analysis on the output accuracy of different methods. The results prove the superiority of our new proposed methods. In another study, three categories of low-level assembly models are developed for each method to evaluate its software execution time and instruction count when executed on each of three chosen popular processors. Namely, Texas Instruments C6xcopy DSP, Intel's Pentiumcopy IV, and IBM's PowerPC PPC405copy processors are used as the running engines for this comparison. Some accuracy-speed analysis diagrams are then introduced to guide the designers for choosing the defuzzification method which best suites their application requirements.

[1]  Alessandro Gabrielli,et al.  Very fast rate 2-input fuzzy processor for high energy physics , 2002, Fuzzy Sets Syst..

[2]  G. Ascia,et al.  A pipeline parallel architecture for a fuzzy inference processor , 2000, Ninth IEEE International Conference on Fuzzy Systems. FUZZ- IEEE 2000 (Cat. No.00CH37063).

[3]  José Luis Martín,et al.  Hardware implementation of a pipeline fuzzy controller and software tools , 2002, Fuzzy Sets Syst..

[4]  Jean J. Saade,et al.  Defuzzification techniques for fuzzy controllers , 2000, IEEE Trans. Syst. Man Cybern. Part B.

[5]  Sied Mehdi Fakhraie,et al.  Cost-Performance Co-Analysis in VLSI Implementation of Existing and New Defuzzification Methods , 2005, International Conference on Computational Intelligence for Modelling, Control and Automation and International Conference on Intelligent Agents, Web Technologies and Internet Commerce (CIMCA-IAWTIC'06).

[6]  Miguel A. Melgarejo,et al.  Distributed arithmetic in the design of high speed hardware fuzzy inference systems , 2003, 22nd International Conference of the North American Fuzzy Information Processing Society, NAFIPS 2003.

[7]  Angel Barriga,et al.  HARDWARE IMPLEMENTATION OF A GENERAL PURPOSE FUZZY CONTROLLER , 1995 .

[8]  Bernard De Baets,et al.  A comparison of three methods for computing the center of gravity defuzzification , 2004, FUZZ-IEEE.

[9]  Thomas A. Runkler,et al.  Selection of appropriate defuzzification methods using application specific properties , 1997, IEEE Trans. Fuzzy Syst..

[10]  Osamu Saotome,et al.  A Two-Input, One-Output Bit-Scalable Architecture for Fuzzy Processors , 2001, IEEE Des. Test Comput..

[11]  Sied Mehdi Fakhraie,et al.  Hardware implementation and comparison of new defuzzification techniques in fuzzy processors , 2006, 2006 IEEE International Symposium on Circuits and Systems.

[12]  Witold Pedrycz,et al.  A survey of defuzzification strategies , 2001, Int. J. Intell. Syst..

[13]  M. J. Wierman,et al.  Empirical study of defuzzification , 2003, 22nd International Conference of the North American Fuzzy Information Processing Society, NAFIPS 2003.