Efficient fuzzy compiler for SIMD architectures

This paper presents a real-time full-programmable fuzzy compiler based on piecewise linear interpolation techniques designed to be executed in single instruction multiple data (SIMD) architectures. A full-programmable fuzzy processor is defined as a system where the set of rules, the membership functions, the t-norm, the t-conorm, the aggregation operator, the propagation operator, and the defuzzyfication algorithm can be defined by any valid algorithm. The SIMD platforms selected are the Intel Pentium III (using the SSE set of instructions) and the Texas Instruments TI DSP C6x family. The final speed obtained in both implementations is highly satisfactory and better than the speed provided by standard specific hardware.

[1]  Dimitar P. Filev,et al.  Fuzzy SETS AND FUZZY LOGIC , 1996 .

[2]  Yan Shi,et al.  Fuzzy inference chip FZP-0401A based on interpolation algorithm , 1998, Fuzzy Sets Syst..

[3]  Masaki Togai,et al.  Expert System on a Chip: An Engine for Real-Time Approximate Reasoning , 1986, IEEE Expert.

[4]  F. Fernández,et al.  A Shape-preserving Affine Takagi-Sugeno Model Based on a Piecewise Constant Nonuniform Fuzzification Transform , 2001 .

[5]  Paolo Faraboschi,et al.  Hardware solutions for fuzzy control , 1995, Proc. IEEE.

[6]  Constantin von Altrock,et al.  Fuzzy Logic and NeuroFuzzy Applications in Business and Finance , 1996 .

[7]  Jerry M. Mendel,et al.  Uncertainty, fuzzy logic, and signal processing , 2000, Signal Process..

[8]  C. von Altrock,et al.  Recent successful fuzzy logic applications in industrial automation , 1996 .

[9]  Siegfried Gottwald,et al.  Fuzzy Sets and Fuzzy Logic , 1993 .

[10]  F. Matia,et al.  A fast piecewise-linear implementation of fuzzy controllers , 1994, NAFIPS/IFIS/NASA '94. Proceedings of the First International Joint Conference of The North American Fuzzy Information Processing Society Biannual Conference. The Industrial Fuzzy Control and Intellige.

[11]  R. Rovatti,et al.  Linear and fuzzy piecewise-linear signal processing with an extended DSP architecture , 1998, 1998 IEEE International Conference on Fuzzy Systems Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98CH36228).

[12]  Juan Luis Castro,et al.  Fuzzy logic controllers are universal approximators , 1995, IEEE Trans. Syst. Man Cybern..

[13]  George J. Klir,et al.  Fuzzy sets and fuzzy logic - theory and applications , 1995 .

[14]  Hao Ying,et al.  General Takagi-Sugeno fuzzy systems are universal approximators , 1998, 1998 IEEE International Conference on Fuzzy Systems Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98CH36228).

[15]  Hung T. Nguyen,et al.  Fuzzy systems are universal approximators for a smooth function and its derivatives , 2000 .

[16]  C. V. Altrock.  Fuzzy logic and neurofuzzy applications explained , 1995 .

[17]  Herbert Eichfeld,et al.  A 12b general-purpose fuzzy logic controller chip , 1996, IEEE Trans. Fuzzy Syst..

[18]  Yongsheng Ding,et al.  Typical Takagi-Sugeno and Mamdani fuzzy systems as universal approximators: necessary conditions and comparison , 1998, 1998 IEEE International Conference on Fuzzy Systems Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98CH36228).

[19]  Liliane Peters,et al.  A high-speed, reconfigurable fuzzy logic controller , 1995, IEEE Micro.

[20]  Serge Boverie,et al.  Applications of fuzzy logic: towards high machine intelligence quotient systems , 1997 .

[21]  Silvio Simani,et al.  High-speed DSP-based implementation of piecewise-affine and piecewise-quadratic fuzzy systems , 2000, Signal Process..

[22]  Alessandro Gabrielli,et al.  A fast digital fuzzy processor , 1999, IEEE Micro.