Data processing: artificial intelligence – Fuzzy logic hardware
Reexamination Certificate
1999-04-14
2001-08-07
Powell, Mark R. (Department: 2122)
Data processing: artificial intelligence
Fuzzy logic hardware
C706S004000, C706S005000, C382S181000, C382S224000
Reexamination Certificate
active
06272476
ABSTRACT:
BACKGROUND OF THE INVENTION
1. Field of the Invention
The present invention relates to a fuzzy processor for pattern recognition, more particularly, to a programmable and expandable fuzzy processor for comparing a to-be-recognized pattern with a plurality of standard patterns.
2. Description of Related Art
The idea of fuzzy logic was introduced by L. A. Zadeh in 1965, which plays an important role in the field of computer science and has been successfully applied in many applications. Fuzzy logic is commonly implemented in computer software. However, because software fuzzy logic can not satisfy many applications requiring real-time processing, a design for hardware fuzzy logic has become an important research initiative.
Because of the imprecise, vague and incomplete nature of available information about a collection of objects, people usually has to proceed in fuzzy inference and judgement, which forms the physical basis for the fuzzy mathematics applied in pattern recognition. The principle rule of fuzzy pattern recognition is the maximum membership degree rule. In actual application, a standard pattern usually has a plurality of fuzzy features. If there are n standard patterns each having m fuzzy features and the jth fuzzy feature of the ith pattern is Aij, where i=1,2, . . . ,n; j=1,2, . . . ,m, then each standard pattern Ai is a fuzzy vector Ai=<Ai1, Ai2, . . . . , Aim>, 1<i<n. Assuming that u=(u
1
, u
2
, . . . ,U
m
) is a pattern to be recognized, each member of u, that is each u
j
, corresponds to a fuzzy feature. If there exists an i &egr; {1,2, . . . ,n} such that &mgr;
Ai
(u) =max{&mgr;
A1
(u), &mgr;
A2
(U), . . . , &mgr;
An
(u)} then u relatively belongs to Ai, wherein it is assumed that &mgr;
Ai
(u)=M
m
(&mgr;
Ai1
(u
1
), &mgr;
Ai2
(u
2
), . . . , &mgr;
Aim(u
m
)), and M
m
( ) is a synthesis function.
The above expression of &mgr;
Ai
(u)=max{&mgr;
A1
(u), &mgr;
A2
(u), . . . , &mgr;
An
(u)} discloses the recognition rule for conventional fuzzy pattern having multiple features. Currently, most of the hardware implementations for fuzzy pattern recognition are based on the rule which only finds the closest standard pattern for the to-be-recognized pattern. However, with the rise in system complexity, the increase in the number of standard patterns and especially the development of expanded systems with multiple stages, the above hardware implementation of fuzzy logic appears to be unsatisfactory. To enhance the system performance, it is necessary to find two or more of the closest standard patterns for the to-be-recognized pattern according to the synthesis membership degrees between the to-be-recognized pattern and the standard patterns. Therefore, a novel fuzzy processor is set forth hereinafter, which can sequentially output the synthesis membership degrees as well as the corresponding standard patterns in an order of magnitude. Accordingly, the h closest standard patterns can be found sequentially where 1≦h≦n. This will greatly improve the system performance by increasing the recognition rate and reprocessing and reusing data in a multi-stage expanded system.
There are many choices for the synthesis functions. The most frequently used are the minimum-finding function,
j
(X)=
j
x
j
for j=1 to m, and the summation function, &Sgr;X=&Sgr;x
j
for j=1 to m. The minimum-finding function is not suitable for pattern recognition since it only emphasizes a local feature and neglects the other features. The summation function is able to include the effects of all features whereby it is suitable for pattern recognition. Therefore, the summation function is adopted by the fuzzy processor in accordance with the present invention.
SUMMARY OF THE INVENTION
One object of the present invention is to provide a fuzzy processor which can be programmed to satisfy the requirements in different applications.
Another object of the present invention is to provide a fuzzy processor which can be expanded to enhance its adaptability in various applications.
In accordance with one aspect of the present invention, the fuzzy processor comprises a membership function I/O circuit for inputting and outputting a plurality of membership functions respectively corresponding to each one of a plurality of features of each one of a plurality of standard patterns, a feature decoder for receiving a to-be-recognized pattern having a plurality of input features for generating a plurality of feature values, a membership function generator for storing the plurality of membership functions and receiving the plurality of feature values to generate a plurality of current-type membership degrees for the plurality of input features corresponding to the plurality of standard patterns respectively, a plurality of accumulators for receiving the plurality of current-type membership degrees respectively for generating a plurality of synthesis membership degrees, and an expandable synthesis membership degree comparing circuit for receiving the plurality of synthesis membership degrees from the plurality of accumulators to output said plurality of synthesis membership degrees as well as the corresponding standard patterns in an order of magnitude. Other objects, advantages, and novel features of the invention will become more apparent from the following detailed description when taken in conjunction with the accompanying drawings.
REFERENCES:
patent: 5179668 (1993-01-01), Ejima et al.
patent: 5357449 (1994-10-01), Oh
patent: 5495558 (1996-02-01), Tashima
patent: 5561738 (1996-10-01), Kinerk et al.
patent: 5604842 (1997-02-01), Nishidai
patent: 5638490 (1997-06-01), Eckert et al.
patent: 5724483 (1998-03-01), Gianguido et al.
patent: 5732191 (1998-03-01), Kunemund et al.
patent: 5790755 (1998-08-01), Pagni et al.
patent: 5799132 (1998-08-01), Rizzotto et al.
patent: 5802204 (1998-09-01), Basehore
patent: 5805774 (1998-09-01), Viot et al.
patent: 5809486 (1998-09-01), Cuce
patent: 5867386 (1999-02-01), Hoffberg et al.
patent: 5870495 (1999-02-01), Mancuso et al.
patent: 5915247 (1999-06-01), Pappalardo et al.
patent: 5918221 (1999-06-01), Manaresi et al.
patent: 5943664 (1999-08-01), Abruzzese et al.
patent: 6035385 (2000-03-01), Le Van Suu
patent: 6061672 (2000-05-01), Caponetto et al.
patent: 6185331 (2001-02-01), Shi et al.
patent: 6188998 (2001-02-01), Cuce′ et al.
patent: 6205438 (2001-03-01), Shi et al.
Li et al.; “A Modified Current Mode Hamming Neural Network for Totally Unconstrained Handwritten Numeral Recognition”. IEEE[online], The 1998 IEEE Joint Conference on Neural Networks, May 1998, vol. 3, pp. 1857-1860.*
Liu et al.; “A Multi-Input Fuzzy Processor for Pattern Recognition”. IEEE[online], International Conference on Solid-State and Integrated Circuit Technology, Oct. 1995, pp. 112-114.*
Lin et al.; “A Novel Current-Mode Fuzzy Processor for Pattern Recognition”. IEEE[online], 1998 Fourth International Conference on Signal Processing Proceedings, Oct. 1998, vol. 1, pp. 541-544.*
Gabrielli et al.; “VLSI Design and Realisation of a 4 Input High Speed Fuzzy Processor”. IEEE[online], Proceedings of the Sixth IEEE International Conference on Fuzzy Systems, Jul. 1997, vol. 2, pp. 779-785.*
Ascia et al.; “A Dedicated Parallel Processor for Fuzzy Computation”. IEEE[online], Proceedings of the Sixth IEEE International Conference on Fuzzy Systems, Jul. 1997, vol. 2, pp. 787-792.*
Ascia et al.; “Design of a VLSI Parallel Processor for Fuzzy Computing”. IEEE[online], Proceedings of the 8th International Conference on VLSI Design, Jan. 1995, pp. 315-320.
Lin Gu
Shi Bingxue
Booker Kevin
Kolisch Hartwell Dickinson & McCormack & Heuser
Powell Mark R.
Winbond Electronics Corp
LandOfFree
Programmable and expandable fuzzy processor for pattern... does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Programmable and expandable fuzzy processor for pattern..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Programmable and expandable fuzzy processor for pattern... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-2503804