Fuzzy Logic Is a Way to Deal with Imprecise Concepts

As his work on mathematical systems gained international recognition Zadeh's paper on fuzzy logic began a new phase of his career and since then almost all of his publications were fuzzy logic or soft computing Including Zingh. Since fuzzy logic is a more realistic way to deal with incorrect concepts, it can be applied to inaccurate situations in the real world. As written by Peterson, rather than dealing with true or false, fuzzy logic handles the actual order, which represents the specified value between 0 and 1.

Fuzzy logic - fuzzy logic is the place where probability theory and propositional logic meet. The problem of propositional logic is transactions of absolute values ​​such as trading, correct or incorrect, for traders 0. The reliability of these results can not be judged. Fuzzy logic overcomes this limitation by introducing a membership function that specifies the range in which variables belong to a particular domain. For example, the company (GOOG) would be 0.7 for domain name {BUY} and 0.3 for domain name {SELL}. The combination of neural network and fuzzy logic is called the neurofuzzy system. In the survey, we will explain various fuzzy rule extraction methods.

Fuzzy logic (FL) is a reasoning method similar to human inference. Fuzzy logic is the science of reasoning, thinking, inference, identifying and using phenomena in the real world - everything is a matter of degree. Fuzzy logic does not assume that everything is black and white (traditional logic), but assuming that most things are actually somewhere in the middle, that is, they are various gray tones I will. It was promoted by the University of California engineer Lofti Zadeh (1965). It uses continuous set membership from 0 to 1. On the other hand, Boolean logic or traditional logic is clearly distinguished. In other words, it is 0 if false, 1 if true. Medicine is essentially an ongoing field and most medical data are inherently inaccurate. Fuzzy logic is a mathematical logic that attempts to solve the problem by assigning values ​​to incorrect data spectra to reach the most accurate conclusion.

Several expert systems in the field of linear and nonlinear control, pattern recognition, financial systems and data analysis use fuzzy logic to deal with incorrect rules and inputs. Fuzzy logic in such systems typically uses preset tags to classify real-time inputs and uses fuzzy reasoning to compute numerical conclusions from incorrect rules. The knowledge database is not easy to access. Expert system tools are often based on LISP and lack the ability to integrate with other applications written in traditional languages. Most systems can not be ported yet between different hardware. All of these system integration problems can lead to increased costs and risks. A new system architecture is required to fully integrate the external system and knowledge database