A researcher called Zadeh developed the fuzzy logic technique in 1965. Recently this area has featured more in research. This fuzzy logic technique can be used for uncertainty and it can also be utilized in information granularity and imprecision. The generation of keen mapping among output and input space can be done effectively by means of fuzzy logic. Some of the main modules are given as follows:
The present classification table will be transferred onto a continuous classification in the initial stage. This operation in fuzzy logic is referred to as fuzzification. Then the domain experts will produce an inference engine based on the knowledge base. With the aid of this the operation will be carried out within the fuzzy domain. The database and rule base will come under the knowledge base. The generated fuzzy number will then be transferred back onto the single value called the “real world”. This operation is referred to as defuzzification.
Among the various existing quantities, fuzzy number is one among them. The value for this is imprecise. This value will be found to be similar to a normal single value number. The fuzzy number is defined as a membership function. The domain of the function is more specified. The domain contains real numbers in the range between the [0, 1] interval is referred to as a positive number. A specified value will be allocated for every numerical value in the domain. The highest possible value in this membership function is 1, similarly the lowest possible value is 0. The various forms for plotting fuzzy numbers are given as follows:
- • Parabolic shaped fuzzy numbers.
- • Trapezoidal fuzzy numbers.
- • Triangular fuzzy numbers.
Fuzziness: Fuzzy numbers are referred to as distinct fuzzy sets w'hich denotes the information is of uncertain quantity. They wall be either exhibited as normal or convex and frequently denoted as single modal values. These fuzzy numbers are linked to some fuzziness or vagueness.
Mamdani-style inference: The fuzzy set in each rule will be correlated by means of an aggregation operator resulting in fuzzy inference. The gathered fuzzy set will be defuzzified further in order to obtain the outcome.
Membership function (MF): The degree to which the input fits to set or is otherwise correlated to the concept is referred to as function.