Application of Interval Type-1 Fuzzy Inference System to analyze the quality of memorization Qur’an

In this modern world, the use of artificial intelligence needed. One of the intelligence methods raised in this study is to use the Interval Type-1-Fuzzy Inference System (IT-1-FIS). In Muslim schools (Madrasah Ibtidaiyah) where there is subject matter memorizing the Qur’an. The fluency determines the quality of memorization of the Qur’an in pronouncing letters (Input-1), Tajweed Rules (Input-2), and reading fluency (Input-3). These three points become input for forecasting Memorization Quality Of The Qur’an. IT-1-FIS requires primary inputs and rules to obtain the output of forecasting Memorization Quality Of The Qur’an. By using IT-1-FIS, it can predict that students will get the quality of memorization based on the trace value obtained on each point. So from the beginning the teacher will know the quality of a student’s memorization in the future. The estimated condition in memorization of the Qur’an can be known faster, and the teacher will be able to increase the points that are less to get the desired quality of memorization of the Qur’an by the habits practiced by students. These students’ patterns are the basic rules of input in the IT-1-FIS process.


Introduction
In the last ten years, the development of artificial intelligence is speedy. This development is shown by the increasing variety of new algorithms that help every side of life. The more advanced the algorithm used is more straightforward and has a higher processing speed [1,2]. More and more electronic devices are using artificial intelligence. So that the smaller the electronic dimensions, the more complex the ability and the faster.
Among the artificial intelligence algorithms is Fuzzy logic. Fuzzy Logic was introduced by Prof. Zadeh in 1965 [3,4]. He explained that among logical binary numbers, one has a meaning, Yes and 0 have a sense No. Fuzzy logic will discuss the area between 1 and 0. Therefore Fuzzy logic is also known as obscurity logic. It means that analysis in areas outside 1 and 0 will be discussed in this Fuzzy logic [4,5]. So this Fuzzy Logic has a higher level of precision when compared to other algorithms.
Utilization of Fuzzy Logic, among others, in the field of forecasting. In the field of forecasting Fuzzy Logic is used to predict the growth of electrical loads. For flood forecasting, for forecasting production and forecasting the graduation rate of a school and so on. In other fields, that can be used as a method for analyzing a process. Fuzzy logic in analyzing a process that is as a control device to carry out a particular process. For example, a washing machine using Fuzzy logic [6]. The robot of fire extinguisher devices using Fuzzy logic to increase precision in finding hotspots and so on [7]. In its development, Fuzzy Logic is the better method of analysis. In this inference process, Fuzzy Logic incorporates basic rule elements for its analysis [8]. This basic rule is obtained based on experience or previous research. Therefore, in its development, Fuzzy logic is known as the Interval type 1 Fuzzy Inference system .
In this study, IT-1-FIS is used to analyze and predict how good the level of Qur'an memorization is in a Madrasah Ibtidaiyah [9,10]. For this analysis, three input variables are needed. These 3 variables are: fluency in pronouncing letters (Input-1); Tajweed Rules (Input-2); and reading fluency (Input-3). These three variables will be analyzed with the basic rules, then the results of the IT-1 FIS analysis will be obtained in the form of how good the Qur'an Recitation level is. Secondly, the teachers can estimate the current conditions for some time in the future they will have the ability to memorize the Qur'an how well [11,12].

Variabel and membership function
In IT-1 FIS processing, the path that must be traversed is to prepare the input variables and the output variables. Input variables that will be used are a.  The membership function of the triangle above has the following equation: or can be defined as follows: The x parameter is the input of crisp, a and c represent the toe of the triangle, while b represents the peak of the triangle. Fuzzy Logic Process is known as the Fuzzy Inference System (FIS).

Fuzzy Inference System
The fuzzy inference is doing reasoning using fuzzy input and fuzzy rules that have been determined to produce fuzzy output [13,14]. The five sequences of the Max-Min FIS method are as follows [13]:  Fuzzy set formation (input and output variables) Defuzzification is a mapping process from the results of areas of fuzzy inference to non-Fuzzy regions (Crisp). In the implementation of fuzzy real-time controls, the Center of Area (COA) defuzzification process is used. The defuzzification of the center of the area produces the center of gravity of the distribution of control actions stated in the equation:  Other input variables can be recognized in the same way. For output has a Memorization Quality variable with the set: Good, Medium, and Bad can be seen in Figure 3. As for the FIS editor, it can be seen in Figure 4. Fuzzy Inference System Editor Schema with the number of input variables are three variables and one output variable. In the above process, the value limits of each set are entered into the variable so that the graph is obtained as in Figure 2 and 3. The next process is to make the basic rules of FIS. In more detail can be seen in the section below.

Rule-based
This basic rule is a rule made based on experience that has occurred either in the form of research or looking for qualitative data. In this study, it is stated that with three input variables, 27 basic rules are entered into the Matlab software. From this basic rule, each case will get a value of the degree of membership that greatly affects the results of the analysis set out in the output analysis. The basic rules used in this study are set out in Table 1. The numbers listed in table 1 are input in Matlab to produce a Rule-based graph. In figure 4, there appear three input variables and one output variable and their set. From the input and input variable data, each of them can be given a score on each set; then, the final result is as stated in the output graph, which is the rightmost part of the graph. The results of the analysis calculations can be shown in table 3. If seen in Figure 2, 3, it appears that the variable F has a triangle area on each of its rules according to the analysis picture, as shown in Figure 3. Similarly, for the variables W, T, and L.

Results and discussion
The results of the analysis of calculations using Matlab as can be seen in table 2. Table 2 shows the score of the variable F; W and T are entered into Matlab, then Matlab will analyze and produce an output calculation L.   Output values Table 3 shows the different levels of each change in the value of the input variable. Meanwhile, if you use Matlab, then the results are flat in certain positions. Of course, this happens because of the influence of the basic rules applied to the analysis process using IT-1 FIS. The following graphically displayed a comparison between analyses using IT-1 FIS and ordinary calculations. As in figure 5. LG. So the output produced has a flat value. If compared only using ordinary calculations, it will have different results. Then whether the results of the analysis use IT-1-FIS can be used. Of course it can be used by considering the existing rules, the results of the analysis can be used.

Conclusion
From the above explanation, it can be concluded that analyzing the ability to memorize the Qur'an of madrasah ibtidaiyah students by using IT-1 FIS, 3 inputs and one output gets the result that there is a difference between IT-1 FIS analysis with ordinary calculations. This shows that the IT-1 FIS calculation includes elements of the basic rules of graduation. Not only based on values in ordinary mathematical calculations but also consider the experience factor that is inputted by the basic rules of the IT-1 FIS.