Analysis and Application of the Certainty Factor Method in the Diagnostic Expert System for Broiler Chicken Diseases

An expert system is a system that uses human knowledge recorded in a computer to solve problems that normally require human expertise. Certainty Factor is a clinical parameter value given by MYCIN to indicate the level of trust. The certainty factor is also a way of combining belief and disbelief in a single number. Certainty factor introduces the concepts of belief/belief and disbelief/unbelief. In the system analysis stage, the author analyzes to find weaknesses in the system that is currently running in an organization or company with the aim that the system can be proposed for improvement. Implementing the program that has been designed requires a tool in the form of a computer or laptop, which requires three supporting components to operate the computer or laptop itself, such as hardware, software, and brainware. The expert system application has been running with the Certainty Factor method and to make a diagnosis on chickens the user can choose a value according to the Certainty Factor Interpretation that has been given and processed with the CF expert. Based on the tests carried out, the value of system accuracy with experts is almost the same . And the Inference engine works well, according to the pre-programmed rules. After diagnosing a chicken disease, the system will display how to treat and handle sick broiler chickens


Introduction
Technology is currently experiencing rapid development to assist human activities in everyday life. As this technology develops, humans with their knowledge and abilities develop a science called artificial intelligence. One part of artificial intelligence is an expert system or expert system. Expert systems are computer-based applications that are used to solve problems as experts think. .Although the Expert System was created by storing the expertise of an expert into a computer system, it does not mean to replace the role of the expert but to promote expert knowledge and assist the general public in finding solutions to the problems they face [1].
An expert system is a computer program that mimics thought processes and knowledge to solve specific problems. One implementation that is applied is in the field of medicine [ 2]. This expert system is used to diagnose a disease. Symptoms and test results are fed to the expert system which then tracks its knowledge base to match specific disease conditions. Expert systems can also provide pictures, descriptions, arguments and diagnoses and work or run like the reasoning done by an expert [ 3].
So far, diagnosing diseases in broiler chickens in particular is still being done by checking symptoms and carrying out direct tests, so that to determine and analyze what types and diseases exist in broiler chickens requires quite a long time and process.
This problem needs a solution by creating an expert system for diagnosing diseases in broiler chickens. The purpose of this system is to add knowledge to broiler business owners to determine the diseases suffered by chickens and their solutions so that they can be handled more quickly. Whereas for the general public it is used as a guide to take action or prevention that must be done on chickens and to find out the possibility of diseases that are being suffered by chickens.
This expert system for diagnosing broiler diseases uses the Certainty Factor method with the concept of identifying broiler diseases based on the likelihood and symptoms experienced by these chickens. This expert system seeks to help overcome the problems that occur above and this system is to provide support and assist broiler business owners in analyzing chicken diseases so that it can make it easier for employees who take care of chickens to carry out proper handling of chicken diseases.
The Certainty Factor (CF) method is a method for proving whether a fact is certain or uncertain in the form of metrics that are usually used in Expert Systems. This method is very suitable for expert systems that identify something that is uncertain. In expressing the degree of confidence, a value called (CF) is used to assume the degree of confidence of an expert in a data [4]. Calculation of the Certainty Factor method is carried out by calculating the multiplication value between the user's CF value and the expert's CF value and producing a combined CF value. The highest combined Certainty Factor value is the final result of the calculation process of the Certainty Factor method [5].
CF is one of the many methods that can be used to assist the process of solving a problem by working in the form of measuring certainty in facts and rules [6]. CF can prove whether a fact is certain or unsure in metric form. This method is very easy to use because it depends on determining the weight given and calculated based on facts that appear as symptoms [7]. CF has been used in the early diagnosis process for the corona virus which helps medical staff for the first stage in administration actions properly before the examination process is carried out thoroughly in the laboratory to ascertain whether the patient is positive or negative [8]. Another research is in the form of a CF combination to diagnose Rubella disease . The results are in the form of information about the symptoms of rubella disease based on what is felt [9]. Certainty Factor is also used to identify student personality and is able to identify the type of student personality according to the level of confidence [10].
Utilization of this expert system is expected to minimize costs that must be incurred by users and with this expert system users can obtain information about diseases and how to treat diseases suffered by broiler chickens. The process used by this expert system to diagnose broiler chicken diseases is by looking at the symptoms that exist in chickens and the resulting data is in the form of a report about the name and type of chicken disease and how to treat the chicken disease.

Research methodology
The research framework is a concept or stages that will be carried out in research. So that the steps taken by the author in this design do not deviate from the subject of discussion and are easier to understand, the sequence of research steps will be made systematically so that they can be used as clear and easy guidelines for solving existing problems. The research framework that the authors conducted in the study can be described in Figure 1. The research stage is a sequence of processes or steps that will be carried out in completing this research. The stages of this research are as follows:

Preliminary Research
From a research, first is to analyze the object to be processed. With preliminary research, it can provide initial evidence that the problems we will examine in the field really exist. Therefore, time is needed for data collection, research time, research locations, research methods, field research, library research, and laboratory research.

Data collection
In collecting data, the authors obtained data from various sources, such as this research, obtained from articles, obtained from other references, and the authors conducted interviews directly with the owner of the Maninjau Broiler Chicken Business. The author records some important information related to the research being carried out.

Analysis
The analysis contains the problems faced and system requirements. The results of the analysis are then written in system requirements analysis, requirements analysis, functional requirements analysis, and nonfunctional requirements analysis.

Design
In this design stage, researchers used the Unified Modeling Language (UML) as a tool in explaining the flow of program analysis, where UML was used, namely: use case diagrams, class diagrams, sequence diagrams, activity diagrams, deployment diagrams.

Implementation
Implementation is a stage that is carried out when the designed application is ready to operate. Implementation is carried out aiming to confirm the results of application design, so that users can provide input to application developers. Implementation is done using PHP and MYSQL programming languages.

Testing
System testing is the stage that will be carried out on the resulting system to find out whether the expert system that has been designed can run correctly and in accordance with the design carried out in diagnosing broiler chicken diseases.

Certainty Factor (CF) Method
The success of an expert system lies in knowledge and how to process this knowledge so that a conclusion can be drawn. Knowledge obtained from interviews and analysis through books is converted into a table of diseases and symptoms to facilitate the process of finding solutions. This table of types of disease and symptoms is used as a pattern for matching the information entered by the user (user) and the knowledge base. In Table 1 there are 13 diseases that are given codes P01 to P13. Next, the data on the symptoms of broiler chicken diseases will be described in Table 2 below: In the table above it can be seen that there are 43 symptoms of disease in broiler chickens where each symptom is coded G01 to G43. The knowledge gained will be presented in the form of a rule that is useful for finding conclusions about the types of diseases of broiler chickens . The way to get the confidence level (CF) of a rule that researchers use is by interviewing an expert. The CF (Rule) value is obtained from the "term" interpretation of the expert, which is converted into a certain CF value according to Table 3 below: Based on the results of data processing of symptoms and data on the type of disease, 13 rules were obtained for diagnosing disease in broiler chickens which can be seen in Table 4.

Certainty Factor Calculation Process
The process of calculating the percentage of confidence begins with solving a rule (rule) which has multiple symptoms, into rules (rules) which have a single symptom. Then each new rule calculates its CF using the equation: Among the conditions that occur are that there are several antecedents (in different rules) with the same consequence . In this case, we have to aggregate the overall CF value for each condition. The following formula is used: If both CF > 0 , then the formula is: If both CF < 0 , then the formula is: If both CF < 0 , then the formula is:

System Testing
In the testing section of this program, we will explain the use of the application that was created. An explanation of the application made includes the appearance of the application, the control functions in the application, and how to use it. The sub-chapters will explain the use of applications per menu system, starting from the appearance of the main menu, its functions and how to use it until it's finished.

User Home Page
The user's home page is the page that is visible when the Expert System for Diagnosing Diseases in Chickens website is activated by typing localhost/spkayam, so it appears as shown in Figure 2.

Diagnostics Page Display
The diagnosis page is a diagnosis selection where there is a choice of symptoms and the user must select the symptoms found in the field, the condition has 6 (six) choices, namely: very sure, sure, quite sure, a little sure, don't know and don't, so it looks like Figure 4 . The diagnosis results page is a continuation of the diagnosis page where from the results of the selected symptoms a disease that attacks chickens will be displayed in the form of CF and % (percent) values, then the user presses the process button so that it appears as shown in Figure 5. This diagnostic results print page is useful for printing diagnostic results performed by visitors, then the user wants to display the diagnostic results, so click the print action button and it will automatically display the results, so that they appear as Figure 6.

Conclusion
Based on the results of the discussion of the design of the chicken expert system application with the application of the Certainty Factor method, it has been running by analyzing the symptoms and being able to determine what types and diseases exist in broiler chickens. And already able to provide disease information and solutions do not require a long time.