Application of an Expert System with the Breadth First Search (BFS) Method in Diagnosing Areca Plant Diseases

Current technological developments are growing very quickly and have produced a lot of software or systems that can make things easier for humans. Continuous scientific progress drives extensive technological development. One form of information technology known is an information system. One popular type of information system is an expert system, which can be used to improve various services. An expert system is a program that combines human knowledge into a computer to help solve problems that are usually solved by experts. This research aims to identify gaps in research that has been conducted, as well as encourage the development of new ideas and increase capabilities in utilizing existing research resources. Areca nut is a high agricultural resource so it has many benefits in the pharmaceutical industry. . The method that will be used in this research is Breadth First Search (BFS). The algorithm carries out the search process on all nodes that are at the same level or hierarchy one by one. An algorithm that performs a wide search that visits nodes in preorder, that is, visits a node first. There are 16 data on areca plant diseases here and have 33 symptoms which will be processed using the Breadth First Search Method. By diagnosing areca plant diseases using an expert system, it is hoped that we can find more in-depth information about diseases in areca palm trees.


Introduction
Areca nut is known as an industrial plant that has many benefits for humans.Because from the roots to the fruit, everything can be used for human needs.Areca nut is a high agricultural resource so it has many benefits in the pharmaceutical industry.Areca nut is widely used as a mixture of traditional medicines and is even processed into natural dyes [1] [2].One factor in the low development and productivity of areca nut plants is the lack of knowledge and information possessed by cultivators and the public regarding pests and diseases that attack areca nut plants and how to deal with them.Limited time and a lack of experts in this matter are obstacles in cultivating areca palm plants [3] [4].The Breadth First Search algorithm is an algorithm that has the simplest flow5 ] [ 6].The algorithm carries out a search process on all nodes that are at the same level or hierarchy one by one, the nodes expand from left to right sequentially based on the level of the node first.before continuing the search process at the node at the next level.If at one level the desired solution has not been found, the search continues to the next level.And so on until a solution is found, then, in this way, the method guarantees that a solution will be found if the solution does exist [7].
Expert systems are a branch of artificial intelligence that is quite old because this system began to be developed in the mid-1960s.This system works to adopt human knowledge to computers that combine basic knowledge to replace an expert in solving a problem [8][9] [10].With an expert system, even lay people can solve quite complex problems that can only be solved with the help of experts.For experts, expert systems will also help their activities as very experienced assistants [11].An expert system is a system that adopts the knowledge of experts or experts in a particular field into a computer, so that the computer is able to solve problems that are usually solved by experts.Expert systems involve knowledge, facts and ways of thinking in solving problems which are usually solved by experts in their field [12] [13].
Breadth first search is an algorithm that performs a broad search that visits nodes in preorder, that is, visiting a node first [14] [15] .Next, nodes that have not been visited are neighboring nodes that have previously been visited, and so on.If the graph is in the form of a rooted tree, then all vertices at level d are visited first before the vertices at level d+1 [16].This algorithm requires a queue q to store the nodes that have been visited.These nodes are needed as a reference for visiting neighboring nodes.Each node that has been visited enters the queue only once.This algorithm also requires a Boolean table to store the nodes that have been visited so that no node is visited more than once [17].
An example of the Breadth First Search algorithm tree can be seen below: This research shows that the DFS algorithm can diagnose diseases in hydroponic mustard greens plants.The DFS algorithm is able to explore all the symptoms shown by the system chosen based on complaints from hydroponic farmers [18].Hanan Hussein et al also conducted research on epth-first-search-tree based D2D power allocation algorithms for V2I/V2V shared 5G network resources, where in this research the DFST algorithm was used to regulate V2I/V2V channel assignment procedures to increase network utilization.Simulation results demonstrate the efficiency of the proposed algorithm.By guaranteeing a lower bound on V2I ergodic capacity, OPT-DFST algorithm shows better network bandwidth with effective runtime than other algorithms.It is also capable of operating even at an increased number of V2V per channel [19].
By diagnosing areca plant diseases using an expert system, it is hoped that we can find more in-depth information about diseases in areca palm trees.With this expert system, it is hoped that it will make it easier for areca nut farmers to identify cashew diseases occurring in areca palm plants

Research methodology
The research framework is the concept or stages that will be carried out in the research.So that the steps taken by the author in this design do not deviate from the main discussion and are easier to understand, the sequence of research steps will be made systematically so that it can be used as a clear and easy guide for solving existing problems.In the DFS algorithm, the search is carried out at one node in each level from the leftmost one.If at the deepest level a solution has not been found, then the search continues at the node on the right.The node on the left can be deleted from memory.If at the deepest level a solution has not been found, then the search continues to the next level previously .And so on until a solution is found.If a solution is found, there is no need for a backtracking process (searching to get the desired path).For example, a problem state space is shown in Figure 2 below: In a search using the Depth First Search (DFS) algorithm, the deepest nodes in the tree will be searched first.For example, Figure 2. The initial search sequence (S) to the goal state (G) is starting from node S, then to node A, then to node B, then to node C, after that it will go to node E, then go to node D , after that it will go to node F after passing node E, and the last one will go to node G.

Pentakit Data
The disease data that has been determined along with the disease code can be seen below.

Symptom Data
The disease data that has been determined along with the disease type can be seen below.

G21
The tips of the leaves turn yellow 22.

G22
The female flowers will fall 23.

G23
The leaves show dark green spots 24.

G24
The underside of the leaf is covered in bacteria 25.

G25
The leaves are irregular and turn grayish white 26.

G26
The leaf stem is tapered 27.

G27
The distance between stem segments shortens 28.

G28
The crown of the tree turns into a rose 29.
G29 Dark red discoloration on the stem 30.

G30
The stem tissue secretes a dark brown fluid 31.

G31
The color of the fruit is yellowish when the fruit is half ripe 32.

G32
The color of the leaves becomes dull 33.

G33
The stem spots ooze fluid

Conclusion
Based on the results of the analysis and design of the expert system, the Breadth First Search method in diagnosing areca nut plant diseases can diagnose disease or predict disease in areca nut plants.The system designed can help the BPP Department and farmers or the public in increasing knowledge to identify areca nut diseases .

Figure 1
Figure 1 Breadth First Search Flow Previous research by Gustina et al on Diagnosing Diseases in Hydroponic Green Mustard Vegetable Plants Using the Depth First Search (DFS) Algorithm.This research shows that the DFS algorithm can diagnose diseases in hydroponic mustard greens plants.The DFS algorithm is able to explore all the symptoms shown by the system chosen based on complaints from hydroponic farmers[18].Hanan Hussein et al also conducted research on epth-first-search-tree based D2D power allocation algorithms for V2I/V2V shared 5G network resources, where in this research the DFST algorithm was used to regulate V2I/V2V channel assignment procedures to increase network utilization.Simulation results demonstrate the efficiency of the proposed algorithm.By guaranteeing a lower bound on V2I ergodic capacity, OPT-DFST algorithm shows better network bandwidth with effective runtime than other algorithms.It is also capable of operating even at an increased number of V2V per channel[19].

1 .
Figure 3 Decision Tree 3.2 System Implementation 1. Admin Login Page Display This page functions as an admin login page, where the admin must log in first so that the admin can add, edit and delete existing data.

Figure 4 page display 2 .
Figure 4 Login page display

Figure 5 page display 3 .
Figure 5 Initial page display3.Disease Data Page DisplayThis page functions to display disease data that has been entered, and also this page functions to edit and delete disease data.

Figure 6 4 .
Figure 6 Display of the Disease Data Page4.Symptom Data Page DisplayThis page functions to display the symptom data that has been entered, and also this page functions to edit and delete symptom data.

Figure 7
Figure 7 Display of the Symptom Data Page5.Consultation Page ViewThis page functions as a way for farmers to consult on diseases of areca nut plants.Consultations are carried out by answering yes or no to the symptom questions that appear on the website.

Figure 8 page display 6 .
Figure 8 Consultation page display 6. Consultation Results Page Display

Figure 9
Figure 9 Display of the Consultation Results Page

Table 2
Symptom Data