Optimation Certainty Factor Method for an Expert System to

Determinination Large Red Chili Diseases

Linda Perdana Wanti

, Nur Okti Fiarni

and Murni Handayani

Department of Informatics, Politeknik Negeri Cilacap, Jln. Dr. Soetomo No.1 Sidakaya Cilacap Selatan Cilacap,

Indonesia

Department Agro-Indrustri Product Development, Politeknik Negeri Cilacap, Jln. Dr. Soetomo No.1 Sidakaya Cilacap

Selatan Cilacap, Indonesia

Keywords: Certainty Factor Method, Expert System, Optimation, Large Chili, Disease.

Abstract: In accordance with the market demand for large red chillies as one of the kitchen ingredients and the rising

number of spicy lovers, chilli farmers have to increase production and maintain the quality of large red chilli

plants therefore the harvest can give satisfactory results. Large red chilli plants cultivation often encounters

obstacles, including pests that attack the plants, farmers’ lack of understanding of how to handle large red

chilli plants that are attacked by pests, a lack of agricultural extension workers specifically for large red chilli

plants and a consultation system that has not been integrated become the reasons underlying this research. An

integrated consultation system with several criteria used to diagnose large red chilli plant diseases can help

solve the problems faced by large red chilli farmers. A certain method is used to process data on disease

symptoms and can be used to diagnose large red chilli plant diseases. The system development method is the

end user development method because it is most suitable for the expert system approach. The output of this

study is a recommendation for diseases that attack large red chilli plants based on the symptoms shown;

therefore, farmers can use these recommendations to increase the yields and quality of large chillies by

minimising the damage.

1 INTRODUCTION

Chili plant (Capsicum annuum L) is a vegetable that

is classified as an annual herbaceous plant, much

needed by humans as a cooking spice, because of its

spicy nature that comes from essential oil (Nimnoi &

Ruanpanun, 2020). Based on data from the Central

Statistics Agency and the Directorate General of

Horticulture, during 2017 and 2018 in Central Java

Province, large chili production tended to decline by

12.16% and cayenne pepper production by 11.29%

(Pertanian & Indonesia, 2018). One of the factors

affecting the decline is the pests and diseases that

attack large chili plants (Fachriyan & Wijaya, 2019).

This can actually be controlled by observing the

symptoms and then taking precautions therefore the

disease does not spread to large, healthy chili plants

(El-Shabasy et al., 2019). One of the red chili

producing areas is Binangun, Cilacap. This area

https://orcid.org/0000-0002-6679-2560

https://orcid.org/0000-0003-0601-0026

cultivates large red chilies as a leading vegetable

commodity that has almost never been absent from

harvesting in the last 3 years based on data from the

Binangun vegetable harvest (Cilacap, 2018). Chili

farmers will experience problems when the rainy

season arrives because it affects their red chili plants

which need special handling and care (Fadhila et al.,

2020). Many plants will rot or flower but not bear any

fruit (Islam et al., 2020). Consultations were carried

out with agricultural extension workers in the sub-

district by observing the symptoms that occurred in

chili plants and the results of the consultation would

lead to a conclusion about the disease. One of the

difficulties that arises when the extension worker is

not available is that consultation will be suspended.

Minimal and out-of-date disease data while there are

many new symptoms that attack large red chili plants

in the field underlies the creation of an expert system

that optimizes two methods, namely certainty factors

Wanti, L., Fiarni, N. and Handayani, M.

Optimation Certainty Factor Method for an Expert System to Determinination Large Red Chili Diseases.

DOI: 10.5220/0011710500003575

In Proceedings of the 5th International Conference on Applied Science and Technology on Engineering Science (iCAST-ES 2022), pages 11-19

ISBN: 978-989-758-619-4; ISSN: 2975-8246

method to produce consultation results with a good

level of accuracy between consultation with experts

and consultation with the developed system.

Several technologies are used to solve various

problems faced by humans, including expert systems

that can accommodate all the information obtained to

solve the problems, namely the symptoms which are

used to identify the diseases that attack large chili

plants and a decision which can be taken to stop the

spread of the diseases (Linda Perdana Wanti &

Romadlon, 2020). Factors that affect chili production

include land area, seeds, fertilizers, pesticides, pests,

diseases, and labor (Islam et al., 2020). the method of

certainty factor works by searching for the measure

of believe to get the most optimum certainty factor

value, which is close to 1 since the closer the CF value

is to 1, the better the conclusions are generated from

calculating the measure of believe of each symptom

shown by the chili plants that lead to a disease (Wang

et al., 2020).

The system development method implemented is

the end user development method because this

method is the most suitable for all the stages that will

be carried out later (Barricelli et al., 2019). The

process of developing an expert system for large red

chilies detection begins with initiating the technology

that will be used for the process of developing the

information system used by farmers to consult on

problems that attack large red chili plants (Johnsson

& Weibull, 2016). The next stage is contagion, which

is the stage where the user begins to be introduced to

the information technology used to reveal diseases

that attack chili plants without considering the

advantages and disadvantages of the process

(Johnsson & Magnusson, 2017). The third stage is

control; at this stage the advantages and

disadvantages of the use of information technology

are taken into account as one of the solutions for the

development of an expert system to diagnose large

red chili plant diseases (Karimi et al., 2015). The last

stage of this system development method is the

mature stage, namely the stage where the

organization / company uses the implemented

information technology. They do not only consider

the benefits but also considers the costs that must be

spent on implementing the technology and makes it a

superior tool in achieving a purpose (Schnall et al.,

2016).

Several studies that have been conducted are by

Khairina et al who use the certainty factor method to

diagnose ENT diseases. The user will input the

symptoms into the developed expert system. The

research conducted has been successfully

implemented to provide a diagnosis of the disease by

using a web-based certainty factor. There are 24

symptoms of ENT disease that the patient can choose,

which then narrowed down to 5 diseases. The results

displayed by the system are then tested by experts to

determine the accuracy level of diagnosis using an

expert system and based on the results of expert

diagnoses, namely ENT specialists.

The second research was conducted by M. Arifin

et al who carried out research on expert systems to

detect pests and diseases that attack tobacco plants by

using the certainty factor method. The problem in this

research is the difficulties faced by tobacco farmers

to distinguish between pests and diseases that attack

their tobacco plants. The certainty factor method is

used to provide certainty values on the diagnosis

results of pests and diseases on tobacco plants. It is

delivered in percentages that represent the level of

accuracy in determining diseases and pests infected

tobacco plants. Disease determination is based on

symptom selection by system users to obtain MB

values from the system and MD values from experts.

The results of the consultation process get the highest

percentage value of 99,985 %. Although it never

reaches 100%, this method is most suitable to be

implemented to diagnose of pests and diseases in

tobacco plants. Further research by Ahmad Yatiman

and Hindayati Mustafida implemented the certainty

factor method to help diagnose eye diseases. Eye

diseases in this study were grouped into 12 sub eye

diseases, each of which had certain symptoms. The

output of this study is the result of diagnostic

recommendations for eye diseases. It is conducted by

using an expert system to determine the MB and MD

values and measure the certainty value of a disease.

The process is done by using the certainty factor

method which can be utilized as a tool for medical

officers to make an early diagnosis of eye disease.

2 RESEARCH METHOD

An expert system is a computer-based information

system that represents an expert's knowledge into a

knowledge base about a problem to be solved

(Castelli et al., 2017). The problem that is resolved in

the discussion this time is to represent the knowledge

of an expert, namely agricultural extension workers

from Cilacap district agriculture agency into a

knowledge base about diseases that attack large red

chilies by observing the symptoms found in large red

chilies.

iCAST-ES 2022 - International Conference on Applied Science and Technology on Engineering Science

Figure 1: Expert System Framework.

Figure 1 shows the expert system framework for

detecting diseases that attack large red chili plants

developed where the expert system consists of several

parts that are centred on the design cycle using the

end user development method (Santra et al., 2020).

System requirements are identified through the

initiation stage to map functional and non-functional

system requirements (Liu et al., 2020). Then the base

of expert system knowledge and expert system design

lie in the knowledge cycle section by optimizing the

certainty method and the design cycle through the

flowchart of the two optimized methods and the

expert system tracing flow carried out at the

contagion stage (Oluwole et al., 2016). The

evaluation process is in the control stage after the

expert system is implemented to find out the results

of the search using the certainty factor method to

determine the results in the form of the confidence

value of a disease that attacks large red chili plants

(Linda Perdana Wanti et al., 2020). For the last stage,

namely the mature stage, is used to compare the

suitability of the search results between the

consultation processes carried out by an expert

(agricultural extension agent) with the search results

using an expert system based on occurred cases (Ooi

& Tan, 2016). There is a method that are optimized

for identifying and diagnosing diseases based on the

symptoms that attack large red chilies, namely the

certainty factor method. The method have roles in the

tracing process which begins with the symptoms of

the disease and ends at the conclusion in the form of

a disease. The certainty factor method is used to find

the measure of believe of the disease infecting large

red chili plants based on the symptoms selected by the

user during the consultation process (Azareh et al.,

2019). The role of the method that is optimized in the

developed expert system is discussed further below.

2.1 Expert System

The implementation of two methods in developing

expert systems for early detection of large red chilies

diseases requires several variables involved,

including data on disease symptoms, disease data,

rules of symptoms that refer to a disease, and weight

values given by experts (an agricultural extension

worker) with a value range between 0 and 1 (Mathew

et al., 2020). The parameters in Figure 1 below are a

series of things that must be considered by developers

in order to promote user satisfaction in using the

system (L P Wanti et al., 2020), (Karimi et al., 2015).

Figure 2: End User Satisfaction Parameters.

The measure of end user satisfaction (expert

system users) for early detection of diseases that

attack large red chilies is shown in Figure 2 where the

user observes from all sides such as the content of the

expert system, namely the information conveyed by

the expert system, the accuracy level of problem

solving decisions, the format of the expert system

design that is user friendly, and whether the relevance

of expert knowledge with the developed expert

system is appropriate and easy to use or not (Brown

et al., 2018). These five things become a measure of

end user satisfaction in using the system (Aggelidis &

Chatzoglou, 2012). While the process of developing

an expert system in accordance with the end user

development method framework is shown in Figure 2

below:

Figure 3: End User Development Framework.

Optimation Certainty Factor Method for an Expert System to Determinination Large Red Chili Diseases

The framework for developing the end user

satisfaction method consists of several interconnected

components, including the end user of the expert

system, the staff who is the administrator whose job

is to update the information base for disease symptom

data and disease data that attacks large red chili plants

and the work station database used to process all

expert system knowledge bases and current

supporting data. The work station database consists

of hardware and software containing tools (Coronado

et al., 2020), namely:

a. The query language that functions in the

database programming language.

b. Graphic language that functions on the display

processing of the developed user interface of the

expert system.

c. Report generation used to manage reports that

will be displayed on the expert system and

linked to the system database.

d. Application development that functions for the

construction and development of expert systems

to detect diseases.

2.2 Certainty Factor Method

The certainty factor method is a method for tracing a

conclusion that starts with observing the symptoms

(Li & Zhang, 2017). Tracing a conclusion is used to

measure the certainty of a set of facts or rules (Arifin

et al., 2017). In this case, the set of facts referred to is

the symptoms collected by observing the state of the

large red chili plants that grow but die before harvest

time (Azareh et al., 2019). The value of certainty

factor (CF) is calculated to show confidence in the

facts of an event (Nugraha et al., 2018). One of the

reasons for choosing a certainty factor method to

diagnose diseases in large red chilies is that this

method can measure certainty and uncertainty in

making a decision on an expert system that is being

developed.

The measure of the certainty of a fact is denoted

by MB (Measure of increased Belief) while the

measure of uncertainty is denoted by MD (Measure

of increase Disbelief) (Wang et al., 2020). The stages

of the search for CF value are as follows:

a. Determine the CF value



[

, 

]

=

[

, 

]

−[,] (1)

With:

CF [H,E] : a measure of the certainty of the

hypothesis H which is influenced by E symptoms

MB [H,E] : a measure of MB's confidence in H

which is influenced by E

MD [H,E] : a measure of MD's distrust of H-

influenced E

b. Determines the value of the CF combination that

is determined by one premise



[

, 

]

=

[



]

∗

[



]

=

[



]

∗[]

(2)

c. Determines the value of a CF combination that is

determined by more than one premise



[

∧

]

=

(



[



]

,

[



])

∗[}

(3)



[

∨

]

=

(



[



]

,

[



])

∗[}

(4)

d. Determines the CF value for the same conclusion

 

[

1, 2

]

= 1 + 2 ∗ (1 − 1)

(5)

The end result of the certainty factor method is to

provide a certainty value for a decision, namely the

name of the disease that attacks large red chili plants.

The accuracy of the calculation results of this method

is maintained because it can only process two data for

one calculation.

3 RESULT AND DISCUSSION

3.1 Initiation

The initial stage in the end user development system

method is the initiation where the organization starts

to get to know information technology for the first

time. At this stage, an expert system that will be

developed to detect early disease in large red chilies

begins by collecting all observed symptom data

through the field observation process, namely in the

Binangun sub-district agricultural area. The data used

to build this expert system are symptom data, disease

data, MB and MD values which are both formulated

by experts and developers to build a knowledge base

of expert systems. Determination of the classification

class to raise the chances of the disease attacking is

also formulated at this stage. The organization begins

to collect data and starts to analyze all the resources

needed for the information technology development

process including user requirements, both system

functional requirements and system non-functional

requirements. Symptom data obtained through the

observation process is shown in table 1 and disease

data that attacks large red chilies is shown in table 2

after a consultation process with agricultural

extension workers in Binangun sub-district.

iCAST-ES 2022 - International Conference on Applied Science and Technology on Engineering Science

Table 1: Symptoms of Big Red Chili Plant Disease.

Symptom

Codes

Name of Big Red Chili Plant Disease

Symptoms

1 S01 Wet rotten fruit

2 S02

Leaves, twigs, and branches dry, rot

and turn blackish brown

3 S03

Black spots appears and the fruit turn

soft

4 S04

Leaves grow old (turn yellow)

prematurely

5 S05

The leaves have round spots, gray and

brown on the edges

6 S06 Stems rot

7 S07

Plants wilt starting from the shoots

and then spread to the bottom

8 S08

There are small dark green wet spots

on the fruit and stems of chilies

9 S09 The fruit becomes dry and wrinkles

10 S10 Warts develop on the roots

11 S11 Plants keep withering

12 S12 Stunt plant

13 S13

The shoot leaves change color from

light green to rotten brown, and black

14 S14 Stems rot

15 S15 Stems peel off easily

16 S16 Growing leaves accumulate

17 S17 Stunt plant

18 S18

Leaves curving downward with

wrinkles

19 S19

Glossy green leaves and uneven

surface

20 S20

Plants wilt start from the shoots and

the leaves remain green

21 S21

The rootstock and roots become

brownish

22 S22 The leaves turn yellow

23 S23 Leaves curl upward

24 S24 Fallen shoots and flowers

25 S25

The leaves become stiff and curl

downward

26 S26 The underside of the leaves is coppery

27 S27 Leaves are abnormally shaped

28 S28

The leaves are coppery brown and

curly

29 S29

Leaves appear wrinkled, curl, and curl

upward

30 S30

Stunted plant growth and plant shoots

die

31 S31 Irregular holes appears on the fruit

32 S32 Bare plants

33 S33 Loss of fruit

34 S34

The base of the chili fruit has a black

dot

35 S35 Wet rotten fruit

36 S36 Stunt plant

37 S37

The leaves become wrinkled and

yellowish

Table 2: Table of Large Red Chili Plant Diseases.

Disease Code Disease Data

D01 Antraknosa

D02 Serkospora leaf spots

D03 Fusarium wilt

D04 Phytophora Fruit Rot

D05 Swollen Roots

D06 Leaf rot Choanepora

D07 Leaf Curl Virus

D08 Bacterial wilt

D09 Gemini Virus

D10 Mite Pests

D11 Thrips pests

D12 Armyworm

D13 Fruit Fly Pests

D14 Aphids Pests

3.2 Contagion

The second stage in the end user development method

is the organization starts to implement the developed

information technology without taking into account

its advantages and disadvantages .At this stage an

expert system also begins to be built by making

designs such as flow chart, user interface designs, use

cases, sequence diagrams, activity diagrams and

building a database to accommodate a knowledge

base in the form of rules for the disease tracking

process.

Figure 4: Flowchart of the Certainty Factor Method.

Figure 4 shows a flow chart for the disease

tracking process using the certainty factor method

based on the MB (Measure of Believe) and MD

(Measure of Disbelieve) values, a symptom that leads

Optimation Certainty Factor Method for an Expert System to Determinination Large Red Chili Diseases

to a certain disease by calculating the CF value, and

the CF value that is closest to 1 represents a disease

that attacks large red chili plants. The level of expert

confidence in a statement / recommendation is stated

using certainty factors, such as the level of expert

confidence in a recommendation for a disease based

on the symptoms observed / researched (Azareh et al.,

2019). Certainty factor expresses belief in the

occurrence of attack of large red chili plants in the

form of the field facts such as the symptoms studied

or hypotheses based on the incident or from an

expert's assessment (Santra et al., 2020).

The assessment of the certainty factor ranges from

-1 (certain negative) to 1 (certain positive) in giving

the value for the division of the confidence level

according to table 3 after the CF framework image,

(Wang et al., 2020). In the figure below, there is a

combination CF equation, if a value for the certainty

level has been given by an expert in the formation of

a knowledge base each diagnostic rule, and the expert

indicated a level of confidence on every symptom that

attacks large red chili plants, then the level of

certainty of the system is determining the results

diagnosis of diseases that infect large red chili plants.

Table 3: CF Certainty Level.

No Uncertainty Term CF

1 Definetely Not 0.2

2 Almost Certainty Not 0.3

3 Probably Not 0.4

4 Maybe Not 0.5

5 Unknown 0.6

6 Maybe 0.7

7 Probably 0.8

8 Almost Certain 0.9

In Figure 6, it is shown that each disease indicated

by notation D1 to D14 has specific symptoms, each

of which is indicated by notation S01 to S37. For

example D01 disease has specific symptoms, namely

S01, S02 and S03, as well as D02 disease. Specific

symptoms are S04 and S05 and so on. A list of disease

names and symptoms is shown in table 1 and table 2.

The following is the process of calculating the CF

value/ confidence percentage according to the

formula in equation 1 to equation 5.

Leaves, twigs, and branches dry, rot and turn blackish

brown

CF1 = 0.20*0.80 = 0.16

Black spots appears and the fruit turn soft

CF2 = 0.40*0.80 = 0.32

CF Combine1 = 0.16 + 0.32 *(1-0.16) = 0.4288

Figure 5: Expert System Tracking Flow.

Plants wilt starting from the shoots and then spread to

the bottom

CF3 = 0.40 * 0.80 = 0.32

CF Combine2 = 0.4288 + 0.32 * (1 - 0.4288) =

0.611584

The shoot leaves change color from light green to

rotten brown, and black

CF4 = 0.40 * 0.60 = 0.24

CF Combine3 = 0.611584 + 0.24 * (1 - 0.611584) =

0.704804

Stems peel off easily

CF5 = 0.40 * 0.60 = 0.24

CF Combine4 = 0.704804 + 0.24 * (1 - 0.704804) =

0.775651

CF Combine [R001] = 0.775651 * 100% = 77.565 %

So, the percentage confidence value for the disease

Leaf rot Choanepora is 77.57%.

3.3 Control

At this stage, the organization/company starts to be

effective in the use of information technology both in

terms of hardware and software (Schnall et al., 2016).

The use of information technology is observed and

several things are taken into consideration, such as the

cost that must be incurred by the

organization/company and the benefits that the

iCAST-ES 2022 - International Conference on Applied Science and Technology on Engineering Science

organization/company will get as a result of the use

of information technology. For example, the

organization/company (Cilacap Agriculture Office)

which oversees the Binangun District Agricultural

Extension Center, must evaluate the costs incurred by

the use of information technology while

implementing an expert system to support

agricultural extension activities in maximizing

agricultural yields, especially large chilies.

Evaluation is also to find out the possible benefits that

will be obtained as a positive impact on the

implementation of information technology, namely

an expert system for early detection of diseases that

attack large red chili plants so that farmers can take

preventive action hence the disease does not spread to

productive agricultural land. Decision making on the

use of information technology by

organizations/companies is categorized under this

control stage because not only they need to take into

account the costs and benefits of utilizing information

technology, the company also need reduce the costs

incurred to get maximum benefits.

At this stage the company/organization evaluates

the use of information technology by evaluating the

results of the expert system to detect diseases, starting

with calculations using the certainty value of a

disease that attacks large red chili plants using the

certainty factor method which begins by determining

the CF value using equations 1 to 5 and ends by

determining the CF Combine value by using equation

(8). The CF Combine value is obtained according to

table 4 below:

Table 4: Result of MB and MD of Large Chili Disease.

No MB and MD Disease CF (X) CF (Y)

Combine

1 MB Primary Disease 0.248852 0.038852 0.287704

MB Secondary

Disease

0.244269 0.034269 0.278538

3 MD Primary Disease 0.063852 0.053852 0.117704

MD Secondary

Disease

0.059269 0.049269 0.108538

3.4 Contagion

The last stage in the end user development model is

the mature stage. At this stage,

companies/organizations do not only consider the

benefits or costs that the company/organization has to

spend as a result of the use of information technology

but also how the use of information technology can

be utilized as a tool to produce superior products as a

means of competing with other

organizations/companies as a competitive advantage

(Coronado et al., 2020). The implementation of the

end user development/end user computing method is

said to be successful when the organization/company

can implement each stage well (Schnall et al., 2016).

Organizations/companies can use several strategies

so that end user development can be maximally

implemented, namely by creating an information

system centre that acts as a supervisor for the progress

of end user development at each stage. The

information system centre also plays a role in

controlling the quality, data integrity and security

standards as well as other predetermined standards. In

addition, the information centre also functions as a

system training unit for end users, looking for and

evaluating system development tools that can help

system users. These tools include DBMS (Database

Management System), visual language and CASE

(Computer Aided Software Engineering) (Johnsson

& Weibull, 2016).

The process of tracing diseases that attack large

red chili plants by optimizing the naïve Bayes method

begins by identifying the symptoms of the disease to

find the prior value, looking for the likelihood value

and looking for the posterior value for each class. The

calculation results by using the certainty factor

method begins by looking for the CF Expert value

multiplied by CF User, then calculating the CF

Combine value according to the CF Confidence level

table shown in table 4 and the flow chart of the

certainty factor method calculation. The results are as

in figure 6 below:

Figure 6: Calculation Results Using the Certainty Factor

Method.

In addition to the above tasks, the

organization/company information system centre can

also analize how well information technology can be

absorbed for production activities in each

company/organization. The stages of information

technology analysis can be done through validation

0,05

0,1

0,15

0,2

0,25

0,3

0,35

Primary

Disease

Secondary

Disease

Primary

Disease

Secondary

Disease

CF Expert CF User CF Combine

Optimation Certainty Factor Method for an Expert System to Determinination Large Red Chili Diseases

testing of expert systems to detect diseases (Santra et

al., 2020). The testing procedure is carried out to

compare the level of accuracy of the tracing that has

been carried out by experts and based on the

expert/information technology system developed by

the company/organization. Of the 117 cases during

the period of January 2020 to December 2020, 105

cases of tracing results between experts, namely

agricultural extension workers were the same as the

results of expert system searches, while 12 cases had

different results between consultations with experts

and tracing using an expert system, so the level of

accuracy could be compared and the result is as

follows:

 =







∗ 100% (6)

With: NA = Accuracy Value

DA = Accuracy Data

JD = Total Data

 = 

105

117

∗ 100% = 89,7%

4 CONCLUSIONS

After testing data on 117 cases of large red chili plant

diseases during the period of January 2020 to

December 2020, it can be concluded that the use of

expert systems to diagnose large red chili plant

diseases by processing symptom data and disease data

resulted in an 89.7% rate. The accuracy of the

diagnostic results using the certainty factor method is

compared with the results of the diagnosis with an

expert, namely the agricultural extension worker in

Binangun, Cilacap. The optimization of the certainty

factor method has a significant effect on the results of

expert system diagnostics (L P Wanti et al., 2020).

The search was using the certainty factor method to

obtain the highest CF value where anthracnose

disease was obtained with a CF value of 0.76, while

fusarium wilt disease was obtained with 0.73. The

system development method implemented in the

entire expert system development process, namely

end user development which is done through four

stages; initiation, contagion, control and mature, can

maximize the development of expert systems and the

involvement of organizations/companies during the

expert system development process.

Organizations/companies have a big role in

implementing the expert system by paying attention

to the costs that must be incurred and the benefits

obtained after implementing the expert system to

detect diseases that attack large red chili plants.

REFERENCES

Aggelidis, V. P., & Chatzoglou, P. D. (2012). Hospital

information systems: Measuring end user computing

satisfaction (EUCS). Journal of Biomedical

Informatics, 45(3), 566–579. https://doi.org/10.1016/

j.jbi.2012.02.009

Arifin, M., Slamin, S., & Retnani, W. E. Y. (2017).

Penerapan Metode Certainty Factor Untuk Sistem

Pakar Diagnosis Hama Dan Penyakit Pada Tanaman

Tembakau. Berkala Sainstek, 5(1), 21. https://doi.org/

10.19184/bst.v5i1.5370

Azareh, A., Rahmati, O., Rafiei-Sardooi, E., Sankey, J. B.,

Lee, S., Shahabi, H., & Ahmad, B. Bin. (2019).

Modelling gully-erosion susceptibility in a semi-arid

region, Iran: Investigation of applicability of certainty

factor and maximum entropy models. Science of the

Total Environment, 655, 684–696. https://doi.org/10.10

16/j.scitotenv.2018.11.235

Barricelli, B. R., Cassano, F., Fogli, D., & Piccinno, A.

(2019). End-user development, end-user programming

and end-user software engineering: A systematic

mapping study. Journal of Systems and Software, 149,

101–137. https://doi.org/10.1016/j.jss.2018.11.041

Brown, B., Balatsoukas, P., Williams, R., Sperrin, M., &

Buchan, I. (2018). Multi-method laboratory user

evaluation of an actionable clinical performance

information system: Implications for usability and

patient safety. Journal of Biomedical Informatics,

77(November 2017), 62–80. https://doi.org/10.1016/

j.jbi.2017.11.008

Castelli, M., Manzoni, L., Vanneschi, L., & Popovič, A.

(2017). An expert system for extracting knowledge

from customers’ reviews: The case of Amazon.com,

Inc. Expert Systems with Applications, 84, 117–126.

https://doi.org/10.1016/j.eswa.2017.05.008

Cilacap, K. (2018). LKjIP Kabupaten Cilacap 2018.

Coronado, E., Mastrogiovanni, F., Indurkhya, B., &

Venture, G. (2020). Visual Programming Environments

for End-User Development of intelligent and social

robots, a systematic review. Journal of Computer

Languages, 58, 100970. https://doi.org/10.1016/j.cola.

2020.100970

El-Shabasy, R., Yosri, N., El-Seedi, H., Shoueir, K., & El-

Kemary, M. (2019). A green synthetic approach using

chili plant supported Ag/Ag2O@P25 heterostructure

with enhanced photocatalytic properties under solar

irradiation. Optik, 192(June), 162943. https://doi.org/

10.1016/j.ijleo.2019.162943

Fachriyan, H. A., & Wijaya, I. P. E. (2019). Aplikasi Model

E-Marketplace Dalam E-Agribusiness. Mediagro,

14(01), 12–24. https://doi.org/10.31942/md.v14i01.2614

Fadhila, C., Lal, A., Vo, T. T. B., Ho, P. T., Hidayat, S. H.,

Lee, J., Kil, E. J., & Lee, S. (2020). The threat of seed-

transmissible pepper yellow leaf curl Indonesia virus in

chili pepper. Microbial Pathogenesis, 143(December

2019), 104132. https://doi.org/10.1016/j.micpath.20

20.104132

Islam, A. H. M. S., Schreinemachers, P., & Kumar, S.

(2020). Farmers’ knowledge, perceptions and

iCAST-ES 2022 - International Conference on Applied Science and Technology on Engineering Science

management of chili pepper anthracnose disease in

Bangladesh. Crop Protection, 133(March), 105139.

https://doi.org/10.1016/j.cropro.2020.105139

Johnsson, B. A., & Magnusson, B. (2017). Towards end-

user development of graphical user interfaces for

internet of things. Future Generation Computer

Systems. https://doi.org/10.1016/j.future.2017.09.068

Johnsson, B. A., & Weibull, G. (2016). End-User

Composition of Graphical User Interfaces for PalCom

Systems. Procedia Computer Science, 94, 224–231.

https://doi.org/10.1016/j.procs.2016.08.035

Karimi, F., Poo, D. C. C., & Tan, Y. M. (2015). Clinical

information systems end user satisfaction: The

expectations and needs congruencies effects. Journal of

Biomedical Informatics, 53, 342–354. https://doi.org/

10.1016/j.jbi.2014.12.008

Li, J., & Zhang, Y. (2017). GIS-supported certainty factor

(CF) models for assessment of geothermal potential: A

case study of Tengchong County, southwest China.

Energy, 140, 552–565. https://doi.org/10.1016/

j.energy.2017.09.012

Liu, Y., Eckert, C. M., & Earl, C. (2020). A review of fuzzy

AHP methods for decision-making with subjective

judgements. In Expert Systems with Applications (Vol.

161). Elsevier Ltd. https://doi.org/10.1016/j.eswa.20

20.113738

Mathew, M., Chakrabortty, R. K., & Ryan, M. J. (2020). A

novel approach integrating AHP and TOPSIS under

spherical fuzzy sets for advanced manufacturing system

selection. Engineering Applications of Artificial

Intelligence, 96(October), 103988. https://doi.org/

10.1016/j.engappai.2020.103988

Nimnoi, P., & Ruanpanun, P. (2020). Suppression of root-

knot nematode and plant growth promotion of chili

(Capsicum flutescens L.) using co-inoculation of

Streptomyces spp. Biological Control, 145(February),

104244. https://doi.org/10.1016/j.biocontrol.2020.10

4244

Nugraha, A. A. S., Hidayat, N., & Fanani, L. (2018). Sistem

Pakar Diagnosis Penyakit Kucing Menggunakan

Metode Naive Bayes – Certainty Factor Berbasis

Android. Jurnal Pengembangan Teknologi Informasi

Dan Ilmu Komputer (J-PTIIK) Universitas Brawijaya,

2(2), 650–658.

Oluwole, A. H., Adekunle, A. A., Olasunkanmi, A. O., &

Adeodu, A. O. (2016). A shoveling-related pain

intensity prediction expert system for workers’ manual

movement of material. International Journal of

Technology, 7(4), 603–615. https://doi.org/10.14716/

ijtech.v7i4.2208

Ooi, K. B., & Tan, G. W. H. (2016). Mobile technology

acceptance model: An investigation using mobile users

to explore smartphone credit card. Expert Systems with

Applications, 59, 33–46. https://doi.org/10.1016/j.es

wa.2016.04.015

Pertanian, K., & Indonesia, R. (2018). Statistik Pertanian

2018.

Santra, D., Basu, S. K., Mandal, J. K., & Goswami, S.

(2020). Rough set based lattice structure for knowledge

representation in medical expert systems: Low back

pain management case study. Expert Systems with

Applications, 145, 113084. https://doi.org/10.1016/j.es

wa.2019.113084

Schnall, R., Rojas, M., Bakken, S., Brown, W., Carballo-

Dieguez, A., Carry, M., Gelaude, D., Mosley, J. P., &

Travers, J. (2016). A user-centered model for designing

consumer mobile health (mHealth) applications (apps).

Journal of Biomedical Informatics, 60, 243–251.

https://doi.org/10.1016/j.jbi.2016.02.002

Wang, J., Zhu, S., Luo, X., Chen, G., Xu, Z., Liu, X., & Li,

Y. (2020). Refined micro-scale geological disaster

susceptibility evaluation based on UAV tilt

photography data and weighted certainty factor method

in Qingchuan County. Ecotoxicology and

Environmental Safety, 189(November), 110005.

https://doi.org/10.1016/j.ecoenv.2019.110005

Wanti, L P, Somantri, O., Abda’U, P. D., Faiz, M. N.,

Maharrani, R. H., Prasetya, N. W. A., Susanto, A.,

Purwaningrum, S., & Romadoni, A. (2020). A support

system for accepting student assistance using analytical

hierarchy process and simple additive weighting.

Journal of Physics: Conference Series.

https://doi.org/10.1088/1742-6596/1430/1/012034

Wanti, Linda Perdana, Maharrani, R. H., Wachid, N., &

Prasetya, A. (2020). Optimation economic order

quantity method for a support system reorder point

stock. International Journal of Electrical and

Computer Engineering, 10(5), 4992–5000.

https://doi.org/10.11591/ijece.v10i5.pp4992-5000

Wanti, Linda Perdana, & Romadlon, S. (2020).

Implementasi Forward Chaining Method Pada Sistem

Pakar Untuk Deteksi Dini Penyakit Ikan. Infotekmesin,

11(02), 74–79. https://doi.org/10.35970/infotekmesin.

v11i2.248

Optimation Certainty Factor Method for an Expert System to Determinination Large Red Chili Diseases