Jurnal Sistem Informasi dan Ilmu Komputer Prima(JUSIKOM PRIMA)

REDESIGN THE UI/UX OF THE PT MNO COMPANY PROFILE WEBSITE USING THE THINKING DESIGN METHOD

Ihsan Putera — 2024-02-20

In the current era of globalization, large and small companies must develop strategies for using websites to improve business branding to the general public. Based on the results of problem identification, there are several UI/UX problems on the PT MNO website, including an unattractive appearance, messy and overlapping fonts, and a messy layout. This research aims to redesign the PT MNO website to improve its UI/UX to make it more informative, clear, and easy to use. The solution can be implemented by redesigning the website design for PT MNO utilizing the design thinking methodology. This method has five phases: Empathize, define, imagine, prototype, and test. Based on observations and interviews, three categories of problems in the current website category were found: content, navigation, and features. Then, five pages were created for the design results or mockup solutions, namely the home page, services, portfolio, programs, and about us. Testing used a usability metric, SEQ (Single Ease Question). Based on SEQ theory, if the results given by respondents are more than 5.5, then the task or scenario is considered successful or easy to do. So, the five functions in terms of convenience were easy for the five respondents to complete.

Keywords: Design Thinking, Redesign, UI/UX, Website.

APPLICATION OF THE ARIMA MODEL FOR PREDICTION OF MONTHLY DIVORCE RATE IN THE RELIGIOUS COURTS IN SOUTH SUMATRA

Sri Fitriati — 2024-02-19

This research discusses predictions of divorce rates in Religious Courts in South Sumatra. This is important to do because the divorce rate has a changing trend. Sometimes high and sometimes low but always at a high trend number, so soCourt officials or social scientists in developing effective strategies for overcoming marriage problems, allocating resources, or supporting families who need counseling can be prepared in advance, especially at the Religious Courts in South Sumatra to reduce the divorce rate because the purpose of marriage is not to divorce. This research discusses the divorce rate in terms of predicting/forecasting because much research has been done on the divorce rate by examining the causes of divorce. This research uses the ARIMA (Autoregressive Integrated Moving Average) model to predict. The ARIMA model is a method that has been widely used in forecasting research to get good results. The research results are that the ARIMA model used is (1,0,2) and (2,0,2), with an error rate of only 0.48% using the MAPE method.

Keywords: predictions, numbers, divorce, arima, mape.

IMPLEMENTATION OF THE AHP METHOD ON DECISION SUPPORT SYSTEM FOR SELECTING THE BEST RICE SEEDLINGS IN MADANG SUKU 1 SUB-DISTRICT

Putri Ela Citra Utami — 2024-03-04

Rice is one of the most widely grown staples in most rural areas in Indonesia. East OKU Regency is the Regency with the second largest rice production in South Sumatra Province, Madang Suku 1 District is one of the Districts in East OKU Regency and is the center of rice production. However, many farmers in Madang Suku 1 do not know the quality of rice seeds that are by the criteria that are suitable for the village where the farm is, resulting in unsatisfactory yields for farmers, which has an impact on the welfare of rice farmers. Therefore, to help overcome the problems that occur, a system is needed that can help farmers in choosing the best rice seeds that suit the conditions of the area. This decision support system uses the AHP method, this method can make decisions effectively with complex and then simplified in a hierarchical arrangement. In addition, this method can also take into account the level of consistency and inconsistency in the assessment carried out by comparing existing factors or criteria. This research resulted in the ranking of rice recommendations for Madang Sub-district Tribe 1 which is 1.855 obtained by MR, Inpari 42 = 1.470, Ciherang = 1.119, Inpari 32 = 1.000, and Ciliwung with a value of 0.558.

Keywords: Decision Support Systems; Analytical Hierarchy Process; Rice Seedlings;

IMPLEMENTATION OF SUPPLY CHAIN MANAGEMENT AT CV.TINGGAR JAYA FOR WEB-BASED STOCK MONITORING

Mohamad Rizqulloh Ramadan — 2024-03-13

Implementation of Supply Chain Management at CV. Tinggar Jaya is a company warehouse system designed for company needs to coordinate company resources. The problem that occurs at CV. Tinggar Jaya still uses manual methods, from ordering to checking or monitoring stock in the warehouse. Therefore, the solution to this problem is implementing supply chain management at CV. Tinggar Jaya will organize and monitor the warehouse's stock amount using the waterfall system design method with the expected goal of implementing supply chain management to monitor the stock of goods to be more efficient in carrying out this process.

Keywords: Warehouse, Supply Chain Management, Goods, Monitoring, Stock, Website

PREDICTION OF POPULATION GROWTH IN KARAWANG CITY USING MULTIPLE LINEAR REGRESSION ALGORITHM METHOD

Fatiya Hanifah Desfianthy — 2024-03-13

Currently, Indonesia is experiencing population growth. The factors influencing this growth are the rates of births and deaths. Every year, the population in an area keeps growing. This growth can have various negative impacts on the region. That's why taking action and making predictions about population growth is crucial. The objective of this study is to use a regression algorithm to estimate how fast the population will grow in Karawang City. The data used for this research comes from population records collected by the Karawang City Statistics Agency between 2017 and 2022. To clean, transform, and analyze this data, we employ the Knowledge Discovery in Database (KDD) approach to data mining. By applying linear regression methods with assistance from RapidMiner tools, we have successfully generated predictions based on data that reveal patterns and relationships between variables that influence population growth rates. According to our predictions, there will increase of 338,011 people from 2022 to 2027. This research will assist the Karawang City government in developing plans to minimize negative impacts while optimizing resource utilization such as energy, food, water, and services.

Keywords: Multiple Linear Regression, Data Mining, BPS, Rapid Miner

IMAGE PROCESSING FOR DETECTION OF DENGUE VIRUS

Christin Panjaitan — 2024-02-24

Dengue is a major health problem in tropical and Asia-Pacific regions which typically spreads rapidly in number of infection patients. Knowing that most of the world's population living in risk areas, in order to diagnose and treat the disease, high skilled experts and human resources are needed. However, in some cases human error potentially may occur. Therefore, in this research we developed a model which can diagnose dengue fever disease. This study used blood smear images that were taken under a digital microscope with 400 x magnification specifications by means of image processing techniques such as color transformation, image segmentation, edge detection feature extraction and white blood cells classification. In this study we used white blood cell counting of the role of cell differentiation as a new feature that can classify dengue viral infections of patientsvia decision tree methods. The results showed that, the white blood cells classification modeling technique of 167 cell images resulted in 92.2% accuracy while dengue classification modeling technique of 264 blood cell images resulted in 72.3% accuracy.

APPLICATION OF DATA MINING USING THE RANDOM FOREST METHOD TO PREDICT HEART DISEASE

Felix Felix — 2024-02-27

A heart attack is when fatty deposits block the arteries. This causes symptoms such as shortness of breath and chest pain. In addition, obstructed blood flow to the heart can cause damage to the heart muscle. Heart attacks are still the highest cause of death in Indonesia to date. The problem today is that it is tough to predict and identify heart disease. The appropriate method needed to predict heart disease is the Random Forest method. This research aims to calculate the level of accuracy in predicting heart attacks. Based on research and data processing carried out by previous study by comparing two K-Neighbor algorithms, which produced an accuracy value of 83% and the Logistic Regression algorithm produced an accuracy value of 88% and it was found that the Random Forest algorithm had an accuracy of 86.88%. Thus, other algorithms are better at predicting heart attacks than the Random Forest algorithm.

Keywords: Heart Attack, Random Forest, Prediction.

ANALYSIS OF THE C4.5 ALGORITHM IN PREDICTING FERTILIZER AND PESTICIDE SALES AT UD. MR ZEN AGRO

Jijon Raphita Sagala — 2024-02-26

ABSTRACT

Fertilizer and Pesticide sales prediction is a process for finding, assessing, and predicting fertilizer and pesticide sales for the future based on sales results in the past few months. The increasing demand from customers for Fertilizers and Pesticides means UD. Mr Zen Agro, which operates in supplying and selling necessities, needs to record sales transactions so that stock shortages and excess stock of goods do not occur. Using data mining techniques and applying the C4.5 Algorithm can help UD. Mr Zen Agro predicts sales of Fertilizers and Pesticides as a reference or guideline in making decision trees, which are able to predict sales data with a high level of accuracy by calculating the entropy value, information gain, split info, and gain ratio until the matter can no longer be calculated or is zero. An application system exists to predict sales of fertilizers and pesticides, which applies the C4.5 algorithm to UD. Mr Zen Agro, it can be seen how big the sales prediction results obtained can be implemented in a decision tree where from the decision tree, it can be seen which fertilizers and pesticides are in demand and which are not for sale. This system was built using the PHP programming language and MySQL as the database.

Keywords: Data Mining, Sales Prediction, Fertilizer and Pesticide, Algorithm C4.5.

THINKING UI/UX DESIGN ONLINE DESCOVERY EVENT TICKETS

Mohammad Maftuh Ihsan — 2024-03-13

This research discusses designing the UI/UX appearance of an online ticket-purchasing application called Discovery Event to solve problems such as the absence of a group chat feature, late withdrawals of funds, and location points in the application. In implementing UI/UX Design Thinking in online ticket purchasing applications, several stages must be carried out: Empathize, Define, Ideate, Prototype, and Test. The Design Thinking method is used to create solutions to solve problems felt by users. The research results show that Discovery Event can solve problems by improving the group chat feature, efficient fund withdrawals, and adding location point features. Tests involved 20 respondents, which showed user satisfaction with the application interface design. Discovery Event offers an attractive and user-friendly interface and provides a foundation for better application development in the future.

Keywords: Online ticket purchasing, Discovery Event, Design Thinking, UI, UX.

IMPLEMENTATION OF DATA MINING ROUGHT SET IN ANALYZING LECTURER PERFORMANCE

Tegas Hadiyanto — 2024-03-13

Lecturers are professional educators or scientists with the main task of transforming, developing, and disseminating science, technology, and art through education, research, and community service by the Tridharma of Higher Education. The main task of lecturers is to implement the tri dharma of higher education with the scope of activities in the form of teaching, research, and community service. Based on this, the Payakumbuh College of Technology assesses lecturers' performance to maintain the educational institution's quality. A method is needed to identify the quality of lecturers' performance. Lecturer performance can be determined using a rough set approach with several stages. Rough set is a data mining technique applied in several fields, including selecting study programs and predicting mobile phone sales income. Based on the results of using the rough set method, lecturer performance information is produced in a certain period, which aims to help leaders understand the possible performance of lecturers in a certain period. The benefit that can be obtained is that the knowledge obtained through the rough set method can determine the possibility of achieving lecturer performance.

ANALYSIS OF FORWARD CHAINING METHOD ON LAPTOP DAMAGE DIAGNOSIS EXPERT SYSTEM

Fikri Ramadhan Jufri — 2024-03-16

The forward chaining method is used in expert systems to reach conclusions by starting from known facts and moving forward to find a solution or diagnosis. In diagnosing damage to student laptops, this method will begin with information about the symptoms or problems experienced by the computer laptop. The system will evaluate these symptoms and match them with pre-programmed rules to identify possible causes of damage. This process continues by adding new information and making decisions based on sequentially applied rules until reaching a final diagnosis. In diagnosing damage to student laptops, the forward chaining method can help systematically identify problems based on observed symptoms, guiding users through the diagnosis process efficiently.

Keywords: forward chaining, expert systems, laptop damage.

MODELING HEART DISEASE CLASSIFICATION USING ROUGH NEURAL NETWORK: A DATA-DRIVEN APPROACH TO THE CLEVELAND HEART DISEASE DATASET

Nursyahrina Nursyahrina — 2024-03-16

This study implements a Rough Neural Network (RNN) intelligent system method, merging rough sets with neural networks to diagnose heart disease effectively. Using the Cleveland Heart Disease Dataset, rough sets identified nine relevant features for model training, simplifying data complexity. Comparative assessment against traditional neural networks revealed the RNN model's superior performance, achieving 88.52% accuracy, 88.14% F1 score, and 88.85% AUC. This hybrid approach improves predictive accuracy while enhancing efficiency and interpretability. The findings contribute to advancing intelligent systems for heart disease diagnosis, facilitating early detection, and improving patient outcomes. Future research may explore selected features' clinical significance and RNN applicability in different contexts.