Publication Search

Typhoid fever is a significant health issue caused by the Salmonella Typhi bacteria, leading to symptoms such as fever, abdominal pain, diarrhea, muscle pain, and serious complications if not treated promptly. A common challenge faced by society is limited access to medical professionals, especially in remote areas, and delays in recognizing symptoms. To address this problem, this study designs and implements a web-based expert system using the Certainty Factor (CF) method, which helps diagnose typhoid fever quickly and accurately. The Certainty Factor method is used to calculate the certainty level of the symptoms experienced by the patient, providing a diagnosis result in the form of early-stage typhoid, mild typhoid, or severe typhoid. The system was developed using PHP programming language and MySQL database, and tested at RSUD Djoelham Binjai City. The research data was obtained from patients at RSUD Djoelham Binjai with a case study on patient number 22. The processing of symptoms through Certainty Factor calculation showed that the patient is most likely to have severe typhoid with a certainty value of 0.9443 or 94.43%. This result proves that the Certainty Factor method can be used to assist in providing an accurate early diagnosis of typhoid fever with a high degree of accuracy.

The Computer-Based National Assessment (ANBK) is an essential instrument designed to comprehensively measure student competence, including literacy, numeracy, and character aspects. However, in practice, many students still face various challenges during preparation, such as cognitive limitations, psychological readiness, and technical barriers, which affect their overall readiness to participate in ANBK. This study aims to analyze the readiness level of students at SMP Negeri 2 Kuala by employing the Rough Set method. The variables examined include digital literacy, subject matter understanding, psychological readiness, and school facility support. Data were collected from 250 ninth-grade students through structured questionnaires and subsequently processed using the Rosetta software to perform attribute reduction and generate decision rules. The findings indicate that digital literacy, subject matter understanding, and psychological readiness are the most influential variables in determining student readiness, while facility support serves only as a complementary factor. The extraction process generated seven decision rules with an accuracy level of 100%, which effectively classified students into three readiness categories: highly ready, ready, and less ready. These results confirm that the Rough Set method is highly effective for identifying dominant factors and producing decision rules that can guide schools in developing targeted strategies to enhance student readiness for ANBK.

Rapid technological advancements have brought convenience to various fields, including healthcare. Osteoarthritis (OA) is a chronic degenerative joint disease that often affects the knees and hips, particularly in the elderly, and is a major cause of pain, joint dysfunction, and reduced quality of life. The prevalence of OA increases with age, with risk factors such as obesity, excessive activity, and muscle weakness. Early and accurate diagnosis is essential for appropriate treatment. This study aims to develop a diagnostic system for inflammatory arthritis, specifically osteoarthritis, using the Dempster-Shafer method. This method was chosen because of its ability to combine various evidence and expert beliefs to produce a more accurate diagnosis. By utilizing mathematical proof theory, this system is expected to assist medical personnel in detecting OA symptoms more efficiently. The research findings are expected to contribute to the healthcare sector, particularly in improving the accuracy of osteoarthritis diagnosis, allowing for earlier and more appropriate treatment. This system can also be a supporting tool for doctors and patients in understanding joint health conditions.

The transition of children from early childhood education to elementary school (SD) is a critical phase in their psychological and academic development. During this phase, children face significant challenges, including changes to a more structured learning environment and increasing academic demands. At SDN 055991 in Langkat Regency, this phenomenon is reflected in the difficulties experienced by some students, particularly with basic skills such as reading, writing, and arithmetic, as well as with socializing with peers. These difficulties can impact children's long-term academic and social development. This study aims to identify the key factors influencing children's learning readiness during this transition period, utilizing artificial intelligence (AI) technology. Specifically, this study uses Artificial Neural Networks (ANN) and Decision Trees as tools to analyze the data obtained. The use of this data-driven approach allows for a more in-depth analysis of the complex patterns and relationships between various variables that influence children's learning readiness, such as family factors, social environment, and students' basic skills. This study also references various previous studies demonstrating the effectiveness of backpropagation and Deep Learning algorithms in the context of education and student performance prediction. This approach is expected to provide more precise solutions for understanding children's learning readiness and provide a more accurate picture of the factors contributing to difficulties experienced by students in the transition to elementary school. The results of this study are expected to provide relevant recommendations for parents, educators, and education policymakers to support children's learning readiness and strengthen basic education policies that are adaptive to the needs of students in this digital era.

This study aims to analyze the correlation between learning models and student achievement at SMA Negeri 1 Kuala by applying the Apriori algorithm in data mining, using Rapid Miner software as the primary tool for analysis. The research is motivated by the shift in educational approaches from conventional teacher-centered methods toward more innovative strategies such as project-based learning and cooperative learning, which are expected to foster higher levels of student engagement and improve academic outcomes. In many schools, particularly at the secondary level, the choice of learning model, availability of facilities, and attendance rates are crucial factors that shape learning effectiveness and student performance. The data collected in this study include student grades, the types of learning models implemented, school facility conditions, and attendance rates for the 2023/2024 academic year, covering a total of 680 students. The Apriori algorithm was employed to discover hidden patterns and associations among these variables, enabling the identification of relationships between learning factors and academic achievement. By applying Rapid Miner software, the research systematically generated association rules that reflect meaningful correlations in the dataset. The results indicated that the use of the Indonesian language subject in combination with a cooperative learning model, adequate and complete school facilities, and good student attendance was strongly associated with the attainment of an A grade. This finding was supported by a support level of 53.33% and a confidence level of 100%, suggesting a robust and reliable relationship between these factors. The implementation of data mining techniques through Rapid Miner not only allowed for efficient data processing but also provided practical recommendations for educators and school administrators in designing effective instructional strategies.