INTERNAL (Information System Journal)

Deteksi Kerentanan Kode PHP Menggunakan TF-IDF, AST Parsing, dan Random Forest

2025-05-07T03:41:22-04:00

Vulnerabilities in PHP programming code remain one of the primary threats to the security of web applications, especially in the absence of automated analysis mechanisms during development. This study presents a hybrid system designed to detect vulnerabilities in PHP code in real time, utilizing a combination of Term Frequency-Inverse Document Frequency (TF-IDF) and Abstract Syntax Tree (AST) parsing techniques, along with the Random Forest classification algorithm. The process begins with preprocessing, cleaning, and tokenization, followed by feature extraction using TF-IDF. The next stage involves AST-based parsing to identify potentially dangerous syntax, such as the use of eval() or include() functions with parameters derived from user input. Both feature sets are combined and used to train a Random Forest model on a labeled dataset that distinguishes between vulnerable and secure code. Reliability testing was conducted on several PHP files from existing applications. The results show that the system is capable of identifying vulnerabilities such as File Inclusion and SQL Injection with confidence scores ranging from 52% to 61%, regardless of the structure or complexity of the code analyzed. Although the confidence level is not yet optimal, the system has demonstrated effectiveness in providing early warnings of potential threats. In the future, this system can be further developed as a simulation tool for static code analysis to support improved secure coding practices in software development.

Rancang Bangun Aplikasi Sistem Pendukung Keputusan Penilaian Siswa Berprestasi Menggunakan Metode MFEP

2025-05-26T02:58:54-04:00

The assessment of outstanding students is an important aspect of education aimed at recognizing academic and non-academic achievements. However, in practice, this process is often time-consuming and prone to subjectivity when conducted manually. Therefore, a decision support system (DSS) is needed to assist in making objective and structured decisions. This study aims to design and develop a decision support system for evaluating outstanding students using the MultiFactor Evaluation Process (MFEP) method. The MFEP method is used to evaluate alternatives (students) based on several assessment criteria with predefined weights. The system was developed using the Agile approach, which includes analysis, design, implementation, and testing stages. The results show that the system can automatically process student assessment data and generate final rankings that match manual calculations. System testing confirmed that all functions performed well and helped make the selection process faster, more accurate, and more transparent.

Deteksi Pneumonia pada Citra Akhir X – Ray Dada Menggunakan Convolutional Neural Networks Berdasarkan Fitur Prewitt Operator

2025-05-06T21:26:46-04:00

Pneumonia is a lung infection that is a leading cause of death, especially in children and adults in developing countries. The diagnosis of pneumonia is usually made through physical examination and interpretation of chest X-rays, but the results can vary depending on the experience of the doctor, potentially leading to misdiagnosis. This study uses a convolutional neural network (CNN) to detect pneumonia in X-ray images, with additional feature processing methods, such as the Prewitt operator to handle class imbalance. The goal is to improve the accuracy of pneumonia detection so that it can assist medical personnel in decision making and reduce misdiagnosis. As a result, the developed model achieved an accuracy of 96.59% on training data with consistent improvement, demonstrating the potential of CNN in supporting pneumonia diagnosis more accurately and reliably.

Sistem Informasi Penggajian Pegawai Berbasis Desktop pada CV.Hijab Geulis Konveksi

2025-05-20T05:26:19-04:00

The payroll process is a critical component of company operations, including in the garment manufacturing (konveksi) industry. However, manual payroll management often leads to various issues such as calculation errors, delayed payments, and inefficiencies in report generation. This study aims to design and develop a desktop-based employee payroll information system to enhance the effectiveness and accuracy of payroll management at CV.Hijab Geulis Konveksi. The research uses the Research and Development (R\&D) method with a Agile approach in software development. The system was built using Visual Basic .NET programming language and MySQL as the database. Key features of the system include employee data management, attendance recording, automated payroll calculation, payslip generation, and payroll reporting. Testing results show that the system functions effectively, reduces calculation errors, and accelerates the payroll process. With its simple and user-friendly interface, the system can be easily operated by non-technical users. In conclusion, this desktop-based payroll information system offers an effective solution to support administrative payroll tasks in small to medium-scale garment manufacturing companies.

Visualisasi Data untuk Analisis Tren Penjualan Skincare dan Makeup Menggunakan Tableau

2025-06-11T21:10:08-04:00

The cosmetic industry has experienced rapid growth, particularly in the skincare and makeup sectors. With increasing competition, understanding sales trends has become a crucial factor for beauty businesses in developing effective marketing strategies. This study aims to analyze sales trends for skincare and makeup products using the Running Total method and monthly sales percentage changes, visualized through Tableau. The research data consists of product sales from various stores within the period of January 2023 to December 2024. The Running Total method is applied to analyze the cumulative sales pattern of skincare products, while monthly sales percentage changes are used to identify fluctuations in makeup product sales. The results indicate that skincare product sales show a stable growth trend, whereas makeup products exhibit more significant fluctuations. Factors such as promotional strategies, market trends, and seasonal effects significantly influence sales variations over different periods. These findings provide valuable insights for beauty businesses to optimize their marketing strategies, inventory management, and data-driven decision-making processes.

Perencanaan Strategis Sistem Informasi Menggunakan Metode Ward and Peppard di Lembaga Penjaminan Mutu Universitas Ma’soem

2025-05-27T03:17:17-04:00

The Quality Assurance Institute (QAI) is vital for improving higher education quality. To support its functions, strategic Information System (IS) planning is essential. This research aims to develop an IS strategic plan for Ma'soem University's QAI, using the Ward and Peppard method. This qualitative case study comprehensively analyzes the university's business and IS/IT environments, utilizing tools like PESTEL, SWOT, and others. The research results show that indicate Ma'soem University's QAI requires integrated IS/IT to optimize the PPEPP quality cycle and support decision-making. Challenges include fragmented data and manual processes. The proposed IS/IT strategy focuses on PPEPP effectiveness, integrated platforms, and sound IS/IT governance. The application portfolio includes a strategic e-SPMI system, quality analytics, and stakeholder collaboration. This planning is expected to enhance the QAI's efficiency, transparency, and accountability, thereby supporting the university's vision.

Klasifikasi Citra Ras Kucing Berbasis CNN dengan Metode MobileNet-V2

2025-05-06T21:29:20-04:00

This study evaluates the performance of a Convolutional Neural Network (CNN) using the MobileNet-V2 architecture in classifying four cat breeds. The lack of public understanding in distinguishing cat breeds, especially due to the prevalence of mixed breeds, presents a significant challenge in accurate identification. The model was tested across multiple epochs to observe training and validation accuracy, aiming to assess its effectiveness and stability. Experimental results show that the highest validation accuracy of 93.81% was achieved at epoch 90. Although the model performed well, further optimization is needed to address overfitting and improve generalization capability. This research contributes to the development of an automated breed identification system that can be applied in education, adoption processes, and veterinary healthcare.

Penerapan Data Mining untuk Menganalisis Kepuasan Nasabah BPRS Al-Ma’soem Menggunakan Algoritma C4.5

2025-05-06T21:33:00-04:00

Customer satisfaction levels with the services provided by BPRS Al Ma’soem Bandung using the C4.5 Customer satisfaction is an important factor in influencing the running of a bank. To understand the indicators that influence customer satisfaction, it is necessary to evaluate the level of customer satisfaction with a service. This article explains the use of the classification method with the C4.5 algorithm at BPRS Al Ma'soem Bandung. Data were obtained from 406 respondents through a questionnaire covering variables such as service, facilities, ease of access, products, and trust. The results of the analysis show that the attributes of trust and suitability have the greatest influence on customer satisfaction. The resulting model has an accuracy level of 96.31%, indicating the effectiveness of the C4.5 algorithm in analyzing data. This study provides recommendations to BPRS Al Ma'soem to improve service quality, adjust facilities, and products to customer needs to maintain competitiveness in the Islamic banking sector.