Vol. 4 No. 1 (2025): May

This research focuses on developing an anomaly detection application for the internet network infrastructure at the Disaster Recovery Center (DRC) building of the Indonesian Attorney General's Training Agency through Security Information and Event Management (SIEM) implementation utilizing Python programming language. The primary objective of this study is to develop a comprehensive application that assists personnel, particularly network administrators at the DRC facility, in monitoring and analyzing internet network communication patterns and traffic flows. The research methodology involves creating a detection system designed to enhance network security capabilities and provide continuous monitoring functionality for network infrastructure protection. The developed application leverages SIEM technology to aggregate and process security-related information extracted from log data across network devices, applications, and hardware components. SIEM technology demonstrates the capability to handle substantial data volumes while correlating and analyzing security events from multiple heterogeneous sources within the network environment. The implementation of this application provides critical visibility into the internal network operations of the DRC facility, enabling proactive threat detection and response capabilities. When security incidents or anomalous activities are identified, the system generates comprehensive reports detailing network conditions and security status, which are subsequently escalated to management for appropriate remedial actions and strategic decision-making.

Market segmentation represents a critical challenge in local product marketing, particularly when addressing complex consumer behavior patterns and uncertain classification environments in today's digital economy. This research develops and validates a hybrid model integrating K-Means Clustering with Dempster-Shafer theory to enhance segmentation accuracy and reliability for local product markets. The K-Means algorithm groups consumers based on demographic, psychographic, and behavioral characteristics, while Dempster-Shafer theory quantifies uncertainty and provides confidence measures for segment assignments. Data collection involved comprehensive consumer surveys and transaction records from 2,847 participants across multiple local product categories over a 12-month period. The hybrid model achieved superior performance with 87.5% accuracy, 85.3% precision, 86.1% recall, and 85.7% F1-score, representing improvements of 5.4% over standard K-Means and 8.2% over hierarchical clustering methods. Four distinct market segments were identified: Young Urban Professionals (28%), Value-Conscious Families (35%), Traditional Loyalists (22%), and Digital Natives (15%), each exhibiting unique purchasing patterns, digital engagement levels, and price sensitivity characteristics. Cross-validation yielded a consistency score of 0.91 with segment stability demonstrated through 8.3% churn rate and conflict measure K = 0.12, indicating substantial agreement among evidence sources. The methodology successfully addresses uncertainty in consumer classification while providing actionable insights for targeted marketing strategies, pricing optimization, and customer retention programs. Local product marketers can implement this framework to develop evidence-based marketing approaches that accommodate both traditional and digital consumer preferences, enabling competitive positioning in increasingly complex market environments. The research establishes a scalable and practical solution for small to medium enterprises seeking sophisticated market analysis capabilities without requiring extensive computational infrastructure or technical expertise.

The rapid development of information technology demands digitalization across various public service sectors, including child health systems at Posyandu (Integrated Health Service Posts). Posyandu Kenanga Depok conducts monthly child health monitoring activities to ensure nutritional status and child development. However, the manual recording system for Child Health Cards (Kartu Sehat Balita/KSB) creates various operational problems. Posyandu cadres experience difficulties in data recording processes, information storage, and monthly report generation. Additionally, paper-based KSB held by parents are prone to loss and damage, resulting in poorly documented child development data. This research aims to develop a web-based KSB application to address these problems using the Rapid Application Development (RAD) methodology. The RAD method was chosen for its ability to accelerate system development processes by actively involving users in every development stage. The application was developed using PHP programming language, CodeIgniter 4 framework, MySQL database, and Visual Studio Code editor. The system is designed with three user levels: Posyandu cadres for managing child data and generating reports, parents for monitoring child development, and doctors for managing immunization and vitamin data. Development results demonstrate that the application successfully automates child data recording processes, facilitates monthly report generation, and enables parents to access child development information in real-time. The system also provides growth chart visualizations and immunization schedule reminders to support optimal child health monitoring.

This study aims to analyze the development of deep learning methods for optimizing complex data classification model performance through a Systematic Literature Review (SLR) approach examining 25 Scopus-indexed scientific articles published between 2024 and 2025. The analysis employs bibliometric techniques using VOSviewer to map keyword networks, temporal trends, and term density patterns. Visualization results identify three primary clusters: (1) LSTM-based classification and intrusion detection systems in cybersecurity applications; (2) CNN optimization and model efficiency for medical imaging and satellite image classification; and (3) artificial intelligence integration with visual classification and evolutionary optimization algorithms. Recent trends demonstrate the dominance of keywords such as "optimization," "effectiveness," and "feature selection," alongside growing interest in hybrid approaches and metaheuristic algorithms. This research provides a comprehensive overview of methodological transformations and application directions of deep learning in complex data classification domains. These findings are expected to serve as strategic references for advancing research and applications in big data-driven artificial intelligence technologies.

Marriage represents a sacred milestone requiring meticulous preparation from every couple. CV. Ruang Event, a wedding organizer service provider in Bandar Lampung, faces significant operational challenges due to outdated manual systems. Primary issues include unstructured client documentation, fragmented transaction data storage, and time-consuming report generation prone to human error. These conditions result in data inaccuracy, delayed information retrieval, and deteriorating customer service quality. The research aims to develop a web-based information system to optimize CV. Ruang Event's business processes using the Waterfall methodology. Development phases encompass system requirement analysis, database and interface design, implementation using PHP and MySQL, and functional testing. The research produces a web application facilitating online wedding organizer package bookings, event schedule management, digital payment systems, and automated reporting. Core features include package catalogs (Silver, Gold, Diamond/Platinum) priced from IDR 3,500,000 to IDR 38,000,000, booking calendars, payment confirmations, and administrative dashboards. Testing demonstrates 60% operational efficiency improvement, 85% reduction in recording errors, and enhanced customer satisfaction through improved information accessibility. The system successfully integrates entire business processes from booking to reporting, delivering a complete solution for wedding organizer service digitalization.