Journal of Enhanced Studies in Informatics and Computer Applications

A Systematic Literature Review of Artificial Intelligence Algorithms for Deepfake Detection

Aulia Roessati Putri — 2026-02-27

The evolution of information technology has positioned multimedia content as a pillar of digital communication, but at the same time, it has opened a gap for serious threats in the form of deepfakes. This highly realistic media manipulation challenges information authenticity, privacy, and cybersecurity, which, for Information Technology professionals, presents both technical and ethical challenges. This Systematic Literature Review (SLR) aims to map the development of Artificial Intelligence based algorithms in deepfake detection. Using the PRISMA methodology on 20 selected primary articles (2021-2025), this study aims to identify trends in the use of AI algorithms for deepfake detection, determine the most effective approaches, and analyze the factors contributing to their effectiveness. The analysis results show a paradigm shift from single models (such as CNN) to hybrid architectures (CNN-LSTM-Transformer) and complex multimodal fusion systems. It was found that hybrid algorithms are the closest approach to best practice due to their ability to handle spatial and temporal dimensions simultaneously. Key contributing factors include hierarchical feature extraction, generative data augmentation, and the integration of Explainable AI (XAI).

Hierarchical Clustering Analysis of Biopharmaceuticals Crop Production Across Indonesian Provinces

Mayang Anglingsari Putri — 2026-02-27

This study analyzes biopharmaceuticals (medicinal crop) production across Indonesian provinces using 2023 data from eight major commodities: ginger, galangal, kencur, turmeric, lempuyang, temulawak, temu ireng, and keji beling. Data from 38 provinces were normalized and analyzed using agglomerative hierarchical clustering with Ward’s linkage and Euclidean distance. The results identify three distinct clusters representing high, medium, and low production levels, with Java provinces dominating the high-production cluster, while provinces outside Java fall into moderate and low clusters. These findings highlight regional disparities and potential specialization in biopharmaceuticals cultivation. This study contributes a comprehensive national-scale multivariate clustering framework for medicinal crop production and demonstrates the applicability of hierarchical clustering for spatial agricultural analysis. The findings provide practical implications for policymakers in designing targeted agricultural development strategies, regional specialization planning, and supply chain optimization in Indonesia’s biopharmaceuticals sector.

The 2D Android Game ‘Bung Tomo Adventure’ uses the Finite State Machine Method

Doan Oggie Adriansz — 2026-02-27

Educational games are an effective media to improve the youth’s understanding on national history, especially when the game is presented in an interactive and engaging manner. The adoption of Finite State Machines (FSM) in 2D games makes the game to be more realistic and more dynamic. This research aims to develop an Android-based ‘Bung Tomo Adventure’ game by adopting the FSM method to control character’s behavior and to enhance the user's playing experience. The research methodologies include literature review, system’s design, coding using Godot Engine, Black Box Testing, device testing, and user evaluation. Besides that, the Black Box testing outcome shows that the game features work as expected. The user experience testing shows that 87% respondents gave positive response (categories Good and Average), which means this game is quite well received especially in terms of storyline and ease of play, although some aspects such as visual appearance and game distribution need more improvement.

Stock Forecasting using Daily Sales Transaction at Hundred Smoke Outlets with the Trend Moment Method

Aditya Prakasa — 2026-02-27

Hundred Smoke Outlet is a culinary business experiencing fluctuating customer demand that changes weekly, creating a risk of imbalance between raw material inventory and actual needs. This research aims to develop a web-based forecasting system using the Trend Moment method that processes daily sales data and converts it into a Bill of Materials (BOM) structure to more accurately predict raw material requirements. The system is designed with two user types: admin and staff, who can manage sales data, inventory, and run the forecasting process. Based on black-box testing results for 11 scenarios across various system features, all functions performed as expected with a 100% success rate. Forecast accuracy was evaluated using the Mean Absolute Percentage Error (MAPE), which showed a maximum error of 0.50, a minimum error of 0, and an average error of 22.62%. These results indicate that the system can provide a fairly good level of accuracy in supporting raw material requirement planning.

Systematic Literature Review on Data Security and Privacy for e-Government

Mela Firdini Azzahra — 2026-02-27

The use of e-Government is increasing along with efforts to improve the efficiency, transparency, and quality of public services. However, advances in digitalization are also accompanied by cybersecurity risks and threats to data privacy. This study aims to examine the implementation of data security and privacy in e-Government, as well as evaluate the technologies used to mitigate data leaks and misuse. The method used is Systematic Literature Review of articles published between 2021 and 2025 through Scopus, ScienceDirect, and Google Scholar databases. The research selection followed the PRISMA 2020 guidelines, resulting in 16 articles meeting the eligibility criteria. The study findings indicate that information security implementation in government institutions remains inconsistent, with key challenges related to weak security management, technical system vulnerabilities, and low public trust in personal data protection. Several technologies considered to have potential to improve security include blockchain, advanced cryptography, and automation for vulnerability detection, although their implementation remains hampered by cost, scalability, and human resource readiness. Overall, this study emphasizes that a comprehensive approach that combines technology, management, and increased security awareness is needed to strengthen data protection in e-Government.