Claim Missing Document
Check
Articles

Found 2 Documents
Search
Journal : G-Tech : Jurnal Teknologi Terapan

Personalized Learning System Based on Artificial Intelligence to Enhance Learning Effectiveness: A Bibliometric Analysis Iswari, Ni Made Satvika
G-Tech: Jurnal Teknologi Terapan Vol 9 No 3 (2025): G-Tech, Vol. 9 No. 3 July 2025
Publisher : Universitas Islam Raden Rahmat, Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70609/g-tech.v9i3.7355

Abstract

The integration of artificial intelligence (AI) in personalized learning systems has emerged as a transformative approach to address diverse educational needs and enhance learning effectiveness. However, comprehensive insights into the research landscape, trends, and challenges remain underexplored. This study aims to systematically map and analyse the development of AI-driven personalized learning systems over the past decade to understand their evolution, thematic focus, and future directions. To achieve this, a bibliometric analysis was conducted on 368 Scopus-indexed publications (2015–2025). Utilizing VOSviewer, the analysis reveals a significant surge in research output post-2021, with conference papers and articles dominating scholarly communication. Key themes include adaptive learning, machine learning algorithms, and educational innovation, while emerging clusters highlight advancements in generative AI (e.g., ChatGPT) and language models. Findings indicate that AI-based systems improve academic performance, engagement, and retention through tailored content and real-time feedback. However, challenges such as data privacy, algorithmic bias, and accessibility disparities persist. This study provides a data-driven synthesis of the field’s intellectual structure, offering actionable insights for educators, policymakers, and researchers to optimize AI’s potential in creating equitable and effective learning environments.
DeepFake Image Detection Using Convolutional Neural Network with EfficientNet Architecture Dharma, Eddy Muntina; Iswari, Ni Made Satvika; Arimbawa, I Putu Rama Astra
G-Tech: Jurnal Teknologi Terapan Vol 9 No 4 (2025): G-Tech, Vol. 9 No. 4 October 2025
Publisher : Universitas Islam Raden Rahmat, Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70609/g-tech.v9i4.7727

Abstract

The growing sophistication of generative Artificial Intelligence (AI) has intensified the threat posed by deepfake technologies, which are capable of producing highly realistic yet fabricated facial images and videos. These manipulated visuals can mislead the public, infringe on personal privacy, and damage reputations. This study aims to develop an effective deepfake image detection system using Convolutional Neural Networks (CNN) enhanced with EfficientNet architectures (B3–B5). The research adopts the Cross Industry Standard Process for Data Mining (CRISP-DM) methodology, providing a structured data science framework that spans from problem definition to deployment. Three open-access datasets (Celeb-DF v2, DeeperForensics-1.0, and DFDC) are utilized to train and evaluate the models. Experimental results show that EfficientNet-B5 achieves the highest classification accuracy at 93.2%, outperforming both the baseline CNN and other EfficientNet variants. The proposed method demonstrates strong cross-dataset generalization and computational efficiency, making it suitable for real-world applications. This research contributes a comparative evaluation of scalable deepfake detection models, practical deployment insights, and a foundation for future work in explainable and real-time AI-based media forensics.