The integration of Artificial Intelligence (AI) in education has accelerated rapidly, reshaping teaching and learning processes through intelligent, adaptive, and data-driven systems. Despite its widespread adoption, a consolidated understanding of implementation trends, benefits, and challenges across educational contexts remains limited. This study aims to examine the current state of AI adoption in education by identifying key applications, success factors, and implementation barriers. A systematic literature review (SLR) was conducted by analyzing 32 peer-reviewed journal articles published within the last five years and indexed in reputable academic databases. The reviewed studies focus on adaptive learning systems, intelligent tutoring systems, and learning analytics. The findings demonstrate that AI contributes significantly to personalized learning, real-time performance assessment, and improved learner engagement. However, effective implementation is strongly influenced by institutional readiness, educator digital literacy, data quality, and ethical governance. Major challenges identified include data privacy concerns, lack of standardization, and unequal access to technological infrastructure. This study concludes that AI has substantial potential to support more adaptive and inclusive educational systems, but sustainable integration requires coordinated efforts among educators, policymakers, and technology developers.
Dairy cattle data management plays a crucial role in supporting operational efficiency and the sustainability of the livestock sector. However, conventional practices at Mamad Jaya Farm in animal identification still present severe operational and animal welfare challenges. The existing traditional marking methods carry high physical risks for the livestock, frequently leading to torn ears from ear-tagging, severe skin irritation from branding, and high human-error risks in manual paper-based record-keeping. To mitigate these invasive drawbacks, this study aims to develop an artificial intelligence-based facial recognition system for dairy cattle as a non-invasive solution to support digital and integrated livestock data management. A Convolutional Neural Network (CNN) architecture was uniquely implemented for the identification process due to its superior capacity to automatically and hierarchically extract complex spatial biometric features from facial images without manual feature engineering. The research methodology involved collecting a multi-angle facial dataset from a herd of 15 dairy cattle at Mamad Jaya Farm, Karangpawitan, Garut, which was then processed using Roboflow. The developed model was integrated into a web-based livestock platform named BonvaLink. Empirical testing on 15 distinct cattle facial images demonstrated that the system achieved an individual identification accuracy of 93.33%, with the majority of correct predictions yielding robust confidence scores. These results indicate that the CNN-based biometric approach is highly effective and reliable in recognizing individual dairy cattle identities under practical barn environments
The growth of the fintech lending industry (LPBBTI) in Indonesia has expanded access to financing but has also increased credit risk, as reflected in the 90-day Default Rate (TWP90). This condition demands proactive regional risk monitoring, while existing approaches are still dominated by historical descriptive analysis. This study aims to develop a high-risk provincial classification as a transparent and accountable early warning system. The research methodology uses multi-sheet data integration from the Financial Services Authority (OJK) LPBBTI Statistics to create a provincial-monthly panel dataset covering supply, demand, and transaction activity. The Logistic Regression model was used as the baseline model due to its interpretability and support for decision auditability. Model evaluation using a time-based split approach during the May–July 2025 test period demonstrated good performance, with an ROC-AUC of 0.8598, an accuracy of 0.8462, and a precision of 0.8000. The results of feature analysis indicate that scale and activity indicators, particularly the outstanding amount, the number of active borrowers, and the value of disbursed funds, contribute significantly to risk probability. Although detection sensitivity (recall: 0.5333) still needs improvement, this study provides a measurable, relevant regional risk-ranking framework for regulatory decision-making.
The Bayah Dome Geopark in Lebak Regency possesses significant geological and cultural heritage; however, it currently holds the status of an "Aspiring Geopark." A primary challenge in optimizing its geotourism potential—particularly for the Baduy tribe—is the physical accessibility constraint caused by adverse weather conditions and rugged terrain. This study aims to develop and evaluate a mobile-based 360-degree virtual tour website as an inclusive digital geocultural and educational medium. The research follows a Research and Development (R&D) approach using the Multimedia Development Life Cycle (MDLC) framework, encompassing concept, design, material collection, assembly, testing, and distribution stages. The system integrates 360-degree panoramic visualizations with interactive navigation and informational hotspots to represent Baduy’s local wisdom. Empirical results from black-box testing confirmed 100% functional validity across all system features. Furthermore, a User Acceptance Test (UAT) conducted using a Likert scale yielded an average acceptance index of 82.8%, categorizing the platform as "Very Good." This virtual tour serves as a strategic digital solution for cultural preservation and sustainable geotourism promotion, effectively surmounting geographical and temporal barriers for a global audience.
The development of wireless communication technology is increasing along with the need for high-speed internet access, both in urban and rural areas. Point-to-Point (PtP) technology based on the IEEE 802.11ac standard is one of the main solutions for providing long-distance connectivity, particularly in backhaul networks, ISPs, and inter-building communication. However, the network implementation process often relies on link simulations using software such as ISP Design Center or AirLink, which do not always accurately represent field conditions. Wave propagation factors, terrain contours, and obstacles in the Fresnel Zone significantly affect signal quality. The Fresnel Zone is a three-dimensional propagation area that must be at least 60% free of obstacles for optimal transmission. Previous research has shown limitations in studies related to evaluating the accuracy of Fresnel Zone simulations on Ubiquiti 802.11ac devices. Therefore, this research evaluates and compares the parameters of RX Signal Strength, throughput, channel width, and Fresnel Zone clearance between simulation results and direct field testing on a PtP connection. The research results are expected to serve as a technical reference for network practitioners in validating simulation results and providing recommendations for more accurate and efficient PtP connection design. This research also emphasizes the importance of Line of Sight (LOS) and Fresnel Zone optimization in maintaining the stability of outdoor wireless networks based on IEEE 802.11ac
