Low-resolution magnetic resonance imaging (MRI) may reduce visibility of fine anatomical details, motivating computational super-resolution (SR) to enhance perceived image quality. This study proposes an SR pipeline for 2D brain MRI images using a U‑Net baseline model and a reinforcement learning (RL) agent to automate hyperparameter tuning. Because the selected public dataset does not provide paired low-resolution/high-resolution (LR–HR) images, LR inputs are generated synthetically using a controlled degradation process (blur–downsample–upsample–noise), with deterministic degradation for validation and testing to ensure stable evaluation. The baseline U‑Net is trained using an L1 objective (optionally mixed with differentiable SSIM loss), AdamW optimizer, and ReduceLROnPlateau scheduler guided by validation PSNR. A Double Deep Q‑Network (Double DQN) agent then selects discrete action combinations of learning rate and SSIM-weighted loss mixing to fine-tune the baseline. For the held-out test set (n=60), the baseline improves degraded inputs from 27.04±3.21 dB to 30.10±3.59 dB PSNR and from 0.706±0.132 to 0.875±0.064 SSIM, respectively. RL fine-tuning yields a modest additional PSNR gain to 30.20±3.58 dB and SSIM remains comparable at 0.873±0.066. The paired statistical tests confirm that the PSNR improvement is significant (p<0.01), while changes in SSIM are not statistically significant, suggesting that for the tested synthetic degradation setting RL can provide reliable but incremental refinement when the baseline is already strong.

This study aims to objectively analyze the feasibility of prospective recipients of the Smart Indonesia Card Scholarship (KIP-K) by integrating the Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm and the Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) method. The research dataset consists of 287 data on prospective scholarship recipients with 11 main attributes that reflect the socio-economic and academic conditions of students. The research process includes data collection, pre-processing, transformation of categorical attributes into numerical values using a linear weighting scheme, cluster analysis using DBSCAN, and candidate ranking using TOPSIS. DBSCAN is used to identify cluster patterns and detect anomalies in the data of potential recipients, while TOPSIS is used to rank candidates based on proximity to the ideal solution. The results of the grouping produced 10 clusters and one noise cluster that showed a variety of socio-economic characteristics of prospective scholarship recipients. The results of the ranking show that some of the candidates with the highest TOPSIS scores come from clusters with higher levels of economic vulnerability. In addition, some of the high-scoring candidates also came from the noise cluster, indicating that even though they did not belong to a particular group, they still met the eligibility criteria based on a multi-criteria evaluation. These findings show that the combination of DBSCAN and TOPSIS has the potential to support the process of analyzing the eligibility of scholarship recipients in a more systematic and data-driven manner.

This study examines public sentiment among X users toward the proposal to return regional head elections (Pilkada) to an indirect electoral mechanism through the Regional People’s Representative Council (DPRD), using a decision-tree classifier based on the C4.5 approach. A dataset of 4,127 tweets collected via X API v2 between December 2024 and January 2026 was analyzed using a seven-stage text preprocessing pipeline. Sentiment labels were generated through a hybrid lexicon-based approach, followed by manual verification of 500 stratified tweets by two independent annotators, yielding substantial inter-annotator agreement (Cohen’s Kappa = 0.78). TF-IDF was used for feature extraction, and the dataset was divided using an 80:20 stratified train-test split. The classifier achieved 81% accuracy, 82% precision, 79% recall, and an F1-score of 80%, outperforming Naive Bayes (74%) and Support Vector Machine (79%) baselines on the same dataset. The sentiment distribution showed that 45% of tweets were negative, 32% were positive, and 23% were neutral, indicating a predominantly critical response among X users toward the proposal. These findings describe discourse on X during the study period and should not be interpreted as representative of broader public opinion. Overall, the study highlights the potential of machine learning methods for analyzing Indonesian political discourse on social media.

The rapid diffusion of artificial intelligence (AI) in higher education necessitates a deeper understanding of both institutional and individual factors influencing its adoption, particularly in developing-country contexts. This study examines the drivers of AI adoption in Indonesian higher education institutions by integrating the Technology Acceptance Model (TAM) and the Technology, Organization, Environment (TOE) framework. Addressing a gap in prior research that often separates individual acceptance from institutional readiness, this study adopts a quantitative survey approach involving 366 academic stakeholders, including lecturers, students, and administrative staff. Data collected between October and December 2025 were analyzed using Partial Least Squares Structural Equation Modeling (PLS-SEM). The findings indicate that perceived ease of use strongly influences attitude toward AI, which in turn significantly affects behavioral intention. Perceived usefulness also has a positive, albeit weaker, effect on behavioral intention. At the institutional level, environmental context is found to significantly influence AI readiness, while other contextual factors exhibit limited explanatory power. Several hypothesized relationships, including the effects of AI readiness on perceived usefulness and the moderating roles of digital literacy and top management support, are not supported. These results suggest that AI adoption in higher education is primarily shaped by user-centered factors, while institutional readiness may depend on additional determinants not fully captured in the model. This study provides empirical insights into the role of AI readiness as an intermediate construct within an integrated TAM–TOE framework in higher education.

Micro, Small, and Medium Enterprises (MSMEs) are economic activities conducted by individuals or groups, particularly in the culinary sector. The rapid expansion of culinary MSMEs, especially in tourism-oriented regions such as the Special Region of Yogyakarta, necessitates effective data clustering to systematically analyze their characteristics. High-quality clustering plays a crucial role in supporting informed decision-making, including business development planning, MSME assistance programs, and the formulation of well-targeted policies. This study applies the K-Means algorithm to cluster culinary MSME data; however, its performance is sensitive to centroid initialization, which may result in suboptimal clustering outcomes. To address this limitation, Ant Colony Optimization (ACO) is employed as a centroid optimization approach. ACO is a metaheuristic algorithm inspired by the foraging behavior of ant colonies, where pheromone trails guide the search toward optimal solutions. The results indicate that the integration of ACO enhances clustering performance compared to K-Means. The silhouette scores obtained are 0.88 and 0.89 for two clusters, 0.80 and 0.86 for three clusters, and 0.80 and 0.92 for four clusters for K-Means and ACO-optimized K-Means, respectively. These findings demonstrate that ACO effectively improves centroid initialization, with four clusters identified as the optimal configuration.

This study explores the key factors influencing the adoption of the Education Management Information System (EMIS) within Indonesia's Ministry of Religious Affairs (Kemenag), which is vital for managing data and distributing Teacher Professional Allowances (TPG). Data inconsistencies have been a significant challenge, leading to delays in TPG disbursement. To understand the determinants of EMIS adoption, this study integrates the Government Adoption Model (GAM) and DeLone & McLean’s (D&M) Information Systems Success Model. A quantitative approach was used, collecting data from 328 valid responses from MTsN teachers in Kebumen Regency, analyzed using Partial Least Squares Structural Equation Modeling (PLS-SEM). The results show that Perceived Uncertainty (PU), Perceived Security (PSC), and Perceived Privacy (PP) positively contribute to Perceived Trust (PT). Additionally, Information Quality (IQ) emerged as the strongest predictor of EMIS adoption, followed by System Quality (SYQ), Service Responsiveness (PSR), and Trust. The study emphasizes that improving data accuracy (IQ), ensuring system reliability (SYQ), and strengthening security measures (PSC) are critical for accelerating EMIS adoption. The findings offer practical implications for Kemenag to optimize the implementation of EMIS, ultimately improving the efficiency and timeliness of TPG disbursements for educators.

This study addresses the challenge of detecting network pivoting, a lateral movement technique that is difficult to identify in insider and BYOD environments because malicious transitions can resemble normal internal activity. The objective was to improve detection of both known and unknown pivoting behaviours while supporting practical triage in resource-constrained institutions. A hybrid detection framework was developed that fuses Snort signature alerts with machine learning classification and unsupervised anomaly detection using behavioural features derived from BYOD-like network traffic. The approach was evaluated in a controlled testbed and supported by organisational survey findings on awareness and monitoring practice. Results show the hybrid system achieved 96.2% classification accuracy with a 4.5% false positive rate when distinguishing normal traffic, suspicious activity, and pivoting attacks. Compared with signature-only and machine-learning-only baselines, the hybrid design detected simulated pivoting attempts earlier and more consistently. User acceptance testing also reported strong satisfaction with the integrated dashboard for monitoring, filtering, and reporting. The key contribution is a unified, dashboard-oriented fusion of signature and behavioural evidence that strengthens early lateral movement detection and reduces manual correlation effort.

This study integrates Aspect-Based Sentiment Analysis with Customer Satisfaction Index (CSI) and Importance Performance Analysis (IPA) to determine priority development features in digital service applications in the telecommunications sector. A total of 10,000 MyIM3 user reviews were analyzed using sentiment analysis with Pseudo-labeling and Fine-Tuned IndoBERT, then from the results of the analysis, negative sentiment was mapped into several topics using LDA. The topic is used to compile question indicators based on the five dimensions of SERVQUAL. After the questionnaire data is declared valid and reliable, CSI and IPA analysis is carried out. A CSI value of 79.22% indicates that user satisfaction is in the "borderline" category, but several aspects still need to be improved, especially system updates (RS3), application attention to user needs (E2), and feature personalization (E3) which are in quadrant I (Concentrate Here). This hybrid approach offers novelty by demonstrating how ABSA and LDA can be systematically integrated with CSI and IPA to provide more comprehensive and user-oriented insights. The limitations of this study include focusing on negative sentiment data for feature exploration, as it is most relevant for identifying problems and opportunities for improvement and development of telecommunication digital services.

This bibliometric analysis examines the evolving trends of digital transformation (DT) and information systems (IS) in U.S. businesses. It explores how technology—focused on strategy, efficiency, innovation, and customer engagement—is reshaping organizations and workplaces. Using a PRISMA-based systematic review and data from Scopus (2016–2026), the study applies the Bibliometrix R package to assess publication patterns. Results show significant growth, with 2,692 documents reflecting a 43.58% annual increase and 18.39% involving international collaboration. Key themes include AI/ML integration in business processes, digital sustainability, and IS as a strategic driver for business model evolution. U.S. businesses are increasingly aligning digital transformation with sustainability goals. This study addresses a key research gap by offering detailed insights into DT and IS impacts on operations and sustainability practices. It underscores the need for integrated socio-technical strategies, responsible data governance, and global collaboration to foster innovation and bridge digital divides.

This study conducts a bibliometric analysis of digital marketing in public health through the lens of cybersecurity, aiming to evaluate research trends from 2015 to 2025. It identifies key developments, major contributors, and provides guidance for future studies. A total of 1,191 documents were analyzed, revealing a significant annual growth rate of 32.01% and an average of 19.01 citations per document. The analysis explores how digital marketing for public health intersects with cybersecurity, a domain that remains underexplored. Data collection and visualization were conducted using Scopus, Biblioshiny, and VOSviewer, with article selection guided by the PRISMA methodology. Results indicate consistent growth in publications over the decade, though a noticeable decline occurred post-COVID-19 in 2020. The study offers a comprehensive mapping of existing literature and highlights the strategic importance of integrating cybersecurity into digital health marketing to protect patient data, maintain public trust, and enhance health outcomes. It provides valuable insights for researchers, policymakers, and practitioners aiming to improve the security and effectiveness of digital health communication in an increasingly connected world.