Publication Search

Acute Respiratory Tract Infection (ARI) is a global health problem that significantly contributes to high morbidity and mortality rates. The goal of this activity is to educate residents about preventing ARI, so that they have a good understanding of the disease and are able to take preventive measures independently. The program included information on ARI, simple inhalation therapy, and proper waste disposal. Prior to the health promotion on ARI prevention, 70% of residents had poor knowledge about the disease. After the activity, there was a significant increase in knowledge, with 90% of residents demonstrating a good level of understanding. This improvement indicates a positive shift in public awareness regarding ARI prevention. The activity successfully emphasized the importance of prevention efforts for ARI, focusing on promoting Clean and Healthy Living Behaviors (PHBS). Educating the community about ARI prevention is crucial in reducing the incidence of the disease. Regular health promotion activities, particularly those targeting community participation and practical steps for prevention, are vital for enhancing public health and preventing ARI, which remains a major cause of illness and death worldwide. The results highlight the effectiveness of health education in raising awareness and improving knowledge on preventing ARI.

Bullying is a psychosocial hazard that can occur in the school environment and may negatively affect students’ mental health, social interactions, and learning processes. Bullying can take various forms, including physical, verbal, and psychological actions that occur repeatedly and cause victims to experience emotional distress, decreased learning motivation, and feelings of insecurity at school. This Community Service Program (PKM) aimed to increase high school students’ knowledge and awareness regarding the dangers of bullying and its prevention through the principles of Occupational Safety and Health (OSH). The methods used in this activity included delivering educational materials through lectures, conducting question-and-answer sessions to assess students’ initial understanding, and facilitating interactive discussions to encourage active participation. Monitoring and evaluation were also conducted to assess the effectiveness of the activity. The results of the program indicated a significant improvement in students’ understanding and awareness of the forms, impacts, and prevention strategies related to bullying in the school environment. Students also demonstrated a more critical attitude toward bullying behavior and a greater awareness of the importance of creating a safe, healthy, and respectful school environment. The application of an OSH-based approach in bullying prevention is expected to strengthen the safety culture in schools and support the development of a conducive learning environment for all students.

This research benchmarks multiple machine learning (ML) algorithms for large-scale loan default prediction using a real-world dataset of 255,000 borrower records, where default cases represent only ~9–12% of total observations. The study addresses the persistent gap in comparative analyses of ML models that balance predictive accuracy, interpretability, and computational efficiency for credit risk assessment. Six algorithmic families were evaluated Logistic Regression, Random Forest, XGBoost, LightGBM, CatBoost, Artificial Neural Networks (ANN), and Stacked Ensemble—using standardized preprocessing, hybrid imbalance handling (SMOTE, class weighting, under-sampling), and comprehensive evaluation metrics (AUC, F1, Recall, Precision, PR-AUC, and Brier Score). Empirical results show Logistic Regression achieved the highest AUC of 0.732, outperforming nonlinear models under the baseline configuration, while LightGBM attained perfect recall (1.0) but low precision (0.116), indicating over-prediction of defaults. Gradient boosting models demonstrated robust calibration (Brier ≈ 0.114–0.116) and the best computational efficiency, with LightGBM showing the fastest training and lowest memory use. CatBoost exhibited strong recall but the slowest computation, and ANN underperformed on tabular data (AUC ≈ 0.56). The Stacked Ensemble delivered balanced results with AUC = 0.664 and improved overall stability. These findings confirm that boosting-based models, particularly LightGBM and CatBoost, offer superior scalability and calibration, whereas Logistic Regression remains a valuable interpretable baseline. The study concludes that effective default prediction requires integrating rebalancing, calibration, and threshold optimization to enhance recall and operational deployment reliability in large-scale credit ecosystems.

High-dimensional clinical data exhibit complex and non-linear relationships among patient attributes, where outcomes are often influenced by feature interactions rather than isolated variables. However, many existing machine learning models prioritize predictive performance while providing limited interpretability and insufficient insight into interaction structures. This study aims to address this limitation by developing an interpretable and robust framework for feature interaction mining in clinical data. We propose a hybrid tree–neural modeling framework that explicitly captures and ranks feature interactions while maintaining stable predictive performance. Tree-based ensemble models are employed to identify non-linear interaction patterns, while neural representations enhance learning flexibility and generalization. The framework integrates interaction importance analysis, cross-validation–based stability assessment, and evaluation across multiple data splits to ensure robustness and interpretability. Experiments conducted on a real-world high-dimensional clinical dataset demonstrate that the proposed approach achieves consistent predictive performance, with AUC values ranging from 0.628 to 0.641 across five cross-validation folds (mean AUC ≈ 0.633). Performance remains stable under varying train–test splits, indicating strong generalizability. Interaction analysis reveals that a small number of dominant feature interactions—such as age combined with length of hospital stay and medication count combined with diagnostic information—consistently contribute to model predictions, appearing in over 80% of validation folds. Ablation studies further confirm that removing interaction-aware components leads to noticeable performance degradation, highlighting their importance.  In conclusion, this study demonstrates that explicit feature interaction modeling enhances interpretability, stability, and generalization in clinical prediction tasks. The proposed hybrid framework provides a reliable foundation for developing trustworthy and transparent clinical decision-support systems

This study examines the application of Transparent Artificial Intelligence (AI) for fraud detection in public welfare programs using publicly available administrative data. Persistent challenges in welfare governance such as misallocation, fraud, and data inaccuracy necessitate analytical frameworks that are both effective and explainable. The research aims to design and evaluate an interpretable anomaly detection system capable of identifying irregularities in welfare distribution while maintaining transparency and accountability. Methodologically, the study employs two unsupervised models Isolation Forest and Local Outlier Factor (LOF) to detect anomalies in sub-district-level welfare data, incorporating features such as population size, number of beneficiaries, and coverage ratio. An Explainable AI (XAI) framework integrating surrogate Random Forests, Permutation Feature Importance (PFI), and local linear surrogates (LIME-like) is applied to ensure interpretability of both global and local model behaviors. Findings reveal that receivers per 1000 population and percentage coverage are dominant determinants of anomaly scores. Fifteen administrative units were flagged for potential inconsistencies suggesting over- or under-reporting of beneficiaries. Cross-validation between IF and LOF models confirmed consistency in identifying anomalous regions. The integrated XAI explanations enhance transparency, enabling policymakers and auditors to trace the rationale behind detected anomalies. In conclusion, the proposed Transparent AI framework demonstrates that combining anomaly detection with interpretability tools can strengthen accountability and fairness in welfare administration. It offers a reproducible, ethical, and data-driven approach to social program monitoring, reinforcing public trust and supporting responsible AI governance.

Explainable artificial intelligence (XAI) has become a critical requirement in cybersecurity due to the high-stakes nature of security decision-making and the limitations of black-box learning models. This study investigates the construction of an explainable cybersecurity knowledge representation by leveraging standardized terminology from the NIST cybersecurity glossary. The primary problem addressed is the lack of transparent and semantically grounded reasoning mechanisms in existing AI-driven cybersecurity systems, which limits trust, accountability, and analyst adoption. To address this challenge, we propose a NIST-based semantic knowledge graph that embeds explainability directly into its ontology structure and reasoning process. The proposed framework systematically extracts definitional entities and relations from NIST glossary entries to construct a domain ontology and a multi-relational knowledge graph. A rule-based semantic relation extraction method is employed to ensure faithful, interpretable, and reproducible reasoning paths. The resulting knowledge graph contains over 3,000 cybersecurity concepts and approximately 27,000 semantic relations, covering hierarchical, associative, dependency, and mitigation semantics. Experimental evaluation demonstrates that the proposed approach achieves a high level of explainability, with 92.4% of reasoning outcomes being fully traceable and only 1.4% classified as non-traceable. Most explainable reasoning paths are limited to two or three hops, indicating an effective balance between inferential depth and human interpretability. Structural analysis further confirms the presence of meaningful hub concepts that support multi-hop semantic inference. These results confirm that ontology-driven, standard-based knowledge graphs provide a robust foundation for explainable cybersecurity intelligence. The study concludes that explainability-by-design, grounded in authoritative standards, offers a viable and trustworthy alternative to opaque AI models for cybersecurity applications.

Inconsistent terminology across cybersecurity frameworks undermines global governance and interoperability. The National Institute of Standards and Technology Cybersecurity Framework (NIST CSF 2.0) and ISO/IEC 27001:2022 share similar objectives but diverge semantically in defining risk, control, and resilience. This semantic gap causes difficulties in compliance mapping and automated policy translation. Research Objectives: This study aims to analyze the semantic similarity and divergence between NIST and ISO/IEC 27000 terminologies, identify conceptual structures influencing interoperability, and propose an AI-assisted foundation for harmonizing cybersecurity language globally. Methodology: A mixed-method semantic comparative design integrates Natural Language Processing (NLP) and ontology mapping. Using the nist_glossary.csv dataset and ISO vocabularies, terms were normalized and analyzed via cosine similarity using sentence-transformer embeddings. Ontological alignment was visualized through the Semantic Threat Graph (STG) and validated by certified experts using Cohen’s Kappa reliability tests. Results: From 672 term pairs, results show 40.9% high semantic equivalence, 38.8% partial overlap, and 20.3% semantic divergence. Strongest alignment appears in “Protect” and “Identify” domains, while divergences occur in governance and recovery-related terms. Ontology mapping revealed three conceptual clusters—Risk Governance, Technical Safeguards, and Organizational Readiness. Conclusions: Findings confirm a 79.7% total semantic alignment, indicating strong potential for harmonizing global cybersecurity standards. The study contributes an empirical model combining computational linguistics and AI-based ontology mapping to establish semantic interoperability, enabling unified cybersecurity governance and AI-driven compliance automation. Keywords: Semantic Interoperability; Ontology Mapping; Cybersecurity Frameworks; Terminology Alignment; AI Harmonization

This community service aims to provide training on the use of the Joint Marketing Program (eJMP) application module to micro and small industry players in the  Surabaya city, so that marketing of MSI products can be carried out flexibly without being limited by space, place and time, so that marketing can reach a wider network and ensure the sustainability of MSI businesses in the future. This community service activity uses a qualitative descriptive approach by photographing the real conditions of marketing management of micro and small industries, then providing eJMP module training to 20 micro and small industry sector players as well as owners who are domiciled in the Surabaya city. The eJMP module training method is implemented through four stages, namely: (1) identifying the suitability of the eJMP module content to the marketing needs of MSI businesses, (2) determining the eJMP module training model with its marketing literacy priorities, (3) elaborating the eJMP content with MSI marketing literacy materials, and (4) implementing the eJMP module training for micro and small industry players. The results of this training indicate that micro and small industry players still experience difficulties in marketing MSI products, therefore optimizing the use of the eJMP application can help micro and small industry businesses to optimize marketing together, flexibly and effectively. This eJMP application module training includes material on the important role of joint marketing, optimizing the role of cooperatives, an introduction to the eJMP application and joint marketing simulations through the eJMP application. This training, which is carried out in a structured and systematic manner for micro and small industry players, is expected to be able to improve flexible and effective joint marketing and ensure the sustainability of MSI businesses in the future .

The conversion of agricultural land to non-agricultural land continues to increase along with the pressures of urbanization, industrialization, and settlement expansion. This condition poses risks to food security, environmental sustainability, and farmer welfare. This article reviews literature based on 25 abstracts/research results on LP2B in Indonesia to map policy implementation patterns, the relationship between LP2B and regional spatial planning, inhibiting factors, and the direction of policy strengthening. The method used is a narrative review with thematic synthesis of normative legal studies, juridical-empirical, qualitative, mixed methods, and spatial-quantitative approaches. The results of the review indicate: (1) LP2B is highly dependent on the harmonization of spatial planning policies, especially RTRW/RDTR and licensing mechanisms based on KKPR-OSS; (2) many regions are still stuck at the land inventory-identification stage, not yet reaching the determination and operational protection through LP2B Regional Regulations; (3) dominant obstacles include regulatory asynchronous, weak law enforcement, minimal cross-agency coordination, limited data by name by address, suboptimal socialization, and conflicts of interest in non-agricultural development; (4) incentive-disincentive instruments have not been implemented consistently, although socially farmers tend to accept LP2B protection; and (5) quantitative evidence at the national level shows that LP2B policies have a positive effect on the percentage of rice fields, despite being suppressed by population density and real estate sector growth. This article emphasizes the need for an integrated spatial governance approach, strengthening regional institutions, and designing policies that are socially and environmentally just to ensure that LP2B is effective in maintaining regional food security.

Landslides in the Giritengah Catchment Area are influenced by several factors, including geological conditions, rainfall intensity, geomorphology, soil characteristics, and inappropriate land use practices, all of which affect regional spatial planning and environmental stability. This study presents a literature review that analyzes landslide vulnerability, evaluates the impact of land use changes, and proposes integrated Soil and Water Conservation Techniques (SWCT) to support sustainable land management. The analysis applies Geographic Information System methods using thematic map overlays such as rainfall distribution, slope gradient, geological structure, and land use patterns. The results show that areas categorized as having high landslide vulnerability cover 44.02% or approximately 158.69 hectares of the catchment area, while areas with very low vulnerability account for only 0.12% or about 0.79 hectares. Land use conversion, particularly mixed dryland agriculture, has increased landslide risk by reducing slope stability and increasing surface runoff. To address this issue, conservation strategies are recommended, including vegetative measures such as greening 38.51 hectares in settlement areas and implementing agroforestry systems across 218.48 hectares. In addition, structural measures such as three dam retainers and twenty gully plugs are proposed in both protected and cultivation zones to support disaster mitigation and align with regional spatial planning policies.

This research aims to analyze the quality of electronic services (E-Service Quality) on user satisfaction of the DANA digital wallet application in the West Jakarta area. The evolution of financial technology (fintech) in Indonesia has encouraged rapid growth in the use of digital wallets, including DANA which is recorded to have more than 200 million users by 2024. However, this rapid growth is still marred by a number of user complaints regarding system reliability, service response speed and transaction security. Therefore, this study is important to evaluate how much e-service quality dimensions influence user satisfaction levels. The research method used is a quantitative approach with an associative type of research. Data was collected through questionnaires from 100 respondents who were active users of the DANA application in the West Jakarta area using a purposive sampling technique. Data analysis was carried out using SPSS software through validity tests, reliability tests, and simple linear regression analysis. The research results show that E-Service Quality has a positive and significant effect on user satisfaction of the DANA application with a coefficient of determination (R Square) of 0.907, which means that 90.7% of the variation in user satisfaction can be explained by the E-Service Quality variable, while the remaining 9.3% is influenced by other factors outside the research model. The results of the significance test (t test) show a significance value (Sig. < 0.05) which indicates that the influence of E-Service Quality on user satisfaction has been proven to be statistically significant. The results of this study are expected to serve as evaluation material for DANA application managers in improving the quality of digital services, particularly in terms of efficiency, system reliability, security, and user responsiveness. Furthermore, this research is expected to provide theoretical contributions to the development of studies in the field of information systems and digital service management.

The R05 Community Service Program (KKN), Subgroup 1 in Kalikatir Village, Gondang District, Mojokerto Regency, aims to implement hydram pump technology as an environmentally friendly and energy-efficient irrigation solution. This technology is designed to meet the water needs of 100 hectares of banana plantations, especially during the dry season. The implementation method includes initial surveys, design, manufacture, installation, and testing of the hydram pump, involving the participation of Kalikatir villagers. The results show that the pump is capable of lifting water to a height of 30 meters with 70% efficiency, although it has not yet reached the daily target. This technology has been proven to reduce operational costs and increase agricultural productivity. It is hoped that in the future, this technology can be further developed to improve its efficiency and sustainability.

Soil strength characteristics are strongly influenced by its physical and mechanical properties, one of which is shear strength. Soil shear strength is affected by cohesion (c), internal friction angle (ϕ), and soil moisture conditions. In open-pit mining conditions, soil moisture content is greatly influenced by rainfall and water seepage, which can increase the degree of saturation within the soil mass. An increase in the degree of saturation generally leads to a rise in pore water pressure, thereby reducing the effective normal stress and resulting in a decrease in soil shear strength. This study aims to determine the effect of the degree of saturation on soil shear strength. This research employs a quantitative method to analyze the influence of the degree of saturation under three conditions (natural, dry, and saturated) on soil shear strength through laboratory testing using the direct shear test. The tests conducted include soil physical properties testing in accordance with SNI 1965-2008, specific gravity testing based on SNI 1964-2008, and soil shear strength testing following SNI 3420-2016. The results indicate that the average degree of saturation under natural conditions is 64.63% with a cohesion value of 7.4 kN/m², under dry conditions is 33.18% with a cohesion value of 8.2 kN/m², and under saturated conditions is 83.08% with a cohesion value of 3 kN/m². It can be concluded that a higher degree of saturation or more saturated soil samples result in lower cohesion values, whereas a lower degree of saturation or drier soil samples lead to higher cohesion values.

This study aims to analyze the effect of information technology (IT)-based learning media on improving students' academic performance. With the advancement of digital technology, the use of IT-based media such as interactive presentations, educational videos, Learning Management Systems (LMS), and online quiz applications has become part of modern teaching strategies. This study uses a quantitative approach with a quasi-experimental method. The subjects of the study were secondary school students divided into experimental and control groups. The instruments used include learning achievement tests to measure academic performance and observation sheets to assess the implementation of IT media usage. Data were analyzed using t-tests and simple regression analysis. The results show a significant difference in academic performance between students who used IT-based learning media and those who used conventional methods. The experimental group showed a higher average score compared to the control group. These findings indicate that the use of IT-based learning media, when planned and implemented systematically, can improve students' motivation, engagement, and understanding of learning materials. Therefore, the integration of information technology into the learning process is recommended as an innovative strategy to enhance the quality of education.

This study aims to formulate a Blue Ocean Strategy to enhance business competitiveness through a SWOT analysis approach. The research was conducted using a descriptive qualitative method. Primary data were obtained through interviews with competent parties to identify the internal and external factors of the business, while questionnaires were used as supporting data to capture respondents’ perceptions of the identified factors. The interview results served as the basis for developing the IFAS and EFAS matrices to determine the business position within the SWOT matrix. Furthermore, the SWOT analysis results were used to formulate alternative strategies aimed at creating new value in line with the Blue Ocean Strategy concept. The questionnaire results indicate that respondents’ perceptions tend to support the internal and external factors identified through interviews, thereby strengthening the analytical findings. Based on the results, it can be concluded that formulating a Blue Ocean Strategy through SWOT analysis provides a more innovative and competitive strategic direction. The resulting strategies are expected to help businesses create sustainable competitive advantages and avoid direct competition in saturated markets.

Advances in information technology have driven the transformation of banking services towards digitalization through mobile banking. Bank Central Asia (BCA), one of the largest private banks in Indonesia, offers m-BCA services to facilitate quick, practical, and efficient customer transactions. However, issues such as delayed notifications, system disruptions, and login problems still exist. This study aims to evaluate m-BCA user satisfaction using the PIECES Framework, which consists of six dimensions: Performance, Information, Economy, Control and Security, Efficiency, and Service. A descriptive quantitative approach was used, with a questionnaire distributed to 105 active m-BCA users in South Jakarta. Data were analyzed using mean values to assess satisfaction levels for each dimension, and validity and reliability tests were conducted. The results showed average scores of 4.02 for Performance, 4.08 for Information, 4.08 for Economy, 4.18 for Control and Security, 4.20 for Efficiency, and 4.09 for Service. The overall score of 4.10 falls into the "Satisfied" category. The highest score was for Efficiency, indicating strong support for users’ banking activities, while the Performance dimension scored lower, suggesting room for improvement. Overall, users are satisfied with m-BCA, but system performance improvements are needed for service stability and sustained satisfaction.

This study aims to evaluate the level of user satisfaction with the user interface of the Academic Information System (SIAKAD) at Esa Unggul University using the End User Computing Satisfaction (EUCS) method. This method assesses user satisfaction based on five key dimensions: content, accuracy, format, ease of use, and timeliness. The study employed a quantitative descriptive approach by distributing questionnaires to active Esa Unggul University students as primary system users. The collected data were analyzed using SPSS software to test validity, reliability, and the relationships between variables that influence user satisfaction with the SIAKAD interface. The results show that, in general, users are quite satisfied with the SIAKAD interface, particularly in the ease of use and accuracy dimensions, which obtained the highest scores. This indicates that usability and information accuracy are the dominant factors in creating a positive user experience. However, the timeliness and content dimensions still require further improvement, as they were rated as less optimal in providing fast and comprehensive information. These findings highlight the importance of an intuitive, efficient, and informative interface design in enhancing user satisfaction. This research is expected to serve as a reference for Esa Unggul University in developing and improving its Academic Information System to become more effective, efficient, and user-friendly. Evaluating user satisfaction through the EUCS approach provides valuable insights for system developers to refine the interface, improve information quality, and enhance system responsiveness. Thus, the results of this study are expected to contribute to improving academic service quality and supporting the digitalization of education at Esa Unggul University.

The increasing integration of internet technology in educational institutions requires structured network governance to ensure that digital resources support academic activities effectively. Unrestricted access to online platforms often leads to non-academic usage such as online gaming and social media engagement during instructional hours, which may reduce learning concentration and degrade network performance. This research develops and evaluates a network access control simulation using a MikroTik RouterBoard RB951Ui-2HnD device. The system applies firewall filtering mechanisms, hotspot-based authentication, and bandwidth allocation strategies through Simple Queue configuration. Network segmentation is implemented to differentiate teacher and student access privileges. The study adopts a Research and Development (R&D) approach to design, configure, test, and evaluate the proposed system. Testing results indicate that the firewall configuration successfully restricts access to selected online games (Mobile Legends, Clash of Clans, Roblox) and social media platforms (YouTube, TikTok, Shopee, Instagram, Telegram). Furthermore, bandwidth management demonstrates effective traffic prioritization, ensuring more stable allocation for teacher accounts in accordance with configured maximum limits. The findings confirm that structured firewall and bandwidth policies can improve network discipline, enhance performance stability, and support a controlled digital learning environment in schools.

This study aims to redesign the raw material yarn warehouse layout at PT. XYZ using the Class Based Storage method to improve storage and retrieval efficiency. The main problem identified in the warehouse is random item placement, resulting in relatively long retrieval times of approximately 10–15 minutes per pallet. This research applies a descriptive quantitative approach using a case study method. The data used consists of inbound, outbound, and inventory records of yarn raw materials from November 2024 to April 2025. The analysis was conducted using the FSN (Fast Moving, Slow Moving, and Non-Moving) method through the calculation of consumption rate and average stay, combined with ABC classification to determine storage priority. The results show that 9 types of yarn are classified as Class A, 11 types as Class B, and 11 types as Class C. Based on this classification, a new warehouse layout was designed by placing Class A items near the input-output area, Class B items in the middle area, and Class C items in the back area of the warehouse, thereby improving storage efficiency and reducing retrieval time.

This study aims to redesign the raw material yarn warehouse layout at PT. XYZ using the Class Based Storage method to improve storage and retrieval efficiency. The main problem identified in the warehouse is random item placement, resulting in relatively long retrieval times of approximately 10–15 minutes per pallet. This research applies a descriptive quantitative approach using a case study method. The data used consists of inbound, outbound, and inventory records of yarn raw materials from November 2024 to April 2025. The analysis was conducted using the FSN (Fast Moving, Slow Moving, and Non-Moving) method through the calculation of consumption rate and average stay, combined with ABC classification to determine storage priority. The results show that 9 types of yarn are classified as Class A, 11 types as Class B, and 11 types as Class C. Based on this classification, a new warehouse layout was designed by placing Class A items near the input-output area, Class B items in the middle area, and Class C items in the back area of the warehouse, thereby improving storage efficiency and reducing retrieval time.