Publication Search

This research was conducted to describe the condition of displaced communities who experience limitations in meeting basic needs, such as decent housing, access to education, and health services. Socio-economic inequality is the main factor that affects the quality of life of vulnerable groups, including children, adults, and the elderly. The Rumah Asa program is designed as an effort to provide protection, psychological support, and economic empowerment through skills training and health services according to needs. The research used a qualitative approach through interviews, field observations, and questionnaire dissemination to gain an in-depth understanding of the respondents' living situation. The research population consisted of displaced individuals who had the potential to become beneficiaries of the program. The data obtained were analyzed to identify patterns of vulnerability and intervention needs. The results showed that each respondent faced unstable socio-economic conditions, with limited income, lack of family support, and high health risks. The discussion showed that neglect is multidimensional and requires comprehensive interventions that include material, emotional, social, and health aspects. The conclusion of the study confirms that the Rumah Asa Program has great potential as a model of effective social intervention in improving the quality of life of vulnerable groups, as long as it is supported by the collaboration of the community, government, and social institutions.

The development of digital technology has driven significant changes in modern learning methods by integrating various multimedia media. However, multimedia's ability to facilitate learning depends largely on the extent to which its presentation aligns with the principles of learning psychology, particularly those outlined in the Cognitive Theory of Multimedia Learning (CTML). This study aims to examine the role and effectiveness of multimedia in transforming modern learning methods by combining the results of recent empirical research from 2020 to 2024. This study used the Systematic Literature Review (SLR) method by analyzing 22 journal articles obtained from several databases such as Scopus, Web of Science, ScienceDirect, Google Scholar, and Sinta. Research shows that the use of interactive multimedia helps increase student enthusiasm for learning, participation, understanding of concepts, and the ability to remember course material. However, disorganized multimedia design can add unnecessary mental burden, thereby reducing learning effectiveness. These findings suggest that the successful use of multimedia depends not only on the level of technological advancement but also on the quality of learning design that applies cognitive theory. This study provides a comprehensive summary of the latest research and provides tangible benefits for educators in creating effective digital learning content.

Fixed asset management is a crucial component in supporting the performance of local governments. However, the Polewali Mandar Regency Government still faces obstacles in managing assets conventionally, such as the risk of recording errors, duplicate data, and difficulties in field data verification which is time-consuming. This study aims to design and build a Web-Based Fixed Asset Management Information System integrated with Quick Response Code (QR Code) technology as a digital solution for real-time asset data collection, tracking, and monitoring. The approach taken for system development is known as the Waterfall approach, encompassing the phases of analyzing requirements, system design, execution, evaluation, and ongoing support. The creation of the system was carried out utilizing the PHP coding language, the MySQL database system, and Tailwind CSS to achieve a mobile-friendly interface. Data collection techniques were conducted through observation, interviews, and literature studies at the General Affairs Division of the Regional Secretariat of Polewali Mandar Regency. The result of this research is a fixed asset management information system featuring the generation of unique QR Code labels for each asset, category and location management, and reporting features divided into three access levels: Admin, Operator, and Verificator. Based on the system testing results, an average score of above 4.00 was obtained for indicators of ease of use (user-friendly), access speed, and information accuracy. In conclusion, the implementation of this QR Code-based system is proven to increase the efficiency of the asset identification process in the field, minimize manual input errors, and improve accountability in regional asset management in Polewali Mandar Regency.

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

The rapid development of technology in the era of the Industrial Revolution 4.0 has driven the education sector to continuously adapt to the evolving demands of digital-based industries. One of the key technological innovations supporting this transformation is the Internet of Things (IoT), which enables data acquisition, real-time monitoring, and remote control of systems through internet networks. In response to these developments, a community service program was conducted to enhance the understanding and technical skills of students at SMK Negeri 1 Sindang through the provision and utilization of an IoT Trainer Kit Simulator as a practical learning medium. This activity aimed to bridge the gap between theoretical knowledge and industry-relevant technological applications by introducing students to hands-on IoT system implementation. The program included demonstrations and guided practice on the use of sensors, microcontrollers, and web-based monitoring platforms to simulate real-world industrial scenarios. The results indicate that students showed high enthusiasm and active participation throughout the activity. Moreover, participants were able to grasp the fundamental concepts of IoT systems, understand component integration, and recognize the relevance of IoT applications in supporting automation and digital transformation. Overall, this community service activity contributed positively to strengthening students’ digital competencies and preparedness for the demands of the contemporary industrial and technological landscape.

Teachers’ managerial competence plays a crucial role in ensuring effective and relevant learning, particularly in vocational education. Teachers are required not only to master subject matter but also to plan, manage, and evaluate learning through well-structured and contextual learning tools. This Community Service activity aimed to strengthen teachers’ managerial competence through training on the development of learning tools using a deep learning approach at SMK Muhammadiyah 2 Tangerang Selatan. The implementation method included conceptual material delivery, practical training, and mentoring in designing learning tools. The deep learning approach was applied to encourage learning designs that emphasize deep understanding, critical and reflective thinking, and alignment with workplace demands. The results showed an improvement in teachers’ understanding and skills in developing more systematic, innovative, and adaptive learning tools aligned with 21st-century competencies. This activity contributed positively to strengthening teachers’ roles as learning managers and supporting the improvement of learning quality in vocational schools.

This community engagement program addresses the limited digital marketing utilization of Be Bloomy Bouquets, a creative knitting business, within the MBKM Entrepreneurship framework. The program aims to design and implement adaptive digital marketing strategies to enhance brand visibility, competitiveness, and business sustainability. Using a Participatory Action Research (PAR) approach, the program was conducted from October to November 2025 through preparation, implementation, and evaluation stages. The results indicate that digital marketing assistance via Instagram and TikTok significantly increased audience reach, customer interaction, and brand awareness, while marketplace utilization still requires further optimization. The discussion highlights that integrating handmade product creativity, digital branding strategies, and participatory reflection fosters entrepreneurial behavior change and strengthens local leadership capacity. In conclusion, the program generates not only technical improvements in marketing performance but also social transformation through enhanced digital literacy, independence, and local leadership. Future recommendations emphasize content consistency, production management, and sustainable digital marketing strategies.

Micro, Small, and Medium Enterprises (MSMEs) play a vital role in supporting the Indonesian economy, especially in rural areas where they contribute significantly to employment and local income. Sait Buttu Saribu Village in Simalungun Regency possesses considerable potential in the agricultural, tourism, and culinary sectors, which can be developed through strong MSME activities. Nevertheless, many local MSMEs continue to experience challenges related to limited promotion, weak branding, and restricted market access. This study aims to analyze visit-based and promotional strategies for MSMEs as an effort to strengthen the village economy and enhance business competitiveness. The research methods consist of a literature review of relevant previous studies and field observations conducted through community service activities in the village. The findings indicate that industrial visits, digital promotion via social media platforms, the utilization of Google Maps for location visibility, and branding that highlights local wisdom are effective strategies for expanding market reach and increasing MSME competitiveness. Through strong synergy among the village government, MSME actors, and the local community, MSMEs in Sait Buttu Saribu Village can grow more optimally and contribute to sustainable economic development and tourism.

Information systems are an important element in the business world that helps businesses increase work efficiency and reduce human error. In practice, many businesses still produce financial reports manually. Manual preparation of financial reports is inefficient and tends to have a higher potential for delays, lateness, or errors in data entry. This makes the financial reports presented inaccurate and unreliable as a basis for making decisions. To address this problem, a community service program was implemented by designing an accounting system using Microsoft Access, which provides various features that can help users in data processing. The method carried out starts with observation, system design, and evaluation by the partner. The result of implementing this program is that the system designed in Microsoft Access successfully accelerated the work process for partners, making the preparation of financial reports more efficient and timely. The financial reports presented also became more accurate and reliable.      

This research aims to describe the process of transforming Micro, Small, and Medium Enterprises (MSMEs) toward a digital economy through QRIS (Quick Response Code Indonesian Standard) training and the creation of creative banners as promotional media in Batu Karang Village, Karo Regency. Digital transformation has become an essential need for MSMEs to adapt to changes in consumer behavior and rapid technological development. This study employs a descriptive qualitative approach focusing on training materials and the implementation process, without using quantitative data or interview results. The findings indicate that QRIS training provides MSME actors with conceptual and practical understanding of digital payment systems that are efficient, secure, and convenient. In addition, creative banner development functions as a visual promotional tool that strengthens business identity and enhances consumer attraction. The integration of QRIS with creative banners creates synergy between digital payment systems and promotional strategies that are relevant to the conditions of rural MSMEs. Overall, this research demonstrates that digital-based training combined with creative promotional media can serve as an effective strategy to enhance MSME readiness in facing the digital economy era in a sustainable manner.

Employee work discipline is one of the important aspects of human resource management, especially in service companies that heavily rely on their employees' performance. PT CAI, as an event organizer company, still faces issues related to employee work discipline, such as tardiness, absenteeism without notice, and low consistency in completing work responsibilities. This activity is a form of Community Service by students aimed at increasing employees' understanding and awareness of the importance of work discipline through educational and practical approaches. The implementation methods of the activity include observation, interviews, discussions, documentation, and the implementation of an educational program in the form of work discipline posters as well as providing recommendations for a simple reward and punishment system. The results of the activity show that internal educational media serve as an effective visual reminder in increasing employee awareness of punctuality and work responsibility. This community service activity is expected to support the improvement of employee performance, service quality, and the operational sustainability of PT CAI.

The community service program in Dusun Bendrong aimed to foster environmental awareness through the planting of timber and fruit seedlings as a response to declining forest quality and reduced water availability caused by vegetation loss. This program sought to enhance community participation in forest conservation while strengthening local wisdom related to environmental stewardship. The activity was conducted in three stages: pre-activity observation and coordination with the Village Head and community leaders, joint planting of 14 seedlings by Student Community Service (KKM) participants and local residents, and monitoring and evaluation to assess implementation and participant understanding. The results showed that all seedlings were successfully planted, with high levels of participation from both students and community members. The activity increased awareness of forest conservation and highlighted the importance of collective action in maintaining environmental sustainability. Timber trees contributed to forest restoration, improved water absorption, and reduced erosion risk, while fruit trees provided additional economic and social benefits for the community. Overall, this participatory approach proved effective as a sustainable model for community service programs that integrate environmental conservation and community empowerment.

An earthquake occurs when energy is suddenly released within the earth’s layers, potentially causing loss of life and environmental damage. One factor contributing to the high impact of earthquakes is the lack of student understanding and inadequate education on disaster preparedness. This study aimed to assess earthquake disaster management education at the Nur Adia Junior High School Education Foundation, Tanjung Selamat, Deli Serdang. A quantitative pre-experimental design with a one-group pretest and posttest was applied, involving 63 eighth-grade students. Data were collected through questionnaires to measure students’ knowledge before and after the educational intervention on earthquake disaster management. The results indicated that before the education, 69.8% of students rarely received information about earthquake causes, 61.9% had never participated in school earthquake evacuation simulations, and 55.5% had never practiced evacuation drills. After the educational intervention, knowledge improved, with 66.6% of students reporting that the program significantly increased their understanding of earthquakes. Statistical analysis showed a significant difference between pretest and posttest scores (Sig. 2-tailed = 0.000 < 0.05), confirming the effectiveness of the intervention. The study concluded that education on earthquake disaster management can enhance students’ knowledge and preparedness. It is recommended that schools implement regular educational programs and disaster simulation exercises to cultivate students’ readiness and promote a culture of disaster preparedness within the school environment.

The postpartum period is a crucial phase for mothers to recover after childbirth. One of the common problems is perineal wounds, caused either by episiotomy or spontaneous rupture, which require proper care to prevent infection and accelerate healing. This case study aimed to provide midwifery care for Mrs. M, 28 years old, P3A0H3, with a second-degree perineal wound at PMB Bd. Silvi Ayu, S.Keb. The SOAP approach was applied through assessment, diagnosis, intervention, implementation, and evaluation over five days (June 12–16, 2025). Interventions included education on perineal hygiene, encouragement of nutritious food intake, light mobilization, and perineal wound care using boiled binahong leaves. The results showed decreased pain, reduced edema, a dry wound, and complete healing on the fifth day, with the REEDA score decreasing from 11 to 0. The discussion emphasized that flavonoids, saponins, and ascorbic acid in binahong leaves contribute to tissue regeneration and faster healing. Limitations of this study included the short monitoring period, limited sample, and reliance on maternal compliance. In conclusion, binahong leaf decoction was found to be effective, practical, and able to enhance maternal independence in wound care. This study is expected to serve as a reference for midwifery practice and as a basis for further research with a wider scope.

The development of information technology requires educational institutions to adapt so that administrative processes and internal management can run more effectively and efficiently. Islamic boarding schools as modern Islamic educational institutions are also not exempt from this need. This Community Service Program (PKM) aims to optimize computer networks and improve the understanding of pesantren staff regarding folder sharing systems, printer sharing, and data management ethics at Pondok Pesantren Modern Darel Azhar, Rangkasbitung, Banten. Implementation methods include initial observation, network design and installation, material delivery and training, data sharing system implementation, and technical evaluation. The results show that the pesantren now has a more organized, stable, and optimally utilized local area network (LAN). In addition, administrative staff gained a better understanding of computer network basics, data sharing systems, and digital data management ethics. This activity has a positive impact on the efficiency of pesantren administrative management and can serve as a model for implementing computer network technology in modern pesantren environments.

This study aims to introduce the convenience of digital transactions through socialization of the use of the Quick Response Code Indonesian Standard (QRIS) to residents of Marihat Bukit Village. This activity was motivated by the low public understanding of the use of non-cash transactions, particularly QRIS, which is an innovative integrated digital payment system from Bank Indonesia. Through socialization and direct practice, residents were introduced to how to use QRIS in various daily transactions, such as shopping, paying for services, and other local economic activities. The results of the activity showed an increase in public understanding and interest in the use of digital transactions that are easier, faster, and safer. It is hoped that this activity will encourage digital financial inclusion in rural areas and support government programs to expand literacy and the application of financial technology in the community. Furthermore, active community participation in this activity shows great potential to reduce dependence on cash transactions and encourage digital transformation at the village level. This activity is also expected to accelerate the transition to a more inclusive and digital-based society.