Publication Search

Object detection plays a crucial role in intelligent transportation systems, particularly for outdoor traffic monitoring applications that require accurate and real-time performance under limited computational resources. Recent developments in YOLO-based architectures have introduced multiple model variants; however, their practical performance under constrained training conditions remains insufficiently explored. This study presents a comparative evaluation of YOLOv5, YOLOv7, and YOLOv8 for outdoor traffic object detection using a real-world dataset and identical experimental settings. The main objective of this research is to analyze the robustness and detection quality of different YOLO variants when trained with a limited number of epochs, reflecting practical deployment scenarios. All models were trained and evaluated using the same dataset, preprocessing pipeline, and hardware configuration to ensure a fair comparison. Performance evaluation was conducted using multiple metrics, including precision, recall, mAP@50, Precision–Recall curves, area under the curve (AUC), and peak F1-score. Experimental results indicate that YOLOv5 outperformed YOLOv7 and YOLOv8 in terms of overall detection stability and robustness. The merged Precision–Recall analysis shows that YOLOv5 achieved a higher effective AUC and superior mAP@50, reflecting better global detection performance. In addition, YOLOv5 exhibited a higher peak F1-score, indicating a more balanced trade-off between precision and recall. In contrast, YOLOv7 and YOLOv8 showed performance degradation under limited training conditions despite their more advanced architectures. These findings suggest that YOLOv5 remains a reliable and efficient solution for outdoor traffic object detection, particularly in resource-constrained environments. The study highlights the importance of comprehensive evaluation metrics and practical experimental settings when selecting object detection models for real-world applications.

 Low student thesis completion productivity is a challenge in higher education, particularly at UIN Palangka Raya. Thesis writing requires self-regulation skills and time discipline to enable students to complete their final assignments effectively and on time. This study aims to analyze the role of self-regulated learning and time discipline in improving the thesis completion productivity of final-year students. The study used a qualitative approach with a case study design of five final-year students who were in the process of completing or had completed their theses. Data collection techniques included in-depth interviews, limited observation, and documentation. The data were then analyzed using the Miles and Huberman interactive model through the stages of data reduction, data presentation, and conclusion drawing. The results indicate that self-regulated learning plays a role in helping students plan goals, control motivation and emotions, and conduct consistent self-evaluation. Time discipline has been proven effective in reducing procrastination through the implementation of daily schedules, prioritization, and distraction management. Therefore, the integration of self-regulated learning and time discipline is an important strategy in increasing the thesis completion productivity of students and supporting sustainable academic success.

This study aims to identify the learning needs of deaf students in internship programs, examine the challenges they face, develop appropriate solutions, and design as well as evaluate a visual module-based learning model to improve their work skills. The study used a Research and Development (R&D) approach with a 4D model: Define, Design, Develop, and Disseminate. The participants included deaf students from special needs high schools (SMALB) involved in vocational internships, mentor teachers, and industry supervisors. Data were collected through observation, interviews, questionnaires, documentation, and focus group discussions, and analyzed using qualitative techniques supported by descriptive analysis. The findings indicate that deaf students require visual, structured, and easily understandable work instructions supported by symbols, color codes, and guidance materials. Major challenges include limited verbal communication, difficulty understanding instructions, and risks of procedural errors. To address these issues, a systematic and communicative visual module-based learning model was developed, incorporating collaborative support from schools and industry. The resulting model integrates planning, implementation, mentoring, and evaluation stages, and has proven feasible and effective in enhancing students’ independence, technical competence, and overall work readiness.

Interpersonal communication is the main foundation in the process of communication and interaction in life, including in the context of caregivers and children with disabilities at orphanages, enabling the creation of emotional closeness, also known as bonding. This study uses a qualitative approach with data collection methods through interviews, participatory observation, and documentation studies. The results of this study illustrate that the interaction process between caregivers and children with disabilities occurs through interpersonal communication involving the use of verbal and nonverbal communication. In addition, emotional closeness through the communication process does not form immediately, but rather through stages leading to emotional closeness established in the interaction between caregivers and children with disabilities at the Bhakti Luhur Orphanage in Baumata Village. Nevertheless, in the interaction process, there are certainly obstacles that disrupt the effectiveness of communication and interaction, namely limitations in resources, learning challenges in interacting with children with special needs, and communication problems such as miscommunication. However, all of these can be overcome by caregivers who strive to become parental figures for children with disabilities through evaluation processes and intensive approaches with each child.

This study aims to evaluate the impact of leadership education and training on organizational service effectiveness within the Tambrauw Regency Government, Papua. Leadership training is an important instrument in developing the competencies of Civil Servants to enhance leadership capacity, managerial skills, and public service quality. However, its implementation needs evaluation to determine its impact on organizational performance and service effectiveness. This research uses a qualitative approach with descriptive analysis. The analytical framework applied is the Kirkpatrick training evaluation model, covering reaction, learning, behavior, and results. Data collection was conducted through documentation studies, policy analysis, and literature review on civil servant development and public services. The results indicate that leadership training has a positive impact on improving civil servant competencies and service effectiveness. At the reaction level, participants showed high satisfaction with training materials and methods. At the learning level, there was improvement in leadership knowledge and skills. At the behavior level, participants demonstrated more professional work attitudes, better coordination, and improved decision-making. At the results level, training contributed to improved service quality, efficiency, and innovation. However, challenges remain, including limited resources, hierarchical bureaucratic culture, and weak policy support. Therefore, strong local government commitment is needed to enhance training quality and organizational support. This study contributes to public administration research and offers practical insights for policy development.

This study aims to develop Smartboard Book teaching materials based on Augmented Reality that are valid, practical, and effective for improving students' learning outcomes in the IPAS (Science) subject for grade IV at SDIT Al-Farabi. This study uses the Research and Development (R&D) method with the ADDIE (Analysis, Design, Development, Implementation, Evaluation) development model. The subjects of this study were grade IV students at SDIT Al-Farabi. Data collection techniques were conducted through expert validation questionnaires, response questionnaires, and learning outcome tests. The results indicate that the Smartboard Book teaching material was declared very valid, with material and test instrument validation percentages of 88% and media validation of 95%. The teaching material was also declared practical based on teacher and student responses. Furthermore, this media proved to be effective in improving students' learning outcomes with an N-gain score of 0.86, which falls into the high category. Based on these findings, it is recommended that teachers utilize Smartboard Book teaching materials based on Augmented Reality as an alternative medium in learning activities to create a more interactive and engaging learning environment.

Many senior high school students face significant difficulties in generating ideas, organizing thoughts, and selecting appropriate vocabulary when writing descriptive texts. Traditional teaching methods often limit creativity, making the integration of visual media crucial. Therefore, this study aims to develop creative poster-based learning module for teaching descriptive writing. A Research and Development (R&D) design was employed, adapting the ADDIE (Analysis, Design, Development, Implementation, Evaluation) model. However, due to time constraints, this research is strictly limited to the Analysis (Needs Analysis) and the initial Development (Prototype Development) stages. The participants for the needs analysis consisted of 22 senior high school students in Indonesia, selected through purposive sampling. Data were collected using an online needs analysis questionnaire. The findings indicate a strong student preference for visual support, which informed the design and creation of a poster-based learning module prototype intended to help students visualize concepts. The implications suggest that while the prototype aligns with student needs, further research is required to validate and test the product.

The PPA Symphony recorded 7,842 cases of violence against children by mid-2024, indicating the need for preventive efforts through early sexual education. Sexual education for children aims to improve their understanding of body awareness, body privacy, and self-protection from inappropriate behaviors. This community service activity aimed to increase students’ understanding of sexual education through interactive PowerPoint media. The activity was conducted at SD Negeri Gebang Surakarta on April 25, 2025, involving 63 students from grades 3, 4, and 5. The method used was an interactive lecture supported by PowerPoint media, storytelling, and mini games. Evaluation was conducted using pre-test and post-test questionnaires to measure students’ knowledge. The results showed an increase in the average knowledge score from 9.827 in the pre-test to 10.210 in the post-test. These findings indicate that interactive PowerPoint media is effective in improving students’ understanding of basic sexual education, particularly regarding body parts, body privacy, safe and unsafe zones, and strategies for refusing uncomfortable behaviors. Therefore, interactive learning media can serve as an effective educational strategy to strengthen early sexual education among elementary school students.

This community service program aims to enhance teachers’ competence in developing Higher Order Thinking Skills (HOTS)-based assessment items to support improved performance in the Computer-Based National Assessment (ANBK) at SMP Negeri Kletek. The main problem faced by the partner school is the limited understanding of teachers in designing assessment instruments that measure higher-order thinking skills, as well as insufficient ability to develop literacy- and numeracy-oriented questions aligned with ANBK characteristics. This condition has resulted in suboptimal learning evaluation quality and limited student readiness for national assessment. The program employed a Participatory Action Research (PAR) approach, emphasizing the active involvement of participants throughout all stages. The implementation included the planning stage through needs assessment and problem identification, the action stage through training and mentoring in HOTS-based item development, the observation stage through evaluation of participants’ work, and the reflection stage to identify achievements and challenges. Data were collected using pre-test and post-test, observation, and reflective discussions. The results indicate an improvement in teachers’ understanding and skills in developing HOTS-based items, as reflected in higher post-test scores. Teachers were able to design competency-based blueprints, contextual stimuli, and analytical, evaluative, and creative questions. This program effectively strengthens teachers’ professional competence and school readiness for ANBK.

This community service activity aims to enhance students’ competencies in business management, production, and operations through an industrial visit to PT. XYZ. The activity involved 65 students from the Entrepreneurship Study Program of Universitas Negeri Medan and was conducted in December 2025. The method used was experiential learning, allowing students to gain direct exposure to real industrial practices. The stages of the activity included preparation, implementation of the industrial visit, observation and data analysis, and evaluation and reflection. The results of the activity indicate significant improvements in five key areas: understanding of business management, production processes, operations management, development of soft skills, and increased entrepreneurial motivation and interest. Students were able to connect theoretical knowledge with real-world applications, thereby enhancing their analytical and practical abilities. In addition, the activity contributed to the development of communication skills, teamwork, critical thinking, and professional attitudes. Overall, this program demonstrates that industrial visits are an effective learning strategy in entrepreneurship education to produce competent, adaptive, and competitive graduates.

This study aimed to develop a flipbook-based multimedia teaching material for the Tennis Learning course. The research employed a Research and Development (R&D) approach using the ADDIE model as the development framework, which consists of five stages: (1) Analysis, (2) Design, (3) Development, (4) Implementation, and (5) Evaluation. The research subjects included students of the Physical Education, Health, and Recreation Study Program, Faculty of Sports and Health, Universitas Pendidikan Ganesha, as well as subject matter experts, instructional design experts, instructional media experts, and field practitioners. The product was evaluated through individual trials (3 students), small group trials (7 students), and large group trials (21 fourth-semester students). The validation results indicated feasibility percentages of 96% from the subject matter expert, 97% from the instructional design expert, 100% from the instructional media expert, and 97% from the field practitioner. Meanwhile, student trial results showed feasibility percentages of 97% in the individual trial, 96% in the small group trial, and 97% in the large group trial. Therefore, the flipbook-based multimedia teaching material on officiating in the Tennis Learning course was categorized as excellent and highly feasible for use as a supporting instructional resource in both classroom and field learning activities.

This study aims to develop flipbook-based multimedia instructional materials for the basic techniques of forehand and backhand volley in the Tennis Learning course. This research employed a Research and Development (R&D) approach using the ADDIE model, which consists of five stages: analysis, design, development, implementation, and evaluation. The validation subjects included a content expert, a learning media expert, an instructional design expert, and a field practitioner. Product trials were conducted with students of the Physical Education, Health, and Recreation Study Program, Faculty of Sports and Health, Universitas Pendidikan Ganesha, through individual trials involving three students, small-group trials involving seven students, and large-group trials involving twenty-one students. Data were collected using questionnaires with rating scales and were analyzed using descriptive qualitative and quantitative analysis in the form of percentages. The results indicated that the content expert validation achieved 98%, the media expert 93%, the instructional design expert 97%, and the field practitioner 98%, all categorized as very good. The individual trial obtained 97%, the small-group trial 98%, and the large-group trial 96%, all classified as very good. Therefore, the flipbook-based multimedia instructional materials on basic volley techniques are considered highly feasible for use as learning resources in tennis instruction.  

The Community Partnership Program (PKM) aims to improve the capacity of teachers at Rara Elementary School in understanding and implementing the National Assessment as an educational evaluation tool. The problems faced by partners are limited understanding of the concept of National Assessment and technical skills in managing instruments, analyzing data, and following up on assessment results. The methods used in this activity are participatory-based socialization and technical training involving teachers as active participants. Activities are carried out through material delivery, interactive discussions, and hands-on practice using assessment tools. The results of the activity showed an increase in teachers' knowledge and skills in understanding the National Assessment indicators, developing learning strategies in line with the Pancasila learner profile, and optimizing the use of assessment results to improve the quality of learning in the classroom. Thus, this PKM activity contributed to improving the quality of learning at Rara Elementary School while supporting the achievement of national education standards.

The results of the 2022 PISA indicate that science skills and interest in Indonesia are still low. One way to increase interest in science is by introducing inventor figure of science and techonology. However, alternative learning media that are communicative and relevant to adolescents' media consumption habits are needed. Therefore, this study aims to design a character design for an inventor in the field of science and technology for a Webtoon comic as an educational tool for adolescents aged 15–18. This study used qualitative and quantitative methods. The qualitative method was used to understand the needs and interests of the target audience and to gather information from the literature for scientific sources in designing the inventor character. The quantitative method was used as one of the character design evaluation criteria, based on voting results by adolescents aged 15–18. The character design used Marika Nieminen's principles: demographics, silhouette and shape, color, and characteristics. Several alternatives were used to generate character designs, which were then evaluated to determine the final design. The character design evaluation will be assessed using several variables within an evaluation framework.

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.  

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

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.

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.

Learning media is a tool that can be used to help students learn better and more efficiently. The media used in SMP Negeri 23 Pekanbaru is a teacher-centered picture/poster media so that students quickly get bored, and because of the limited media from the school. Most students prefer learning that involves them directly such as the element of games. The learning models used are discovery, PBL, and lecture models, and student learning activities are still lacking or less active in science learning. The purpose of this study is to develop learning media in the form of a cooperative-based snakes and ladders game with the Teams Games Tournament (TGT) type which aims to train student learning activities. The research method used is Research and Development (R&D) by implementing the ADDIE model which consists of five stages, namely Analyze, Design, Development, Implement, and Evaluation. Based on the validation results obtained, media experts were 94% with very feasible criteria, material experts were 92% with very feasible criteria, teachers gave a practicality assessment of 95% with very practical criteria, and students' responses were 85% with very interested criteria. This shows that the snakes and ladders media based on Teams Games Tournament (TGT) is very reasonable, very practical to use, and very interesting for students during the learning process. The results of observations on all student learning activities showed that 79% got a good interpretation.

This study aims to explore the effectiveness of group counseling services integrated with self-regulated learning (SRL) techniques in enhancing students’ learning motivation. Learning motivation is a crucial factor influencing academic achievement, yet many students still experience low motivation due to various internal and external challenges. The integration of SRL is considered beneficial as it encourages students to actively manage their learning processes through goal setting, self-monitoring, and reflective evaluation. This research employs a literature review approach by examining recent and relevant academic sources. The findings indicate that the application of SRL within group counseling contributes positively to students’ motivation, as reflected in increased participation, improved learning discipline, and stronger responsibility toward academic tasks. Furthermore, students demonstrate better ability in organizing their learning activities and maintaining consistency in achieving learning objectives. These results suggest that SRL-based group counseling can serve as an effective strategy for school counselors in supporting students’ academic motivation and engagement.