Publication Search

Predictive maintenance (PdM) plays a crucial role in modern industrial systems by minimizing downtime, reducing maintenance costs, and optimizing asset performance. However, many predictive models operate as “black box” systems, limiting transparency and making it difficult for operators to interpret their outputs. This study aims to integrate Explainable Artificial Intelligence (XAI) techniques with Remaining Useful Life (RUL) prediction models to improve both accuracy and interpretability. Various machine learning and deep learning approaches, including Support Vector Machines (SVM), Random Forest (RF), XGBoost, Long Short-Term Memory (LSTM), and Convolutional Neural Networks (CNN), are employed to predict RUL using real-time sensor data from rotating machinery. XAI methods such as SHAP, LIME, and attention mechanisms are applied to provide human-understandable explanations of model predictions. The models are evaluated based on accuracy, Root Mean Square Error (RMSE), and interpretability scores. The results show that XAI-enhanced models outperform traditional approaches in predictive performance while offering greater transparency. These explanations help maintenance engineers better understand the factors influencing predictions, thereby improving decision-making and trust in the system. Nevertheless, the integration of XAI introduces additional computational complexity, which may pose challenges for large-scale industrial implementation. Overall, this study highlights the potential of combining XAI with RUL prediction to develop more reliable, transparent, and effective predictive maintenance solutions.

Introduction: Additive Manufacturing (AM) has revolutionized the production of complex geometries, offering flexibility, customization, and precision across various industries. However, optimizing multiple process parameters simultaneously to enhance AM performance remains a significant challenge. This study focuses on improving both mechanical properties and surface quality by utilizing multi-objective optimization techniques. Literature Review: The research reviews existing approaches in AM optimization, highlighting the limitations of single-objective optimization and the potential of multi-objective evolutionary algorithms (MOEAs). Previous studies demonstrate the difficulty of balancing competing objectives, such as tensile strength and surface roughness, within AM processes. Materials and Method: This study employs NSGA-II, MOEA/D, and SPEA2 algorithms to optimize AM parameters like layer thickness, build orientation, and infill density. The optimization aims to improve mechanical performance, including tensile strength and impact resistance, while reducing build time and surface roughness. The methodology integrates experimental validation with computational predictions to evaluate the effectiveness of these algorithms. Results and Discussion: The optimization process yielded Pareto-optimal solutions that balanced mechanical strength and surface quality. The results demonstrated improvements in tensile strength and surface finish without significantly increasing build time. Trade-off analysis highlighted the inherent conflicts between mechanical performance and surface quality, allowing for better decision-making in industrial applications. The study contributes to the AM industry by offering a comprehensive optimization framework for improving both efficiency and product quality.

One of the most common problems faced by students is academic procrastination. This issue often leads to increased stress, poor academic performance, and difficulties in self-control. This study aims to examine academic procrastination behavior and evaluate the Solution Focused Brief Counseling (SFBC) approach as an alternative intervention. The research was conducted using a qualitative approach in the form of a literature study. Data were obtained from various relevant scientific sources, including national and international journals, reference books, and previous research findings published within the last ten years. The data were analyzed using a content analysis technique by organizing the information into several main themes, including the factors causing academic procrastination, its impact on students, and the effectiveness of SFBC implementation. The findings indicate that academic procrastination is influenced by internal factors, such as low learning motivation, weak self-control, and poor time management skills. External factors also include an unconducive learning environment and a lack of social support. In addition, the results show that the SFBC technique helps students reduce task-delay behavior by setting clear goals, strengthening self-potential, and developing realistic solution plans. Therefore, SFBC can be considered a relevant and effective approach in guidance and counseling services to address academic procrastination.

Hydrogen-based hybrid microgrid systems have emerged as a promising solution to enhance renewable energy integration and improve energy supply reliability. By combining renewable sources such as solar and wind with hydrogen production and storage technologies, these systems address the intermittency of renewable power while ensuring continuous energy availability. This study evaluates the techno-economic feasibility, environmental impact, and scalability of hydrogen-based hybrid microgrids, with a focus on cost-effectiveness and system performance under varying operating conditions. Simulation tools, including HOMER Pro and MATLAB Simulink, are used to model the system and conduct sensitivity analyses on hydrogen production costs and demand fluctuations. Key performance indicators such as Levelized Cost of Energy (LCOE), Net Present Value (NPV), and CO₂ emissions reduction are assessed. The results show that although the system requires a high initial investment, it becomes economically viable over time due to reduced operational costs and improved efficiency. Additionally, the system demonstrates significant environmental benefits, outperforming conventional fossil fuel-based systems in terms of emissions reduction. Sensitivity analysis further indicates that advancements in hydrogen production technologies could substantially enhance economic feasibility. Overall, hydrogen-based hybrid microgrids offer a reliable and low-carbon energy solution, supporting sustainable energy transitions and reducing dependence on fossil fuels.

The development of digital technology has encouraged Micro, Small, and Medium Enterprises (MSMEs) to utilize social media as the main instrument in building brand awareness. This study uses a qualitative descriptive approach with a field research type (field research). Data collection was carried out through observation, in-depth interviews with six sources (owner, financial manager, social media team, admin, crew, and customers), and documentation of the content of the TikTok account @mtm43surabaya. The results of the study show that: (1) MTMSBY43 implements a digital branding strategy with three main components, namely brand positioning as a social-based one-stop solution, a brand identity that focuses on a human-centered service approach, and a brand personality that reflects the character of local youth who are solution-oriented and socially concerned; (2) MTMSBY43 TikTok content is classified into three pillars, namely humanistic and realistic content (daily vlogs & live documentation), educational and transparent content (service portfolio), and humorous content (entertainment & engagement content) that builds high organic appeal; (3) TikTok acts as a primary growth driver for MTMSBY43's brand awareness through three mechanisms: creating brand recognition through the FYP algorithm, which reaches new audiences; driving brand recall through consistent uploads and a distinctive communication style; and building customer trust and brand loyalty through responsive two-way interactions

The development of information technology encourages government agencies to switch from manual systems to digital systems that are more efficient and accurate. One important aspect of office administration is recording the absence of village officials, which is often done conventionally so it is prone to errors, data manipulation, and takes longer in the recapitulation process. Based on these problems, this research designs and implements a Qr-Code based attendance system at the Palatta Village Government Office. The design of this system is to provide a faster, more accurate and transparent attendance solution by utilizing Qr-Code technology which is integrated into a web-based application. The system is built with main features such as user login, Qr-Code scanning, attendance history, as well as an admin dashboard to manage data and generate reports. The results of implementation and testing using the Black Box method show that all functions run as required. Testing on users also shows that the system is easy to use, speeds up the attendance process, and helps admins in monitoring and recapitulating data. Thus, this Qr-Code attendance system is suitable to be implemented as a substitute for manual methods to increase work efficiency and discipline in the village office environment.

This study aims to analyze the implementation of the Sustainable Food Crop Land (LP2B) management policy in Madiun Regency based on Regional Regulation Number 3 of 2020 and identify factors inhibiting its implementation, as well as formulate alternative solutions to strengthen the policy in supporting agricultural land sustainability and regional food security. This study uses an empirical legal method (empirical juridical) with a qualitative descriptive approach. Primary data were obtained through in-depth interviews with the Department of Agriculture, and farmers, as well as field observations, while secondary data were obtained through a study of laws and regulations and policy documents. The analysis was conducted by examining aspects of communication, resources, disposition, and bureaucratic structure in policy implementation, using triangulation techniques to ensure data validity. The results show that LP2B implementation is not optimal. The main obstacles include farmers' low understanding of legal provisions, limited human resources and budget, weak cross-sectoral coordination, and economic pressures and high land sales prices. In addition, the national target of fulfilling 87% of Raw Paddy Land adds to the complexity of implementation at the regional level. Strengthening implementation requires improving legal communication, strengthening institutional capacity, synchronizing policies with spatial planning, and a participatory approach that actively involves farmers.

Administrative letter services at the village (nagari) level are still largely conducted using conventional methods, resulting in various issues such as limited service hours, slow processing times, and risks of document loss. This study aims to develop a web-based letter service system with the implementation of digital signatures in Nagari Bukit Bais to improve efficiency, security, and transparency of public services. The research adopts the Agile Development method with an iterative approach, including requirement analysis, system design, implementation, and testing. The developed system enables citizens to submit requests online and is equipped with features such as officer verification, digital signing by the village head, automatic notifications, digital archiving, and document verification using QR Codes. Security mechanisms are implemented using SHA-256 cryptographic hashing and RSA-2048 digital signature algorithms, supported by X.509 digital certificates. Functional testing using end-to-end methods shows that all system features operate successfully without failures, while non-functional testing confirms the reliability of document security and integrity. The resulting system is able to automate the entire service process, reduce processing time, and ensure document authenticity and security. Therefore, this system can serve as a solution to support the digital transformation of public services at the village level.

Software Defect Prediction (SDP) aims to identify defective modules early in the software development lifecycle to improve software quality and reduce maintenance costs. However, SDP datasets commonly suffer from high dimensionality, feature redundancy, and class imbalance, which can degrade model performance and stability. This study proposes a hybrid feature selection framework to address these challenges and enhance prediction performance. The proposed approach integrates Combined Correlation and Mutual Information (CONMI), which combines the Pearson Correlation Coefficient (PCC) and Mutual Information (MI) to capture both linear and nonlinear feature relevance. The selected features are further refined through Top-K selection, correlation-based filtering to reduce multicollinearity, and Backward Elimination (BE) to obtain an optimal feature subset. To address class imbalance, SMOTE-Tomek is applied by combining over-sampling and data cleaning techniques. Experiments are conducted on twelve NASA MDP datasets using Logistic Regression (LR) and Naïve Bayes (NB) classifiers. The results show that the proposed framework consistently achieves the best performance, with Logistic Regression combined with SMOTE-Tomek obtaining the highest average AUC of 0.7923 ± 0.0714, while NB achieves 0.7554 ± 0.0580. Statistical analysis using a paired t-test indicates that the proposed method significantly outperforms MI+SMOTE-Tomek and BE+SMOTE-Tomek for Logistic Regression, whereas no significant differences are observed for NB. In addition to improving overall classification performance (AUC), the proposed approach also enhances minority class detection, as reflected in improved Recall and F1-score. Overall, the proposed hybrid framework provides an effective and reliable solution for software defect prediction, particularly for high-dimensional and imbalanced datasets.

The management of integrated network services, including WiFi, CCTV, and Cable TV, requires high data accuracy to ensure customer satisfaction and revenue stability. PT. Sumber Aiti faced operational challenges due to manual administrative systems, causing data redundancy, delays in handling service disruptions, and financial discrepancies in the billing cycle. This study aims to design and develop a Web-Based Integrated Network Service Management Information System using the Waterfall development method. The Waterfall method was selected for its structured, sequential phases, requirements analysis, design, implementation, testing, and maintenance, which align with PT's stable, procedural business processes. Sumber Aiti. The system integrates customer registration, service monitoring, and automated billing management (e-billing). Functional testing using Black Box Testing on 11 test scenarios showed that 10 of 11 features (90.9%) functioned correctly, including authentication, service registration, payment processing, and administrative reporting. Comparative analysis of business processes indicates that the system reduces manual recording steps from 7 to 3 stages (57% reduction) and eliminates data redundancy across WiFi, CCTV, and Cable TV service records. The implementation of this system provides a strategic solution for improving operational efficiency and administrative accountability at PT. Sumber Aiti.

The importance of education as a foundation for developing an intelligent and qualified generation, with an emphasis on Islamic religious education as a tool for shaping students' character and morals. Islamic religious education, particularly in the study of faith and morals, emphasizes ethical values ​​such as caring and honesty. With the challenges in education becoming increasingly complex, one example is that many educators are unable to utilize learning media in today's advanced technology. One proposed solution is the use of the digital platform Kahoot, which has been proven to attract student interest in learning faith and morals, overcoming the boredom often encountered with traditional methods, such as lectures. It is emphasized that schools need adequate facilities and strategies for using gadgets to enhance students' learning experiences.The quantitative method used in this study is a pre-experimental study. In this study, the researcher used the one-group pretest and posttest design model. Based on the research results, there was a pretest score with a mean of 93.46, a median of 95, and a mode of 95. The posttest score had a mean of 84.62, a median of 90, and a mode of 100. The sig. (2-tailed) table showed 0.002 with a research alpha of 5% or 0.005. It can be concluded that there is no effect because 0.002 < 0.005. Therefore, H1 is rejected. Therefore, there is no effect of using the Kahoot application on the subject of faith and morals on improving student learning outcomes at MAS Tarbiyah Islamiyah.

The development of information technology has transformed civil dispute resolution mechanisms in Indonesia, most notably through the issuance of Supreme Court Regulation (PERMA) Number 3 of 2022 on Electronic Mediation in Courts. Despite the normative framework it provides, the implementation of electronic mediation continues to face persistent challenges, particularly regarding limited digital infrastructure, low digital literacy among disputing parties, and insufficient technical capacity of mediators. More critically, when electronic mediation fails to produce a settlement agreement, the subsequent enforcement of civil court decisions encounters serious normative gaps not yet adequately addressed by existing legal instruments. This study aims to identify and analyze the causes of civil judgment enforcement failures arising in the context of failed electronic mediation under PERMA Number 3 of 2022, and to propose normative solutions for the identified regulatory gaps. Using a normative juridical method supported by statutory, conceptual, and case approaches, this study finds that the primary causes of enforcement failure include the absence of clear legal standards governing electronically signed peace deeds, weak synchronization between PERMA Number 3 of 2022 and civil procedural law on execution, and procedural obstacles in enforcing decisions that originate from electronic proceedings. This study recommends targeted regulatory reform to ensure that peace agreements resulting from electronic mediation carry unambiguous executorial force and that enforcement mechanisms are adapted to accommodate the distinctive characteristics of electronic dispute resolution.

Inequality in Indonesia remains significant, particularly due to the concentration of wealth among high-net-worth individuals (HNWIs). Emphasizing the importance of addressing this disparity can motivate policymakers to pursue equitable solutions, thereby promoting social justice through wealth taxation. Using a literature review and an empirical legal approach, this research analyzes relevant regulations, policy discussions, and academic literature on wealth taxation in Indonesia. The study also evaluates institutional readiness and potential challenges in implementing such a policy. The results indicate that the wealth tax has considerable revenue potential, ranging from IDR 54 trillion to IDR 155.3 trillion, depending on the tax model applied. Highlighting this potential can empower policymakers and foster optimism about the tangible benefits of implementing such a policy.

Public services are a state obligation to meet the basic needs of the community and have a strong legal basis through various laws and regulations in Indonesia. However, in practice, the implementation of public services still faces various problems such as slow service processes, unclear procedures, lack of transparency in costs and service times, and maladministration. This study aims to analyze the gap between the normative concept of public services and their implementation in practice and to identify factors that influence the low quality of public services. The research method used is a qualitative approach with library research through analysis of various literature, laws and regulations, and data from public service supervisory agencies. The results show that the main problems in public services in Indonesia are related to the weak implementation of service standards, low transparency and accountability, and suboptimal professionalism of the apparatus. In addition, maladministration practices such as prolonged delays and procedural deviations are still common. Digital transformation through the implementation of e-government is one effort to improve service quality, although its implementation still faces obstacles in human resources, infrastructure, and bureaucratic culture. Therefore, strengthening public service governance, increasing transparency, and optimizing oversight are necessary to ensure public services are more effective, accountable, and oriented toward the public interest.

This study aims to analyze the effectiveness of play-based methods in Physical Education, Sports, and Health (PJOK) learning for sixth-grade students at Pelangi Elementary School. The background of this study is the decline in movement motivation in upper-grade students due to excessive focus on academic workload. The research method used is descriptive qualitative with data collection techniques in the form of participatory observation and in-depth interviews with key informants. The results of the study indicate that the integration of structured games in the Lesson Implementation Plan (RPP) can improve motor coordination and students' social values. In addition, modifications to game tools and rules provide creative solutions to overcome the limitations of existing facilities. The conclusion of the study confirms that the play-based approach functions not only as a recreational activity but also as an effective formal instructional method to achieve curriculum targets holistically, supporting students' physical and social development simultaneously. This approach is expected to be implemented more widely in schools to improve the quality of PJOK learning.

Rice plants (Oryza Sativa L.) are the main staple food commodity in Indonesia, as most of the Indonesian population relies on rice as their primary food. One of the causes of low rice production in Indonesia is that farmers generally cultivate rice improperly, such as in land preparation or land selection. Land suitability in rice cultivation greatly affects crop productivity. A process that can support decisions regarding rice land suitability is the development of a Decision Support System (DSS) website using a combination of the Simple Additive Weighting (SAW) method and the Technique for Order Performance of Similarity to Ideal Solution (TOPSIS). This combination is performed by taking the average (µ) of the final results from the SAW and TOPSIS methods. The final scores of each method are calculated separately, and then the average (µ) of these two results is taken to obtain the final ranking of the alternatives. The data used to determine the suitability of rice land is based on five criteria: soil type, soil pH, rainfall, temperature, irrigation and water supply. The alternative data used in the study includes six alternatives: Sungai Kunjang, Sambutan, Samarinda Utara, Palaran, Loa Janan Ilir, and Samarinda Seberang. The aim of this research is to provide information on alternative solutions to farmers or farmer groups in determining rice land suitability. The results of the combination of the SAW and TOPSIS methods show that the alternative with the highest final score is Samarinda Utara (A3), with a final score of 0.7337. Meanwhile, the alternative with the lowest final score is Sambutan (A2), with a final score of 0.4402.

This community service project aims to accentuate inclusive values among the youth of Tanjung Dapura, Makassar City, to strengthen social cohesion in a heterogeneous urban environment. The implementation methods included team consolidation, material preparation, and strategic coordination with local government authorities. The core activities were conducted through participatory counseling and Focus Group Discussions (FGD) to independently analyze social exclusion challenges. The materials focused on the importance of respecting diversity and the strategic role of youth as inclusive agents of change. The results indicated a significant increase in participants' understanding of inclusion literacy and their ability to formulate creative solutions for local discrimination issues. Evaluation through observation and reflection confirmed a paradigm shift among the youth from passive tolerance toward active participation in embracing differences. This project concludes that the synergy between critical education and collaborative dialogue successfully transforms youth into resilient pillars of social harmony. The accentuation of these inclusive values is expected to become the foundation for a more just and sustainable coastal community in Makassar.

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.

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.

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.