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.

Education plays a crucial and essential role in improving the quality of human resource globally, thus a research was conducted with the aim of producing a product, namely a learning module. This module is one of the learning resources that can be used by students independently. Therefore, the module was developed to function as a learniing guide for students. The lerning model used in this research is Creative Problem Solving. In this learning model, the teacher presents problems so that students can find answers innovatively and sharpen  their critical thinking skills. The suitability of this learning module will be evaluated based on three aspect, namely validity, practicality, and effectiveness. Based on the research sample data, this consists of students from class XI Electrical Power Installation Techniques (TITL) 1 at SMKN 1 Driyorejo. This method uses the Research & Development (R&D) approach. The analysis of differences in learning outcomes was carried out using the One Group Pretest-Posttest Method, the treatment in the form of a learning module based on the Creative Problem Solving model was given to student. The research result show that (1) the modules suitability is stated as very valid wth a score of 89,60, (2) aspect, it is stataed as very practical with a total average reaching 90,60, (3) effectiveness is proven from the improvement in learning outcomes in terms of knowledge and domains with an average pretest score of 51,3, while the average posttest score is 85 with a significance of 0.000.

Freshwater fish diseases significantly affect aquaculture productivity and economic sustainability, while accurate visual classification remains challenging due to interclass similarity and image variability. This study presents a comparative evaluation of three deep learning architectures—DenseNet201, ResNet50, and EfficientNetV2-S—using a stepwise optimization strategy combined with Gradient-weighted Class Activation Mapping (Grad-CAM) for freshwater fish disease classification. Models were trained through three phases: baseline, optimized, and fine-tuned. Performance was evaluated using accuracy, precision, recall, F1 score, Matthews correlation coefficient (MCC), Cohen’s kappa, and per-class ROC–AUC. Results show consistent performance improvement across all architectures, with EfficientNetV2-S achieving the highest accuracy (97.14%), followed by ResNet50 (96.11%) and DenseNet201 (94.40%). High ROC–AUC values (>0.98) indicate strong discriminative capability. Grad-CAM analysis confirms that all optimized models focus on biologically relevant lesion regions, enhancing model transparency and reliability.

This study presents ReflectAI, a web-based system designed to automate the creation of teaching materials tailored to students' learning styles using behavior data from a Learning Management System (LMS). Student digital activity data—such as logins, material access, forum participation, assignment submission, and quiz results—are extracted and processed using a Hierarchical Clustering algorithm to categorize students into three learning styles: visual, auditory, and kinesthetic. Based on the clustering results, the system automatically generates personalized learning modules using generative AI (ChatGPT API), aligned with each student's learning preferences. Employing a data-driven system development approach, the system was tested with data from 230 students in a mathematics course. The results show diverse learning style distributions and relevant, tailored content generation. ReflectAI is designed to reduce teachers’ administrative workload and enhance personalized and adaptive learning. This system contributes to educational transformation through deep, data-driven technology integration.

This research develops a machine learning model to classify customer loyalty using the Random Forest algorithm. Customer churn is a critical issue that reduces revenue and increases acquisition costs. A dataset of 50,000 customers from global e-commerce and subscription platforms was processed through data cleaning, imputation, outlier handling, and class balancing with SMOTE. The Random Forest model was built as a baseline and optimized with hyperparameter tuning. Evaluation using accuracy, precision, recall, and F1-score shows that the optimized model achieved 90.81% accuracy and 83.87% F1-score, outperforming previous Naïve Bayes approaches. Feature importance analysis highlights customer service interactions, lifetime value, and demographic factors as key predictors of churn. These findings demonstrate Random Forest’s effectiveness in churn prediction and provide practical insights for customer retention strategies

The increasing sedentary lifestyle in the digital era has the potential to cause various health problems due to lack of physical activity. One approach that can be taken to encourage physical activity is through the use of digital games with body movement-based control mechanisms. This study aims to develop a body gesture-based game character control system using a hybrid Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) model. CNN is used to extract spatial features from each video frame, while LSTM serves to model the temporal relationship between frames so that movement patterns can be recognized sequentially. The research method used refers to the Machine Learning Lifecycle stages, starting from data collection, preprocessing, model development, to implementation in the endless runner game genre. Testing results show that the CNN–LSTM model is capable of classifying body gestures and generating outputs that can be used as commands to control game characters. The implementation of this system enables more natural and interactive game interactions without conventional input devices, and has the potential to encourage players to lead a more active lifestyle.

Sentiment analysis on social media is widely used to represent public perceptions of sports performance, particularly in international competitions. This study aims to analyze the sentiment of YouTube user comments regarding the performance of the Indonesian National Football Team during the FIFA World Cup 2026 Asian Qualifiers. The data were collected from user comments on videos related to the matches and analyzed using a machine learning–based sentiment analysis approach. Sentiment classification was performed using the Naive Bayes algorithm. The results indicate that the proposed approach is able to effectively identify public sentiment toward the national team’s performance during the qualification matches. The findings of this study are expected to provide insights into public perceptions and contribute to sentiment analysis research in the field of sports.

Learning to read the Al-Qur'an at TPA Al-Amin Brahu Ponorogo still relies on conventional methods, which lead to low motivation and boredom among students. This study aims to design and develop interactive learning media based on Augmented Reality (AR) through the AR-Iqro' Jilid 5 application on the Android platform. The development method employed is the System Development Life Cycle (SDLC) using the Waterfall model, which encompasses the stages of planning, design, implementation, testing, and maintenance.The results of the study indicate that the application performs exceptionally well, with material validation reaching 96%, media design at 96%, and user testing at 97%. These findings prove that the AR-Iqro' Jilid 5 application is highly feasible for use due to its ease of navigation and intuitive visual interface. The implication of this research is the availability of an innovative alternative learning medium capable of increasing students' interest in learning the Al-Qur'an, with the potential for broader implementation in technology-based Islamic educational institutions.

Open-pit mining activities in Indonesia contribute significantly to the national economy but require stringent monitoring to mitigate environmental degradation. Conventional monitoring methods relying on terrestrial surveys are often constrained by vast coverage areas, high operational costs, and limited field accessibility. This study aims to develop an artificial intelligence model capable of automatically detecting and mapping mining areas to enhance surveillance efficiency. The applied method is Deep Semantic Segmentation utilizing the U-Net Convolutional Neural Network (CNN) architecture. The model was trained using Sentinel-2 satellite imagery, focusing exclusively on Red, Green, and Blue (RGB) spectral channels to replicate human visual perception. Experimental results demonstrate that the proposed model performs reliable segmentation of mining areas, achieving an Accuracy of 93.58% and a Global Intersection over Union (IoU) of 0.8067. These findings indicate that the U-Net architecture can effectively extract spatial features of mines even when utilizing standard visual data. This research contributes to the development of an efficient, cost-effective, and scalable digital monitoring prototype to support innovation in sustainable environmental governance.

This study examines community capacity building for flood mitigation in flood-prone regions of Central Kalimantan through disaster education, technical training, and the construction of an amphibious house prototype. Using a community-based disaster risk reduction (CBDRR) framework, the program integrates participatory training, field surveys, and adaptive structural innovation. Findings indicate a 40% increase in community knowledge based on  Community Empowerment Level Analysis results, active engagement of 35 participants in disaster education, and significant improvement in technical skills among 22 trainees involved in amphibious foundation construction. The prototype achieved 100% completion within four effective working days, demonstrating the feasibility of amphibious technology using locally available materials. Strengthening youth organization structures further enhances community readiness and institutional resilience. Overall, the integration of participatory learning and adaptive technology effectively builds community self-efficacy and disaster preparedness in flood-prone environments.