Publication Search

This study presents a comprehensive comparative analysis of four traditional machine learning algorithms Decision Tree, Random Forest, K-Nearest Neighbors, and Support Vector Machine for Android malware detection using the preprocessed TUANDROMD dataset comprising 4,465 instances and 241 features representing both static and dynamic application characteristics. Motivated by the limitations of conventional signature-based and hybrid detection methods, especially in managing imbalanced datasets and detecting emerging malware variants, the study employed SMOTE to ensure balanced training data and fair model evaluation. The dataset was divided into 80% training and 20% testing subsets, and models were assessed using key performance metrics including accuracy, precision, recall, F1-score, and ROC AUC. The findings revealed that the proposed Random Forest model outperformed the other classifiers, achieving an accuracy of 0.993, precision of 0.992, recall of 1.000, F1-score of 0.996, and a near-perfect ROC AUC of 0.9998 surpassing state-of-the-art approaches. These results affirm the superior predictive capability, consistency, and robustness of the Random Forest algorithm in Android malware detection. The study concludes that base models, when integrated with class-balancing techniques, provide reliable and efficient malware detection across imbalanced datasets. For future research, the study recommends exploring advanced hybrid or ensemble frameworks that integrate Random Forest with deep learning architectures or other meta-heuristic optimization techniques to further enhance detection accuracy, adaptability, and resilience against rapidly evolving Android malware threats.

The integration of Artificial Intelligence (AI) into precision agriculture has significantly improved plant disease recognition; however, many existing deep learning models remain computationally expensive and feature-redundant, limiting their deployment on low-power and edge devices. To address these limitations, this study proposes a lightweight framework for maize leaf disease recognition based on serial deep feature extraction, dimensionality reduction, and machine-learning–based classification. A pre-trained MobileNetV2 network is employed as a fixed feature extractor to obtain discriminative visual representations, while Principal Component Analysis (PCA) is applied to reduce feature dimensionality by approximately 76%, retaining 95% of the original variance and improving computational efficiency. The compressed features are subsequently classified using a Radial Basis Function Support Vector Machine (RBF-SVM), optimized via grid search and cross-validation. Experiments conducted on a four-class maize leaf disease dataset (Northern Leaf Blight, Common Rust, Gray Leaf Spot, and Healthy), with class imbalance handled during training, demonstrate that the proposed MobileNetV2–PCA–SVM pipeline achieves 97.58% accuracy, 96.60% precision, 96.59% recall, and 96.59% F1-score, outperforming the DenseNet201 + Bayesian-optimized SVM baseline (94.60%, 94.40%, 94.40%, and 94.40%, respectively). This improvement corresponds to a 2.98% accuracy gain, a 55% reduction in error rate, an 86% reduction in model parameters (20.31M to 2.75M), and an 85% reduction in model size (81 MB to 12 MB). These results indicate that the proposed framework provides a compact and efficient solution with strong potential for deployment in resource-constrained agricultural environments.

This study presents a Graph-Augmented Isolation Forest (GAIF), an unsupervised anomaly-detection framework for analyzing mobile user behavior. The proposed framework represents users and behavioral attributes as a user–feature bipartite graph, enabling the capture of relational dependencies that are not explicitly modeled in conventional vector-based approaches. Low-dimensional user representations are learned through Node2Vec and Graph Sample and Aggregate (GraphSAGE), and the resulting embeddings are subsequently processed by an Isolation Forest to produce anomaly scores. Experiments are conducted on a Mobile Device Usage and User Behavior dataset comprising 700 user profiles derived from application-level behavioral indicators. The dataset is treated as a behavioral abstraction rather than as a malware classification benchmark. A consistent 80:20 stratified train–test split is employed, with all learning-capable operations restricted to the training data to mitigate information leakage. Detection performance is evaluated post hoc using precision, recall, F1-score, and area under the curve (AUC) metrics. Under the evaluated setting, GAIF achieves an F1-score of 0.94 and an AUC of 0.97, demonstrating improved anomaly detection effectiveness relative to representative unsupervised baseline methods. These results are obtained on a static, proxy dataset and should not be interpreted as evidence of real-time deployment capability. Model interpretability is supported through post-hoc Uniform Manifold Approximation and Projection (UMAP) visualizations of the learned embeddings, providing structural insights into anomalous user behavior. Overall, the findings indicate that integrating graph-based representation learning with isolation-based anomaly scoring constitutes a computationally efficient approach for unsupervised mobile user behavior anomaly detection within the scope of this study.

This article aims to explore the evaluation of the context, inputs, processes, and products of the implementation of Islamic Religious Education and Character Education at SMA Negeri 1 Tikep. Until now, there are still many obstacles faced by a number of educational institutions, especially in the aspects of implementation and evaluation. This study uses a qualitative approach and a type of evaluation research with the CIPP (Context, Input, Process, and Product) evaluation model, which was developed by Stufflebeam. This research was conducted by analyzing the data to answer the problem formulation without testing the hypothesis. The main data from this study were obtained through descriptive analysis, with the data collection process through interviews, documentation, and Post-Test as additional data. The results of this study indicate that from the perspective of the CIPP evaluation model developed by Stufflebeam, the context, input, process, and product aspects of PAI and Budi Pekerti learning based on the 2013 curriculum at SMA Negeri 1 Tikep  are included in the good category.

This study explores the shift from traditional to modernist educational paradigms in Islamic boarding schools (pesantren), which have been in existence since before Indonesia’s independence. The shift involves adapting learning methods while retaining traditionalist approaches, ensuring that they meet modern needs without eliminating their core values. The study uses a qualitative-phenomenological approach to examine three main areas: (1) the strategy of educational values and spiritual practices employed by pesantren leaders, with an emphasis on the TAQWA method, which aims to improve student understanding quickly; (2) the integration of Qur'an literacy, religious traditions, and environmental empowerment in the educational process; and (3) the impact of this model on student character development. Qur'an literacy in this context extends beyond reading and memorizing verses, focusing on understanding and actualizing its values in daily life. Religious practices such as book study, worship routines, and etiquette coaching promote moral development. Environmental activities, such as agriculture and natural resource management, encourage independence and ecological awareness. This holistic approach can serve as a model for character education, blending spiritual, social, and environmental aspects, while strengthening pesantren's role in fostering moral and ecological awareness.

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.

The maritime education sector faces complex challenges in preparing competent seafarers amid the rapid advancement of digital technology. This study investigates the effect of artificial intelligence-based simulations and AI-based competency assessments on competency achievement levels among nautical cadets at Indonesian maritime training institutions. The research design employed a convergent parallel mixed-methods approach, integrating quantitative and qualitative methods to gain a comprehensive understanding. Quantitative data were collected from 150 cadets using a validated questionnaire. In comparison, qualitative data were obtained through in-depth semi-structured interviews with fifteen instructors and ten cadets. Multiple regression analysis revealed that the research model significantly predicted cadet competency achievement. The findings indicate that AI-based assessments exert a stronger influence than AI simulations in improving competency. The qualitative exploration highlighted adaptive feedback mechanisms and personalized learning pathways as critical success factors in implementing learning technologies. This study provides empirical evidence for maritime institutions to prioritize strategic investments in AI-based assessment systems while maintaining a human-centered pedagogy. The research contribution lies in integrating fourth industrial revolution technologies into the training, certification, and watchkeeping standards compliance framework for seafarers, thereby strengthening Indonesia's maritime education ecosystem and aligning it with international standards.

This study was motivated by the importance of the availability and quality of infrastructure as a major supporting factor for the comfort and smooth running of the lecture process at the postgraduate level. The purpose of this study was to evaluate educational facilities and infrastructure based on the perceptions of postgraduate students in the Islamic Education Study Program (PAI) using the Context, Input, Process, and Product (CIPP) evaluation model. This research is an evaluative study with a qualitative approach, involving PAI graduate students as research subjects. Data collection was conducted through questionnaires, in-depth interviews, and field observations, then analyzed using the Question Discourse technique to obtain a comprehensive understanding of the students' experiences and assessments. The results show that students view facilities and infrastructure as important to very important in supporting the lecture process. In general, the facilities are considered adequate, but there are still limitations in the air conditioning system and internet network stability, which affect the comfort and effectiveness of learning. The implications of this study emphasize the need for continuous improvement in the quality, maintenance, and management of facilities and infrastructure to support the quality of PAI postgraduate education.

This study aims to: (1) Determine the effect of the discovery learning model with the aptitude treatment interaction strategy on the mathematical concept comprehension and self-efficacy of 10th-grade students at SMA Negeri 3 Tarakan; (2) Determine the effect of the discovery learning model with the aptitude treatment interaction strategy on the mathematical concept comprehension of 10th-grade students at SMA Negeri 3 Tarakan; (3) Determine the effect of the discovery learning model with the aptitude treatment interaction strategy on the self-efficacy of 10th-grade students at SMA Negeri 3 Tarakan. The research population included all tenth-grade students of SMA Negeri 3 Tarakan in the 2024/2025 academic year. The research sample consisted of two classes selected randomly: one experimental class receiving discovery learning with an aptitude treatment interaction strategy and one control class receiving conventional learning. The research instruments consisted of a test measuring mathematical concept understanding on trigonometry material and a self-efficacy questionnaire. The data obtained were tested for prerequisites through normality and homogeneity tests before being analyzed using inferential statistical tests in the form of an independent samples t-test with the assistance of SPSS software version 26.0. The research results show that the implementation of the discovery learning model with the aptitude-treatment interaction strategy has a significant impact on students' mathematical concept understanding and self-efficacy simultaneously, with a significance value of 0.006 < 0.05. Partially, this learning model has a significant effect on students' mathematical concept understanding, with a significance value of 0.018 < 0.05. However, the effect of the discovery learning model with the aptitude-treatment interaction strategy on students' self-efficacy is not statistically significant, as indicated by a significance value of 0.089 > 0.05, even though there is a tendency for increased self-efficacy among students participating in the experimental class learning. Nevertheless, the influence of the discovery learning model with the aptitude treatment interaction strategy on students' self-efficacy is not statistically significant in partial terms, although there is a tendency for an increase in self-efficacy among students participating in the experimental class. These findings suggest that the discovery learning model with the aptitude treatment interaction strategy is effective in improving students' understanding of mathematical concepts in trigonometry material and has the potential to support the development of self-efficacy in mathematics learning.

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

Islamic boarding schools (Islamic boarding schools) are required to integrate classical scholarly traditions and modern education, one way of doing this is through the integration of the study of yellow books (tahfidzul Qur'an) and Qur'an memorization (tahfidzul Qur'an). The Baitul Abidin Darussalam Wonosobo Tahfidzul Qur'an Islamic Boarding School implements an integrative learning system to balance Qur'an memorization and understanding of Islamic law (shari'a). However, it still faces obstacles such as a tight schedule, different methods, and weak coordination and evaluation. This study examines the implementation patterns, challenges, and impacts of this system, with the hope of serving as a reference for developing a balanced and sustainable model of Islamic boarding school education. This research uses a qualitative approach with a case study design to understand in-depth the implementation of the integrative learning system between Qur'an memorization and the study of yellow books (tahfidzul Qur'an) at the Baitul Abidin Darussalam Wonosobo Islamic Boarding School (PPTQ). Subjects were selected purposively, including the boarding school administrator, tahfidz teachers, yellow book teachers, and students. Data were collected through in-depth interviews, participant observation, and documentation studies. Data analysis was conducted interactively using the Miles and Huberman model, which encompasses data reduction, data presentation, and conclusion drawing and verification to obtain a holistic and contextual understanding. The discussion shows that the integrative learning system in Islamic boarding schools is implemented through a balanced daily schedule between Quran memorization and yellow book study, allowing memorization, understanding, and moral development to occur simultaneously within the students' daily routines. Integration is achieved structurally through scheduling, methodologically by linking verse memorization with book study, and culturally through the instillation of values, etiquette, and pesantren traditions. The success of integration is supported by the exemplary behavior of the kiai (Islamic teachers) and ustadz (Islamic teachers), the religious environment, and the motivation and discipline of the students, despite challenges such as busy schedules, physical exhaustion, differences in student abilities, and limited facilities. The impact of implementing this system is seen in the improved quality of contextual memorization, a more critical understanding of the scriptures, the formation of disciplined and moral character, and the holistic spiritual development of students.

This study aims to develop a pop-up book learning medium with the theme “Einkaufen” (Shopping) as a German language instructional medium for Grade XI students at SMA Negeri 3 Binjai. The background of this study is the low level of students’ understanding of the learning materials and their lack of learning motivation due to the use of monotonous conventional media. This research employs a Research and Development (R&D) approach using the ADDIE development model, which includes the stages of Analysis, Design, Development, Implementation, and Evaluation. The results of the implementation stage indicate that 98.3% of students agreed that the pop-up book is effective for use in German language learning, and 96.7% stated that the material content is easy to understand. The pop-up book consists of six pages containing learning materials and exercises that focus on reading, writing, and speaking skills. Validation by material and media experts yielded a score of 90, categorized as very good. These findings demonstrate that the developed pop-up book medium is not only visually engaging but also capable of enhancing students’ motivation and comprehension in an integrative German language learning process. This medium can serve as an effective alternative for improving the quality of foreign language learning at the secondary school level.

This study aims to evaluate the effectiveness of the Tahsin Qur'an program at Ma'had Al-Jamiah IAIN Kendari using the Goal Free Evaluation model. This evaluation emphasizes tangible results without being tied to the initial objectives of the program. This study uses a descriptive qualitative approach through observation, interviews, and documentation. The results indicate that the program has had a significant positive impact: participants showed improved reading ability in hijaiyah letters, mastery of basic tajweed, and increased self-confidence and spiritual closeness to the Quran. The high level of participant attendance and consistent enthusiasm for learning indicate active involvement in the learning process. The program has also proven to be able to create a conducive and sustainable learning community, even though it is run voluntarily without financial incentives. Several recommendations for development include the provision of advanced classes, improvement of learning materials, and increasing reach and wider support. This evaluation confirms that the andragogy-based tahsin learning approach is highly relevant for Quranic education for adults and deserves further development.

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.

This study aims to evaluate the implementation of the At-Turats Book Study Program using the Context, Input, Process, and Product (CIPP) evaluation model to provide an overview of the program’s relevance, resource readiness, implementation, and outcomes. The research method used is descriptive qualitative, with data collection techniques through observation and interviews. The results show that in terms of context, the study of classical texts meets the needs of the santri and aligns with the vision of Ma’had Al-Jami’ah, which aims to deepen religious and cultural understanding. In terms of input, the program is supported by qualified instructors and representative classical reference books, although there are still limitations in the number of teachers, the varying abilities of the santri, and supporting facilities. Regarding the process, the study is carried out using the halaqah method with a bandongan approach, which is relatively consistent, although the participation and interaction of the santri are limited. Some santri are still hesitant to engage actively in discussions, which can reduce the effectiveness of learning. In terms of product, the program has a positive impact, including an improvement in religious understanding, the development of more moderate and tolerant religious attitudes, and enhanced ability to comprehend classical texts among some of the santri. Overall, the program has achieved its main objectives but still requires improvement in terms of facilities and interaction during the learning process.

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 was motivated by the low learning outcomes of students in Social Studies, particularly on natural disaster material in Grade IV of SDI Halibenaus. The purpose of this research was to describe the implementation of the Active Learning model in improving students’ learning outcomes. This study employed a qualitative approach using Classroom Action Research (CAR) conducted in two cycles, each consisting of planning, action, observation, and reflection stages. The research subjects were 17 fourth-grade students consisting of 10 boys and 7 girls. Data collection techniques included observation, tests, and documentation, while data analysis was carried out through data reduction, data display, and conclusion drawing. The results indicated an improvement in students’ learning outcomes in each cycle. The average score in Cycle I was 64.35% with a mastery level of 35.29%, which increased in Cycle II to 83.17% with a mastery level of 82.35%. Based on these findings, it can be concluded that the implementation of the Active Learning model is effective in improving students’ learning outcomes in Social Studies on natural disaster material for fourth-grade students at SDI Halibenaus.

This study aims to compare the performance of Multiple Linear Regression (MLR) and Random Forest Regression (RFR) in predicting student performance based on academic scores. Student performance is defined as the average of math scores, Reading Scores, and writing scores. This study uses a quantitative approach with a comparative design based on predictive modeling. The data used is secondary data from the Student Prediction dataset obtained through the Kaggle platform, which was processed using the Python programming language through the Google Colab platform. The analysis stages included the formation of performance variables, the separation of training and test data with a ratio of 80:20, model training, and evaluation using the Mean Squared Error (MSE), Mean Absolute Error (MAE), and coefficient of determination (R²) metrics. The results show that the Multiple Linear Regression model produced an MSE value of 2.74 × 10⁻²⁸, an MAE of 1.51 × 10⁻¹⁴, and an R² of 1.000. Meanwhile, Random Forest Regression produced an MSE of 0.296, an MAE of 0.375, and an R² of 0.998. These findings indicate that both models have a very high level of accuracy, but Multiple Linear Regression provides the best performance. This is due to the strong linear relationship between the input variables and the target variables formed directly from the combination of academic values. Thus, the linear regression model is proven to be more suitable for use in data structures that have simple linear relationships compared to ensemble-based models.

Science education in elementary schools requires the active involvement of students through meaningful learning experiences. One of the essential subjects in fourth grade elementary school is the growth and development of animals and plants. However, science education is still often conducted conventionally, so that students' scientific process skills have not developed optimally. This study aims to analyze and describe the application of the Project-Based Learning (PjBL) model in science learning projects on the growth and development of animals and plants with the support of Seesaw and Flashcard Quizlet digital media through a Systematic Literature Review (SLR) approach. The research method used SLR with a descriptive qualitative approach to relevant scientific articles published between 2019 and 2025. The results of the study show that the application of PjBL can increase student learning activity, scientific process skills, and understanding of science concepts. The use of Seesaw was effective as a medium for project documentation and reflection, while Flashcard Quizlet helped reinforce concepts and formative evaluation. Thus, the integration of PjBL, Seesaw, and Quizlet can be an innovative learning alternative that is relevant to the Merdeka Curriculum and the needs of elementary school students.