Publication Search

This study aims to describe the implementation of Islamic school culture in shaping the religious character of students at SMK Islam Insan Mulia. The research employed a descriptive qualitative approach based on interview transcripts with three students from different vocational programs, namely Mechanical Engineering, Accounting, and Culinary Arts. Data were analyzed through data condensation, thematic coding, data presentation, and interpretive conclusion drawing to obtain a comprehensive understanding of students’ experiences. The findings indicate that Islamic school culture is implemented through religious routines, student discipline, teacher guidance, ethical vocational learning, and the development of a clean and orderly school environment. These practices contribute to the formation of religious character, which is reflected in students’ worship awareness, moral responsibility, honesty in learning, discipline, cooperation, and future orientation. The study also identified several challenges, including limited student independence, peer dependence in group assignments, and the gradual development of facilities in a new vocational program. These findings suggest that Islamic school culture needs to be managed consistently through habituation, teacher role modeling, continuous monitoring, and integration with vocational competencies. The study implies that strengthening Islamic school culture can support both religious character formation and vocational readiness among students.

Python programming has become a fundamental competence in the digital era, yet students often struggle to transform algorithmic logic into functional code. This gap between conceptual understanding and practical implementation skills requires a thorough investigation into learning challenges within the Industrial Informatics Engineering Technology (TRIN) program at Politeknik Manufaktur Bandung. Grounded in Bloom's Revised Taxonomy and Cognitive Load Theory, this descriptive quantitative study utilized a Likert-scale questionnaire and an objective comprehension test administered to 87 third-year students. Data were analyzed using descriptive statistics to map performance across three aspects: conceptual understanding, syntactic comprehension, and implementation ability. Results indicate the conceptual aspect achieved the highest average of 4.15, followed by syntax at 3.56 and implementation at 3.54, with objective test accuracy rates of 76.09%, 65.52%, and 67.36%, respectively. Major obstacles identified include difficulties with looping, debugging, and comparison operators. Therefore, enhanced structured practice and Project-Based Learning approaches are recommended to strengthen students' implementation competencies.

 Education in vocational high schools (SMKs) requires effective data management to improve students’ academic achievement and discipline. At SMK Islam Secang, students’ academic scores and attendance data have so far functioned merely as administrative archives, making it difficult to identify patterns of student performance. This study aims to classify students based on academic achievement and discipline by applying the K-Means Clustering algorithm using RapidMiner. The data used in this study consist of scores from six subjects and attendance records of 35 students from the Light Vehicle Engineering (TKR) department over two semesters. The data were obtained from original school records, compiled using Microsoft Excel, and processed in RapidMiner. The clustering process employed four clusters for academic achievement and two clusters for discipline, with Euclidean Distance used as the similarity measure. The results show that in the first semester, students were grouped into four academic achievement clusters: high achievement (6 students), moderate achievement (7 students), potentially problematic (14 students), and problematic (8 students). In the second semester, the distribution changed to high achievement (19 students), moderate achievement (14 students), potentially problematic (4 students), and problematic (1 student). Meanwhile, student discipline was divided into two clusters: disciplined (31 students) and undisciplined (4 students). These results demonstrate that K-Means Clustering is effective in mapping student conditions, revealing patterns in academic performance and attendance, and supporting educational evaluation, learning planning, and early detection of students who require academic or disciplinary intervention. Keywords: Data Mining, K-Means Clustering, Academic Achievement, Discipline, RapidMiner, Vocational High School (SMK)

Recent Internet of Things (IoT) intrusion detection studies have reported near-perfect benchmark performance for Distributed Denial of Service (DDoS) detection, yet limited attention has been given to understanding how different traffic representations contribute to the detection process under highly imbalanced traffic conditions. This study presents an ablation-driven analysis to investigate the contribution of statistical and temporal representations for large-scale IoT DDoS detection using the CICIoT2023 dataset. Three experimental scenarios are evaluated, including statistical representation, temporal sequence representation, and hybrid statistical–temporal representation. Temporal representations are learned using a one-dimensional Convolutional Neural Network (1D-CNN) with lag-based traffic sequences, while ensemble tree-based classifiers are employed for final classification and representation analysis. In addition, multiple ablation configurations are designed to evaluate the impact of temporal dependency modeling and feature engineering strategies on detection performance. Experimental results show that statistical traffic representations remain highly effective for DDoS detection on CICIoT2023, achieving 99.36% accuracy and 99.31% weighted F1-score in the statistical representation scenario. Feature importance analysis further indicates that engineered statistical features contribute substantially more to the classification process than CNN-based temporal representations. Although temporal modeling captures sequential traffic behavior, its contribution is relatively limited and mainly acts as a complementary representation. Furthermore, the hybrid configuration produces only marginal improvements over the statistical representation alone. These findings highlight the importance of representation-level analysis for understanding the actual contribution of statistical and temporal modeling in modern IoT intrusion detection systems beyond relying solely on benchmark accuracy.

Student dropout in higher education remains a persistent socioeconomic challenge, yet many predictive models reported in the literature are methodologically compromised by randomized cross-validation schemes that introduce temporal data leakage and artificially inflate predictive performance. This study proposes a longitudinal prescriptive learning analytics framework integrating three complementary methodological components: a Leave-One-Cohort-Out (LOCO) temporal validation protocol, a hybrid SMOTE-ENN class balancing strategy, and temporal velocity feature engineering derived from Learning Management System (LMS) behavioral trajectories. The framework was evaluated on a longitudinal dataset comprising 464,739 enrollment records and 77 features. Five predictive algorithms—XGBoost, LightGBM, CatBoost, Random Forest, and Logistic Regression—were comparatively assessed on a strictly isolated blind holdout cohort (2022), with CatBoost emerging as the champion estimator, achieving a PR-AUC of 0.8859, a Macro F1-Score of 0.9143, and the lowest Brier Score (0.0221), thereby demonstrating superior calibration and discriminative capability under severe class imbalance (93:7 ratio). Comprehensive ablation analysis revealed that temporal velocity features function not merely as additive predictors, but as a structural prerequisite enabling Synthetic Minority Oversampling Technique with Edited Nearest Neighbors (SMOTE-ENN) to generate high-quality synthetic boundary instances; removing these features reduced minority-class precision from 0.8302 to 0.6721. To operationalize predictive outputs into actionable intervention pathways, Diverse Counterfactual Explanations (DiCE) were implemented under a three-tier causal constraint architecture on 96 borderline high-risk students, generating 384 feasible intervention scenarios exclusively targeting forward-looking behavioral velocity metrics without constraint violations. Collectively, these findings advance the paradigm of prescriptive learning analytics by providing educational institutions with interpretable risk diagnostics and operationally feasible intervention guidance grounded in empirically validated behavioral and temporal dynamics.

Cloud job-length prediction remains challenging when the target distribution is highly skewed and contains rare extreme values. This study proposes a log-transformed, regime-based machine learning framework for robust prediction of cloud job length, represented in million instructions (MI). The approach integrates sequential feature engineering, logarithmic target transformation, weighted learning, and regime-aware modeling to distinguish between normal and extreme job-length behavior. Using an ordered GoCJ-derived cloud job-length sequence of 1000 jobs, the dataset exhibits a heavy-tailed distribution, with a mean of 129,662 MI, a median of 93,000 MI, a 95th percentile of 525,000 MI, a 99th percentile of 900,000 MI, and a skewness of 3.695. The proposed model is evaluated against sequential baselines and stronger machine learning baselines, including Naive_Last, RollingMean_5, Global_Log_ExtraTrees, RandomForest, GradientBoosting, and MLP_Log. On the main test split, the proposed Regime_Log_ExtraTrees achieved the best RMSE of 206,255.66 and the least negative R² of −0.01062, while Global_Log_ExtraTrees remained competitive in terms of MAE, MedAE, and RMSLE. Additional walk-forward validation confirms that the regime-aware model consistently achieves the best mean RMSE and mean R² across temporal folds. Ablation results further show that regime-aware learning is the primary contributor to robustness, although accurate prediction of extreme jobs remains challenging. These findings indicate that log-transformed, regime-based learning provides a practical and more robust strategy for cloud job-length prediction under heavy-tailed workload conditions.

This study aims to strengthen students’ networking competencies through the implementation of straight and cross LAN cable assembly training at SMKN 53 Jakarta. The background of this research is based on the need to enhance students’ practical skills in basic computer networking, particularly in understanding cable configurations and applying crimping techniques according to industry standards. Many students experience difficulties in differentiating wiring standards and applying correct crimping procedures, which impacts their readiness for industry practice. This research employed a practical training approach combined with demonstration and hands-on methods. The participants were students of the Computer and Network Engineering program. Data were collected through observation, performance assessment, and competency tests before and after the implementation. The findings indicate a significant improvement in students’ understanding of cable color standards (T568A and T568B), accuracy in assembling straight and cross cables, and testing results using LAN testers. Students demonstrated higher levels of technical accuracy, problem-solving skills, and work discipline after the intervention. The implementation of structured practical activities proved effective as a medium for strengthening networking competencies. The study implies that continuous practice-based learning aligned with industry standards is essential in vocational education to improve students’ technical readiness and employability in the networking field.

Industrial visits are widely recognized as an experiential learning approach that bridges the gap between theoretical knowledge and real industrial practices in engineering education. This study aims to examine the relationship between industrial visits and the improvement of production system understanding and critical thinking skills among students of the Faculty of Industrial Technology at Universitas Nahdlatul Ulama Al-Ghazali (UNUGHA) Cilacap. A quantitative approach with a one-group pretest–posttest design was employed. The participants consisted of 43 industrial engineering students who took part in industrial visits to PT Dirgantara Indonesia and the National Research and Innovation Agency (BRIN) in Bandung. Data were collected using Likert-scale questionnaires and analyzed through Paired Sample t-Test. The results reveal a significant increase in students’ understanding of production systems, with mean scores rising from 64.23 (pretest) to 81.47 (posttest) (p < 0.05). Similarly, critical thinking skills showed a significant improvement, increasing from a mean score of 63.05 to 83.12 (p < 0.05). These findings demonstrate that industrial visits have a substantial positive impact on enhancing students’ academic competencies. This study highlights the importance of systematically integrating industrial visits into the industrial engineering curriculum to strengthen learning outcomes and improve graduates’ readiness for industrial challenges.

This study analyzes the comparison of the Trapezoidal, Simpson 1/3, and Simpson 3/8 to approximate numerical integration using Microsoft Excel, with the variation of the interval . The test function is  on the interval . Because it is smooth and lacks an elementary antiderivative, the results indicate that the Simpson Method outperforms the Trapezoidal method in accuracy. The Trapezoidal method yields absolute errors on the order of  to , while Simpson 1/3 and 3/8 achieve  to , with Simpson 1/3 performing best across all . These findings confirm the higher convergence order of Simpson methods ) vs . Excel implementation proves effective as an accessible learning tool for numerical methods, supporting integral computation in higher education. This research contributes to simplifying computational approaches for engineering applications and education, and opens up opportunities for more effective implementation of numerical methods in practical teaching. The results of this research are expected to enrich understanding of numerical applications in engineering and science.

This study aims to examine the effect of the Jigsaw learning model on X grade students of the Electrical Installation Engineering program at SMKS Raden Paku, enhanced with the use of the Kahoot! platform. The research employs a quantitative method with a quasi-experimental design and a nonequivalent control group design. The subjects of the study were divided into two groups: the control group, which applied the Jigsaw learning model using PowerPoint media, and the experimental group, which applied the Jigsaw model using the interactive Kahoot! media. Data were collected through pretest and posttest, as well as observation sheets to assess students' learning outcomes in the affective and psychomotor aspects. Data analysis techniques included normality test, homogeneity test, paired sample t-test, independent sample t-test, and normalized gain (N-Gain) analysis. The findings showed that the average learning outcomes difference between the control group (71.5%) and the experimental group (72.3%) was in the moderately effective category. However, the use of the Jigsaw learning model with Kahoot! had an effect on student learning outcomes, but the influence was not very large. This study provides insights into the effectiveness of using Kahoot! in the Jigsaw learning model.

Stock price prediction remains a complex challenge due to the dynamic and non-linear nature of financial markets, especially for banking stocks like PT Bank Negara Indonesia (Persero) Tbk (BBNI). This study aims to optimize BBNI stock price forecasting by integrating an automated Extract, Transform, Load (ETL) pipeline with the Long Short-Term Memory (LSTM) algorithm within a data engineering framework. Historical data from 2019 to 2025 were processed through a structured ETL sequence—including data cleaning, feature engineering, and MinMaxScaler normalization—to ensure high data quality. The dataset was partitioned into 80% for model training and 20% for testing to ensure rigorous evaluation. The results demonstrate that the systematic ETL approach significantly enhances model stability and predictive accuracy compared to conventional methods. The LSTM model effectively captured long-term temporal dependencies, providing reliable trend forecasts with an impressive test accuracy, achieving a Root Mean Squared Error (RMSE) of 0.0354. This research underscores that integrating robust data engineering practices with deep learning is essential for building resilient financial decision-support systems.

The retail industry generates an extremely large and continuously growing volume of transactional data along with the advancement of digital technology, thereby requiring sophisticated and systematic data analysis approaches to support effective and evidence-based business decision-making. This study aims to analyze retail sales data by utilizing the Retail Sales Dataset obtained from the Kaggle platform, which consists of 100,000 transaction records and broadly represents the characteristics of retail transactions. The main focus of this study is to classify product categories and predict customer segments, including the identification of high-spending customers (high spenders), based on demographic attributes such as age and gender, as well as various transaction-related features. The research methodology includes data preprocessing, label encoding, and feature engineering to generate additional variables, including Age_Group, Is_Holiday, and Spender_Group, which are expected to enhance the predictive capability of the models. Several machine learning algorithms, namely Decision Tree, Random Forest, and XGBoost, were implemented and evaluated to compare their respective performance. The experimental results indicate that multiclass product category classification achieves relatively low accuracy, ranging from 27% to 34%. These findings suggest the high complexity of retail data and highlight the need for further model optimization, class balancing techniques, and feature refinement to improve predictive performance in future studies.

This study aims to develop learning media for motorcycle hydraulic brake systems through three main aspects. First, it examines the development procedures covering the planning, design, and implementation stages. Second, it evaluates the feasibility of the developed media for Automotive Engineering Education students at Muhammadiyah University of Purworejo in terms of effectiveness, ease of use, content relevance, and visual and functional appeal. Third, the study analyzes the effect of the media on improving students’ learning motivation, including learning interest, active participation, and persistence in understanding automotive materials. The research employed a Research and Development (R&D) approach involving purposively selected students from the Automotive Engineering Education program. Data were collected using questionnaires to assess media feasibility and student responses. Data analysis consisted of a normality test, homogeneity test, and a t-test to identify significant differences between pre- and post-intervention learning outcomes. The results indicate that the developed learning media is feasible and effective, and has a positive impact on students’ learning motivation and learning outcomes at Muhammadiyah University of Purworejo.

The use of Artificial Intelligence (AI) in higher education learning has increased significantly, particularly among Informatics Engineering students. Although AI provides various benefits in supporting the learning process, its utilization also raises ethical concerns, especially related to algorithmic bias and responsible use of technology. This study aims to analyze the perceptions of Informatics Engineering students regarding bias and ethics in the use of artificial intelligence in learning. The research employed a quantitative descriptive approach. Data were collected through a Likert-scale questionnaire distributed to 80 Informatics Engineering students who had experience using AI in learning activities. Descriptive statistical analysis was conducted using mean scores and percentages. The results indicate that students demonstrate a high level of ethical awareness and responsibility in using AI; however, their perception of potential bias in AI systems remains at a moderate level. These findings reveal a gap between normative ethical awareness and critical understanding of algorithmic bias. This study recommends strengthening contextual and applied AI ethics literacy within the Informatics Engineering curriculum to promote responsible and ethical use and development of artificial intelligence technologies.

Academic productivity is a vital indicator of student success in higher education, but it is often hampered by the complexity of tasks, transitions in the learning environment, and digital distractions that trigger procrastination. This phenomenon demands a high degree of adaptability so that students do not become trapped in physical and mental exhaustion due to unmanaged workloads. Therefore, this study aims to analyze in depth the causal relationship between time management skills and academic productivity, as well as investigate their role in mitigating academic stress levels in students. The research method applied is a literature review with a qualitative-descriptive approach. The research data was sourced from secondary data in the form of 21 reputable scientific articles (national and international journals) published between 2020 and 2025. The data analysis process was carried out through the stages of data reduction, synthesis of findings, and narrative conclusion drawing to systematically map the relationship between variables. The results and discussion of the study show that time management has a significant positive correlation with improved learning achievement. Specific indicators such as daily schedule planning, priority setting, and self-regulation have been empirically proven to increase task completion efficiency and Grade Point Average (GPA) achievement. Conversely, poor time management was identified as a major predictor of cognitive overload and exhaustion, especially among students with dense curricula such as engineering majors. This study concludes that mastery of time management is not merely a scheduling tool, but a fundamental cognitive strategy that functions as a coping mechanism to maintain mental health and achieve an optimal study-life balance.

This study aims to determine the effect of implementing the Problem-Based Learning (PBL) model on student learning outcomes in the Ignition System competency at SMKN 1 Katapang. The background of this study stems from the low understanding of students regarding the ignition system material due to the dominant use of the Teacher-Centered Learning (TCL) model, which tends to make students passive and only memorize concepts without understanding the overall working process. PBL is considered more relevant because it emphasizes real problem-solving, critical thinking, collaboration, and analysis according to constructivist theory. The method used is a quasi-experiment with a Nonequivalent Control Group Design. The research subjects consist of two classes of 11th-grade Light Vehicle Engineering students: an experimental group using the PBL model and a control group using TCL, with a total population of 70 students. Data collection was done through pretests and posttests using a validated multiple-choice objective test instrument. Data analysis includes comparing the learning outcome improvements of both groups to determine the effectiveness of PBL. The results show a more significant improvement in learning outcomes in the class using the PBL model compared to the TCL class. This proves that the implementation of PBL is effective in improving analysis skills and diagnostic skills in the ignition system. Therefore, PBL is recommended as a more suitable teaching model for practice-based subjects in vocational schools, especially in automotive electrical competencies.

The gap between academic curriculum content and modern industrial needs is often an obstacle for fresh graduates in the Information Technology field, particularly in the rapidly evolving Artificial Intelligence (AI) sector. This study aims to identify the relationship patterns among technical competencies (hard skills) most demanded by the global industry. The method employed is Association Rule Mining with the Apriori algorithm to discover association rules between skills, and Network Graph Analysis to visualize the topological map of these competencies. The research dataset covers 15,000 AI job vacancies from the 2024-2025 period, analyzed in depth using Support, Confidence, and Lift Ratio evaluation parameters to validate the strength of relationships between items. The results show that Python is the central competency with the highest frequency of occurrence. Strong association rules were found indicating that proficiency in TensorFlow has a high probability of requiring Python proficiency. The Network Graph visualization reveals three main competency clusters: Data Engineering Ecosystem, Deep Learning, and Infrastructure. These findings offer a strategic foundation for aligning curricula with the job market. Focusing on strengthening the identified competency clusters is expected to directly enhance the relevance and work readiness of graduates.

This study aims to develop Google Site-based learning media on Electronic Fuel Injection (EFI) System Maintenance material for class XI students of Automotive Light Vehicle Engineering (TKRO) at SMK Negeri 1 Padang. The background of this study is based on the problems of learning that is still monotonous, less than optimal use of digital technology in the teaching and learning process, and low motivation and independence of student learning. This study uses the Research and Development (R&D) method with a 4-D development model that includes the Define, Design, Develop, and Disseminate stages. The research subjects consisted of two experts, namely media experts and material experts, two subject teachers, and 31 class XI TKRO students. Data collection techniques were carried out through validation questionnaires and practicality questionnaires. The results of the study showed that Google Site-based learning media has a very high level of validity based on the assessment of media experts by 93.33% and material experts by 90.00%. In addition, this media was considered very practical by teachers with a percentage of 94.25% and practical by students with a percentage of 78.2%. Thus, Google Site-based learning media is declared suitable for use as a learning tool to increase learning motivation, student independence, and learning effectiveness in the EFI System Maintenance material in vocational schools.  

This study aims to design and develop an electrical installation panel by applying engineering safety principles in the water spray booth of a vehicle body painting system. Field observations indicate that electrical panels in painting rooms often do not meet safety standards, which can lead to short circuits and potential fire hazards. The research employed a Research and Development (R&D) method using a simplified Borg and Gall model consisting of nine stages, starting from problem identification to effectiveness testing. Expert validation results obtained a score of 87.5% (highly valid), practicality testing yielded 90% (very practical), and effectiveness tests showed an average current of 4.1 A, with both the MCB and emergency stop functioning optimally. The developed panel product is declared feasible to be used as a practical learning media for automotive electrical systems. Based on the test results, the panel product was declared suitable for use and can be used as a learning medium in automotive electrical practice, helping to increase understanding of the application of safety in electrical installations in the automotive industry.  

This study aims to classify customer payment methods at 17 Coffee & Eatery using machine learning algorithms, namely Naïve Bayes and Support Vector Machine (SVM). The increasing use of digital and non-cash payments has generated large volumes of transaction data that are rarely analyzed optimally, even though such data contain valuable information for business decision making. This research used secondary transaction data collected from January to March 2025, consisting of 10,147 transaction records. The dataset included several attributes such as order time, payment time, transaction type, total sales, number of items, and payment method. Data preprocessing was performed through data cleaning, feature engineering, normalization, and label encoding before being divided into training and testing sets with an 80:20 ratio. The Naïve Bayes and SVM models were then trained and evaluated using accuracy, precision, recall, F1-score, and ROC–AUC metrics. The results show that both algorithms were able to classify payment methods effectively, but SVM achieved higher accuracy and more stable performance than Naïve Bayes. These findings indicate that SVM is more suitable for handling complex and heterogeneous transaction patterns. The implementation of machine learning for transaction classification can support more efficient financial management and data-driven decision making for small and medium enterprises in the culinary sector.