Publication Search

The research approach used is Classroom Action Research which is carried out in 2 cycles where each cycle is as many as 4 meetings, as for the learning steps given in the classroom action research approach, namely paying attention to teacher explanations, asking questions during discussions, collaborating with groups, presenting results and concluding material.The results showed that there was an increase in student learning outcomes seen from the test results obtained by students each cycle increased, besides that student activity in the classroom also increased. This can be seen from the number of percentages in the first cycle of the first meeting only got a percentage of 57.6% and 84.61% in the second meeting in the second cycle of the previous one, this is because students do not understand the Problem Based Learning (PBL) learning model. It was concluded that by using the Problem Based Learning (PBL) model. In learning Civics class IV UPT SPF SD Inpres Bontomanai is able to improve student learning outcomes.

In carrying out teaching and learning activities, of course learning media is needed that can support student learning. E-module is a learning media that contains images, videos and quizzes that can provide feedback in learning for students. This research focuses on developmente-mode basedandroid on the use of hand tools. Developmente-mode based android uses the ADDIE development model which has several stages, namelyanalysis, design, development, implementation, andevaluation. This research uses a research designone group pretest-posttest. The subjects of this research were class X TAV SMKN 3 Surabaya with 32 students. Validation is carried out to measure feasibilitye-mode. Student responses are needed to measure practicalitye-mode during learning. Student learning outcomes in the knowledge domain and skills domain are analyzed using the T test to measure effectivenesse-mode in learning. The research results show that (1) the validity of the developmente-mode obtained a result of 83.89% with very valid criteria, which means it is very suitable for use in learning. (2) practicalitye-mode which was developed obtained student response results of 89.47% with very practical criteria, which meanse-modebased android very practical for use in learning to use hand tools. (3) effectivenesse-mode obtained from learning results in the knowledge domain and the attitude domain. In the knowledge domain, the average value is obtainedpre-test of 48.9, while the average valuepost-test amounted to 87.91, and the T test significance value was 0.000<0.05. In the skills domain, an average skill value of 91.92 was obtained, greater than the KKM value of 75, and a T test significance value of 0.000<0.05 was obtained. It can be concluded that there is a significant increase in student learning outcomes in the realm of knowledge and skills.

Indonesia requires Islamic Religious Education (PAI) as an important part in making students competent in cognitive, affective and psychomotor aspects (IQ and EQ). PAI functions to shape students' personalities so that they become virtuous and noble human beings (SQ). To increase competence in Islamic religious education, it is necessary to develop varied learning strategies. Varied learning strategies function to design learning methods and models, so that they are able to design teaching and learning environment systems and implement effectively and efficiently what has been planned in the learning objectives. Learning strategies are classified into 5 types: (1) direct learning strategies, (2) indirect learning strategies, (3) interactive learning strategies, (4) empirical learning strategies, (5) independent learning strategies.

This research aims to develop learning tools based on science process skills on ecosystem materials at SMA Negeri 11 Enrekang. The research focuses on creating teaching modules and learner worksheets (LKPD) that can increase students' understanding and active involvement in biology learning. This study uses a 4-D development model consisting of four stages: definition, design, development, and deployment, with this research limited to the development stage. The methodology used involves analyzing the needs of students and teachers, designing learning tools, and testing the validity and practicality of the developed tools. The validity test involved two expert validators, while the practicality test was carried out by involving teachers at SMA Negeri 11 Enrekang. The assessment is carried out through a questionnaire that measures the validity and practicality of the learning tools. The results showed that the learning tools developed received an excellent validity assessment, with a "very valid" score for the teaching module and "valid" for the LKPD. The practicality test also showed positive results, with the learning tools rated "very practical" by teachers. These findings indicate that science process skills-based learning tools effectively improve students' understanding of ecosystem materials. This research significantly contributes to developing process skills-based learning tools, which can be adapted in other schools. Further research could test the applicability of these devices to other materials and in different schools to expand their application in biology learning.

The rapid growth of data-intensive applications has posed significant challenges for classical machine learning (ML) algorithms, particularly in terms of computational efficiency and scalability. This study explores the role of quantum computing in optimizing machine learning performance through the implementation of Quantum Machine Learning (QML), specifically using the Quantum Support Vector Machine (QSVM) model. The research adopts a Design Science Research approach, involving problem identification, model development, system implementation, and performance evaluation. Both classical Support Vector Machine (SVM) and QSVM models are developed and tested using benchmark classification datasets. The results indicate that QSVM outperforms the classical SVM model across multiple evaluation metrics, including accuracy, precision, recall, and F1-score. Additionally, QSVM demonstrates improved computational efficiency by reducing training time, particularly when handling high-dimensional data. These improvements are attributed to the ability of quantum computing to utilize quantum kernel methods and map data into higher-dimensional feature spaces, enabling better pattern recognition and classification performance.  Despite these promising outcomes, the study also identifies several limitations related to current quantum hardware, such as noise, decoherence, and limited qubit availability, which may affect scalability and practical implementation. Therefore, further research is required to enhance quantum hardware reliability and develop hybrid quantum-classical models. In conclusion, quantum machine learning offers a promising solution to overcome the limitations of classical approaches, providing enhanced performance and efficiency for complex data processing tasks in future intelligent systems.

The rapid growth of digital technologies has significantly increased the complexity and frequency of cyber threats, making network security a critical concern in modern information systems. Traditional security approaches, such as rule-based and signature-based systems, are often limited in detecting sophisticated and unknown attacks. Therefore, this study proposes an Anomaly-Based Intrusion Detection System (AbIDS) utilizing machine learning and deep learning techniques to enhance detection capabilities. The research adopts a Design Science Research approach, involving stages of problem identification, data collection, preprocessing, model development, system implementation, and evaluation. Several models, including Decision Tree (DT), Support Vector Machine (SVM), Convolutional Neural Network (CNN), and Long Short-Term Memory (LSTM), are implemented and compared. The results indicate that deep learning models, particularly LSTM and CNN, outperform traditional machine learning methods in terms of accuracy, precision, recall, and F1-score, while maintaining a lower false positive rate. Additionally, the integration of incremental learning enables the system to adapt to new attack patterns without requiring complete retraining, improving scalability and real-time performance. Despite the promising results, challenges such as computational complexity and false positives remain. Overall, the proposed IDS model demonstrates strong potential as an effective and adaptive solution for enhancing network security in dynamic environments.

The rapid advancement of deep learning technologies has significantly transformed healthcare analytics, particularly in medical data prediction and classification. This study proposes a hybrid Convolutional Neural Network–Long Short-Term Memory (CNN–LSTM) framework for multi-modal healthcare data analysis, integrating medical imaging, structured electronic health records (EHRs), and IoT-generated time-series physiological signals. The proposed architecture combines spatial feature extraction through CNN with temporal dependency modeling via LSTM to enhance predictive accuracy and clinical decision support. A quantitative experimental design was employed, utilizing multi-source healthcare datasets that underwent preprocessing, normalization, and feature engineering prior to model training. The performance of the hybrid model was evaluated using Accuracy, Precision, Recall, F1-Score, AUC-ROC, and Mean Absolute Error (MAE), and compared with conventional machine learning models and standalone deep learning architectures. Experimental results demonstrate that the proposed CNN–LSTM model achieves superior performance, with improved classification accuracy and reduced prediction error, while maintaining strong generalization capability. The findings indicate that integrating spatial and temporal feature learning significantly enhances disease detection, risk stratification, and personalized treatment planning. This approach supports the development of intelligent clinical decision support systems and scalable smart healthcare environments. The proposed framework offers a reliable and efficient solution for advanced healthcare analytics in IoT-enabled systems.

This study aims to determine the implementation of blended learning in improving the scientific literacy of SMA/MA students in Indonesia. This research is a type of meta-analysis research. The sample of this research comes from the analysis of 14 articles that have been published from 2017-2022. The sampled articles have been indexed by SINTA, DOAJ, Google Scholar, Scopus and Copernicus. Research sample search through google scolar and sciencedirect. The sampling technique is purposive sampling technique. The data that can be sampled only has a relationship between the independent variable and the dependent variable, namely blended learning and students' scientific literacy. The data analysis technique in this study is a quantitative data analysis technique with SPSS 21 and JSAP applications with a value of sig.0.005. The application is to calculate the value of Effect Size (ES), Mean and Standard deviation (SD). The results of this study concluded that the application of blended learning was able to increase the scientific literacy of SMA/MA students in Indonesia with an Effect size (ES) of 0.494 and an n-Gain of 0.391. So, teachers in the 4.0 revolution era must be able to apply blended learning models to students so that students are able to face current global competitors.

The rapid growth of social media platforms has generated massive volumes of unstructured textual data containing valuable information about public opinions and sentiments. Extracting meaningful insights from this data has become increasingly important for decision-making in various domains, including business, politics, and social analysis. This study aims to evaluate the effectiveness of deep learning techniques for sentiment analysis of social media data, focusing on Convolutional Neural Networks (CNN), Long Short-Term Memory (LSTM), and a hybrid CNN-LSTM model. A quantitative experimental approach is employed, where datasets are preprocessed through text cleaning, tokenization, and feature representation using word embeddings. The models are trained and evaluated using standard performance metrics, including accuracy, precision, recall, and F1-score. The results indicate that all models perform effectively in sentiment classification tasks, with the hybrid CNN-LSTM model achieving the highest performance due to its ability to capture both local textual features and long-term contextual dependencies. This demonstrates that combining CNN and LSTM architectures enhances classification accuracy compared to individual models. Furthermore, the findings confirm that deep learning approaches are more robust in handling the complexity and noisiness of social media data compared to traditional methods. This study contributes to the development of more adaptive and accurate sentiment analysis models and highlights the potential of hybrid deep learning architectures for real-world applications.

The application of cooperative learning strategies is increasingly popular in improving students' cooperation skills at various levels of education. This research aims to determine the application of cooperative learning strategies in PAI learning to increase student cooperation. The data collection used by researchers is a literature study by studying and citing several sources from textbooks, articles, journals, modules and other publications. The research results show that the application of cooperative learning strategies can improve students' cooperation skills significantly. These findings provide an important contribution to the development of learning models that are oriented towards collaboration and cooperation in the educational environment.    

National education faces challenges related to quality, efficiency and management. Several important problems in the education system include: (1) student moral behavior, (2) distribution of learning, (3) less efficient internal systems, (4) poor organization, (5) education management that is not in line with national development, and (6) lack of professionalism in resources. One effort to overcome this problem is to improve learning strategies, which are very important for the success of the learning process. One of the aspects studied in this journal is the teaching of the Islamic religion from Abuddin Nata's perspective. The results of the literature search show that an Islamic-based learning approach can shape student behavior. One effective strategy is to use an approach that is appropriate to the learning objectives and emphasizes skills and learning processes such as the Islamic education model which integrates skills, problem solving and memory formation.

This study aims to determine the effect of the mindmap-assisted STEM approach on students' Higher Order Thinking Skills in learning biology class X SMA Negeri 4 Kerinci. This research is experimental research with a group pretest-posttest design model. The population in this study came from students of class X MIPA SMA Negeri 4 Kerinci in the academic year 2021/2022. The research sample was students of class X MIPA 2 and Class X MIPA 4. The sampling technique used was the random sampling technique. The data collection technique in this study was in the form of an objective test consisting of 20 HOTS questions that had been validated by experts. Data analysis is quantitative data analysis with tests using the SPSS 21 application. The results of the study can be concluded that the STEM approach has a significant effect on students' higher-order thinking skills in learning biology with the results of hypothesis testing 0.00 < 0.05. Furthermore, the STEM approach can increase students' HOTS in biology learning, the average score of the experimental class students is 85.76 and the control class is 70.31.

This paper presents a comparative analysis of various battery management systems (BMS) in electric vehicles, with a focus on incorporating machine learning techniques to improve battery safety and extend battery life. The study evaluates conventional BMS against machine learning-enhanced models in predicting thermal runaway, state of charge (SOC), and state of health (SOH) under diverse operating conditions. Results indicate that machine learning algorithms outperform conventional methods, providing more accurate SOC and SOH estimations, thus enhancing vehicle safety and longevity.

This study explores the development and evaluation of an adaptive Intrusion Detection and Response System (IDRS) driven by Reinforcement Learning (RL) for securing 5G networks. The RL-based IDS is designed to overcome the limitations of traditional security systems by dynamically learning from real time network traffic and adapting to emerging cyber threats. Introduction: The rapid growth of 5G networks, with their increased number of connected devices and complex traffic patterns, necessitates advanced security solutions that can detect and respond to evolving cyberattacks. Literature Review: Traditional Intrusion Detection Systems (IDS), including signature based and anomaly based methods, are not equipped to handle the dynamic nature of 5G networks, leading to high false positives and low detection accuracy. In contrast, RL offers significant improvements in adaptability, detection accuracy, and response time. Materials and Method: The study simulates 5G network traffic and develops an RL-based IDS using Deep Q-Networks (DQN) and Proximal Policy Optimization (PPO) techniques. The performance of the RL-based system is compared to traditional IDS systems, focusing on detection accuracy, false positive rates, and response times. Results and Discussion: The RL-driven IDS demonstrated superior performance, achieving higher detection accuracy (95%) and faster response times (30 milliseconds) compared to traditional methods. However, challenges such as computational cost and model interpretability were identified. The study emphasizes the importance of adaptive learning mechanisms and the integration of RL into Zero Trust Architecture (ZTA) to enhance the security of 5G networks.

Autonomous vehicles (AVs) are revolutionizing transportation by relying on advanced AI techniques like deep learning and reinforcement learning for decision-making and navigation. However, concerns about the opacity of traditional AI models in safety-critical applications such as autonomous driving raise issues related to safety, accountability, and trust. This study explores the integration of Explainable AI (XAI) techniques in AV systems to enhance transparency and interpretability while maintaining high prediction accuracy. XAI methods, such as LIME (Local Interpretable Model-agnostic Explanations) and SHAP (SHapley Additive ExPlanations), provide understandable justifications for AI-driven decisions, addressing biases, fairness, and accountability. These techniques also support regulatory compliance and foster public trust in AVs. A mixed-methods approach, combining experimental simulations and user surveys, was employed to integrate XAI into AV systems and test its performance in urban traffic and highway driving scenarios. Feedback from users, collected through questionnaires and in-depth interviews, revealed that XAI-enhanced systems significantly improved the interpretability of AV decisions, leading to higher user trust and satisfaction. The study highlights the importance of balancing model complexity with interpretability, demonstrating that XAI techniques are crucial for building trust and ensuring accountability in autonomous driving systems.

This research aims to determine a role-playing strategy model in strengthening religious character through learning short story texts. The research method used is the Design Based Research (DBR) method. The research stage is divided into five parts, namely problem identification, product development formulation, product design and development, product testing, and communicating results. The results of observing teacher activities through role playing strategies show that the score obtained from observer one is 92 in the very good category, while the score obtained by observer two is 90 in the very good category. The results of observing students' activities through role playing strategies showed that the score obtained from observer one was 94 in the very good category, while the score obtained by observer two was 92 in the very good category. Based on the results of data analysis obtained from students' self-assessment questionnaires regarding strengthening religious character through learning short story texts using role-playing strategies. The total score obtained by students was 1163 and the average number obtained from 15 students was 77 with a percentage of 96%. To strengthen the character of religiosity in students, teachers must be more creative in cultivating the value of religious character in students through the learning process.

This study compares different machine learning models for time series forecasting in financial data analysis. Models including ARIMA, LSTM, and GRU are applied to predict stock price movements. We measure the accuracy and computational efficiency of each model on various datasets and discuss their strengths and weaknesses in financial forecasting contexts. The findings suggest that deep learning models show significant improvement in capturing complex temporal patterns over traditional methods.

This study presents an advanced structural health monitoring (SHM) system for steel bridges based on wireless sensor networks (WSN) integrated with machine learning algorithms. The proposed system monitors and predicts structural integrity under various load conditions. The research focuses on developing a machine learning model capable of real-time anomaly detection, allowing for early warnings of potential failures. Experimental results from both simulation and field tests demonstrate the system’s effectiveness in prolonging bridge lifespan while reducing maintenance costs.

The growing environmental crisis underscores the need for education systems to foster ecological responsibility among students. This study explores the potential for multifaith schools to cultivate environmental moral education through an interreligious pedagogical model. By integrating diverse religious teachings on ecology, the proposed model aims to promote shared moral values for environmental protection and sustainability. The research addresses the gap in existing environmental education, which often lacks an integrated approach that incorporates various religious perspectives. Through a qualitative research design, the study analyzes curricula, observes classroom practices, conducts interviews with educators, and evaluates existing environmental education frameworks in multifaith schools. The study identifies key strategies, including the incorporation of eco-ethics from different religious traditions, project-based learning, and interfaith dialogues, as effective means of fostering ecological responsibility. However, challenges such as balancing doctrinal differences, overcoming biases, and developing inclusive pedagogy remain. The study emphasizes the importance of designing educational content that respects all faiths and promotes intercultural dialogue, thereby encouraging a collective commitment to sustainability. The findings suggest that multifaith schools can serve as powerful platforms for environmental moral education, highlighting the value of integrating religious perspectives into sustainability education. The study concludes with recommendations for incorporating interreligious eco-ethics into curricula and teacher training programs and suggests future research on the long-term impact of interreligious environmental education and its applicability in diverse cultural contexts.

This study explores the integration of predictive analytics into supply chain management within national e-commerce enterprises. Predictive analytics, which utilizes historical data combined with machine learning algorithms, regression analysis, and time series forecasting, has shown significant improvements in operational efficiency. The study focuses on four key areas: demand forecasting, inventory management, transportation optimization, and customer satisfaction. By predicting demand more accurately, e-commerce platforms can reduce stockouts and overstock situations, streamline logistics routes, and lower logistics costs. The implementation of predictive analytics led to a 20% reduction in delivery times and a 15% decrease in logistics costs, thereby enhancing customer satisfaction. However, the study also highlights challenges in integrating real-time data from multiple sources and scaling predictive models across diverse product categories and geographic regions. The results emphasize the need for e-commerce platforms to invest in technology that enables seamless data integration and the development of region-specific predictive models. The findings are compared with industry benchmarks, showing that the improvements in logistics and supply chain performance align with global trends. Based on these results, the study recommends best practices for implementing predictive analytics, including effective data collection, machine learning model training, and scalability considerations. By following these practices, e-commerce companies can optimize their supply chains, reduce operational costs, and increase customer satisfaction, positioning them for greater competitive advantage in the marketplace.