Publication Search

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.

This article explores the reframing of holistic education by integrating spirituality and ethics as core components to achieve transformative impact. The study highlights the limitations of conventional education systems that prioritize cognitive development while neglecting moral and spiritual dimensions. The objective is to propose a more comprehensive educational paradigm that nurtures learners as whole individuals—intellectually, emotionally, morally, and spiritually. Using qualitative literature analysis, this study identifies the role of spiritual and ethical integration in shaping character, enhancing empathy, and fostering social responsibility. The findings suggest that embedding these values within curriculum design and instructional practices contributes to meaningful personal development and community transformation. By addressing the growing need for a more inclusive approach to education, the article emphasizes how integrating spirituality and ethics can bridge gaps in traditional educational models. The research underscores the importance of fostering emotional and moral intelligence alongside intellectual growth, particularly in a world where global challenges require not only intellectual problem-solving but also ethical decision-making and empathy. The implications emphasize the need for inclusive and humanistic approaches in education, encouraging educators to act as facilitators of life values and agents of change. Through the integration of spirituality and ethics, education can help shape a new generation of compassionate leaders and engaged citizens. By reimagining holistic education through this lens, the article offers a framework that aligns academic achievement with ethical consciousness and spiritual growth, ultimately fostering a more just and compassionate society. This transformative approach offers a comprehensive model for educators and policymakers aiming to prepare students not only for professional success but also for meaningful lives rooted in integrity and responsibility.

This study is motivated by the limited research on holistic education in developing 21st-century skills to address the challenges of the digital era, despite its significant implications for future human resource quality. The objective of this research is to explore the concept of holistic education based on 21st-century skills and its relevance in the digital era through a literature review approach. The method employed is qualitative, focusing on an analysis of academic literature, including documents, journals, books, and various scholarly sources. The analysis was conducted thematically to investigate the principles, models, and practices of holistic education that support the development of critical thinking, creativity, communication, and collaboration skills. The findings indicate that holistic education can serve as a key approach to prepare younger generations to navigate the complexity of the digital era with adaptive, ethical, and innovative thinking skills. This review enriches the literature on holistic education and highlights the importance of an integrated approach that intertwines cognitive, emotional, social, and technological dimensions within the context of modern learning. Practical implications include recommendations for educators and policymakers to design curricula based on 21st-century skills and integrate digital technologies into building holistic learning processes. This study also offers opportunities for further research on the implementation of holistic education in diverse cultural and geographical contexts.

This study is a library research that aims to analyze the concept and relevance of coastal education in the Straits of Malacca in shaping character and improving the welfare of maritime communities. The study reviews a wide range of literature, including scientific journals, books, and policy documents related to character education, Malay local wisdom, and environmental education in coastal areas. The findings indicate that education in the coastal region of the Straits of Malacca serves not only as a means of knowledge transmission but also as a medium for internalizing the cultural and moral values of the Malay maritime community—values characterized by religiosity, independence, and environmental awareness. The ideal form of coastal education is an integrative model that combines Islamic character values, local wisdom, and ecological consciousness within a contextual learning system that reflects the realities of maritime life. The study concludes that strengthening character education based on coastal culture can serve as an effective strategy for creating resilient, competitive, and sustainable coastal societies amid global social and ecological change.

In the 2013 curriculum there are various learning materials that can be implemented by students as a means of physical activity, one of which is shooting free throw, in this material students have difficulty in understanding and lack of skill in implementation. The purpose of this study was to determine the effect of the explicit instruction model on shooting free throw learning outcomes. The type of research used is a pre-experiment with a one group pretest posttest design. The research sample was selected using cluster random sampling technique, consisting of 32 students of class VI-D SDN Rungkut Menanggal I/582 Surabaya. The research instrument used was a learning outcome test, which included a knowledge test in the form of 10 multiple choice questions, and a skill test in the form of 10x free throw shooting. Through the results of the Wilcoxon test and the results of the percentage increase, the knowledge showed a p-Value of 0.00 (sig <0.05) with an increase of 62.83%. Process-oriented skills show p-Value 0.00 (sig < 0.05) with an increase of 231%. Meanwhile, product-oriented skills showed a p-Value of 0.80 (sig ≥ 0.05). The results showed that the application of the explicit instruction model had an effect on the learning outcomes of free throw shooting in the aspects of knowledge and process-oriented skills, but had no effect on the aspects of product-oriented skills.

The Learning Model is a guide for teachers and students in implementing the teaching and learning process. In the model or learning method used, it must aim to improve the learning process or lecture. Therefore, this research will discuss what methods or models can be used to improve the quality of real analysis learning. The method used in this research is Systematic Literature Review (SLR).

Indonesian language subjects consist of several subjects that require students to be able to write, one of which is writing expository texts. The student participants had problems in writing material, especially writing expository texts, which was proven by the average score which was still not optimal. The formulation of the problem raised in this research is how the window shopping type cooperative learning model influences the ability to write expository texts of class X students at Budisatrya Medan Private High School. This research aims to determine the effect of the window shopping type cooperative learning model on the ability to write expository texts of class X students at Budisatrya Medan Private High School. This research is a type of quantitative research using experimental methods, a research method used to determine the effect of a treatment on the characteristics of the subjects studied. The data collection techniques used in this research were observation techniques, interview techniques and test techniques, with data sources consisting of 35 students. Based on data analysis, it can be concluded that: The window shopping type cooperative learning model has an influence on the ability to write expository texts in class This can be seen and proven by the average post-test results for the control class being 69.857 with the average post-test results for the experimental class being 85.

The aim of this research is to determine the positive and significant influence of the Team Assisted Individualization (TAI) learning model on the PAK Learning Motivation and Characteristics of Class VIII Students of SMP Negeri 4 Tarutung, North Tapanuli Regency for the 2023/2024 academic year. The method used in this research is a quantitative method with inferential descriptive data analysis. The population is all 122 students of class VIII of SMP Negeri 4 Tarutung for the 2023/2024 academic year who are Protestant Christians and a sample of 49 people was determined using random sampling techniques. Data was collected using a closed questionnaire with 45 items, namely 21 questionnaire items for variable Class VIII of SMP Negeri 4 Tarutung for the 2023/2024 Academic Year, proven through the following data analysis: 1) Test analysis requirements: a) positive relationship test obtained by the value rxy = 0.561 > rtable(=0.05,n=49) = 0.281, so it is known that there is a positive relationship between variable significant difference between variable b) Regression coefficient of determination test (r2) = 31.5%. 3) Test the hypothesis using the F test to obtain Fcount > Ftable=(=0.05, dk numerator k=20, dk denominator=n-2=49-2=47) namely 21.59 > 1.51. Thus Ha is accepted and H0 is rejected.

In the development of media selection, teaching materials are part of a learning development that cannot be separated from other learning components in a system. Therefore, the selection of media has a variety and methods in accordance with various development models for selecting media for existing teaching materials, including the criteria used in selecting the media. This research aims to determine developments in the selection of teaching material media that will be used in the learning process and as a reference for teachers to develop a teaching material media in the learning process. This research uses qualitative research methods with the type of library research. Qualitative research is the process of producing information in the form of notes and descriptive data. The results of this research show that the development in selecting teaching material media is: (1). selecting teaching materials that fulfill one of the interesting teaching materials and helps students achieve competency and aims to help in the students' learning process, (2) determining the choice of teaching material criteria. must have the ability to improve students' memory, (3) teachers must be skilled in using teaching materials that will be used in learning.

The 21st century is an era where knowledge is easily spread and technology is developing rapidly. The close relationship between science and technology allows for accelerated synergy. This study aims to determine the effect of the Project Based Learning model based on Science, Technology, Engineering, Mathematic. In the subject of Biology on the ability to think critically and creatively in class XII high school students. This study used a Quasi Experiment with research subjects in class XII IPA SMAN 1 Kademangan. The sample used was 34 students as the control class and 34 students as the experimental class. The data analysis technique used is the prerequisite test for normality and homogeneity and the ANACOVA hypothesis test. The results show that there is an increase in critical thinking skills and in the experimental class of 72,6%. In addition, there are differences in the abiliy to think creatively in student who used STEM integrated PJBL. PJBL terintegrasi STEM Meningkatkan Kemampuan Berpikir Kritis dan Kreatif Siswa Kelas XII SMA

The aim of this research is to determine the positive and significant influence of implementing the Group Investigation Type Cooperative Learning Model on the Learning Motivation of PAK Class IX Students at SMP Negeri 1 Simanindo, Samosir Regency for the 2023/2024 Academic Year. The research method used is a quantitative method and a pre-experimental design research type in the form of "One Shot Case Study". The population was all class IX students of SMP Negeri 1 Simanindo, totaling 189 people and a sample of 32 people was determined using the Purposive Sample technique. Data was collected using a research instrument of 36 items, namely 16 items for variable 0.05,n=32) = 0.349. b) Testing a significant relationship obtained a value of tcount= 4.354 > ttable(a=0.05,dk=n-2=30)= 2.042. 2) Test the effect: a) Test the regression equation, obtained the regression equation Y ̂="16.45"+0.98X. b) Regression coefficient of determination test (r2) = 38.7%. 3) Test the hypothesis using the F test to obtain Fcount > Ftable=(a=0.05, dk numerator k=13, dk denominator=n-2=32-2=30) namely 18.94 > 2.09. Shows that there is a positive and significant influence of the application of the Group Investigation Type Cooperative Learning Model on the PAK Learning Motivation of Class IX Students of SMP Negeri 1 Simanindo, Samosir Regency for the 2023/2024 Academic Year. Thus Ha is accepted and H0 is rejected.

Obtaining high-quality, diverse, accurate datasets for sentiment analysis has always been a significant challenge. Traditional approaches include annotators, which may introduce bias to datasets and are also time-consuming and expensive. These types of datasets may also not represent the variety needed to train robust and generalizable sentiment analysis models. This study introduces a novel combination of techniques to approach the problem with a novel solution. The proposed system, SentiGEN includes the use of a transformer, T5, fine-tuned and optimized using an evolutionary algorithm to generate high-quality, diverse, accurate data for sentiment analysis. The generated data is validated using XLNet to ensure high sentiment accuracy. This combination of technologies has proven successful based on the results derived from evaluating multiple models. From complex transformers such as BERT to more straightforward approaches like KNN, those trained using synthetic data demonstrated superior performance compared to their counterparts trained on real data. This enhancement in predictive accuracy was observed when evaluated on benchmark datasets such as SST-2 and Yelp. SentiGEN can generate high-quality, diverse, accurate, realistic data for sentiment analysis and successfully increased the performance of models trained on synthetic data compared to the same model trained on real data.

The aim of this research is to determine whether students' interest in learning about Christian Religious Education and Character Education who are taught using the talking stick learning model is higher than students who are taught without the talking stick learning model in class IX of SMP Negeri 1 Sitiotio for the 2023/2024 academic year. The method used in this research is a quantitative research method with True Experimental design Posttest Only Control statistics. The population is all class IX students of SMP Negeri 1 Sitiotio for the 2023/2024 academic year, totaling 103 people. The sample was determined using a technique taken deliberately (purposive sampling) with the specified conditions that the material being experimented on was in that class, namely class IX-B with 36 people as the experimental class and class IX-C with 7 people as the control class. The research instrument used a 26-item closed questionnaire. The t test used is the separated variance t test according to the analysis requirements, namely n1≠n2 and the variance of the two sample groups is not homogeneous. The results of hypothesis testing obtained a value of t = 11.233 > t table = 2.691, so H0 was rejected and Ha was accepted. This research concludes that there is a higher interest in learning about Christian religious education and character in students who are taught using the talking stick learning model than students who are taught without the talking stick learning model in class IX of SMP Negeri 1 Sitiotio for the 2023/2024 academic year.

In the evolving landscape of agricultural technology, recognizing rice diseases through computational models is a critical challenge, predominantly addressed through Convolutional Neural Networks (CNN). However, the localized feature extraction of CNNs often falls short in complex scenarios, necessitating a shift towards models capable of global contextual understanding. Enter the Vision Transformer (ViT), a paradigm-shifting deep learning model that leverages a self-attention mechanism to transcend the limitations of CNNs by capturing image features in a comprehensive global context. This research embarks on an ambitious journey to refine and adapt the ViT Base(B) transfer learning model for the nuanced task of rice disease recognition. Through meticulous reconfiguration, layer augmentation, and hyperparameter tuning, the study tests the model's prowess across both balanced and imbalanced datasets, revealing its remarkable ability to outperform traditional CNN models, including VGG, MobileNet, and EfficientNet. The proposed ViT model not only achieved superior recall (0.9792), precision (0.9815), specificity (0.9938), f1-score (0.9791), and accuracy (0.9792) on challenging datasets but also established a new benchmark in rice disease recognition, underscoring its potential as a transformative tool in the agricultural domain. This work not only showcases the ViT model's superior performance and stability across diverse tasks and datasets but also illuminates its potential to revolutionize rice disease recognition, setting the stage for future explorations in agricultural AI applications.