Publication Search

Indonesian language learning in elementary schools, especially on figurative language, still faces various problems, such as difficult to understand material, limited learning media, and low student interest and understanding. This is also experienced by fifth-grade students of SD 1 Mlati Lor who have difficulty recognizing types of figurative language and understanding their meaning well in context. This study aims to develop an interactive flipbook media about figurative language that highlights the local wisdom of North Sulawesi and test its feasibility and practicality for semantic learning. The method used in this study is research and development (R&D) with the ADDIE model, which consists of analysis, design, development, implementation, and evaluation. The research subjects were fifth-grade students of SD Negeri 1 Mlati Lor. Data collection was carried out through interviews, observations, validation by material and media experts, questionnaires for teachers and students, and learning outcome tests. Data were analyzed using qualitative and quantitative descriptive approaches. The results of the study indicate that the interactive flipbook media inspired by the local wisdom of North Sulawesi was considered very valid by experts. Furthermore, practicality testing demonstrated that teachers and students responded in the "very practical" category, indicating that the media was easy to use and well-received in learning. The application of local cultural elements has been shown to help students understand figurative language concepts more clearly and meaningfully. Therefore, the developed flipbook can be used as an alternative Indonesian language learning medium to improve students' semantic understanding and cultural knowledge in elementary schools.

This study explores the integration of deep learning based approaches in real time video content analysis for intelligent human computer interaction (HCI) in multimedia systems. Traditional video analysis techniques, such as rule-based methods and offline processing, struggle with real time performance and adaptability to complex video data. In contrast, the deep learning model used in this research, particularly Convolutional Neural Networks (CNNs), provides high accuracy in object detection, feature extraction, and real time processing. The integration of CNNs with interactive visualization modules enables dynamic adjustments to video content based on user interactions, ensuring a seamless and engaging user experience. The system was benchmarked in terms of its processing speed, accuracy, and responsiveness, showing significant improvements over traditional approaches in real time video analysis. Moreover, the study demonstrates that combining deep learning with real time visualization enhances the efficiency of interactive multimedia applications, making it suitable for dynamic environments such as surveillance, security monitoring, and interactive media. Despite the system's strong performance, challenges such as computational demands in high-resolution video processing were identified, highlighting the need for further optimization. Future work will focus on optimizing the system for different hardware platforms, incorporating multimodal inputs, and refining deep learning models to address computational bottlenecks. This research contributes to advancing HCI by providing insights into the integration of deep learning for real time video content analysis, which is pivotal for enhancing the interactivity and adaptability of intelligent multimedia systems.

The era of digitalization demands that the world of education adapt quickly to technological developments. One of the basic skills that elementary school students need to have is the ability to operate a computer, particularly in typing and using word processing applications. Community service research was conducted at the Kemala Bhayangkari Foundation 1 Medan with the aim of improving students' digital literacy thru typing training using Microsoft Word and the interactive media 10fastfingers.com. The training method is conducted using a workshop model, which consists of two main topics. The first material is a basic introduction to typing using the ASDF;LKJ pattern and the use of important keyboard keys. The second material is an introduction to basic Microsoft Word features, such as changing font type and size, using Bold, Italic, Underline, changing text color, and highlighting. Additionally, students are trained to use 10fastfingers.com to interactively improve their typing speed and accuracy. The research instruments are pretest-posttest, observation, and student response questionnaires. The research results show a significant improvement in typing skills. Average speed increased from 8–10 words per minute to 20–25 words per minute, with over 85% accuracy. Student responses were also very positive; they felt more confident, more motivated, and able to use Microsoft Word more effectively. This training program has proven effective in improving digital literacy among elementary school students while also fostering an interest in technology-based learning.

Real time decision making applications, such as those used in autonomous vehicles, smart cities, and industrial IoT, require fast, scalable, and accurate analytics to ensure timely responses and optimized operations. Traditional cloud-based systems face significant challenges in meeting these requirements due to high latency, limited scalability, and bottlenecks in data processing. This study explores the use of a hybrid Edge Cloud architecture to optimize End to end machine learning (ML) pipelines for real time applications. The proposed system offloads time-sensitive tasks to edge devices, while computationally intensive processes are handled by the cloud, ensuring efficient use of resources and reduced latency. Experimental results demonstrate that the hybrid model reduces inference latency by up to 70% compared to cloud-only systems, while maintaining model accuracy and increasing throughput. Additionally, the scalability of the hybrid architecture is highlighted, as it can handle large-scale data streams and adapt to varying workloads. The findings show that hybrid Edge Cloud architectures are well-suited for applications where fast decision making is critical, such as autonomous systems and real time analytics in smart cities. However, challenges remain in managing resources across edge and cloud systems, particularly in balancing computational loads and ensuring system reliability. Future research should focus on optimizing task partitioning, integrating advanced edge AI models, and exploring the use of 5G networks to enhance performance further. Overall, the study demonstrates the potential of hybrid Edge Cloud systems in overcoming the limitations of traditional cloud-based ML pipelines and provides insights into the future of real time data processing.

Electronics learning in higher education continues to face various challenges, particularly in the provision of interactive learning media capable of concretely and engagingly visualizing the form, characteristics, and working principles of electronic components. The limitations of conventional learning media often result in abstract learning processes, which in turn lead to a low level of student understanding of basic electronics concepts. This study aims to develop the AMPERE as an innovative and technologically relevant interactive learning medium. The research employed R&D approach using the Borg & Gall model, which includes the stages of needs analysis, design, product development, validity testing, and limited implementation. The AMPERE application was developed using marker based AR technology, in which a smartphone camera detects markers to display and interact with 3D electronic component objects in real time. The results indicate that the AMPERE application achieved a high level of validity, with a score of 0.88 from subject-matter experts and 0.84 from media experts, and was therefore deemed suitable for use as a learning medium. The small-group trial results showed a practicality level of 82.07%, while the practicality test during the implementation stage reached 85.67%. These findings demonstrate that AMPERE is effective in enhancing learning interactivity and assisting students in understanding the form, function, and working principles of electronic components through smartphone-based digital visualization. Theoretically, these results are consistent with constructivist learning theory, which emphasizes active knowledge construction through direct experience and interaction with learning objects.

The increasing adoption of collaborative robots in modern manufacturing environments requires reliable perception systems that can ensure both safety and operational efficiency during human–robot collaboration. This study proposes a CNN-based real-time computer vision system for object and human detection in shared robotic workspaces. The research focuses on developing and evaluating a single-stage deep learning detection model optimized for real-time performance while maintaining high detection accuracy. The proposed methodology includes dataset preparation, model training using transfer learning, real-time system implementation, and comprehensive performance evaluation. Experimental results demonstrate that the developed system achieves high detection accuracy, as reflected by strong precision, recall, and mean Average Precision (mAP) values, while maintaining low inference latency suitable for real-time operation. The system consistently operates above real-time frame-rate thresholds, ensuring timely perception updates required for safety-related decision-making in collaborative robotic environments. Graphical and quantitative analyses further confirm the stability of inference performance under dynamic interaction scenarios involving human movement and multiple objects. Compared with existing approaches, the proposed system provides a balanced trade-off between accuracy and computational efficiency, making it practical for deployment in safety-aware human–robot collaboration scenarios. Overall, the findings indicate that CNN-based real-time object detection systems can effectively support perception and situational awareness in collaborative robotics, contributing to safer and more efficient industrial automation.

Concept drift, the phenomenon where the statistical properties of data streams change over time, poses a significant challenge in machine learning, particularly for long term data streams. Traditional machine learning models, including batch learning and non-adaptive approaches, struggle to detect and adapt to these changes, leading to degraded performance and inaccurate predictions. This study proposes an adaptive computational model designed to detect and respond to concept drift using incremental learning techniques and statistical drift detection mechanisms. The model integrates an Adaptive Drift Detector (ADD) and Incremental Learning System, enabling real-time adjustments to data distribution changes. The model is evaluated across synthetic and real-world datasets, demonstrating its superior ability to detect abrupt, gradual, and recurring drifts compared to traditional models. Experimental results indicate that the adaptive model maintains high prediction accuracy, minimizes false positive rates, and reduces detection delays. Furthermore, the model performs well in resource-constrained environments, making it suitable for real-time applications such as healthcare prediction, fault detection, and IoT systems. Despite its promising performance, the study identifies challenges related to computational complexity and the model’s performance with imbalanced datasets and noisy data. Future research should focus on optimizing the model’s scalability, computational efficiency, and adaptability to more complex data types to ensure broader applicability in dynamic environments. This work contributes to advancing the detection and adaptation of concept drift, offering a robust solution for dynamic and evolving data streams.

Teaching fiction in Indonesian language classrooms is often constrained by text-centered instruction and limited use of engaging digital media. In the era of Generation Z learners who are visually and digitally oriented, innovative learning materials are needed to enhance motivation, interpretation, and comprehension of literary texts. This study aims to develop and evaluate a Scribus-based digital magazine for fiction learning by integrating the ADDIE model within a qualitative descriptive framework. The research adopted a qualitative descriptive design comprising five stages of the ADDIE model: Analysis, Design, Development, Implementation, and Evaluation. The study was conducted at SMP Negeri 10 Semarang, involving one Indonesian language teacher and fifteen Grade VIII students, who were selected through purposive sampling. Data were collected through observation, interviews, and documentation, and analyzed using the Miles and Huberman model (data reduction, data display, conclusion drawing). Media and content experts conducted validation to assess the feasibility, usability, and pedagogical quality of the content. Findings revealed that the Scribus-based learning media effectively increased students’ engagement and comprehension in analyzing fictional elements such as plot, character, and setting. Expert validation results indicated a high feasibility level, with mean scores above 85% in design and content quality. Teachers reported improved classroom interaction and creativity, while students expressed enthusiasm for the visual and interactive format. The study concludes that open-source tools, such as Scribus, can provide cost-effective and pedagogically sound alternatives for developing literary learning media. The integration of ADDIE and multimodal design promotes contextual, engaging, and sustainable learning experiences. Future research should explore multimedia enhancements, such as audio storytelling and cross-curricular applications, to broaden the pedagogical impact.

The integration of Augmented Reality (AR) technology into higher education has emerged as a promising approach to enhance collaborative learning experiences. This study aims to design and evaluate an AR multimedia framework that facilitates real time interaction and spatial visualization, creating immersive and engaging learning environments for students. The AR framework was developed with a focus on improving student engagement, collaboration, and learning outcomes through interactive 3D models and real time feedback. By leveraging AR technology, the study sought to address common challenges in traditional learning environments, such as limited student interaction and engagement, and lack of real time feedback. The experimental evaluation involved two student groups: one using the AR-based system and the other using conventional multimedia tools. Findings revealed that students using the AR framework showed significant improvements in engagement, interaction frequency, and collaborative task performance. Additionally, the AR framework contributed to better learning outcomes, including enhanced comprehension, retention of complex concepts, and improved problem-solving skills. The study also highlighted the importance of incorporating a user-centered design approach in developing AR applications to ensure that the system meets the needs and preferences of learners. Qualitative feedback from students indicated that the AR system provided an enriched learning experience, although challenges such as interface navigation were noted. Overall, the study demonstrates the effectiveness of AR in fostering collaborative learning and offers practical insights for its integration into higher education curricula. Future research should explore the integration of AR with other immersive technologies to further enhance collaborative learning experiences.

This study aims to determine the effectiveness of the Problem Based Learning (PBL) model integrated with Canva in improving students’ reflective thinking skills in the Aqidah Akhlaq subject at MTsN 3 Tuban. Reflective thinking is an essential competency that enables students to analyze moral behavior, evaluate decision-making processes, and connect Islamic ethical concepts with real-life experiences. However, preliminary observations indicated that students’ reflective thinking skills were still low and tended to remain at the level of theoretical understanding without deeper analysis. This research employed a pre-experimental design using a one-group pretest–posttest model. The subjects consisted of 30 eighth-grade students. The research instrument was a reflective thinking test developed based on indicators of moral evaluation, situation analysis, and experiential reflection, which had been validated through expert judgment. The learning process was conducted by applying the stages of Problem Based Learning integrated with Canva as a visual media to organize problem-solving steps and present students’ reflective outputs. Data were analyzed using descriptive statistics and a paired samples t-test. The findings showed a significant improvement in students’ reflective thinking skills after participating in PBL learning supported by Canva. Pretest scores ranged from 48 to 71 with an average of 59.67, while posttest scores increased to a range of 60 to 89 with an average of 71.20. The mean gain of 11.53 points was statistically significant as indicated by the t-test results (t = 10.39; sig. = 0.000), further supported by Cohen’s d value of 1.90, which falls into the category of a very large effect size. Qualitatively, students demonstrated enhanced abilities in identifying core problems, analyzing alternative actions, evaluating their cognitive processes, and visualizing moral reflections systematically through Canva. In conclusion, the PBL model integrated with Canva is effective in improving students’ reflective thinking skills in the Aqidah Akhlaq subject. This model not only enhances academic outcomes but also strengthens character development, creativity, and higher-order thinking skills, which are essential for 21st-century learning.

Distributed software systems face significant challenges related to data quality due to their complex, decentralized architecture. These systems often involve multiple nodes responsible for processing and storing data, making it difficult to maintain consistency and ensure accurate data across the entire network. In particular, issues like data inconsistency, latency, and data fragmentation are prevalent in distributed environments. To address these challenges, this study proposes an integrated data quality governance strategy that combines real time monitoring and automated anomaly detection using machine learning models. The proposed strategy aims to improve data consistency, enhance anomaly detection capabilities, and reduce the need for manual intervention, ultimately improving overall data governance in distributed systems. Real time monitoring ensures immediate identification of data issues as they occur, while machine learning models, such as autoencoders and Isolation Forests, automate the detection of anomalies based on high reconstruction errors and data isolation techniques. The study evaluates the proposed strategy through real-world distributed system scenarios, comparing its effectiveness to traditional approaches like periodic audits and manual validation. Results demonstrate that the integrated approach leads to faster anomaly detection, reduced data inconsistencies, and improved overall system performance. The use of advanced machine learning techniques and real time analytics significantly enhances the system's ability to maintain high data quality standards across multiple distributed nodes. This strategy has wide-ranging implications for industries that rely on distributed systems, such as finance, healthcare, and IoT, where data integrity is essential for operational success. Future research can focus on integrating more advanced machine learning techniques and optimizing the real time monitoring framework to handle larger and more complex systems.

This research aims to develop a multiclass flower image classification system using the Convolutional Neural Network (CNN) algorithm with the EfficientNet architecture. The main problem addressed is the difficulty of manual identification of flower species that share high visual similarity. The research stages include collecting 17,299 flower images across 19 classes, performing data preprocessing such as image resizing, pixel normalization, and augmentation, followed by model training using the EfficientNet transfer learning approach. The model was trained for 10 epochs with an 80:20 training-validation data split. The evaluation results show that the model achieved a validation accuracy of 98.05% with a loss value of 0.0968, and an average precision, recall, and F1-score of 0.98. The trained model was then implemented into a web-based application built using the Next.js framework, enabling users to upload flower images and obtain real-time classification results via the Hugging Face API. The system successfully identified flower species with a confidence level of 99.87%. These findings demonstrate that combining a modern CNN architecture with transfer learning provides efficient and highly accurate flower classification performance, which can be effectively implemented for educational and digital conservation purposes.

The increasing complexity and scale of modern cybersecurity threats necessitate the development of advanced systems capable of efficiently detecting, analyzing, and mitigating incidents in real time. This paper proposes an automated framework for digital forensics and incident response that leverages big data analytics and real time network traffic profiling. The framework integrates cutting-edge technologies, including Apache Spark for real time data processing and Hadoop for scalable data storage, combined with machine learning models like LSTM and Autoencoders to detect anomalies and threats in network traffic. By automating the process of incident detection and response, this framework significantly reduces the time required to identify threats and improves the accuracy of forensic evidence correlation across heterogeneous network environments. The study highlights the advantages of using machine learning models and big data tools to address the limitations of traditional manual and semi-automated systems, which often struggle to keep pace with large-scale data generation. Testing results demonstrate that the proposed framework can handle large data volumes efficiently, providing real time, actionable insights with significantly reduced response times. Additionally, the framework improves forensic analysis by enabling the correlation of evidence from different devices and protocols, making it more effective than traditional methods in identifying the root cause of security incidents. However, challenges related to data heterogeneity, scalability, and system integration were encountered during testing. The proposed framework holds promise for significantly enhancing the efficiency and effectiveness of cybersecurity operations, with future work focusing on further integration of advanced AI techniques and machine learning models for dynamic and adaptive incident response.

Explainable Artificial Intelligence (XAI) has become a critical area of research within artificial intelligence, focusing on improving the transparency and interpretability of machine learning (ML) models, often referred to as "black-box" models. The need for XAI techniques arises from the inherent complexity of ML models, which can make their decision-making processes difficult for users to understand. This study investigates various XAI techniques, including LIME (Local Interpretable Model-agnostic Explanations) and SHAP (SHapley Additive exPlanations), to assess their impact on model interpretability without significantly compromising predictive performance. A comparative experimental design was used, applying these XAI methods to different ML models, including deep neural networks and ensemble methods, within large-scale enterprise data analytics systems. The results indicate that XAI methods significantly enhance model transparency and decision traceability, allowing users to understand the influence of individual features on predictions. While a slight reduction in predictive accuracy was observed, especially with simpler models, the trade-off between interpretability and performance was deemed acceptable, particularly in fields requiring transparency, such as healthcare, finance, and autonomous systems. The use of XAI in enterprise data systems has practical implications for fostering trust and enabling informed decision-making among stakeholders. Furthermore, the study discusses the challenges and limitations of applying XAI techniques, such as complexity, scalability, and model-specific limitations. Future research is suggested to focus on developing more scalable and efficient XAI methods, enhancing their applicability across various model types, and addressing the challenges of real-time applications. This will be crucial in ensuring the widespread adoption of XAI in critical domains, promoting the ethical use of AI while maintaining predictive accuracy.

The increasing sophistication of cyber threats has rendered traditional cybersecurity models insufficient in safeguarding enterprise networks. This study introduces a risk aware cybersecurity governance model that integrates real time threat intelligence with predictive anomaly detection to proactively mitigate potential threats. By leveraging advanced machine learning and AI techniques, the model enhances the ability to identify and address cyber threats before they can escalate into significant incidents. The model’s ability to predict anomalies, analyze real time threat intelligence feeds, and provide early warnings allows for faster response times and reduced risk exposure compared to traditional reactive models. Through simulations and real-world use cases, the proposed model demonstrated a 30% reduction in response time and a 25% decrease in overall risk exposure, showing its potential to improve security decision-making and resilience in dynamic threat environments. Unlike traditional models that rely on static rules and periodic policies, the proposed model uses predictive analytics to stay ahead of evolving threats, ensuring continuous monitoring and rapid adaptation. This proactive approach enhances organizational resilience, particularly in handling sophisticated cyber threats such as ransomware, malware, and phishing attacks. Despite its effectiveness, challenges such as data overload, scalability, and the need for interpretability in AI models remain. Future research will focus on refining predictive models, improving scalability for larger networks, and enhancing the explainability of machine learning models to foster greater trust in automated cybersecurity systems. This study contributes to the ongoing evolution of cybersecurity governance by demonstrating the value of integrating predictive and real time monitoring technologies for enhanced threat detection and mitigation.

User reviews on the Shopee e-commerce platform represent an important source of information for understanding consumer perceptions of products and services. Sentiment analysis is commonly applied to classify user opinions into positive, neutral, and negative sentiment categories based on textual data. This study aims to analyze the performance of the Long Short-Term Memory (LSTM) method in sentiment classification of Shopee user reviews. The dataset used in this study consists of Indonesian-language user reviews that have undergone preprocessing stages, including case folding, text cleaning, tokenization, and stopword removal. The LSTM model was trained using preprocessed text represented as word sequences. Model performance was evaluated using overall accuracy and class-wise classification results. The experimental results indicate that the LSTM method achieved an overall accuracy of 87.62%. In addition, the classification performance for the positive sentiment class reached 95.27%, the neutral class achieved 4.96%, and the negative class reached 74.26%. These results demonstrate that the LSTM method performs well in classifying sentiment in Shopee user reviews, particularly for positive sentiment. This study is expected to provide insights and references for the application of deep learning methods in sentiment analysis of Indonesian e-commerce review data.

The rapid proliferation of Internet of Things (IoT) devices across diverse industries has significantly increased the vulnerability of IoT edge networks to sophisticated cyber threats. Traditional intrusion detection systems (IDS), such as signature-based and anomaly-based approaches, are often insufficient in addressing the dynamic and evolving nature of these threats. This study proposes a hybrid intrusion detection system (IDS) framework that combines supervised machine learning (ML) techniques with deep reinforcement learning (DRL) to enhance detection performance in real-time, resource-constrained IoT environments. The proposed framework utilizes supervised learning for initial traffic classification and DRL for adaptive decision-making, enabling the system to continuously learn and optimize its detection policies based on new attack patterns. The hybrid approach significantly improves detection accuracy and reduces false positives when compared to conventional signature-based and single-model ML systems. In addition to improved detection capabilities, the framework's computational efficiency allows it to operate effectively within the constraints of IoT devices, ensuring that it is suitable for large-scale deployments. Benchmark evaluations using publicly available datasets, such as NSL-KDD, IoT-23, and BoT-IoT, show that the hybrid IDS framework outperforms traditional methods, providing a more robust and adaptive solution to cybersecurity challenges in IoT edge networks. The findings of this study suggest that combining machine learning with deep reinforcement learning offers a promising approach to secure IoT environments and address the limitations of existing IDS techniques. Future work will explore enhancing real-time adaptability, scalability, and the detection of zero-day attacks in evolving IoT ecosystems.

This study was based on the low ability of third-grade students at SD Negeri 2 Wonorejo to understand syntactic material, particularly the use of conjunctions, due to a lack of interactive and contextual learning media. This study aimed to develop EKUJARSI E-Flipbook learning media based on Kudus local wisdom that has been tested for feasibility and practicality to improve student understanding. The research method used was Research and Development (R&D) with the ADDIE (Analyze, Design, Development, Implementation, Evaluation) development model. The test subjects included subject matter experts, media experts, classroom teachers, and third-grade students. Data collection instruments used validation sheets and user response questionnaires. The results showed that the EKUJARSI media was highly valid for use, as evidenced by a validation percentage of 89.6% from media experts and 86.15% from subject matter experts. The practicality test also showed positive responses, with teachers giving a score of 80% and students giving a score of 85.9%, which is considered very feasible. Specific findings show that the ease of use aspect received a perfect score of 100% from students, indicating that this media is very user-friendly. It is concluded that the EKUJARSI E-Flipbook is feasible and practical to be implemented as an innovative learning media that effectively integrates local cuisine to facilitate understanding of language concepts.

The goal of Christian education is not only to increase students' knowledge but also to shape character that reflects the values ​​of faith in Christ. In the context of a diverse society, an inclusive and tolerant attitude towards differences is crucial for students. This paper aims to illustrate how students can be shaped to develop an inclusive and tolerant attitude based on the values ​​of the Christian faith. Through Christian Religious Education (PAK) learning that emphasizes love, respect for one another, justice, and peace, students are encouraged to recognize that every human being is created in the image and likeness of God. An inclusive and tolerant attitude can develop when students understand that differences are part of God's plan and implement this in their interactions with others. Therefore, Christian education plays a crucial role in instilling the value of Christ's love so that students can live peacefully together, appreciate differences, and become role models in a diverse society.

The rapid development of digital technology has brought significant changes to the business landscape, transforming how products are marketed, services are delivered, and business relationships are built. In this context, students, as future members of the workforce and potential entrepreneurs, are required to possess strong digital literacy skills in order to effectively face challenges and seize emerging business opportunities. This study aims to analyze the importance of digital literacy in supporting students’ readiness to respond to future business trends. The research employed a descriptive approach using a literature review and observations of the entrepreneurship learning process in vocational schools. The findings indicate that digital literacy plays a crucial role in enhancing students’ creativity, adaptability, and ability to utilize digital platforms for online marketing, branding, and business communication. Furthermore, digital literacy helps students understand market dynamics, analyze consumer behavior, and adopt innovative business models that align with technological developments. Students with adequate digital literacy are better prepared to face rapid changes in the business environment and demonstrate higher confidence in applying technology to entrepreneurial activities. In conclusion, the integration of digital literacy into entrepreneurship education is essential to produce competitive, innovative, and adaptable graduates who are capable of thriving in the digital era and contributing to sustainable economic development.