Publication Search

This study aims to analyze the effect of the implementation of the Intelligent Tutoring Sistem (ITS) based on Artificial Intelligence (AI) on improving the understanding of mathematical concepts, especially in fractional and basic geometry materials, in Class V students of SD Negeri 2 Badran, Temanggung Regency. The research method used was a quasiexperimental experiment with a Non-equivalent Control Group Design. The research sample consisted of 48 students who were divided into two groups, namely the experimental group (n=24) who received learning with the help of AI-based ITS, and the control group (n=24) who received conventional learning with lecture methods and practice questions. The research instrument is in the form of a test of understanding of mathematical concepts that has been validated by experts and tested for reliability. Data were analyzed using parametric statistical tests of the Independent Sample t-test and N-Gain Score to measure the improvement. The results showed that there was a significant difference in understanding of mathematical concepts between the experimental group and the control group. The average post-test score of the experimental group (82.45) was significantly higher than that of the control group (70.12) with a p< value of 0.05. N-Gain analysis showed that the improvement in conceptual understanding in the experimental group was in the "moderate" category (g=0.56), while the control group was in the "low" category (g=0.32). These findings indicate that AI-based ITS is effective in improving students' understanding of mathematical concepts. The advantages of the system lie in its ability to provide instant feedback, personalize materials according to learning pace, and present interactive materials, thus helping to better construct students' conceptual understanding. It is recommended that schools consider the integration of ITS technology as a supplementary tool in mathematics learning at the elementary level.

Effective communication is a key competency for medical professionals, but traditional classroom-based methods in Indonesia face challenges such as limited practice, geographical barriers, and insufficient exposure to diverse patient scenarios. Mobile-assisted learning (MAL) offers a promising solution to enhance medical communication training outside traditional settings. This study investigates the effectiveness of MAL interventions in developing communication skills among Indonesian medical students and healthcare professionals. A mixed-methods approach was used, involving a quasi-experimental design with pre- and post-assessments of communication competence among 180 participants from three Indonesian medical schools. The MAL intervention included a mobile app with video demonstrations, interactive case scenarios, peer feedback, and microlearning modules. Quantitative data showed a significant improvement in communication competence (mean increase of 23.4%, p<0.001), with notable gains in information gathering (28%), relationship building (26%), and patient education (21%). The mobile platform saw high engagement (average of 4.3 sessions/week) and 87% module completion. Qualitative data revealed increased confidence in consultations, improved cultural sensitivity, and better time management. Challenges included inconsistent internet access, varying digital literacy, and resistance from traditional educators. MAL shows potential for improving medical communication in Indonesia, offering flexible, accessible training. Successful implementation requires addressing infrastructure issues, integrating MAL into existing curricula, and training faculty. This study adds to the growing evidence supporting technology-enhanced medical education in resource-limited settings.

Arabic holds an important position in Islamic education as the language of the Qur'an and Hadith. However, the teaching of Arabic in Islamic educational institutions often focuses only on linguistic aspects, thus not fully achieving the goals of comprehensive Islamic education. This study aims to analyze the strengthening of Arabic language education objectives from the perspective of Islamic Tarbiyah. The method used in this study is qualitative, with a literature study and descriptive analysis approach. The analysis was conducted on relevant sources. The findings indicate that Arabic education within the framework of Islamic Tarbiyah not only emphasizes mastery of language skills but also the importance of shaping students' faith, morals, and Islamic character. The integration of tarbawi values into the objectives, materials, methods, and evaluation of learning becomes a key element in creating Arabic language education that is valuable and aligned with the goals of Islamic education. Its implications are expected to serve as a reference for curriculum development, teacher competence improvement, as well as the formulation of contextual, integrative, and sustainable Arabic language learning policies in national Islamic educational institutions.

Arabic holds an important position in Islamic education as the language of the Qur'an and Hadith. However, the teaching of Arabic in Islamic educational institutions often focuses only on linguistic aspects, thus not fully achieving the goals of comprehensive Islamic education. This study aims to analyze the strengthening of Arabic language education objectives from the perspective of Islamic Tarbiyah. The method used in this study is qualitative, with a literature study and descriptive analysis approach. The analysis was conducted on relevant sources. The findings indicate that Arabic education within the framework of Islamic Tarbiyah not only emphasizes mastery of language skills but also the importance of shaping students' faith, morals, and Islamic character. The integration of tarbawi values into the objectives, materials, methods, and evaluation of learning becomes a key element in creating Arabic language education that is valuable and aligned with the goals of Islamic education. Its implications are expected to serve as a reference for curriculum development, teacher competence improvement, as well as the formulation of contextual, integrative, and sustainable Arabic language learning policies in national Islamic educational institutions.

The integration of Information and Communication Technology (ICT) and tools like Canva has revolutionized English Language Teaching (ELT) in Indonesia, shifting from traditional methods to interactive, student-centered approaches. This study aims to explore the benefits and challenges of incorporating these technologies into ELT practices. Employing a qualitative literature review methodology, the research analyzed over 20 empirical studies from 2020 to 2023 on Canva and ICT in Indonesian ELT, supplemented by global Computer-Assisted Language Learning (CALL) frameworks. Key findings reveal that ICT and Canva enhance student motivation, creativity, and communicative skills through multimodal and constructivist learning, while fostering authentic language exposure and collaboration. However, challenges include inadequate infrastructure, limited teacher training, digital inequities between urban and rural areas, ethical issues such as copyright infringement, and increased teacher workload. The implications underscore the need for systematic professional development, institutional support, curriculum alignment, and policies promoting equitable access to ensure transformative and sustainable technology integration in Indonesian ELT.  

This study aims to analyze the effectiveness of the application of direct and indirect methods in teaching English, specifically the topic of "Telling Time," at MTs Al-Amiriyyah through microteaching practice. This research employs a descriptive qualitative approach with data collection techniques including observation, interviews, and documentation. The research subjects consist of an English teacher and the students of class VIII A. The data were thematically analyzed to identify significant patterns in the teaching process. The findings indicate that the direct method is effective in building students' foundational understanding of time concepts, as it emphasizes explicit and concrete use of the target language and allows teachers to easily assess students' comprehension through drilling. On the other hand, the indirect method proved to enhance students’ ability to use English more naturally through contextual activities such as role play and daily schedule games. Moreover, students with kinesthetic learning styles responded more positively to the indirect method, as it enables them to learn through physical activity and direct participation. These findings suggest that a combination of both methods yields optimal results: the direct method is effective for the initial stage of concept acquisition, while the indirect method supports the development of communicative skills in a functional and enjoyable manner, aligning with students' characteristics.

Jambi Province is one of the largest natural rubber producing regions in Indonesia; however, rubber factories under GAPKINDO Jambi still face productivity issues, particularly the gap between production capacity and actual output, and productivity assessment that is still conducted manually by GAPKINDO Jambi. This study employs Decision Tree, Random Forest, KNN, and SVM algorithms within a structured pipeline involving preprocessing, feature selection, standardization, data balancing using SMOTE, and hyperparameter tuning. The proposed solution applies productivity level classification both individually and through paired combinations (ensemble voting). The results show that the Decision Tree + Random Forest model achieves the best performance with an accuracy of 0.84 and an F1-score of 0.83, confirming the effectiveness of ensemble methods in supporting productivity improvement decisions.

This study presents a high-accuracy real-time soft failure detection framework for large-scale fiber-to-the-home(FTTH) optical access network using a hybrid ensemble of Isolation Forest and One-Class Support Vector Machine (OCVSM). The proposed model was trainde and validated on a real-word multivariate performance dataset comprising more than 1.8 million samples collected at 5-minute intervals from 50 Optical Line Terminal (OLTs) and over 3,000 Optical Network Terminals (ONTs) across a five-month periode(June-October 2025). Ground-truth validation was performed using 111 confirmed network incidents in October 2025 affecting 12,990 customer. The hybrid ensemble achieved Precision 0.940, Recall 0.982, with an average detection delay of only 7.8 minutes-representing an 87.7% reduction compared to conventional manual response (63.5 minutes). The framework significantly outperforms traditional threesholding and recent ML-based methods while demonstrating practical deployability in live operational enviroments.

Islamic character education faces dual challenges: declining moral values among students and conventional teaching methods inadequate for developing higher-order thinking skills. This study examines the implementation of a smart learning environment (SLE) model to enhance metacognitive understanding in Aqidah Akhlak (Islamic Creed and Ethics) instruction among eighth-grade students at MTs Salafiyah Merakurak. Employing a mixed-methods action research design, involved 16 eighth-grade students divided into two groups. Data collection utilized classroom observations, semi-structured interviews, and learning documentation. The SLE model integrated Google Classroom, interactive video content, WhatsApp Group discussions, and Google Forms assessments to create a technology-enhanced learning ecosystem. Findings revealed substantial improvements in students' metacognitive capacities: planning skills increased from 25% to 75%, monitoring abilities rose from 31% to 81%, and evaluation competencies grew from 19% to 69%. Students demonstrated enhanced learning autonomy, active participation in collaborative discussions, and improved self-reflection on content comprehension. The SLE approach successfully fostered engaging learning experiences while facilitating deeper internalization of Islamic ethical values. However, implementation encountered constraints including limited technological infrastructure and varied digital literacy levels among students. This research underscores the critical need for developing teachers' digital competencies and strengthening madrasah technological infrastructure to optimize technology-integrated Islamic education.

This study aims to analyze the effect of the use of kahoot game media on the cognitive learning outcomes of moral beliefs in grade VII C MTS negeri 1 Tuban students. The background of this research is the low enthusiasm and learning outcomes of students in learning moral beliefs which are still dominated by conventional methods while the characteristics of agency students demand a more interactive and adaptive learning approach to technology. This study uses a quantitative approach with a quasi-experimental design of one group pretest design involving 34 students as a sample. This research instrument is in the form of a multiple-choice cognitive learning outcome test of 20 questions covering 4 levels of bloom taxonomy, namely remembering, understanding, applying, and analyzing. The data was analyzed using descriptive statistics and normalistic calculations, the results of the study showed a significant increase in students' cognitive learning outcomes where the average class score increased from 66.03 in the pre-test to 80.29 in the post-test with an engine value of 0.42 which was in the medium category. These findings identify that kahood media has a positive impact on improving students' cognitive learning outcomes.

That Christian Religious Education teachers update their professionalism and competencies to ensure that Christian education remains relevant, effective, and transformative. This study aims to analyze the modernization of the professionalism of Christian Religious Education teachers, including the integration of spirituality with modern pedagogical approaches and strategies for developing teacher competencies in addressing the challenges of the digital generation. The study employs a descriptive qualitative approach, collecting data through literature review from books, journals, notes, and relevant reports, and presenting the findings in a narrative form. The results show that the modernization of teacher competencies involves the development of pedagogical, personal, social, spiritual, and professional competencies, with the ability to integrate spirituality, technology, and modern teaching methods such as collaborative and digital learning to create contextual, engaging, and transformative learning experiences. In conclusion, the modernization of professionalism among Christian Religious Education teachers is an urgent necessity to enable teachers to deliver God’s Word in a relevant manner, shape students’ character and spirituality, and enhance the effectiveness of Christian education through mastery of holistic and collaborative competencies.  

This study aims to improve the kinesthetic intelligence and physical fitness of students with hearing impairments through rhythmic gymnastics lessons in Physical Education, Sports, and Health (PJOK) at SLB Muhammadiyah Kelayu, East Lombok Regency. The research employed a collaborative classroom action research (CAR) approach involving both the researcher and the PJOK teacher. The action was conducted in two cycles, each comprising planning, implementation, observation, and reflection stages. The research subjects consisted of eight students with hearing impairments, including four females and four males. Data were collected through documentation, observation, and performance assessments using developed kinesthetic intelligence and physical fitness instruments, and then analyzed descriptively using quantitative methods. The results indicate that after the rhythmic gymnastics intervention, kinesthetic intelligence improved, with 75% of students reaching the expected development level by the end of Cycle II. Physical fitness also showed significant improvement across five main components: endurance increased to 68.7%, muscle strength and endurance to 65.6%, agility to 68.7%, flexibility to 65.6%, and balance to 71.8%. Rhythmic gymnastics proved to be an effective approach to support inclusivity while enhancing the kinesthetic intelligence and physical fitness of students with hearing impairments.

This study aims to evaluate the impact of role-playing methods on learning interest and number concept mastery in 4-5-year-old children at TK Inomata, Suwawa Selatan District, Bone Bolango Regency. The approach used is a quantitative experimental method with purposive sampling of 8 children, and data collection was carried out through observations of aspects such as enjoyment, focus, activity, and enthusiasm, using a 1-4 scale. The results show that the average learning interest score using the traditional method was only 5.86 (low category), with details: enjoyment 1.71, focus 1.29, activity 1.29, and enthusiasm 1.57. In contrast, the role-playing method of trading/store games showed an average score of 13.86 (very good category), with details: enjoyment 3.57, focus 3.43, activity 3.29, and enthusiasm 3.57. This significant improvement indicates that the role-playing method is more effective in creating interactive, enjoyable, and contextual learning, as well as supporting number comprehension through everyday activity imitation and social skill development. It is recommended to routinely apply this method in early childhood education (PAUD) with adequate teaching aids, as well as involve parents to support the holistic development of children during the golden age.

The rapid development of digital streaming platforms such as Netflix has generated a large volume of content data with diverse characteristics, thereby requiring effective analytical methods to understand emerging patterns and trends. This study aims to classify Netflix content into two main categories, namely movies and television shows, and to analyze genre trends and content characteristics using a data mining approach with the Naive Bayes algorithm. The dataset used in this study is the Netflix Shows dataset, consisting of 8,809 content entries, with the primary features analyzed including genre, rating, and country of production. The research process begins with data exploration and preprocessing stages, including data cleaning, handling missing values, and transforming categorical features to enable effective model construction. Subsequently, the dataset is divided into training and testing sets to objectively and systematically build and evaluate the Naive Bayes classification model. Model performance is evaluated using accuracy, precision, recall, and F1-score metrics to assess the model’s ability to accurately distinguish between Netflix content types. The experimental results demonstrate that the Naive Bayes algorithm is able to classify Netflix content into Movie and TV Show categories with accuracy, precision, recall, and F1-score values of 100%, respectively. The confusion matrix indicates that no misclassification occurred, suggesting that genre, rating, and country of production features provide a very clear separation between content classes. These findings indicate that the Naive Bayes algorithm can achieve exceptionally high classification performance with optimal evaluation results. The results further reveal distinct differences in characteristics between movies and television shows based on genre and production attributes. Therefore, this study is expected to contribute to the development of content recommendation systems and strategic content management within the streaming 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.

AImbalanced data remains a significant issue in heart disease classification using machine learning, as it tends to cause models to overestimate the majority class while ignoring minority classes with high clinical value. This can lead to a decrease in accuracy and the model's ability to accurately detect disease cases. Therefore, this study aims to assess the effectiveness of oversampling techniques, namely Random Oversampling and Synthetic Minority Oversampling Technique (SMOTE), in improving the performance of the K-Nearest Neighbors (KNN), Naive Bayes (NB), and Random Forest (RF) algorithms. The dataset used comes from Kaggle and consists of 918 data sets with 12 attributes representing patient information related to heart disease prediction. The research stages include data preprocessing, baseline model testing, and re-evaluation using the two oversampling methods. Experimental results show that oversampling can improve the performance of all algorithms. KNN achieved the best results with SMOTE, with an accuracy of 72.98% and an F1-score of 75.39%. In the Naive Bayes algorithm, both oversampling techniques produced relatively stable performance, with the highest F1-score of 73.56% using SMOTE. Meanwhile, Random Forest showed the most optimal performance when combined with Random Oversampling, with an accuracy of 79.19% and an F1-score of 81.51%. These findings confirm that the success of data balancing techniques is strongly influenced by the characteristics of the classification algorithm used, and provide a practical contribution in determining strategies for handling imbalanced data in health research.

The Mastery Learning Strategy is a learning approach oriented towards achieving comprehensive student competencies before they move on to the next material or learning stage. This approach is based on the assumption that every student has the potential to succeed, provided they are given the appropriate time, methods, and guidance. In its application, Mastery Learning emphasizes systematic learning planning, the establishment of clear learning objectives, and ongoing evaluation to measure the level of student mastery. Students who have not yet achieved competency standards will receive corrective feedback and remedial activities, while students who have completed them will be provided with enrichment programs to deepen their understanding. With this mechanism, learning gaps can be minimized so as not to hinder the learning process in the next stage. Furthermore, this strategy encourages individualized, structured, and measurable learning according to student needs. Therefore, the implementation of Mastery Learning is considered effective in improving the quality of the learning process, strengthening conceptual understanding, and contributing to optimal and sustainable learning outcomes.  

Digital literacy is important in education in the era of Society 5.0, because teachers are required to be facilitators in supporting students to become digital learners. To support the success of students in becoming digital learners, the role of teachers in the use of technology during learning activities also contributes. The existence of these demands makes the use of virtual reality media in the learning environment an alternative that can be done to create learning activities that meet the demands in the Society 5.0 era. The purpose of this service activity is to improve the digital literacy of IGI Pekanbaru. as well as introduce virtual reality-based learning media as a renewable learning media innovation to support student learning activities in the digital era. In this service, the methods include presentation, demonstration, and practice. The results showed that teacher training in making VR learning media can improve their digital literacy. This training can also help teachers create interactive and interesting technology-based collaborative learning media for modern learning.

Flower disease detection is a significant challenge in modern agriculture, particularly with factors such as changes in leaf color, petal shape and structure, and environmental conditions affecting the accuracy of conventional models. These factors make it difficult to achieve optimal results using traditional methods. Transfer learning is an effective solution to improve image detection performance, especially when data is limited. This study used several pre-trained models, namely VGG16, ResNet50, and EfficientNet-B0, to detect three types of flower diseases: black spot on roses, white powdery mildew, and leaf rust. The research process included data processing, increasing the data volume using augmentation techniques, model training, and evaluation of the results. Experimental results showed that the EfficientNet-B0 model produced the highest accuracy of 97.2%, significantly better than the CNN model built from scratch with an accuracy of 85.1%. This study demonstrates that transfer learning is highly effective in improving the accuracy of flower disease detection, making it a more reliable alternative to methods that do not utilize pre-trained models, especially for agricultural applications that require high levels of accuracy in disease detection.

This study examines the role of mathematics learning in improving logical thinking skills in early childhood. The background of this study is based on the importance of logical thinking skills as a foundation for children's cognitive development, which can begin at an early age through appropriate mathematics learning. The purpose of this study is to analyze how mathematics learning can stimulate the development of logical thinking in early childhood and explore effective learning strategies. The methods used are library research and observation of several models of mathematics learning for early childhood in early childhood education institutions. The findings indicate that fun and concrete activity-based mathematics learning can improve children's abilities in critical thinking, constructing patterns, drawing conclusions, and solving simple problems. The implications of this study emphasize the need for the application of creative and interactive mathematics learning methods to support the development of logical thinking from an early age, while also encouraging educators to integrate mathematics into children's daily activities. This study also recommends the development of learning media appropriate to children's developmental stages for optimal results.