Publication Search

Sudden Infant Death Syndrome (SIDS) is a sudden and unexpected death in infants that is often associated with the prone sleeping position. This study aims to develop an automated monitoring system capable of detecting SIDS risk factors using the YOLOv8 algorithm and to analyze the effect of data augmentation on model performance. The dataset consists of two classes, baby-lying-on-back (supine) and baby-lying-on-stomach (prone), which were processed through model training and evaluation using precision, recall, F1-score, and mAP metrics. The model was trained under two scenarios, without data augmentation and with data augmentation. The results show that the model without augmentation achieved a precision of 90%, recall of 85%, F1-score of 86%, and mAP50 of 93.7%. After applying augmentation, performance improved to a precision of 90%, recall of 87%, F1-score of 88%, and mAP50 of 95.1%. These findings indicate that augmentation increases detection accuracy and enhances model generalization, including robustness against variations in lighting and camera angles. Furthermore, testing with image and video inputs revealed that the non-augmented model exhibited a tendency toward overfitting, particularly in favor of the baby-lying-on-stomach, whereas the augmented model successfully classified both classes accurately. The developed system is also equipped with an alarm feature and early-warning notifications via Telegram to smartphone when a prone position is detected for a certain duration. Overall, the results demonstrate that YOLOv8 with data augmentation is effective for an automated, non-invasive monitoring system for infants, making it suitable for detecting and preventing potential SIDS risk factors.

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.

The increasing volume of online hotel reviews provides valuable insights into customer perceptions but poses challenges for manual analysis due to its unstructured nature. This study aims to compare the performance of Recurrent Neural Network (RNN) and Bidirectional Encoder Representations from Transformers (BERT) in hotel review sentiment analysis. A total of 20,491 TripAdvisor hotel reviews were classified into three sentiment categories: negative, neutral, and positive. The research methodology includes text preprocessing, stratified data splitting, class imbalance handling using Random Over-Sampling, tokenization, and supervised model training. Model performance was evaluated using a confusion matrix and classification metrics. The results indicate that BERT outperforms RNN, achieving an accuracy of 80.54%, while RNN reached 62.21%. BERT demonstrated superior capability in capturing contextual and semantic information in hotel reviews. These findings suggest that transformer-based models are more effective for sentiment analysis of complex textual data in the hospitality domain and can support data-driven service improvement strategies.    

Sentiment analysis is a technique in Natural Language Processing (NLP) used to identify user opinion tendencies based on textual reviews. This study analyzer user reviews of the Maxim application on the Google Play Store and compares three Machine Learning algoritmhs-Naïve Bayes, Support Vector Machine (SVM), and CatBoost-in classifying sentiment. The research stages include data collection, text preprocessing, feature extraction using TF-IDF and Chi-Square, class balancing using SMOTE, and performance evaluation through Accuracy, Precision, Recall, and F1-Score. ANOVA is used to examine the influence of feature selection on model performance. The results show that each model exhibits different performance level across the tested feature combinations. The CatBoost achieved the highest accuracy of 99,26% and demonstrating the most stable performance. Meanwhile, the Naïve Bayes and SVM models experienced performance decreases experiments, especially after applying SMOTE. These findings indicate that the choise of algorithm, feature extraction method, and class balancing technique significantly affects classification outcomes. Overall, CatBoost is identified as the best-performing model, providing more consistenst classification result in accordance with the characteristics of the user reviews.

The use of protective equipment in the form of helmets is an important aspect of ensuring motorcycle rider safety. However, violations of helmet usage still frequently occur and are difficult to monitor continuously. This study proposes a real-time helmet detection system using the YOLOv8 object detection method. The YOLOv8n model was trained using a helmet and no-helmet image dataset that underwent data augmentation to improve the model’s robustness against variations in environmental conditions. The system was implemented using the Python programming language with the support of the Ultralytics and OpenCV libraries. The system input was obtained from a webcam with a resolution of 640×640 pixels, where each video frame was processed in real time to detect the Helmet and No Helmet classes. The system displays bounding boxes and class labels in real time and is equipped with a violation duration calculation mechanism. When a no-helmet condition is detected continuously, the system generates pop-up alerts and automatic notifications via the Telegram application. The experimental results show that the system is capable of detecting helmet usage and no-helmet violations in real time with stable performance. The integration of violation duration calculation helps reduce momentary detection errors and improves the reliability of identifying valid violations

Reading comprehension, especially in personal letter texts, is challenging for many Indonesian high school students due to limited vocabulary and low motivation. Blooket, a game-based learning platform, offers potential to improve engagement and learning outcomes.Objective: This research aims to examine the effectiveness of Blooket learning media in improving students’ reading comprehension of personal letters at Grade XI of SMA PGRI Pekanbaru. A quantitative approach with a quasi-experimental non-equivalent control group design was used. The sample consisted of 39 students, divided into an experimental group taught with Blooket and a control group taught conventionally. Pre-tests and post-tests (25 multiple-choice items) were administered, and data were analyzed using normality, homogeneity, The experimental group’s mean score increased from 55.21 to 84.96, while the control group improved from 51.53 to 72.00. The paired sample t-test yielded p = 0.000 (<0.05), indicating a significant effect of Blooket on reading comprehension. Blooket’s interactive and competitive features effectively enhanced students’ reading comprehension of personal letters, motivation, and participation, making it a valuable alternative for teaching short functional texts in EFL classrooms.

This study aims to design and build a population distribution application in Demak Regency in 2025 using a Geographic Information System (GIS) approach. The study focuses on three main variables: population, population density, and population growth rate per sub-district. The author used the research method of collecting data and references that can later strengthen the results of this study and the application design using the waterfall model. Non-spatial data, namely data in the form of population information, was obtained from the Central Statistics Agency of Demak Regency, while spatial data is data related to regional administrative boundaries. Data processing was carried out using QGIS 2.18 through the stages of joining attributes, classification using the Natural Breaks (Jenks) method, and thematic map creation. The results show that population distribution is uneven. Demak Kota, Karangtengah, and Sayung sub-districts have the highest number and density, while coastal sub-districts such as Wedung and Bonang have low densities. The highest population growth rate is in Karangtengah sub-district at 0.8%. The application of GIS has proven effective in visualizing population distribution and supporting spatial-based regional development planning.  

ARP spoofing attacks are a serious threat to network security, particularly in vulnerable Internet of Things (IoT) environments. This final project aims to detect ARP spoofing attacks on IoT net-works using a combination of Random Forest (RF) and Robust PCA methods. RF is chosen for its classification capabilities and handling of non-linear data, while Robust PCA is used for di-mensionality reduction and handling outliers in the data. The dataset used is "MITMArpSpoof-ing.pcap.csv," which contains network traffic data. The data is processed by performing prepro-cessing, feature scaling, and converting labels to binary (0 for benign, 1 for ARP spoofing). Subsequently, Robust PCA is applied to reduce data dimensions, and then the data is trained using the RF model. The test results show that the RF model with Robust PCA achieves an accu-racy of 96.02% in detecting ARP spoofing attacks. This method has proven effective in identify-ing and classifying ARP spoofing attacks on IoT networks.

Contemporary developments in science, technology, and socio-cultural dynamics have given rise to various new fiqh issues (masailul al-fiqhiyyah al-mu‘ashirah) that were not explicitly discussed in classical Islamic jurisprudence. These contemporary fiqh issues demand contextual ijtihad that is responsive to current realities while remaining grounded in Islamic legal principles. This study aims to analyze contemporary fiqh issues and examine their implications for the moral formation of students in Islamic education. This research employs a qualitative library research approach by analyzing classical fiqh literature, contemporary fiqh studies, and relevant educational theories. The findings indicate that contemporary fiqh issues such as digital ethics, biomedical technology, and socio-economic practices carry significant moral dimensions that directly influence students’ attitudes and behavior. Integrating contemporary fiqh discourse into Islamic education encourages critical thinking, moral reasoning, and ethical awareness among learners. Therefore, contemporary fiqh learning not only functions as a legal reference but also as a strategic instrument for strengthening students’ moral character in accordance with Islamic values. The study implies that Islamic education institutions should contextualize fiqh instruction to address contemporary moral challenges faced by students.

Hypertension is a major global health risk that requires accurate early detection, yet conventional methods struggle with complex and imbalanced health datasets. This study aims to optimize hypertension prediction using a Logistic Regression model integrated with Borderline-SMOTE to enhance recall and provide model transparency through SHAP (Shapley Additive Explanations). The method utilizes the BRFSS dataset, applying Borderline-SMOTE to address class imbalance at the decision boundary and XAI techniques for global and local interpretation. The findings show that the model achieved an accuracy of 0.719, an AUC of 0.800, and a significantly improved recall of 0.756. SHAP analysis identified age, high cholesterol, and BMI as the most influential risk factors, while waterfall plots successfully clarified individual risk extremes, ranging from 1.72% to 99.43% probability. These results imply that the proposed approach provides a sensitive and transparent screening tool for public health practitioners, effectively balancing statistical efficiency with clinical accountability.

Injustice against women in contemporary Islamic law practice is still a serious problem, especially in cases of divorce, child custody, and the division of common property, which are often decided textually without considering the social, economic, and psychological aspects of women. This phenomenon shows that the application of Islamic law is still normative and does not fully reflect substantive justice as the purpose of maqāṣid al-syarī'ah. This research aims to analyze the nature of justice for women in the modern era, identify the steps needed to realize this justice, and formulate Islamic legal solutions based on maqāṣid al-syarī'ah that can be applied contextually in the religious justice system. The research method used is qualitative with a normative-empirical approach through literature analysis, case studies, and empirical data from religious court decisions and reports of official institutions such as Komnas Perempuan. The results of the study show that justice for women can only be achieved through a dynamic maqāṣid approach, by placing the interests of women and children above the legal-formalities of classical fiqh. The efforts needed include the integration of empirical data in judges' decisions, reform of religious justice policies, increasing the capacity of judges in understanding maqāṣid, and empowering women through legal literacy.

Globalization and modernization amid the strong digital flow have become a huge challenges and obstacles for shaping moral and ethics of the students. There are many students who come to the class physically without having readiness and awareness in the study. Teacher as an educator needs to give an efforts in every process of learning with attractive concept and model to give attention and meaning in the study. Through the mindful learning, it is considered capable of giving full attention and self-awareness while studying which in the end not only gives good quality in learning but also shapes islamic ethics in the stundents. This research aims to know the concept, urgency, and the implementation of mindful learning which is capable of shaping islamic ethics. The method of the research is a qualitative approach with a literature study from various readings such as articles and journals that are relevant to the topic. The reasearch results show that mindful learning is a learning process that emphasizes self-reflection and self-awareness so students feel ready and motivated in learning. It shows that deep learning has a huge urgency in shaping student’s Islamic ethics. The implementation of mindful learning in Islamic education Studies is carried out through the pedagogic strategies that emphasize the conditioning of awareness, active students involvement, and deep reflection of Islamic values. Thus, mindful learning is capable of increasing internal awareness through muraqabah with the involving of students in every learning process.

This research examines the implementation of the Deep Learning approach in Islamic Religious Education (PAI) learning at SMAN 61 Jakarta and its contribution to the development of students' critical thinking skills. This study was conducted due to the need for a learning model that encourages students to understand religious concepts through active, reflective, and meaningful learning experiences. The purpose of this research is to describe the implementation of Deep Learning in PAI learning and its influence on the development of students' critical thinking skills. This study employs a qualitative method with a descriptive research design, using interviews, classroom observations, and documentation as data collection techniques. The findings indicate that the Deep Learning approach supports students in participating more actively in discussions, analyzing religious issues related to real-life situations, and constructing arguments based on their own understanding. Students also demonstrate improvement in evaluating information, considering diverse perspectives, and providing more reflective responses to classroom problems. The study further identifies several challenges, including limited digital facilities, varying levels of student participation, and teachers’ readiness in managing diverse learning strategies and media. These findings suggest that Deep Learning has strong potential to enhance students’ critical thinking skills when applied systematically and designed to foster active participation and meaningful exploration during the learning process.

This study aims to determine the relationship between learning motivation and learning outcomes in SMAW welding engineering among eleventh-grade students at SMKN 2 Solok. This research employed a quantitative method with a correlational approach. The population consisted of all students from classes XI TPM 1 and XI TPM 2, totaling 51 students, using a total sampling technique. Learning motivation data were collected through a validated and reliable questionnaire, while learning outcome data were obtained from post-test scores in the SMAW welding subject. Data were analyzed using the Pearson Product Moment correlation test with the assistance of SPSS software. The results showed a correlation coefficient of r = 0.783 with a significance value of 0.000 < 0.01, indicating a strong, positive, and statistically significant relationship between learning motivation and students’ learning outcomes. These findings suggest that higher learning motivation leads to better learning outcomes in SMAW welding engineering. Therefore, learning motivation plays an important role in improving students’ academic performance. This study is expected to provide useful insights for teachers and schools in developing instructional strategies that enhance students’ motivation and learning outcomes.

Political participation is an important aspect in a democratic state structure, as well as a characteristic feature of political modernization. Political participation influences the legitimacy of society regarding the running of a government. One way of implementing political participation is through General Elections (Pemilu). The aim of this research is to determine the influence of presidential candidate debate broadcasts on multi-platform broadcast media on the political participation of FISIP UMJ student class of 2020. This research has an independent variable, namely presidential candidate debate broadcasts with the dimensions of frequency, attention and duration, and has a dependent variable, namely providing voting rights in elections, lobbying with officials, becoming a member of a political party. This research method uses a survey method by distributing questionnaires online to respondents via Google Form which aims to collect data from a sample of 2020 FISIP UMJ students who actively watch presidential candidate debates and know about political participation, with a total of 66 respondents selected. The data collection tool uses a questionnaire using a Likert Scale. The results of this research show that the presidential debate broadcast has an influence on political participation, which has a value of 0.736 or 73.6%, which means that the presidential debate broadcast influences political participation by 73.6% and the rest is influenced by other factors.

Sarcasm is a literary device and one of the most expressive forms of figurative language, often used to convey humor, criticism, or emotional tension in both daily conversation and literature. This study explores the use of sarcasm in William Shakespeare‟s Much Ado About Nothing by applying Elizabeth Camp‟s (2011) typology, which classifies sarcasm into four types: propositional, lexical, illocutionary, and like-prefixed sarcasm. Using a qualitative descriptive method, the researchers collected all sarcastic utterances from the play, classified them according to Camp‟s framework, and analyzed their pragmatic functions in the dramatic context. The findings reveal a total of 50 sarcastic utterances, with propositional sarcasm being the most frequent (42%), followed by illocutionary sarcasm (28%), lexical sarcasm (24%), and like-prefixed sarcasm (6%). These results indicate that sarcasm serves as both a comedic and dramatic device, shaping character interactions, driving conflicts, and reinforcing Elizabethan cultural norms. Beatrice and Benedick‟s witty verbal duels exemplify how sarcasm fosters humor and intimacy, while Claudio‟s sarcasm highlights themes of honor and social tension. Overall, the study demonstrates that sarcasm in Shakespeare‟s play is not merely humorous banter but a sophisticated rhetorical strategy that enhances characterization, thematic depth, and audience engagement.

This study aims to implement the Christian Religious Education and Character Education (PAK) teaching module in grade V of SDN 1 Sabaru, Palangka Raya, with a focus on the topic “Jesus Was Crucified, Died, and Risen for Me.” The learning process is designed to support students’ spiritual and character development through an interactive and project-based approach. Teaching methods include group discussions, the use of miniature media as visual learning aids, collaborative activities, and guided reflection on Christian values relevant to students’ daily experiences. The results of classroom observations show that most students are active, enthusiastic, and involved in the learning process, able to understand the theological meaning of the crucifixion, death, and resurrection of Jesus, and apply the values of love, gratitude, and responsibility in everyday life. Obstacles found include a lack of self-confidence in some students and less optimal group dynamics during activities. These findings serve as important evaluation materials for improving the effectiveness of future learning implementation

The RIGEM community service program was carried out with the aim of strengthening character education for early childhood through the use of children’s songs in TK B. The background of this activity stems from concerns about the increasing exposure of children to adult songs and content, which may influence their behavior and moral values. Children’s songs were chosen as the main medium because they have simple melodies, easy-to-remember lyrics, and contain positive values that can stimulate children's cognitive, affective, and social development. This study employs a descriptive qualitative approach using the CIPP evaluation model (Context, Input, Process, Product) to assess the effectiveness of the program. Data were collected through observations, interviews with teachers and parents, and documentation of activities. The results show that the children’s songs introduced particularly those containing messages about politeness, cooperation, and responsibility were effective in improving children's understanding of moral values and encouraging positive behavioral changes. Children became more accustomed to using polite expressions, showing empathy, and cooperating during classroom activities. Teachers and parents played an important role in reinforcing these habits both at school and at home. Overall, the RIGEM program proved to be an effective, enjoyable, contextual, and easily implemented effort to foster character development in early childhood education.

The RIGEM community service program was carried out with the aim of strengthening character education for early childhood through the use of children’s songs in TK B. The background of this activity stems from concerns about the increasing exposure of children to adult songs and content, which may influence their behavior and moral values. Children’s songs were chosen as the main medium because they have simple melodies, easy-to-remember lyrics, and contain positive values that can stimulate children's cognitive, affective, and social development. This study employs a descriptive qualitative approach using the CIPP evaluation model (Context, Input, Process, Product) to assess the effectiveness of the program. Data were collected through observations, interviews with teachers and parents, and documentation of activities. The results show that the children’s songs introduced particularly those containing messages about politeness, cooperation, and responsibility were effective in improving children's understanding of moral values and encouraging positive behavioral changes. Children became more accustomed to using polite expressions, showing empathy, and cooperating during classroom activities. Teachers and parents played an important role in reinforcing these habits both at school and at home. Overall, the RIGEM program proved to be an effective, enjoyable, contextual, and easily implemented effort to foster character development in early childhood education.

Gestational Diabetes Mellitus (GDM) is a pregnancy-related metabolic disorder that poses health risks to both mother and fetus if not detected early, requiring accurate prediction methods for early screening and clinical decision-making. This study applies the Random Forest algorithm to detect GDM risk using clinical data from the Pima Indian Dataset. Data preprocessing included handling missing values, standardization, feature engineering, and a 70:30 train–test split. Two models were developed: a baseline and an optimized model using GridSearchCV hyperparameter tuning, validated with 5-fold cross-validation. Performance was assessed using a classification report, confusion matrix, and ROC–AUC. Results show that the optimized model outperforms the baseline, achieving 88% accuracy, an AUC of  93%, and average recall of 81%–85%. Compared to previous studies, this approach demonstrates improved predictive performance. The findings indicate that combining Random Forest with comprehensive preprocessing, feature engineering, and model optimization is effective and feasible for developing a medical decision support system for early GDM risk screening.