The Balanced Academic Curriculum Problem (BACP) is a complex optimization problem in educational institutions, involving the allocation of courses across academic terms while satisfying various constraints. This study aims to optimize BACP using the Teaching-Learning Based Optimization (TLBO) algorithm, addressing the limitations of existing approaches and providing an efficient framework for curriculum balancing. The novelty lies in applying TLBO to BACP, offering a parameter-free, nature-inspired metaheuristic that balances exploration and exploitation effectively. The proposed method models BACP as a mathematical optimization problem and implements TLBO to minimize total load balance delay across academic terms. Computational experiments were conducted on 12 benchmark BACP instances, comparing TLBO against eight other metaheuristic algorithms. Results demonstrate TLBO's superior performance, achieving the best solutions in 75-83% of test problems across various indicators. Statistical analysis using the Wilcoxon rank-sum test confirms the significance of TLBO's improvements. The study concludes that TLBO is a robust and efficient tool for optimizing BACP, outperforming existing methods in solution quality and convergence speed. Future research could focus on enhancing TLBO through hybridization with other algorithms and applying it to real-world BACP scenarios in educational institutions.

This research investigates the transformative potential of Artificial Intelligence (AI) in aligning educational programs with industry requirements and emerging skill sets. Developed and preliminarily tested an AI-driven framework designed to personalize learning paths, recommend pertinent educational content, and improve student engagement. The AI models achieved a peak classification accuracy of 90% in identifying educational materials relevant to industry needs, with an optimized average recommendation response time of 0.4 seconds. These results were derived from pilot testing involving 300 students (150 in the control group and 150 in the experimental group), with statistical significance confirmed using t-tests and chi-square tests. In pilot studies, students using AI-recommended materials experienced an average improvement of 15% in assessment scores compared to those using traditional methods. To validate these improvements, used both t-tests and chi-square tests to confirm statistical significance, with a control group of 150 students following traditional educational methods. Additionally, educators reported a 75% engagement rate with AI-driven learning paths, indicating strong acceptance and effective integration of AI tools within educational environments. The control group comparison showed that students using traditional methods had a significantly lower engagement rate of 60%, confirming the higher efficacy of the AI system. However, these results should be interpreted cautiously as further detailed statistical analysis and control mechanisms are necessary to fully validate the effectiveness of the AI framework. The study highlights the importance of addressing ethical considerations such as data privacy, algorithmic bias, and transparency to ensure responsible AI deployment. The results underscore AI's potential to enhance educational outcomes, adapt curricula dynamically, and better prepare students for future career demands, contributing to a more relevant and industry-aligned educational system.

The problem of this research is how to overcome the need for Maritime English textbooks that integrate English language skills (reading, writing, speaking and listening). This research aims to develop a valid, practical and effective English textbook to improve students' understanding of English in the maritime field. The research design uses the Research and Development (R&D) method. This research was conducted at the Banyuwangi Maritime Academy's Commercial and Port Shipping Management Study Program (KPNK). Data collection was carried out through documentation techniques, Focus Group Discussions, questionnaires, and administering tests. The instruments used include documentation sheets, validation, questionnaires and self-evaluation. Data analysis focuses on the validity, practicality, and effectiveness of textbooks with the parameters (1) level of validity, (2) level of practicality, and (3) level of effectiveness. The results of the study show that the English for Maritime textbook received very high validation from experts and user lecturers. The assessment by two experts showed a validity level of 96.96%, covering aspects of English language skills (reading, writing, listening, and speaking), appearance, presentation, material, and language, all of which are in the very valid category. Further assessment by user lecturers resulted in a score of 100%, which is also in the very valid category, confirming that this textbook is suitable for use without improvement. With high scores from experts and users, this book has been proven to meet the eligibility standards as a teaching material in supporting the mastery of English language competencies in the maritime field.

Rapid progress in generative artificial intelligence (AI) technologies has brought forth stupendous challenges in differentiating AI-written text from human text. The Naturalness Score, a composite measure that considers lexical diversity, syntactic complexity, sentiment variability, and grammatical faults, is a new idea that emerged from this study. The Naturalness score is part of a larger machine learning framework, although it does have an individual classifier called the Naturalness-Based Logistic Regression Classifier or NLRC. The NLRC model was analyzed against a large, diverse corpus of nearly 45,000 text samples, most of which were student essays, articles, and web-scraped content. The proposed model outperformed all existing baseline models with an accuracy of 96.41%, precision of 0.98, recall of 0.95, and F1 score of 0.96. The high areas under the receiver operating characteristic curve (AUC=1.00) and precision-recall curve (AUC-PR) also indicate the effectiveness of the model in differentiating AI generated from human-written text. The proposed approach offers several advantages including increased detection accuracy, resilience against AI-generated content, cross-domain applicability, and interpretability. The research has implications for applying such models in schools, although it also calls for future research on the implications of the rapidly changing landscape of AI-generated content which it states. It emphasizes the importance of these findings in developing robust and adaptive detection systems to ensure the integrity of academic assessments, thereby preventing the misuse of AI tools.

This article presents the implementation of a machine learning-based face anti-spoofing method to enhance the security of an educational information portal for university students. The study addresses the challenge of preventing academic dishonesty by ensuring that only authorized individuals can complete intermediate and final assessment tasks. The proposed method leverages the Tiny neural network model, selected for its efficiency in compact data processing, alongside the dlib system in Python and the LCC_FASD dataset, which enables precise detection of 68 facial landmarks. Using a confusion matrix to evaluate performance, the method achieved a 94.47% accuracy in detecting spoofing attempts. These findings demonstrate the effectiveness of the proposed approach in safeguarding educational platforms and maintaining academic integrity.

The analysis of medical data plays a critical role in improving diagnostic accuracy, refining research methodologies, and informing decisions regarding the allocation of medical resources, particularly for critical diseases. Artificial intelligence (AI) provides essential tools for analyzing such data to generate reliable predictions. This study proposes a predictive framework for cardiovascular disease that utilizes key risk factors through a hybrid model combining an Improved Particle Swarm Optimization Algorithm with Mutation Criteria (MPSO) and a Recurrent Neural Network-Long Short-Term Memory (RNN-LSTM) architecture. The model's performance was evaluated on two datasets: one from the University of California Irvine (UCI) Machine Learning Repository and another comprising real-world data collected from Baghdad Medical City Hospital and Ibn al-Bitar Hospital. The proposed framework achieved high predictive accuracy, with Data1 yielding an accuracy of 98.36%, precision of 98.48%, sensitivity of 98.48%, and specificity of 98.21%. Data2 demonstrated an accuracy of 98.75%, precision of 100%, sensitivity of 94.12%, and specificity of 100%. These results indicate that the model generalizes effectively across datasets and outperforms state-of-the-art methods in predicting cardiovascular disease, as evidenced by robust performance metrics.

In agile development, user stories are the primary method for defining requirements. These days, managing user stories effectively is difficult because software projects typically contain a large number of them. A project can involve a large amount of user stories, which should be clustered into different groups based on their functionality’s similarity for systematic requirements analysis, effective mapping to developed features, and efficient maintenance. Unfortunately, the majority of user story clustering methods now in use require a great deal of manual work, which is error-prone and time-consuming. In this research, we suggest an automated framework that uses a family of machine learning algorithms to classify user stories. First, preprocessing the data is done in order to examine user stories and extract keywords from them. After that, features are taken out, which allow user stories to be automatically grouped into distinct categories. We use four feature extraction algorithms and six clustering algorithms. According to our experimental results, K-means and BIRCH clustering outperform other clustering methods, whereas cosine similarity and distance are the best feature extraction for user stories categorization to form the more balanced clusters as they both have the standard deviation is 3.08.  In case of user stories cohesion, the silhouette coefficient value is 0.225 for spectral with (cosine similarity and cosine distance feature extraction) is best outcome than other clustering algorithms. The usefulness and applicability of the suggested framework are demonstrated by this study. Additionally, it offers some useful recommendations for enhancing the effectiveness of user stories clustering, for example through parameter adjustments for enhanced feature extraction and clustering.