Online-Journals.org (International Association of Online Engineering)
Not a member yet
9805 research outputs found
Sort by
Elevating Mobile Security: An Ensemble Approach for Enhanced Malware Detection with M-iForest
Get PDFThe rapid advancement of technologies and the widespread use of smartphones have given rise to new malware threats. However, the sophisticated techniques adopted by malware creators have significantly diminished the effectiveness of traditional security measures, including signature-based detection and antivirus tools solutions ineffective. To address this issue, current malware detection methods rely on extracting malware features and analyzing them using static, dynamic, or hybrid techniques. In this paper, an innovative fusion Android malware detection system has been proposed. The fusion system is based on two parallel subsystems working together. The first subsystem is trained on benign-labeled applications, while the other one focuses on malware-labeled applications. Each subsystem leverages an ensemble approach, combining one class support vector machine (OC-SVM), local outlier factor (LOF), and a modified isolation forest (M-iForest) classifier. The evaluation has been done using two benchmark Android malware datasets, which are DREBIN and CICAndMal2017. The proposed system achieves an accuracy rate of 97.05% and an F-score of 95.87% for the DREBIN dataset. Similarly, for the CICAndMal2017 dataset, it attains an accuracy rate of 99.01% and an impressive F-score of 96.58%. The proposed approach outperforms several existing methods that use the same dataset in terms of accuracy, F-score, and false-positive rate (FPR)
The Role of Lecturers’ AI Leadership in Enhancing Postgraduate Student Teachers’ Integration of Mobile AI Tools: A Mixed-Methods Study in Malaysian Education Faculties
Get PDFThis study examined the influence of lecturers’ artificial intelligence (AI) leadership on postgraduate student teachers’ motivation to integrate AI into their curricula in Malaysian higher education. Using a sample of 62 participants, the study employed a mixed-methods approach to explore ethical implications and the alignment of AI with traditional teaching practices. By means of open-ended questions and online surveys, the study generated both quantitative and qualitative understanding of how leadership influences acceptance of AI in educational settings. Key findings showed that transformative and visionary AI leadership approaches not only improve feedback systems and tailored learning opportunities but also inspire teachers by means of interactive, game-like learning activities. AI leadership enables early identification of learning gaps by means of real-time analytics, enabling targeted interventions and a more inclusive learning environment. However, over-reliance on AI highlights the need for strategic planning to ensure that AI complements rather than replaces traditional teaching methods. The research emphasized the need for strategic leadership and professional development in embedding AI ethically and successfully inside curricula, offering a framework for both curriculum design and educator training programs. These results support current debates on educational innovation and place leadership as key in promoting a balanced, ethical AI integration matched with present educational aims
Text Classification of Duolingo Reviews on Google Play: Insights for Enhancing M-Learning Applications
Get PDFAs digital education tools gained prominence, user feedback played a crucial role in refining and personalizing learning experiences. This study analyzed over 100,000 Google Play reviews of the Duolingo language-learning app, using text classification techniques to extract key insights into user sentiment and preferences. By employing natural language processing (NLP) methods, specifically logistic regression and Naive Bayes classifiers, the study categorized feedback into four primary themes: content, instruction, performance, and user interface and user experience (UI/UX). Logistic regression achieved an AUC score of 0.812, precision of 0.904, recall of 0.900, and F1-score of 0.894, while Naive Bayes achieved an AUC score of 0.806, precision of 0.904, recall of 0.900, and F1-score of 0.894. Both models demonstrated an accuracy rate of 90%. The results indicated that content was the most significant concern for users, comprising 74.2% of all reviews, followed by instructional feedback (14%) and performance issues (9.1%). This analysis provided valuable insights for developers aiming to enhance Duolingo’s user experience by addressing content quality, improving pedagogical approaches, resolving technical issues, and refining the user interface. The findings also contributed to the broader field of educational technology by demonstrating the application of machine learning techniques in understanding user feedback at scale
Enhancing Student Achievement through a Digital Learning Module: The TEFA-T Model in a Teaching Factory of Automotive Vocational Education
Get PDFThis study is based on preliminary studies that identified the problem of suboptimal learning quality. The objective of the study is to develop a digital e-module within the teaching factory (TEFA) (TEFA)-T learning model as an effort to improve the academic achievements of automotive vocational students, ensuring the module is valid, practical, and effective. The study method is research and development (R&D) using the Instructional Development Institute (IDI) model development procedure, which consists of three stages: define, develop, and evaluate. The results of this study generally produce a comprehensive digital learning e-module design consisting of a cover, preface, table of contents, learning structure, learning patterns, e-module position map in learning, glossary, learning introduction, learning activities, evaluation, and closing. The TEFA-T learning e-module is statistically validated and practical. The average Aiken’s V value obtained is 0.967, indicating that the digital e-module content is in the valid category. The TEFA-T learning e-module is considered very practical, as shown by the average practicality assessment scores of 92.20% from lecturers and 90.60% from students, both in the “Very Practical” category. In conclusion, after implementing the TEFA-T learning e-module, students can build knowledge inductively and deductively, as well as gain learning experiences through one-way interaction, personal interaction, and effective learning interaction, significantly improving student academic achievement (Sig. 2-tailed value is less than 0.05)
Interactive Visual Communication Design of Mobile App Interface Based on Artificial Intelligence Technology
Get PDFMobile app interface design is a crucial aspect of human-computer interaction. Interactive mobile app interface design becomes even more important. However, the traditional design system based on convolutional neural networks (CNN) has low accuracy and poor effect. It is important to improve the system to enhance user experience. To address these issues, the study utilizes the K-means clustering (KMC) algorithm and principal component analysis to analyze the collected user data for demand analysis. Then, a deep adversarial CNN is employed to generate a design scheme for the interactive mobile cell phone application. After evaluation by several mobile front-end engineers, the system designed products with an average rating of 85 for aesthetics, 89 for ease of use, and 83 for information intuitiveness. These excellent results highlight the method’s supremacy in interface design aesthetics and user experience, as well as its effectiveness and clarity in information organization and presentation
Innovative Models of Student Entrepreneurship Education Supported by Mobile Technology in Higher Education
Get PDFIn the context of rapid globalization and digital transformation, entrepreneurship education has become a crucial component of higher education systems. With the swift advancement of mobile technology, leveraging its potential to support student entrepreneurship education has emerged as a significant area of inquiry. Mobile technology not only offers convenient access to learning resources but also fosters entrepreneurial interest and potential through diverse interactive means, enhancing students’ entrepreneurial capabilities and innovative thinking. Existing research highlights the notable advantages of mobile technology in education, particularly in resource accessibility and learning interaction. However, traditional studies often focus on the isolated functionalities of technology, lacking a systematic investigation into the overall innovation of entrepreneurship education models. Moreover, current methods show limitations in resource matching and personalized recommendations, failing to fully meet students’ diverse entrepreneurial needs. To address these gaps, this paper proposes an intelligent entrepreneurship resource matching model that integrates mobile interactive networks with attention mechanisms. The model consists of five key components: the knowledge embedding layer, attention-enhanced mobile interactive entrepreneurship resource propagation network, attention-based entrepreneurship resource knowledge graph convolutional network, vector fusion layer, and entrepreneurship resource intelligent matching prediction layer. This study not only enriches the theoretical understanding of the integration of entrepreneurship education and mobile technology but also provides practical guidance and reference for educators, offering significant application value
elearning Strategies to Enhance Eye Care Training
Get PDFMyopia prevalence in Asia remains among the highest globally, accompanied by widespread misconceptions about its management. For eye care practitioners, staying updated on emerging research and debunking myths is critical to delivering effective patient care. However, traditional approaches to professional development, such as in-person workshops or online modules, often fail to account for the time constraints and demanding schedules of practitioners. Effective learning strategies must go beyond mere knowledge delivery to address the behavioral and motivational challenges that impact the application of knowledge in real-world settings. This paper explores an award-winning eLearning initiative by the Singapore National Eye Centre designed to advance professional development in basic myopia management. By leveraging innovative online learning strategies, this project equips practitioners with evidence-based insights while fostering meaningful behavioral change. The program’s design aligns with the evolving demands of healthcare education, emphasizing practical application, adaptability, and outcomes-driven learning. In the context of a rapidly changing healthcare landscape, this initiative demonstrates how well-structured eLearning can empower practitioners to navigate complex research, dispel prevalent myths, and ultimately improve patient care
Utilization of Generative Artificial Intelligence Technologies as Learning Tools among University Students: A Cross-Sectional Study
Get PDFArtificial intelligence (AI) technologies have the potential to revolutionize the higher-education landscape by offering personalized and adaptive learning experiences. This study aimed to investigate the utilization of AI technologies as a learning tool among university students and identify the factors influencing it. This study utilized a cross-sectional design and collected data through a self-administered questionnaire developed based on the technology acceptance model and Theory of Planned Behavior (TPB). Data from 581 respondents were analyzed using SPSS version 29, employing descriptive statistics and multivariate hierarchical multiple linear regression analysis. The study found that AI technologies were widely utilized by students for various academic tasks, with clarifying understanding (76.1%), paraphrasing (71.6%), and academic translations (71%) being the most common. ChatGPT (91.4%), QuillBot (82.8%), and Grammarly (79.7%) emerged as the most popular AI tools among the participants. A hierarchica1l multiple regression analysis revealed that motivation (β = .17, p = .002), subjective norms (β = .14, p < .001), and intention to use (β = .49, p < .001) were significant predictors of AI technology use among students. This study highlights the widespread adoption of AI technologies for academic tasks among university students. Higher education institutions foster an environment that enhances students’ motivation, addresses subjective norms, and cultivates a positive intention towards AI technology adoption to facilitate its effective integration into the learning process
Construction of a New Data Set of Pleural Fluid Cytological Images for Research
Get PDFThe limited availability of standardized datasets has hindered the implementation of artificial intelligence (AI) models in serous fluid cytology, particularly in pleural fluid analysis. In this paper, we present the construction of a dataset of pleural fluid cytology images. The objective is to generate a dataset of pleural fluid cytologic images validated by two pathologists and classified into five categories for cell diagnosis, which will be used to train AI models. As a methodology, the images represent pleural fluid cytology samples that have been prepared through medical procedures and transferred to slides, providing valuable information when evaluated under the microscope by medical specialists through cytological examination. We documented the entire process for building the pleural fluid cytological image dataset, from image capture, labeling, preprocessing, standardization, and uploading to public platforms. As a result, we obtained a pleural fluid cytology dataset based on the International System (TIS) criteria for reporting serous fluids, classifying samples into AUS, MAL, ND, NFM, and SFM. This dataset is intended to support medical research, deep learning applications in medical image analysis, and improved diagnostic methodologies
Systematic Review of Digital Tools’ Impact on Primary and Secondary Education Outcomes
Get PDFThe systematic review investigates the impact of digital tools on learning outcomes in primary and secondary education. The study synthesizes research published between 2018 and 2023, employing a rigorous methodology that includes a comprehensive literature search across four academic databases, selecting 31 relevant studies through a dual-review process based on strict inclusion and exclusion criteria. The methodology focused on empirical studies examining the direct effects of digital tools on pedagogical practices and student achievement. The analysis revealed a significant positive impact of digital tools on student engagement, conceptual understanding, and academic performance across various subjects and educational levels. Key findings indicate that effective technology integration requires access to digital resources, targeted professional development for educators, infrastructural advancements, and supportive policy frameworks. The research identified challenges such as disparities in technology access and the slow pace of digital skills acquisition. This study contributes to the existing body of knowledge by providing a comprehensive overview of digital tool integration in education, highlighting its potential and the obstacles to its practical use. The findings advocate for a balanced and strategic approach to incorporating technology into educational settings, paving the way for future advancements in educational technology