Online-Journals.org (International Association of Online Engineering)
Not a member yet
9805 research outputs found
Sort by
Ensuring Academic Integrity: Tools and Mechanisms for a Transparent Educational Environment
Get PDFThis paper examines the concept of academic integrity and the various tools and mechanisms designed to ensure transparency and ethical practices within educational institutions. A key focus is placed on the “public integrity whistleblower for academic activities,” which functions as a critical mechanism for identifying and addressing violations of academic integrity. The study investigates the role of this tool in preventing academic non-compliance and supporting an environment of academic accountability and transparency. By providing a platform for reporting unethical conduct, the whistleblower mechanism strengthens the principles of honesty and fairness, contributing to the development of a trustworthy educational environment. The paper also addresses the limitations of the current system, particularly the absence of comprehensive regulatory and procedural frameworks to fully support academic integrity. These challenges underline the need for further research into academic ethics, especially in the context of open-source materials and the growing accessibility of information
Optimization of Personalized English Learning Paths through Mobile Interaction Technology
Get PDFWith the development of information technology (IT), particularly the widespread application of mobile internet and smart devices, traditional methods of English language learning can no longer meet the personalized needs of modern learners. The design and recommendation of personalized learning paths have become key issues in enhancing learning outcomes. Current study primarily focuses on personalized recommendation systems based on big data and artificial intelligence (AI) algorithms. While these systems have achieved a certain degree of accuracy in recommending learners’ interests and learning content, problems such as recommendation precision, dynamic adaptation to changing interests, and insufficient integration of diversified learning scenarios persist. Therefore, improving the adaptability of personalized learning systems through more intelligent and dynamic learning path optimization methods remains a pressing challenge in this field. Building on existing research, a personalized English learning interest point recommendation model based on the graph convolutional network (GCN) was proposed, and personalized learning paths were optimized by incorporating multidimensional contextual information. The GCN was used to uncover the relationships between learners and knowledge points, thus constructing a precise interest point recommendation mechanism. Additionally, learning paths were dynamically adjusted by considering learners’ historical behaviors, learning progress, and situational context, offering a personalized learning experience. This study advances the development of personalized learning recommendation technologies and provides English learners with a more intelligent and precise learning path optimization solution
Identification of Laryngeal Lesions Based on Narrowband Endoscopy Imaging Using Artificial Neural Networks and Visual Programming
Get PDFCertain types of lesions on the laryngeal mucosa may indicate the early stages of laryngeal squamous cell carcinoma (LSCC), which constitutes 98% of malignant laryngeal tumors. This study aims to develop artificial intelligence-based methods to classify laryngeal lesions using digital images obtained through narrowband endoscopy imaging. A total of 1,320 digital images of laryngeal tissue, both healthy and lesioned, were classified into four categories. Five machine learning models were developed, utilizing conventional deep convolutional neural networks (CNNs) and capsule networks (CapsNet): VGG16, VGG19, Inception V3, CapsNet without data augmentation, and CapsNet with data augmentation. The latter used images synthetically generated by an adversarial generative network (GAN). These algorithms were implemented using the Orange visual programming software and the Colab computational platform. The inclusion of GAN-enhanced data augmentation significantly improved the performance of the CapsNet classifier across all lesion types. The CapsNet model with GAN data augmentation achieved an average recall, accuracy, and F1 score of 94.7%, marking it as the second-best performing model. The highest performance was achieved by the CNN Inception V3 model, with 97% recall, accuracy, and F1 score, facilitated through visual programming. The combination of CapsNet with GAN-based data augmentation presents a viable alternative for the classification of medical images. The use of the Orange visual programming tool enabled high classification performance—97% in both accuracy and sensitivity—at low computational costs, without the need for advanced programming skills from the user
High Performance of LSTM on Dengue Shock Syndrome Detection Using DNA Sequence Encoding Methods
Get PDFDengue fever (DF) is a significant global health challenge, affecting approximately 390 million people annually and imposing substantial public health and economic burdens. Accurate DNA sequence classification is crucial for identifying genetic factors in diseases such as DF. However, many machine learning (ML) models for disease detection rely on basic encoding methods such as one-hot encoding, which fail to fully exploit the sequential and contextual nature of DNA data. To address this limitation, this study applies long short-term memory (LSTM) networks, a neural architecture adept at handling sequential data, to classify DNA sequences for detecting dengue and dengue shock syndrome (DSS). The study evaluates three encoding techniques— one-hot encoding, term frequency-inverse document frequency (TF-IDF), and Word2Vec— using datasets of 3,458 DNA sequences sourced from genomics repositories. Preprocessing included the removal of non-ACGT sequences and duplicates to ensure data integrity, followed by under-sampling to address class imbalance. Experimental results demonstrate that the LSTM model with Word2Vec encoding achieved the highest accuracy (0.98), significantly outperforming other encoding techniques. Word2Vec captures contextual and semantic relationships within DNA sequences, enabling superior classification performance. These findings highlight the potential of combining advanced encoding techniques with LSTM networks to improve the accuracy of disease detection models. The study’s approach offers promising implications for genomic diagnostics, particularly in resource-limited settings, and lays the foundation for future research into applying similar methodologies to other diseases or datasets
Application of Blockchain Technology in Medical Dispute Management
Get PDFWith the increasing complexity of global health challenges and the growing awareness of health among individuals, the importance of personal health management has become more prominent. In modern society, due to the frequent occurrence of medical disputes, it has had a significant impact on the protection of the rights and interests of hospitals and patients. How to obtain necessary data in medical disputes and store it safely is a problem that everyone is facing. Against this backdrop, blockchain technology, with its features of decentralization, immutability, and high transparency, offers a potential solution. By leveraging distributed ledgers, cryptographic algorithms, and smart contracts, blockchain technology can effectively enhance the security and privacy of health data, enabling trustworthy data sharing and interoperability. While the application prospects of blockchain technology in personal health management are broad, its development faces multiple challenges, including technological complexity, issues of standardization, and incomplete legal and regulatory frameworks. Therefore, this paper’s in-depth research on the application and impact of blockchain technology in medical disputes, exploring specific implementation pathways to enhance data security, privacy protection, data sharing, and interoperability, holds significant theoretical and practical value for promoting its application in the field of health management
Predictive Analytics in Mobile Education: Evaluating Logistic Regression, Random Forest, and Gradient Boosting for Course Completion Forecasting
Get PDFThis study aimed to compare the effectiveness of three predictive algorithms—logistic regression, random forest, and GBM—in predicting course completion using user engagement data from online learning platforms. By analyzing engagement metrics such as session duration, session frequency, and quiz scores, the study sought to identify the most effective model for forecasting course completion, providing insights into which aspects of student behavior were most predictive of success. Logistic regression emerged as the best overall performer, achieving the highest accuracy (52.13%) and F1-Score (56.17%), indicating its balanced approach to predicting course completion and non-completion. Random forest and gradient boosting machines (GBM) showed strengths in specific areas; random forest maintained a good balance between precision and recall, while GBM excelled in recall, identifying students likely to complete courses but with lower precision, leading to more false positives. The findings have practical implications for educational technology, particularly in designing personalized learning paths and targeted interventions to support at-risk students. The study also acknowledged limitations, including the dataset’s focus on engagement metrics without demographic context and the potential for model-specific biases. Future research should explore additional predictive features, larger datasets, and more advanced algorithms to enhance the robustness and applicability of predictive models in real-time educational settings
The Potential of Artificial Intelligence in Education: Supporting Educational Transformation for Learners and Educators
Get PDFThe advent of text-generating artificial intelligence (AI) started a new era in education, offering transformative possibilities for both learners and educators. This article explores the potential of AI in education, its constructive applications in classrooms, and the necessary changes that must occur in higher education institutions and schools to integrate AI into learning processes. The paper explores potential benefits, challenges, and the importance of teacher-student collaboration in an AI-enhanced educational landscape. To address this, the paper discusses a multi-method comparative study focusing on students’ and pupils’ attitudes and preferences toward text-generating AI in classrooms and lecture halls.1 The study was implemented in two university courses and high school classes. A particular interest lies in data showing similarities and differences between pupils’ and students’ experiences with and attitudes towards textgenerating AI. The study uses semi-qualitative and quantitative interviews through written feedback forms. It analyzes the experiences and attitudes closely and in detail, thus investigating how pupils and students use AI in educational contexts and how they reflect their experiences. The paper also discusses how the results can be constructively implemented to improve future options for integrating AI tools in the higher education and school sectors.
1 In the following, the term “pupils” always refers to pupils in grades 9, 10 and 11. The term“students” always refers to students at a university
Phishing Susceptibility Among Healthcare Workers: The Impact of Awareness, Email Type, and Location
Get PDFWhile attempts by malicious actors to compromise computer systems continue to increase, there have been limited success in educating corporate learners. Most corporations must rely upon firewalls, email filtering, and other tools to prevent compromises since their employees vary in prevention reliability. Recent studies have shown limited success of anti-phishing awareness corporate learning campaigns; however, these studies have mostly utilized students or individuals aware of their participation in an experiment. The current research utilized healthcare workers. Over the course of 18 months and three experiments, we evaluated if different anti-phishing awareness learning campaigns, simulated phishing email content, or the employee’s work location (remote vs. on-site) factored into their susceptibility to phishing. We found that those participants who received anti-phishing awareness interacted with the simulated phishing email less than those who didn’t receive training. Overall, an average of four percent of the workers in each experiment submitted their credentials on the fraudulent website. Our results suggest any type of anti-phishing training may provide optimal results, at least regarding anti-phishing training
Affective Learning in the Context of Remote Experimentation
Get PDFWe analyzed the remote experiment’s position on “affective learning” and found that it significantly influenced students’ attitudes toward the applications. It emphasizes autonomy in learning and the coagulation aspects of ad hoc learning groups based on cognitive criteria, avoiding the artificial criteria (beautiful, ugly, sympathetic, unfriendly) typical of group formation in the physical environment. A detailed analysis of the students’ emotional responses, according to Wlodkowski’s classification, is made. The paper points out that the affective effect of the R.E. is treated as a secondary element in curricula, all assessments being oriented towards “cognitive learning” because the affective components involved are part of the “internal state” of the student. Based on Dave’s (1979) psychomotor taxonomy, the importance of R.E. in blended learning has been presented, where the cognitive content of learning remains unchanged, and the affective effect of the R.E. adds to teaching the techniques and the social dimensions
Evaluating User Experience in Learning Applications among University Students in Nigeria Using UEQ
Get PDFThis study evaluates the user experience (UX) of learning applications among university students in Nigeria using the user experience questionnaire (UEQ). With the rapid shift toward digital and mobile learning platforms in higher education, understanding students’ perceptions of usability, engagement, and overall satisfaction has become crucial. The study surveyed 397 university students to assess six key UX dimensions: attractiveness, perspicuity, efficiency, dependability, stimulation, and novelty. The findings revealed that the learning management system (LMS) users have a positive experience with it and use it frequently. The novelty category, on the other hand, has the lowest moodle mean score. We posit that these results are acceptable since the student aims to access the LMS to learn. The findings provide valuable insights for educators, developers, and policymakers aiming to optimize e-learning applications for improved usability and engagement. This study contributes to the broader conversation on enhancing digital learning experiences in developing regions