Online-Journals.org (International Association of Online Engineering)
Not a member yet
9805 research outputs found
Sort by
Understanding AI and Mobile Learning Adoption in Malaysian Universities: A UTAUT-Based Model
Get PDFThis study explores the key determinants influencing the intention to adopt artificial intelligence (AI) applications and mobile learning in Higher Education Institutions (HEIs) in Malaysia. As AI technologies and mobile learning increasingly transform the higher education landscape, it is crucial to understand the specific factors driving their adoption. The research identifies five critical determinants—social influence (SI), effort expectancy (EE), hedonic motivations (HM), performance expectancy (PE), and consumer trust (TR)—that significantly impact the intention to use AI-powered mobile learning solutions. Through a survey of 263 undergraduate and postgraduate students from Malaysian universities, the study develops an adapted model to assess these adoption factors, contributing unique insights into the integration of AI and mobile learning within the Malaysian higher education context. This model provides actionable recommendations for university administrators, educators, and mobile learning developers, offering practical guidance on promoting the adoption of these technologies to enhance student engagement and learning outcomes. By focusing on real-world application, this study not only bridges theoretical research with practical implementation but also offers valuable lessons for similar educational contexts globally, particularly in emerging markets
AI and Mobile Technologies for Driver Fatigue Detection: Sex Differences Revealed by Eye-Tracking Metrics
Get PDFThe present study examines sex differences in fatigue and visual attention during simulated driving. Using a driving simulator, we evaluated the effects of task duration and sex differences on fatigue-related eye-tracking metrics, including blink duration, fixation rate, and blink rate. Results indicate that fixation rate was significantly influenced by task duration but remained consistent across sexes, whereas blink duration exhibited marginal sex differences and a significant interaction with task duration, with females demonstrating longer blink durations compared to males. These findings suggest that males and females adopt distinct patterns in managing fatigue over prolonged tasks, with implications for visual attention and fatigue. This study advances the understanding of sex-specific fatigue responses in dynamic tasks and underscores the potential of eye-tracking technologies for improving road safety
Developing Multipath Routing Protocol Based on Source Routing Protocol in MANET
Get PDFMobile Ad hoc Networks (MANETs) provide a flexible solution for establishing networks in environments where conventional infrastructure is unavailable, such as disaster areas or military operations. However, routing in MANETs is a critical challenge due to node mobility and limited resources. Numerous protocols have been developed, though their performance varies in various conditions. This study paper introduces a multi-disjoint route technique built on the source routing principle, designed to improve MANET performance for the sake of meeting Quality of Service (QoS) requirements. The performance evaluations of the proposed on-demand multipath source routing protocol using NS-2 in comparison with other DSRbased protocols, namely Modified-DSR, Extended-DSR, and Updated-DSR, the results have suggested that the proposed on-demand multipath source routing protocol has obvious advantages in terms of Packet Delivery Ratio (PDR) and Normalized Routing Load (NRL) over the common existing routing protocols developed for MANET
Empowering Corporate Lawyers: AI-Driven Training for Strategic Leadership and Behavioral Mastery
Get PDFIn the fast-evolving corporate legal landscape, the integration of legal expertise with strategic business acumen has become indispensable. To meet this demand, e-REAL Labs, in partnership with leading legal and management experts, has developed a cutting-edge training program tailored for the corporate legal teams of a prominent multinational company. This innovative program combines advanced AI-driven simulations with an experiential learning approach to bridge the gap between traditional legal training and real-world challenges. Participants engage in immersive, high-stakes scenarios replicating corporate law practice’s complex dynamics. The curriculum focuses on building practical competencies, including collaborative business strategies, refined negotiation techniques, effective decision-making under pressure, and strategic foresight. By blending technology and expertise, the program empowers legal professionals to confidently navigate the intricate demands of today’s corporate environment. Graduates of the program benefit from enhanced negotiation skills, improved decisionmaking capabilities, and the ability to anticipate and influence multifaceted legal and business challenges. This transformative training equips corporate legal teams with the tools to excel in a competitive and dynamic global market
AI-Driven Avatars in Medical Training: Personalized Feedback for Enhanced Learning
Get PDFe-REAL Labs is at the forefront of educational technology, pioneering the use of intelligent avatars—also known as digital humans or embodied conversational agents (ECAs)—to enhance medical training. These sophisticated AI-driven avatars replicate complex human interactions, providing real-time, personalized feedback based on behavioral and conversational cues. This article presents an applied research project developed in collaboration with the Center for Medical Simulation in Boston, showcasing an innovative approach that goes beyond traditional feedback mechanisms. By enabling reflective dialogue and interactive learning, these digital humans foster deeper understanding and skill development. As dynamic learning partners, ECAs represent a transformative shift in medical education, offering an immersive and effective method for professional training. This AI-powered approach redefines the role of feedback in healthcare education, setting a new standard for simulation-based learning and professional development
A Stratified Modeling-Machine Learning Approach to Improve the Accuracy of Non-Invasive Blood Glucose Estimation Using Photoplethysmography Signals
Get PDFDiabetes is a silent killer that can only be controlled with continuous monitoring of blood glucose levels. The method commonly used is invasive and has various weaknesses, but it is more accurate than non-invasive methods. This research aims to develop a method to increase the accuracy of non-invasive estimation of blood glucose levels using photoplethysmography (PPG) signals. The proposed method is to carry out stratified modeling-machine learning. The tested classifiers were support vector machines (SVM), KNN, Naïve Bayes, decision tree, and neural network. The prediction model used simple linear, logarithmic, second-order polynomial, exponential, and power regression. Applying stratified modeling using linear regression in the non-diabetes stratum and logarithmic regression in the diabetes stratum obtained a mean absolute relative difference (MARD) value of 4.5%, root mean square error (RMSE) of 18.9 mg/dl, Pearson correlation 0.985 and Clarke error grid analysis (CEGA) 96% in region A and 4% in region B. The implementation of stratification reveals a marked improvement in efficacy, manifested as a reduction in the MARD by 77.83%, a decrease in the RMSE by 51.91%, an enhancement in the Pearson correlation by 0.065, and a CEGA by 100% in regions A and B, thereby being clinically acceptable. Implementing a stratified modeling-machine learning approach can improve the accuracy of non-invasive blood glucose level estimates
Personalized Upper Limb Assistive Device Socket for Phocomelia Patient Using Topology Optimization Techniques
Get PDFPhocomelia is a congenital limb defect affecting the upper or lower limbs of newborns, significantly impacting their daily lives. Adaptive devices, such as prosthetic limbs, are crucial for helping individuals with phocomelia, yet designing and customizing these devices presents a complex challenge, as traditional prosthetic devices often do not cater to the specific needs of each patient due to their generic design. This study employs topology optimization and finite element analysis (FEA) to enhance the design and mechanical performance of these adaptive devices. The study focuses on improving design through material selection and topology optimization, analyzing mechanical behavior using FEA, and identifying potential improvements in strength and durability. Three materials—acrylonitrile butadiene styrene (ABS), polylactic acid (PLA), and polyethylene terephthalate glycol (PETG)—are evaluated with weight reductions ranging from 10% to 50%. Computational software is used for modeling and analysis based on an existing model from Universiti Teknologi MARA (UiTM), incorporating applied forces and fixed points. Results indicate the stiffness-to-weight ratio for each material and mass reduction scenario, alongside stress, strain, and displacement analyses. This study aims to advance adaptive device design by enhancing functionality and affordability, ultimately improving the quality of life for phocomelia patients
Tax Literacy of University Students in the Czech Republic
Get PDFTax literacy represents one of the essential areas of knowledge for life in the 21st century. Although more and more emphasis is placed on practical skills, these topics are still missing in most educational programs. The paper focuses on the tax literacy of university students in the Czech Republic. The main part of the work involves the analysis of data obtained from a questionnaire survey in which 1,061 students participated. For the analysis, the chi-square test of independence and ANOVA were used. The results indicate that 35% of students have excellent tax literacy, 52% have good tax literacy, and 13% have insufficient tax literacy. Additionally, a total of 10 factors were analyzed. Factors such as the field of study at the university, completion of a tax-related course, and the type of high school attended have a statistically significant impact on the level of tax knowledge. The results of this study may contribute to the discussion about the content, meaning and added value of the educational process
Role of Augmented Reality, Virtual Reality and Streaming Services in the Field of Education (2020–2023) – A Systematic Review
Get PDFThis paper systematically reviews the demand for real-time streaming services in the education sector over the period 2020–2023. The systematic review analyzes the effects of augmented reality (AR) and virtual reality (VR) in education, focusing on the need for real-time streaming services. These technologies have grown significantly in education, enabling collaborative and immersive experiences. VR, supported by leading streaming platforms, has facilitated distance education, especially during the COVID-19 pandemic. The methodology was based on searching for articles in databases such as Ebsco, Springer, IEEE, ScienceDirect, and Scopus. Inclusion and exclusion criteria were applied, creating a final sample of 60 papers, with a geographical distribution highlighting the important role of China and the United States. The results indicate that changes in education, the focus on VR, and the impact of the COVID-19 pandemic are the main drivers of demand for educational streaming. This led to a rapid adoption of online educational platforms. Challenges to implementing streaming services include a lack of training in educational institutions and a lack of practice in certain areas. Content customization, video quality, and adequate technological infrastructure are the most sought-after functionalities by users
Comparative Study of Machine Learning Approaches for Detecting Fake News in Arabic Text
Get PDFIt is evident that fake news remains a critical global problem, especially in the Arabic language, although there is an absence of vast amounts of annotated datasets required for effective stateof- the-art natural treatment. In this paper, we compare deep neural networks (DNNs), XGBoost, gradient boosting (GB), and long short-term memory (LSTM) networks on the task of distinguishing real and fake Arabic news. When we applied special preprocessing for AFND with specific approaches to tackle the class imbalance problem, we observed that XGBoost was found to be the best method, performing with an accuracy of 72.86% on the test database. The present model performed optimally on relevant parameters related to the absence of capitalized terms, precision (0.83%), recall (0.71%), and F1-score (0.76%), especially for “undecided” cases. XGBoost’s performance is revealed in these results, and feature selection and optimization are promoted, leading to improvements in the Arabic natural language processing (NLP) domain