Online-Journals.org (International Association of Online Engineering)
Not a member yet
9805 research outputs found
Sort by
Prediction of Atmospheric Pollution Using Hybrid Machine Learning Algorithms: A Review
Get PDFAccurate prediction of atmospheric pollution is critical for public health, guiding environmental policies, and mitigating the adverse effects of air pollution. Traditional statistical models and standalone machine learning algorithms, while useful, often fail to capture the complex, nonlinear interactions between multiple factors influencing air quality, such as meteorological conditions, traffic emissions, and industrial activities. This paper presents a comprehensive review of machine learning techniques applied to air pollution prediction, with a special focus on the growing trend of hybrid models (HM). In addition, this paper highlights future research directions centered on developing adaptive HM capable of integrating diverse data streams, addressing gaps in data availability, and dynamically responding to changing pollution patterns. Furthermore, the paper presents a strategy on how combining machine learning algorithms can enhance predictive accuracy and robustness by leveraging the unique capabilities of each model. The findings from this study aim to provide a foundation for future research and practical applications in air quality management, ultimately contributing to more effective pollution forecasting and control strategies
Perceptions of University Teachers on Microsoft Teams for Online Instruction: A Case Study in Vietnam
Get PDFIn recent years, Vietnam has experienced a surge in the popularity of online education. Microsoft (MS) Teams has been selected by numerous universities as a platform for online instruction. However, there is a scarcity of research on the perspectives of university educators on the use of this platform. This mixed-methods case study aims to examine the perceptions of Vietnamese university lecturers regarding the platform’s simplicity of use and utility in the delivery of online courses. The study also seeks to determine whether there is a substantial disparity in perceptions between male and female instructors and to investigate the obstacles associated with utilizing MS Teams for online instruction. Sixty-two instructors from a university in the northern region of Vietnam, who have expertise in teaching online courses, were provided with an online questionnaire. Additionally, semi-structured interviews were conducted with nine lecturers to gather more detailed information. According to the findings, the educators demonstrate a significant level of admiration for the platform, particularly in terms of its functionality and user-friendliness. The simplicity of learning to operate the platform is a significant distinction between the two gender categories. The results also indicate that lecturers face psychological, physical, and technological difficulties when employing the platform
Hybrid Deep Learning Model to Predict Students’ Sentiments in Higher Educational Institutions
Get PDFSentiment analysis has been widely used in various fields of social media, education, and business. Specifically, in the education domain, the usage of sentiment analysis is difficult due to the huge amount of information, the nature of language, and processing the diverse perceptions of students. Deep learning emerges as an advanced concept in the realm of machine learning that learns features automatically from raw text data, making them well-suited for sentiment analysis tasks. In recent years, deep learning has been used in analyzing the sentiments. Deep learning architectures have surpassed other machine learning paradigms for performing sentiment analysis. The ability to analyze automatically the students’ sentiments enables HEI to process huge amounts of unstructured data quickly, efficiently, and cost-effectively. The paper aims to predict the sentiments of students’ reviews posted in VLE regarding online learning that enables the educators to optimize their teaching methods for the best results. This study paper explores the usage of CNN, LSTM, and hybrid CNN-LSTM for the prediction of sentiments. The proposed hybrid CNN-LSTM architecture achieves superior performance compared to other baseline algorithms with respect to accuracy, precision, recall, and F1 score. According to outcomes, the recommended technique achieves remarkable accuracy of 97%. The findings facilitate the progress of a more efficient deep learning sentiment prediction system that gives valuable insights from a huge volume of students’ textual data
Conceptualizing Disciplinary Literacy in Higher Education: An Exploratory Review
Get PDFDisciplinary literacy (DL) has been a prominent concern in higher education over the past decade. By utilizing databases such as Scopus and Web of Science, the search strategy has identified articles published between 2014 and 2023. Firstly, this paper critically evaluates previous research in order to advance epistemological understanding of DL by examining DL-related components and strategies. Secondly, it sets the foundation for further research by highlighting gaps in the literature and suggesting topics that require investigation. Eighteen studies from a wide range of disciplines and contexts met the inclusion criteria, falling into four overarching themes, namely cognitive, linguistics, disciplinary reasoning, and sociocultural dimensions. The writing, reading, speaking, thinking, and feedback strategies are among the strategies derived from these dimensions that can enhance both disciplinary knowledge and English language proficiency in the subject discipline. The ongoing controversy about the inconsistent application of DL in higher education settings and its conceptualization in these contexts is corroborated by the existing evidence. Future research should focus more on the application of disciplinary-specific frameworks or clear guidelines based on DL strategies across a wide variety of disciplines with the use of rigorous research methodology taking into consideration diverse populations
ECC-Based Anonymous and Multi-factor Authentication Scheme for IoT Environment
Get PDFOwing to its capability to offer remote services, the Internet of Things (IoT) has immersed itself in all areas of our daily lives. However, this big use of IoT networks makes the user’s data change insecurely in open channels vulnerable to malicious use. As a result, the security of the user’s data in an IoT environment becomes a critical issue. Given that authentication is a mechanism that may prevent hackers from retrieving and exploiting data communicated between IoT devices, researchers have proposed many lightweight IoT authentication schemes in the last decades. However, most of these schemes are based on two authentication factors and are unable to ensure unlink ability, key secrecy, perfect forward secrecy, and resistance to node capture, denial of service (DoS) attacks, stolen verifiers, denning-SSACO attacks, and GWN bypassing. In this paper, we present an anonymous three-factor authentication scheme based on elliptic curve cryptography (ECC), which can provide all security services and resist well-known attacks. Then, based on informal security analysis and the formal security proof using ProVerif we show that our provided scheme is secure and can resist known attacks. Finally, we show the comparison result among our protocol and other protocols in terms of computation overheads, communication overheads, and security features
Helperly: An All-Inclusive Healthcare Application
Get PDFThis work presents the development of a comprehensive healthcare app designed to improve early disease detection and enhance healthcare accessibility. The application integrates cutting-edge yet lightweight machine learning (ML) algorithms like Multinomial Naive Bayes and Decision Tree for symptom analysis and incorporates a range of innovative healthcare APIs like Edamam and Exercise API by Ninjas. Its primary objectives include empowering users with proactive health insights, facilitating timely medical assistance, and promoting overall well-being through personalised health recommendations. Key features of the app include accurate disease prediction through ML-driven symptom analysis, healthy recipe recommendations, customised exercise plans, and a conversational chatbot for diagnosis and treatment suggestions. By leveraging these functionalities, the app aims to enable users to take control of their health effectively, promoting paperless transactions via digital appointment and prescriptions. It also reduces physical visits to healthcare facilities, lowering carbon emissions associated with travel, which eventually paves the way to reduce environmental impact. The database integration via Firebase Auth offers data accessibility and security to data via services like encryption and Cloud Store. The intuitive navigation through the chatbot makes it approachable for users, including those who are less tech-savvy. Dark mode support aligns with sustainability goals by reducing eye strain and energy consumption. Thus, the work adheres to material design principles. With a user-centric approach, this app combines innovative ML-driven features and healthcare APIs to set a new standard in the digital health space, paving the way for advancements in early detection, personalised care, accessible healthcare services and long-term societal impact
Augmented Reality in STEAM Education: A Systematic Review of Collaborative Practices for Primary Schools
Get PDFThis systematic literature review aims to evaluate empirical research on various study types and their outcomes, exploring the potential for enhancing students’ collaboration skills through an augmented reality (AR)-based science, technology, engineering, arts, and mathematics (STEAM) approach in primary education. Key findings include improved student motivation, learning efficiency, the use of visual aids, and hands-on experiences. Furthermore, the study demonstrated enhancements in spatial ability, comprehension of teaching materials, and the creation of an enjoyable learning environment. Additional findings include students’ analytical skills, heightened curiosity, teamwork, and problem-solving abilities. This study emphasizes the utilization of AR-based STEAM in both Western and non-Western countries, showcasing the potential for improved student collaboration. The indicators of improved collaboration include communication, problem-solving, responsibility, and collective decision-making in primary education. This is a crucial issue that requires attention in future research. Therefore, teachers and practitioners must implement interdisciplinary approaches that utilize technology to enhance students’ collaboration skills. Moreover, policymakers need to ensure sufficient technological infrastructure support and training for teachers to effectively utilize AR in teaching
Fostering Engagement and Motivation: Evaluating Gamified Learning in the Metaverse for Architectural History Education
Get PDFEngagement and motivation are critical factors in effective learning, particularly in educational contexts that require deep understanding and retention, such as architectural history. This study investigates the role of gamified learning in the metaverse as a tool to enhance student engagement and motivation. Using the Spatial platform, a virtual learning environment was developed where participants interact with digitally reconstructed historical landmarks and complete tasks that explore architectural styles, techniques, and cultural contexts. The research evaluates the impact of this immersive approach on learning outcomes by focusing on participant engagement and intrinsic motivation. A mixed-methods approach is employed, collecting data through pre-and post-tests, engagement questionnaires, usability surveys, and in-game analytics such as task completion rates and time spent in the virtual environment. Qualitative insights are gathered through interviews to understand user perceptions of the gamified experience. These results show that metaverse-based gamified learning can make people more interested and motivated, making it a great way to teaching architectural history and other complex subjects
AI-Powered Smart Classrooms for C-PBL: Enhancing Mobile and Virtual Learning Technologies
Get PDFThe AI-powered smart classrooms for C-PBL to enhance mobile and virtual learning technology, or C-PBL mobile and virtual learning are based on the integration of artificial intelligence and virtual reality technologies with problem-based learning and cooperative learning with an attempt to enhance students’ analytical thinking and curiosity. Thereby, students are encouraged to do activities in small groups and use analytical thinking skills to distinguish problems in a systematic manner, which is believed to enable them to create their own bodies of knowledge from the problem-solving process in those situations or problems. The results of this research are consistent with the hypotheses, as it is found that the C-PBL mobile and virtual learning system is considered a learning tool that can be practically applied in cooperative problem-based learning processes through virtual smart classrooms in order to promote students’ analytical thinking and curiosity in learning. Meanwhile, it is believed that the C-PBL mobile and virtual learning system herein also enables students not only to create their own bodies of knowledge after doing small-group activities in virtual environments but also to receive brand-new knowledge as to their own abilities from experiential learning. However, there are still some research gaps in this study that need to be further addressed in the future. For instance, future studies should explore a wider scope of application by doing surveys with more varied populations and broader educational environments so as to confirm the validity and clarity of study results. Therefore, the findings in this study are considered merely the findings derived from a pilot study and can be used as just a guideline for future development
Intelligent Education Based on Mobile Learning: Transitioning from Traditional Classrooms to Adaptive Learning Environments
Get PDFWith the rapid development of information technology, mobile learning has become a key means to enhance educational quality and facilitate personalized learning. Traditional classroom teaching models exhibit limitations in terms of personalization, adaptability, and flexibility. Mobile learning, on the other hand, offers the opportunity for learning anytime and anywhere, addressing the individualized needs of students. However, effectively integrating mobile learning with intelligent education technologies to create learning environments that cater to diverse student needs remains a significant challenge in current educational research. In response, an intelligent education framework based on mobile learning was proposed in this study. This framework aims to drive the transition of education from traditional classrooms to adaptive learning environments by integrating heterogeneous network graphs and students’ personalized preferences. The primary focus of this study includes two parts: first, a method for constructing heterogeneous network graphs based on mobile learning, which seeks to enhance the adaptability of learning environments through multi-source data fusion; second, the personalized integration of longand short-term preferences, along with an interest recommendation mechanism, using intelligent algorithms to provide customized learning path recommendations for students. Through these two aspects, the study seeks to offer effective solutions for the transformation of intelligent education, promote the practical application of personalized learning systems, and provide theoretical support and practical guidance for the development of educational technologies