IJMECS Vol. 17, No. 2, Apr. 2025
Cover page and Table of Contents: PDF (size: 606KB)
REGULAR PAPERS
Traditional distance learning has been widely adopted for its capacity to provide educational access to a broad and diverse audience, overcoming spatial and temporal limitations. However, it needs to deliver the same immersion and learning effectiveness as face-to-face instruction, particularly in courses requiring hands-on practice, where these limitations become more pronounced. To address this, virtual reality (VR)-based distance learning has gained attention as a potential solution. Previous studies have confirmed that VR-enhanced distance learning can improve educational outcomes; however, a standardized teaching-learning model designed explicitly for VR-based distance learning has yet to be established. Consequently, instructors have often relied on conventional models, leading to variability in instructional quality. This paper proposes the VR IGLOO model, a structured VR-based teaching-learning framework tailored for distance education. For this purpose, analysis of the conventional studies and focus group interview (FGI) of the expert group were conducted. And the validity of the proposed model was verified through Delphi validation.
[...] Read more.The main goal of the work is to create an intelligent system that uses NLP methods and machine learning algorithms to analyse and classify textual content authorship. The following machine learning models for English and Ukrainian publications were tested and trained on the dataset: Support Vector Classifier, Random Forest, Naive Bayes, Logistic Regression and Neuron Networks. For English, the accuracy of the models was higher due to the more significant amount of text data available. The results for English fiction publication show that the Neuron Networks classifier outperforms the other models in all evaluated metrics, achieving the highest accuracy (0.97), recall (0.96), F1 score (0.98), and precision (0.96). It shows that Neuron Networks is particularly effective in capturing distinctive features of the writing styles of different English authors in scientific and technical texts. For the Ukrainian language,
there is a drop in accuracy by 5-10% due to the smaller number of corpora of texts for teaching. The results for scientific and technical Ukrainian publications show that the Random Forest classifier outperforms the other models in all evaluated metrics, achieving the highest accuracy (0.88), recall (0.87), F1 score (0.87), and precision (0.87). It shows that Random Forest is particularly effective in capturing distinctive features of the writing styles of different Ukrainian authors in scientific and technical texts. Much worse accuracy results were shown by other models such as Support Vector Classifier (77%), Logistic Regression (73%) and Naive Bayes (70%). The results for the Ukrainian fiction publication show that the Random Forest classifier outperforms the other models in all evaluated metrics, achieving the highest accuracy (0.85), recall (0.84), F1 score (0.84), and precision (0.84). Much worse accuracy results were shown by other models such as Support Vector Classifier (77%), Logistic Regression (73%) and Naive Bayes (70%)
By means of a thorough investigation of ensemble methodologies and feature selection approaches, this work explores enhancing predictive modelling in e-learning contexts. The setting is in the growing significance of data-driven decision-making in education and tailored learning programs. The main concern is how to fairly forecast student performance in environments of digital learning. This work intends to solve gaps by investigating new ensemble models and robust feature selection techniques based on already published research. Using cutting-edge analytical techniques including hybrid BR2-2T models and the Chi-square test, the study produces remarkable accuracy surpassing known limits. The results underline the need of feature selection and ensemble methods in improving forecast accuracy and dependability. Finally, this study marks a major step in the field of e-learning predictive modelling since it helps to improve educational results and enable data-driven interventions.
[...] Read more.Federated Learning (FL) is an emerging machine learning approach with promising applications. In this paper, FL is comprehensively examined in relation to teacher performance evaluation. Through FL, teachers can be evaluated based on data-driven metrics while preserving data privacy. There are several benefits, including data privacy preservation, collaborative learning, scalability, and privacy-preserving insights. Additionally, it faces problems related to communication efficiency, system heterogeneity, and statistical heterogeneity. To address these issues, we propose a novel clustering-based technique in federated learning. The technique aims to overcome the challenges of system heterogeneity and improve communication efficiency. We provide a comprehensive review of existing research on clustering techniques in the context of federated learning, offering insights into the state of the art in this field. In addition, we emphasize the need for advanced compression methods, enhanced privacy-preserving mechanisms, and robust aggregation algorithms for future federated learning research. To address these challenges, we present a clustering-based approach to address the merits and challenges of federated learning The clustering-based approach we propose in this research demonstrates promising results in terms of reducing communication overhead and improving model convergence in federated learning. These findings suggest that incorporating clustering techniques can significantly enhance the efficiency and effectiveness of federated learning algorithms, paving the way for more scalable and privacy-preserving distributed machine learning systems. The findings of this study suggest that clustering techniques can improve the efficiency and scalability of federated learning.
[...] Read more.Nowadays, higher education institutions and universities are facing a competitive environment for enhancing the quality of students to achieve extensive knowledge with critical thinking skills and a good personality for better employment in the industry. Universities and other higher education establishments ensure that students overcome the obstacles in these cutthroat environments. In order to do this, it is necessary to analyze the academic performance of each student by determining their strengths and weaknesses. A fuzzy expert system (FES) is used in this study to evaluate student’s academic performance. This FES uses fuzzy logic to classify each student’s performance based on a variety of linguistic factors. It classifies each student’s performance by considering various linguistic factors using fuzzy logic. For this purpose, seven significant input factors have been taken into account which is Stress, Motivation, Confidence, Parent’s support & Availability, Self study hours, Punctuality, and Friend circle. Several defuzzification techniques are applied in order to examine student performance using the FES & generate more precise and measurable results. These findings could aid colleges and other educational establishments in determining the right variables that influence student’s academic performance. Additionally, a comparison of various Mamdani fuzzy defuzzification techniques, including the centroid, bisector, and mean of maxima methods, is provided in this study. After comparing all three techniques by taking different scenarios of all the external factors, it has been concluded that all of them are performing equally.
[...] Read more.The toxic comment detection over the internet through social networking posts found hatred comments and apply certain limitations to stop the negative impact of that information in our society. In order to perform sentiment analysis, NLP text classification approach is very effective. In this paper, we design a specific algorithm using Convolution Neural Network (CNN) approach and perform TextBlob sentiment analysis to evaluate the polarity and subjectivity analysis of posted tweets or comments. This paper can also filter the tweets collected over different locations formed Twitter dataset and then model is evaluated in terms of accuracy, precision, recall and f1-score as calculated results of 0.984, 0.887, 0.905 and 0.895 respectively for the analysis of toxic/non-toxic comment identification. Hence, our algorithm utilized NLTK and TextBlob libraries and suggests that the analyzed post can be recommended to the others or not.
[...] Read more.This article addresses the need for a comprehensive understanding of the rapidly evolving field of Artificial Intelligence (AI) in education, given its potential to transform teaching and learning practices. The study analyzed 1,234 articles from the Web of Science database, using bibliometric techniques and topic modeling. Quantitative analyses of publication trends, citation impacts, and collaboration patterns were conducted using the R programming language, and Latent Dirichlet Allocation (LDA) was employed to uncover latent themes and potential research gaps. The study reveals a dramatic growth in research output, with an annual growth rate of 47.9%. China and the United States emerge as dominant contributors, collectively accounting for 38% of publications. Key research themes include AI in language learning, AI ethics and policy, and AI literacy. The findings highlight the need for more inclusive and diverse research efforts to address the unique challenges and opportunities of AI in education in across socioeconomic contexts.
[...] Read more.