Shahla Asadi

The metaverse marks a transformative frontier in educational technology; however, factors influencing students’ adoption of metaverse-based learning environments remain unclear. This study extends the Technology Acceptance Model by integrating hedonic quality stimulation, cognitive engagement, immersion, subjective norms, and personal innovativeness as antecedents, while examining perceived privacy risk as a moderating factor. Using a hybrid partial least squares (PLS) and artificial neural networks (ANN), we analyzed survey data from 353 computer science students across three Malaysian public universities. The PLS-SEM results indicate that hedonic quality stimulation, subjective norms, immersion, cognitive engagement, and personal innovativeness significantly influence perceived usefulness and perceived ease of use, which collectively explain 66% of the variance in students’ intention to use metaverse technologies. Perceived privacy risk negatively moderates the relationship between perceived usefulness and usage intention, showing that privacy concerns can offset the benefits of perceived utility. The complementary ANN analysis captures nonlinear relationships and identifies subjective norms, hedonic quality stimulation, and perceived usefulness as the strongest predictors of perceived ease of use, perceived usefulness, and usage intention, respectively. Overall, the findings offer actionable insights for institutions designing immersive yet privacy-conscious metaverse learning ecosystems and demonstrate the methodological advantages of a hybrid PLS-ANN approach.

Adversarial Machine Learning (AML), particularly model poisoning, presents a critical threat to Autonomous Vehicles (AVs) in the Internet of Vehicles (IoV) environment. To address this challenge, we propose a framework that integrates Federated Learning (FL) with a Deep Learning-based Intrusion Detection and Behavior Monitoring (DL-based IBM) system, a vehicle scoring mechanism, Digital Twin (DT), and Generative AI (Gen-AI) to enhance security in IoV environments. Each AV employs a DL-based IBM as its local model, which is trained on vehicle-local operational data and contributes to a global model through FL aggregation. A vehicle scoring system is responsible for identifying and flagging compromised AVs (Zombies) exhibiting suspicious behavior. When the DT detects that the Zombie’s model has been manipulated through poisoning attacks, the DT updates the compromised model with the correct global model to restore normal operation. Furthermore, DT leverages Gen-AI to simulate and learn from novel attack scenarios that AVs have not previously encountered, ensuring that the framework adapts to evolving threats. The simulation results demonstrate significant improvements in resilience and detection accuracy, with F1 scores reaching 99% for known attacks and exceeding 87% for new unseen threats. This integrated approach ensures robust and adaptive protection for AVs, maintaining high trust and performance in the dynamic and adversarial IoV network.

Simulation-based learning (SBL) presents a wide variety of opportunities to practice complex computer and networking skills in higher education, employing various platforms to enhance educational outcomes. The integration of SBL tools in teaching computer networking courses is useful for both instructors and learners. Furthermore, the increasing importance of SBL in higher education highlights the necessity to further explore the factors that affect the adoption of SBL technologies, particularly in the field of computer networking courses. Despite these advantages, minimal effort has been made to examine the factors that impact instructors’ intentions to use SBL tools for computers and networking courses. The main objective of this study is to examine the factors that affect instructors' intentions to utilize SBL tools in computer networking courses offered by higher education institutions. By employing Interpretive structural modeling (ISM) and Matriced’ Impacts Croise's Multiplication Appliquee a UN Classement (MICMAC) analysis, the research attempts to provide an in-depth understanding of the interdependencies and hierarchical associations among twelve identified factors. Results showed that system quality, self-efficacy, technological knowledge, and information quality have high driving power. This study offers valuable perspectives for higher education institutions and for upcoming empirical studies and aids in comprehending the advantages of using SBL tools in teaching and higher education.

The significance of big data analytics (BDA) has benefited the health sector by leveraging the potential insights and capabilities of big data in decision making. However, every implementation of BDA within the healthcare field faces difficulties due to incomplete or flawed information that necessitates attention and resolution. The purpose of this systematic literature review is to accomplish two main objectives. Firstly, it aims to synthesize the various elements that contribute to imperfect information in BDA and their impact on decision-making processes within the healthcare sector. This involves identifying and analyzing the factors that can result in imperfect information in BDA applications. Secondly, the review intends to create a taxonomy specifically focused on imperfect information within the context of BDA in the health sector. The study conducted a systematic review of the literature, specifically focusing on studies written in English and published up until February 2023. We also screened and retrieved the titles, abstracts, and potentially relevant studies to determine if they met the criteria for inclusion. As a result, they obtained a total of 58 primary studies. The findings displayed that the presence of uncertainty, imprecision, vagueness, incompleteness, and complexity factors in BDA significantly impacts the ability to sustain effective decision-making in the healthcare sector. Additionally, the study highlighted that the taxonomy for imperfect information in BDA provides healthcare managers with the means to utilize suitable strategies essential for successful implementation when dealing with incomplete information in big data. These findings have practical implications for BDA service providers, as they can leverage the findings to attract and promote the adoption of BDA within the healthcare sector.

Healthcare waste disposal center location (HCWDCL) impacts the environment and the health of living beings. Different and sometimes contradictory criteria in determining the appropriate site location for disposing of healthcare waste (HCW) complicate the decision-making process. This research presents a hybrid multi-criteria decision-making (MCDM) method, named PROMSIS, to determine the appropriate HCWDCL in a real case. The PROMSIS is the combination of two well-known MCDM methods, namely TOPSIS and PROMETHEE. Moreover, fuzzy theory is used to describe the uncertainties of the problem parameters. To provide a reliable decision on selecting the best HCWDCL, a comprehensive list of criteria is identified through a literature review and experts’ opinions obtained from the case study. In total, 40 criteria are identified and classified into five major criteria, namely economic, environmental, social, technical, and geological. The weight of the considered criteria is determined by the Analytical Hierarchy Process (AHP) method. Then, the score of the alternative HCWDCLs in each considered criterion is obtained. Finally, the candidate locations for disposing of HCWs are ranked by the proposed fuzzy PROMSIS method. The results show that the most important criteria in ranking the alternatives in the studied case are economic, environmental, and social, respectively. Moreover, the sub-criteria of operating cost, transportation cost, and pollution are identified as the most important sub-criteria, respectively.

Higher Education Institutions (HEIs) consider resource optimization as an essential concern. Cloud computing (CC) in the fourth industrial revolution became the de-facto standard for delivering IT resources and services. CC is now a mainstream technology, andHEIs across the globe are rapidly transitioning to this model; hence, maintaining the retention of the customers of such technologies is challenging for cloud service providers. Current research concerning CC focused on adoption and acceptance. However, there is still a scarcity of research concerning such technology’s continued use in an organizational setting. Drawing on the prior literature in organizational-level continuance, this paper established a positivist quantitative-empirical study to bridge the research gap and assess the precursors for a continuance of cloud technology in HEIs. Subsequently, this study developed a conceptual framework by integrating the IS success model and the IS discontinuance model through the lens of the TOE framework. The data were collected from the decision-makers of Malaysian HEIs that have adopted CC services, and analyzed using Structural equation Modelling (SEM) based on Partial Least Squares (PLS). The results indicate that the continuance intention can be predicted by technology, organizational, environmental, and other contextualized factors, explaining 85.2% of the dependent variables’ variance. The paper closes with a discussion of the research limitations, contribution, and future directions.

This study aims to develop a new approach based on machine learning techniques to assess sustainability performance. Two main dimensions of sustainability, ecological sustainability, and human sustainability, were considered in this study. A set of sustainability indicators was used, and the research method in this study was developed using cluster analysis and prediction learning techniques. A Self-Organizing Map (SOM) was applied for data clustering, while Classification and Regression Trees (CART) were applied to assess sustainability performance. The proposed method was evaluated through Sustainability Assessment by Fuzzy Evaluation (SAFE) dataset, which comprises various indicators of sustainability performance in 128 countries. Eight clusters from the data were found through the SOM clustering technique. A prediction model was found in each cluster through the CART technique. In addition, an ensemble of CART was constructed in each cluster of SOM to increase the prediction accuracy of CART. All prediction models were assessed through the adjusted coefficient of determination approach. The results demonstrated that the prediction accuracy values were high in all CART models. The results indicated that the method developed by ensembles of CART and clustering provide higher prediction accuracy than individual CART models. The main advantage of integrating the proposed method is its ability to automate decision rules from big data for prediction models. The method proposed in this study could be implemented as an effective tool for sustainability performance assessment.