United Arab Emirates (UAE) has adopted blended learning (BL) as part of its commitment to incorporating technology and learning approaches. At Ajman University in UAE, this study explores students' perspectives on BL's application after the COVID-19 pandemic. A 20-item survey was used, and a descriptive research study was conducted to collect data. We administered the questionnaire to 1,400 undergraduates after validating its validity. With a 3.53% arithmetic mean and 0.957 standard deviations, the study found that undergraduate students expressed a high level of acceptance for BL after COVID-19 spread. In addition, this study found that students' perceptions differ according to gender (males are the most positive for BL), according to the students in the college (medical students are more positive), and finally, according to their years of study (sixth-year students are the most positive). The study recommended that higher education should continue to study BL.

IT-related projects are among the most challenging to manage due to their inherent complexity, uncertainty, and the intangibility of their outcomes. However, a data-driven decision-making approach can help tackle these challenges and increase the chance of IT project success. Machine learning techniques can be used to predict uncertain aspects of IT projects, such as the estimation of time, cost, and effort, when applied to historical data collected from previous or similar projects. This approach can allow the project manager to make informed decisions based on facts rather than human judgment or hunch. In this work, we review the potential of data-driven approaches in the management of IT projects, and we demonstrate a use case that applies three regression algorithms, including polynomial regression, linear regression, and partial least squared (PLS), to predict software effort estimation based on the NASA93 public dataset. The best results were achieved using polynomial regression which scored 82% in R2, 81% in MAPE, 152 in MAE, 276 in RMSE and 76387 in MSE metrics.

Good software design plays an essential role in the software life cycle; refactoring the code smell found during the early stages of software design activity introduces a perfect model design. Finding the code smell manually requires excessive work and is time-consuming. Researchers investigated whether machine learning (ML) models can efficiently be leveraged for code smell detection. In addition to the efficient usage of ML in code smell detection areas, several researchers apply various types of data over-sampling to handle imbalanced dataset issues. Therefore, this paper proposes a new model for code smell detection utilizing the so-called Generative Adversarial Networks (GANS) to over-sample minor smelly code samples. Additionally, this research presents a comparative study focused on using different over-sampling methods, such as SMOTE, and their variations during smell detection. A sequence of experiments has been conducted using five Machine Learning (ML) models using different evaluation metrics: precision, accuracy, recall, and F1 score, which aimed to detect God-class and Data-class at the class level, Long-Method and Feature-Envy and at the method level. All the experimental results indicate that our proposed approach introduced the best result, 99.9

Natural Language Processing (NLP) is an effective tool for analyzing consumer satisfaction with products and services typically sold by e-businesses. This study explores the use of sentiment analysis to understand customer feedback and ratings using a dataset acquired by Amazon. That dataset covers online purchases over a period of eight years. The study aims to examine the factors that impact sentiment polarity throughout different periods and understand changes in consumer feelings and reviews towards online products and services. The applied method comprehensively studies sentiment, extracting features using the Term Frequency-Inverse Document Frequency (TF-IDF) and other text analysis and data processing procedures. Visualization is also applied to illustrate the trends, patterns, and changes in customer satisfaction over time and per product and line of products. The findings underscore the importance of sentimental research in discerning customer sentiments on online e-commerce platforms and offer practical recommendations for enhancing online and improving customer satisfaction.

Globally, over 79.2 million individuals are affected by learning disabilities, with a rising prevalence that challenges educational systems, especially in resource-limited settings. This study explored the effectiveness of artificial intelligence (AI)-based tools in identifying students with learning difficulties (SWLD) in Jordanian schools and investigated educators’ perceptions toward these tools. Guided by the universal design for learning (UDL) and information processing theory (IPT), a mixed-methods research design was adopted. Data were collected between September and November 2024 through an online survey administered to 150 educational professionals, including teachers, school administrators, and policymakers. After excluding pilot respondents, 130 valid responses were analyzed, yielding an 87% response rate. Quantitative data were evaluated using descriptive and inferential statistics (multiple linear regression via SPSS), while qualitative responses underwent thematic analysis. Findings revealed that AI tools—particularly machine learning and natural language processing—were perceived as highly effective in the early identification of learning challenges. Additionally, educators’ positive perceptions significantly predicted AI integration in schools, although concerns about ethical use and data security were noted. The study underscores the necessity of training and equitable access to AI technologies to support inclusive education. These results offer practical and policy-level implications for integrating AI into special education frameworks in Jordan.

Global Software Development (GSD) has changed the phase of software development industry as it provides opportunities to outsourcing software development to another country or different land, it also provides flexibility, more talentpool of human resources, tremendous fasilitated technological infrastructure and much more in analysing cost-efficiency. Still, managing GSD projects presents considerable difficulties such as communication and cooperation problems, RCM, resource allocation problems, and technological limitations. Using qualitative surveys, this research examines, to some extent, both the positive and the negative aspects of GSD project management. Potential advantages or benefits include enhanced access to a wide range of specialists, eradications of silos for knowledge, opportunities for incorporating emerging technologies such as AI and blockchains, together with better approaches to scaling services and products. At the same time, the study focuses on essential issues, such as cultural issues, time dislocations, inadequate resource estimations, and legacy systems. In light of these complexities the following recommendations can be made - get acquainted with structured frameworks, modern collaborative tools, and agile methodologies in order to successfully enhance communication in organizations. Hence, there is an opportunity for organizations to optimise the success of GSD projects and develop high quality software products in the global market by counterbalancing these opportunities and threats.

The primary goal of this research has been to examine the perceptions related to the use of simulation software in the context of e-learning at Engineering PSUT in Jordan, which is acknowledged as one of the leading private universities in the country. The present study and a descriptive study utilized a 25-item survey given to 270 students. The research findings indicate that, according to the students’ subjective viewpoint, the effectiveness of simulation software in the context of online learning was observed to be significantly high. This observation is supported by an average score of 3.89 and a standard deviation of 0.959, indicating a relatively consistent perception among the participants. The study’s results indicate that there were no significant variations observed in terms of academic year, computer skills, student GPA or gender parameters. The research findings underscore the importance of incorporating simulation software in higher educational institutions to improve the teaching and learning experience.

Aim: The study was conducted to improve our knowledge of the current level of knowledge and attitudes towards artificial intelligence among university faculty members at Abu Dhabi University. Method: A questionnaire containing 35 items was distributed to 116 faculty members (n = 116) using the descriptive approach method. It was found that the perceptions of faculty members at Abu Dhabi University about their level of knowledge about artificial intelligence were at a high level, with an arithmetic average of 4.03. Results: It was found that the level of their attitudes towards artificial intelligence was also at a high level with an average of 3.82. Conclusion: Findings have confirmed that the level of knowledge of female faculty members and their attitude towards using artificial intelligence is higher than the level of knowledge of male faculty members. Depending on the category of college (in favor of the Law College) and finally, there was no statistical significance according to academic position. (c) 2024 Ani Publishing Ltd. All Rights Reserved.

The study proposes a simplified energy management system (EMS) that can be a useful tool for small towns with a majority of middle-class residents who are looking to improve their quality of life while lowering energy expenditures and having a smaller environmental effect. This article examines the advantages of setting up an EMS in a small community and offers guidance on how to do so. The system is composed of a wind turbine and a gas turbine. The latter can be fueled either from natural gas or from biogas. The system has been implemented in Matlab/Simulink and executed with real-world data that is publicly available. The research presented in this article can assist small towns in developing an environmentally friendly EMS that will improve citizens’ quality of life, where the results have shown continuity of service for the system over many hours with cheap or even free electricity.

The COVID-19 pandemic resulted in extended school closures and unexpected disruptions to educational processes. The education system in the UAE was compelled to respond rapidly to ensure continuity of learning. This study investigates the impact of remote learning on the performance of educational institutions. Data were gathered from 307 schoolteachers and administrators across the UAE, and the empirical data were analysed using JASP version 0.19.0.0. The findings demonstrate that remote learning significantly influenced institutional performance within the UAE's education sector. The study offers recommendations for improving learning outcomes and fortifying the education system against future crises, providing valuable insights for policy formulation during emergencies.

The quick spread of fake news in different languages on social platforms has become a global scourge threatening societal security and the government. Fake news is usually written to deceive readers and convince them that this false information is correct; therefore, stopping the spread of this false information becomes a priority of governments and societies. Building fake news detection models for the Arabic language comes with its own set of challenges and limitations. Some of the main limitations include 1) lack of annotated data, 2) dialectal variations where each dialect can vary significantly in terms of vocabulary, grammar, and syntax, 3) morphological complexity with complex word formations and root-and-pattern morphology, 4) semantic ambiguity that make models fail to accurately discern the intent and context of a given piece of information, 5) cultural context and 6) diacrasy. The objective of this paper is twofold: first, we design a large corpus of annotated fake new data for the Arabic language from multiple sources. The corpus is collected from multiple sources to include different dialects and cultures. Second, we build fake detection by building machine learning models as model head over the fine-tuned large language models. These large language models were trained on Arabic language, such as ARBERT, AraBERT, CAMeLBERT, and the popular word embedding technique AraVec. The results showed that the text representations produced by the CAMeLBERT transformer are the most accurate because all models have outstanding evaluation results. We found that using the built deep learning classifiers with the transformer is generally better than classical machine learning classifiers. Finally, we could not find a stable conclusion concerning which model works well with each text representation method because each evaluation measure has a different favored model.

As internet technology use is on the rise globally, phishing constitutes a considerable share of the threats that may attack individuals and organizations, leading to significant losses from personal and confidential information to substantial financial losses. Thus, much research has been dedicated in recent years to developing effective and robust mechanisms to enhance the ability to trace illegitimate web pages and to distinguish them from non-phishing sites as accurately as possible. Aiming to conclude whether a universally accepted model can detect phishing attempts with 100% accuracy, we conduct a systematic review of research carried out in 2018–2021 published in well-known journals published by Elsevier, IEEE, Springer, and Emerald. Those researchers studied different Data Mining (DM) algorithms, some of which created a whole new model, while others compared the performance of several algorithms. Some studies combined two or more algorithms to enhance the detection performance. Results reveal that while most algorithms achieve accuracies higher than 90%, only some specific models can achieve 100% accurate results.

3D printers are known for providing parts with relatively good accuracy. However, the level of accuracy in the dimensions of printed objects may not matter if they do not have a mechanical purpose. When multiple 3D-printed parts are intended to be integrated with each other to create a larger system, even a fraction of a millimeter can have a significant impact on the entire system. This study aims to investigate the variation in dimension when a single print file is replicated using the same slicing settings. The findings are then analyzed using quality control tools and compared to the designed measurements. Fused deposition modeling (FDM) technology or fused filament fabrication (FFF) technology was chosen for this study due to its availability to the common user, its relatively low cost, and its increasing popularity in different applications and industries. The material used in this study is polylactic acid (PLA) which is a thermoplastic and the most widely used plastic filament in 3D printing. It has a low melting point, high strength, low thermal expansion, and is relatively cheap. The dimensional accuracy of FDM-produced parts was evaluated by comparing the dimensions of the fabricated specimens with their computer-aided design (CAD) models. Statistical analysis revealed that the mean dimensional deviations were within the specified tolerance limits for most of the tested parts. This suggests that FDM technology is reliable in terms of achieving dimensional accuracy.

Cryptocurrencies like Bitcoin are one of today's financial system's most contentious and difficult technological advances. This study aims to evaluate the performance of three different Machine Learning (ML) algorithms, namely, the Support Vector Machines (SVM), the K Nearest Neighbor (KNN), and the Light Gradient Boosted Machine (LGBM), which seeks to accurately estimate the price movement of Bitcoin, Ethereum, and Litecoin. To test these algorithms, we used an existing continuous dataset extracted from Kaggle and coinmarketcap.com. We implemented models using the Knime platform. We used auto biner for volume and market capital. Sensitivity analysis was performed to match different parameters. The F and accuracy statistics were used for the evaluation of algorithm performances. Empirical findings reveal that the KNN has the highest forecasting performance for the overall dataset in our first investigation phase. On the other hand, the SVM has the highest for forecasting Bitcoin and the LGBM for Ethereum and Litecoin in the individual dataset in the second investigation phase.

The lifespan of business models is continuously shrinking, and consequently, businesses are facing the need to renovate their business models much more frequently than ever before. With a “stale” business model, a business becomes at risk of being unable to sustain itself; let alone reap the benefits new opportunities may bring. This paper presents qualitative exploratory research that aims to identify what constitutes business model transformability and explore the effect of software architecture in this regard. The research uses a grounded theory approach to construct a substantive theory, particularly a code system that IT -based organizations can reference. The study uses theoretical sampling and the constant comparative method to identify required participants and analyze interview data. The resulting code system identifies thirteen main categories, one of which is Transformative Software Architecture, and delves further into its subcategories.

Mobile application testing is an activity that aims to evaluate and improve the quality of the released application by identifying all the defects and issues. The testing results should be consistent and also unbiased, and this comes with a set of challenges and barriers that could appear in different testing levels. In this situation, quality engineers might need to make a trade-off between the test strategy and test efficiency. This paper presents the results of a study that mainly focused on investigating the challenges of testing mobile applications that could affect the testing process in small and medium-sized enterprises in Jordan. This was achieved by conducting a questionnaire distributed to employees and managers in a number of Jordanian companies. The results show that the variety of mobile devices is the most common challenge for many firms. However, most of the firms agreed that battery life or consumption is not affecting the testing of mobile devices.

Different energy sources are typically incorporated into coordinated MGS (Micro Grid Systems) using energy management systems. It is challenging to integrate acceptable energy management models in MGS mainly due to the unpredictable nature, availability estimations and complexities in regulating RES (Renewable Energy Sources). Energy policies are encouraging incorporation of RES while reducing the usage of fossil-based fuels resulting in the need to optimize RES.This study's major goal is to lower running costs of grid-connected MGSs while predicting PV (photovoltaic) based electricity and load demands in near future. In order to enhance the performance of micro-grids, this work focuses on creating a technique for integrating optimized ANN (artificial neutral networks) into an EMS (Energy Management System). The schema called EMS-HANN (Energy Management System - Hybrid ANN) is proposed in this work and it includes forecasts, planning, data gathering, and HMI (human-machine interfaces) components. Day-ahead PV power and load demand estimates are combined with a 3-level SWT (stationary wavelet transforms) as part of the forecasting module's enhanced hybrid forecasting technique and GWO-HANN (grey wolf optimization-based Hybrid Artificial Neural Network). The scheduling module employs AEHO (Adaptive Elephant Herding Optimisation)-based scheduling to deliver the optimal power flow for grid-connected MGS. Subsequently, DAQ and HMI modules monitor, analyse, and change forecast and schedule input variables. The proposed model for applications of MGS is implemented along with current algorithms in MATLAB/Simulink platform where outcomes demonstrate better performances of the suggested model as compared to comparable efforts.

Identity management (IdM) is used in every facet of our electronic society. The need for IdM and the problems these systems face grow as our electronic identities grow and become more complex. When IdMS is concerned with identifying and controlling the individual and access controls in the system, IdMS faces a new level of complexity as the number of users increases, making these systems vulnerable to various threats and attacks. However, while the concepts of attacker and target are well established in the field of information security, when it comes to privacy, these two concepts can be very limited. Personal information can be used for various purposes, and it is not always the scenario that the privacy threat comes from what is considered an attacker from the beginning. Here comes the Cloud and Blockchain 's role in providing more secure and scalable IdMS. This study aims to cover existing solutions by describing their level of security through the risk assessment process to provide a concise picture of the differences.

Intrusion detection is one of the important fields that can detect abnormal behavior on the network. Intrusion detection systems are expected to grow in the market, and the demand for these systems will increase soon. To find the anomalous behavior on the network, building models using data mining classifiers such as Random Forest (RF), K-Nearest Neighborhood (KNN), and Naïve Bayes (NB) is used. The performance of the classifiers was tested on three different data sets (KDDCUP-99, UNSW-NB15, and NSL-KDD). The results proved that Random Forest is the most reliable and adaptable algorithm across all three datasets. Its ensemble learning capabilities, suitability for high-dimensional data, and resistance to overfitting make it a valuable choice for intrusion detection This research is limited in some areas. First, the number of data sets used in this research is limited to three; future studies can include more data sets to get better comparative results. The second limitation is that the technique used in this paper is the classification algorithms only. The researchers suggest using more data mining techniques and comparing the results. Neural Networks is one of the algorithms that can be used in this field. The researchers suggested that future studies focus more on the in-depth analysis of the intricacies of specific datasets, focusing on factors that impact algorithm performance, including data quality and complexity, which can provide insights into fine-tuning algorithms for better results.

— In application development lifecycle, specifically in test-driven development, refactoring plays a crucial role in sustaining ease. However, in-spite of bringing ease, refactoring does not ensure the desired behaviour of code after it is applied. Because refactoring tends to worsen the alignments between source code and its corresponding units. One significant solution to the aforementioned issue is the technique called unit testing. As unit testing enable the developers to confidently apply refactoring while avoiding undesired code behaviour. Unit testing provides effective preventive measures for avoiding bugs by providing immediate feedback, thus assisting to mitigate the fear of change. In this work, we present a tool called GreenRefPlus which efficiently enables the developers to maintain the veracity of code after the process of refactoring is applied. The proposed tool provides automatic recovery for the unit tests after the code is refactored. In this work, we consider Java as our target programming language and we focus on five various types of refactoring, which include Rename Method, Extract Method, Move Method, Parameter Addition and Parameter Removal. Our experiments indicate that the proposed tool GreenRefPlus enables us to consistently refactor the code and apply unit tests. The results presented in our work reveal that the proposed tool assists developers in saving approximately 43% of the total time required to manually recover from broken unit tests.