Papers by Ibrahim A Atoum
A Bibliometric Review of Leadership Literature in Library and Information Science Profession, 1959–2022
Sage Open
This bibliometric study investigates the publishing trends and patterns along with top authors, c... more This bibliometric study investigates the publishing trends and patterns along with top authors, countries, organizations, nature of collaboration, and sub-areas of library leadership literature published from 1959 to 2022. The Scopus database was used for data extraction, and 500 relevant records were selected. The data were analyzed using Microsoft Access, Microsoft Excel, VOSviewer, Biblioshiny, and CiteSpace software. The results highlighted that the United States of America was a global trendsetter in library leadership research, being the top contributing country (313, 62.6% publications). They also identified the top productive author (Martin, J.), top-cited author (Ole Pors, N), top organization (University of Punjab, Pakistan), most preferable sources (Journal of Library Administration) and top-cited article (“Supporting Digital Scholarship in Research Libraries: Scalability and Sustainability” by Vinopal J). The highest research productivity was recorded in 2019, with 42 pu...
Article, 2025
This article examines scaling graph partitioning techniques through traditional and Machine Learn... more This article examines scaling graph partitioning techniques through traditional and Machine Learning (ML) approaches while discussing challenges and solutions. Effective partitioning of large Information Retrieval (IR) datasets requires examining critical factors, including 𝑘 selection choices alongside eigenvector selection and initial strategies while managing data uncertainty. The research strongly emphasizes integrating ML to allow systems to dynamically adapt and improve indexing, query processing, and clustering within large document collections and knowledge graphs. The article examines multiple methods based on their performance with large graphs, their community detection capabilities, parallelization convenience, and the flexibility derived from ML. Through Graph Neural Networks (GNNs) and Reinforcement Learning (RL), ML optimizes partitions by learning from evolving relationships and retrieving performance feedback. The research addresses conventional issues, including computational complexity and workload prediction, while examining ML limitations, which depend on labeled data and face interpretability concerns. The analysis covers several mitigation strategies that boost scalability, adaptive learning systems, and online learning approaches. The examination highlights the essential function of Graph Partitioning (GP) for IR system improvement and the growing influence of ML in this area. The discussion examines applications like social network analysis and fraud detection while exploring the potential advancements in dynamic GP for IR and the expected expansion of ML-based solutions. Through the discussions, it becomes clear that hybrid techniques combining ML methods with traditional approaches lead to better partitioning performance, which creates more resilient and scalable IR systems.
International Journal of Advanced and Applied Sciences, 2025
The presence of missing data in machine learning (ML) datasets remains a major challenge in build... more The presence of missing data in machine learning (ML) datasets remains a major challenge in building reliable models. This study explores various strategies to handle missing data and provides a framework to evaluate their effectiveness. The research focuses on commonly used techniques such as zero-filling, deletion, and imputation methods, including mean, median, mode, regression, k-nearest neighbors (KNN), and flagging. To assess these methods, a detailed evaluation framework is proposed, considering factors such as data completeness, model performance, stability, bias, variance, robustness to new data, computational efficiency, and domain-specific needs. This comprehensive approach allows for a thorough comparison of methods, helping to identify the most suitable technique for specific datasets and tasks. The findings highlight the importance of considering the unique features of the dataset and the goals of the analysis when choosing a method. While basic techniques like deletion and zero-filling may be effective in some cases, advanced imputation methods often preserve data quality and improve model accuracy. By applying the proposed evaluation criteria, researchers and practitioners can make better decisions on handling missing data, leading to more accurate, reliable, and adaptable ML models.
International Journal of Advanced Computer Science and Applications, 2025
Artificial intelligence (AI) possesses the capacity to transform numerous facets of our existence... more Artificial intelligence (AI) possesses the capacity to transform numerous facets of our existence; however, it concomitantly engenders considerable risks associated with bias and discrimination. This article explores emerging technologies like Explainable AI (XAI), Fairness Metrics (FMs), and Adversarial Learning (AL) for bias mitigation while emphasizing the critical role of transparency, accountability, and continuous monitoring and evaluation in AI governance. The Holistic AI Governance Framework (HAGF) is introduced, featuring a comprehensive, five-layered structure that integrates top-down and bottom-up strategies. HAGF prioritizes foundational principles and resource allocation, outlining five lifecycle-specific phases. Unlike the OECD AI Principles, which offer a general ethical framework lacking holistic perspective and resource allocation guidance, and the Berkman Klein Center's Model, which provides a broad framework but omits resource allocation and detailed implementation, HAGF offers actionable mechanisms. Tailored Key Performance Indicators (KPIs) are proposed for each HAGF layer, enabling ongoing refinement and adaptation to the evolving AI landscape. While acknowledging the need for enhancements in data governance and enforcement, the embedded KPIs ensure accountability and transparency, positioning HAGF as a pivotal framework for navigating the complexities of ethical AI.
Comprehensive Rubrics for Evaluating Computer-Related Capstones
Intrusion Detection System Mechanisms in Cloud Computing: Techniques and Opportunities
A collaborative prediction approach to defend against amplified reflection and exploitation attacks
Electronic research archive, Dec 31, 2022
Article, 2023
This bibliometric study investigates the publishing trends and patterns along with top authors, c... more This bibliometric study investigates the publishing trends and patterns along with top authors, countries, organizations, nature of collaboration, and sub-areas of library leadership literature published from 1959 to 2022. The Scopus database was used for data extraction, and 500 relevant records were selected. The data were analyzed using Microsoft Access, Microsoft Excel, VOSviewer, Biblioshiny, and CiteSpace software. The results highlighted that the United States of America was a global trendsetter in library leadership research, being the top contributing country (313, 62.6% publications). They also identified the top productive author (Martin, J.), top-cited author (Ole Pors, N), top organization (University of Punjab, Pakistan), most preferable sources (Journal of Library Administration) and top-cited article (''Supporting Digital Scholarship in Research Libraries: Scalability and Sustainability'' by Vinopal J). The highest research productivity was recorded in 2019, with 42 publications (8.4%), followed by 37 (7.4%) publications in 2018 and 2021. Furthermore, 270 publications (54%) on library leadership were published during the last decade (2011-2020). This study informed that most of the published literature on library leadership was general, following a solo authorship trend (314), with less collaborative research (n = 186) and a significant number (n = 148) of non-cited documents. The critical areas of future research identified in this study, including transformational, ethical, participative, and humanistic leadership, need to be investigated. The study suggests that emerging digital and virtual leadership areas should also be examined along with the areas with limited literature. To the best of our knowledge, this is the first comprehensive bibliometric study to present a holistic picture of the library leadership literature.
Sustainability
In recent years, mobile learning has emerged as a promising educational paradigm, revolutionizing... more In recent years, mobile learning has emerged as a promising educational paradigm, revolutionizing the landscape of higher education. As the world confronts escalating environmental challenges and calls for sustainable solutions, it becomes essential to explore the potential of mobile learning to contribute to a more sustainable future. This review encompasses a comprehensive analysis of the existing literature, focusing on empirical studies, theoretical frameworks, and case studies conducted between 2002 and 2021. A substantial corpus of 981 articles were selected for in-depth examination by employing rigorous inclusion and exclusion criteria. The findings reveal that mobile learning has witnessed significant growth and diversification within higher education, with pervasive adoption across various disciplines and student populations. The identified studies present many innovative mobile learning strategies, encompassing mobile applications, gamified learning platforms, augmented re...
This article is an open access article distributed under the terms and conditions of the Creative... more This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY
IEEE Access
Ongoing researches on multiple view data are showing competitive behavior in the machine learning... more Ongoing researches on multiple view data are showing competitive behavior in the machine learning field. Multi-view clustering has gained widespread acceptance for managing multi-view data and improves clustering efficiency. Large dimensionality in data from various views has recently drawn a lot of interest from researchers. How to efficiently learns the appropriate lower dimensional subspace which can manage the valuable information from the diverse views is challenging and considerable issue. To concentrate on the mentioned issue, we asserted a novel clustering approach for multiple view data through low-rank representation. We consider the importance of each view by assigning the weight control factor. We combine consensus representation with the degree of disagreement among lower rank matrices. The single objective function unifies all factors. Furthermore, we give the efficient solution to update the variable and to optimized the objective function through the Augmented Lagrange's Multiplier strategy. Real-world datasets are utilized in this study to exemplify the efficiency of the introduced technique, and it is contemplated to preceding algorithms to demonstrate its superiority. INDEX TERMS Low-rank representation, spectral clustering, weighted multi-view data, sparse constraints.
International Journal of Advanced Computer Science and Applications, 2023
A convolutional neural network (CNN) is a subset of machine learning as well as one of the differ... more A convolutional neural network (CNN) is a subset of machine learning as well as one of the different types of artificial neural networks that are used for different applications and data types. Activation functions (AFs) are used in this type of network to determine whether or not its neurons are activated. One nonlinear AF named as Rectified Linear Units (ReLU) which involves a simple mathematical operations and it gives better performance. It avoids rectifying vanishing gradient problem that inherents older AFs like tanh and sigmoid. Additionally, it has less computational cost. Despite these advantages, it suffers from a problem called Dying problem. Several modifications have been appeared to address this problem, for example; Leaky ReLU (LReLU). The main concept of our algorithm is to improve the current LReLU activation functions in mitigating the dying problem on deep learning by using the readjustment of values (changing and decreasing value) of the loss function or cost function while number of epochs are increased. The model was trained on the MNIST dataset with 20 epochs and achieved lowest misclassification rate by 1.2%. While optimizing our proposed methods, we received comparatively better results in terms of simplicity, low computational cost, and with no hyperparameters.
IEEE Access
Clustering of multi-view data has got broad consideration of the researchers. Multi-view data is ... more Clustering of multi-view data has got broad consideration of the researchers. Multi-view data is composed through different domain which shows the consistent and complementary behavior. The existing studies did not draw attention of over-fitting and sparsity among the diverse view, which is the considerable issue for getting the unique consensus knowledge from these complementary data. Herein article, a multi-view clustering approach is recommended to provide the consensus solution from the multiview data. To accomplish this task, we exploit non-negative matrix factorized method to generate a cost function. Further, manifold learning model is used to build the graph through the nearest neighbor strategy, which is effective to save the geometrical design for data and feature matrix. Furthermore, the over-fitting problem, sparsity is handled through adaption of frobenious norm, and L 1-norm on basis and coefficient matrices. The whole formulation is done through the mathematical function, which is optimized through the iterative updating strategy to get the optimal solution. The computational experiment is carried on the available datasets to exhibits that the proposed strategy beats the current methodologies in terms of clustering execution. INDEX TERMS Non-negative matrix factorization, multi-view data, manifold structure, nearest neighbor.
International Journal of ADVANCED AND APPLIED SCIENCES, 2021
Big data has been used by different companies to deliver simple products and provide enhanced cus... more Big data has been used by different companies to deliver simple products and provide enhanced customer insights through predictive technology such as artificial intelligence. Big data is a field that mainly deals with the extraction and systemic analysis of large data sets to help businesses discover trends. Today, many companies use Big Data to facilitate growth in different functional areas as well as expand their ability to handle large customer databases. Big data has grown the demand for information management experts such that many software companies are increasingly investing in firms that specialize in data management and analytics. Nevertheless, the issue of data protection or privacy is a threat to big data management. This article presents some of the major concerns surrounding the application and use of Big Data about challenges of security and privacy of data stored on technological devices. The paper also discusses some of the current studies being undertaken aimed at ...
International Journal of Advanced Trends in Computer Science and Engineering, 2019
Big data denotes large volume datasets that grows exponentially over time and cannot be processed... more Big data denotes large volume datasets that grows exponentially over time and cannot be processed or stored using traditional data management tools. There is a huge amount of new data that is stored daily in all areas of our life. This data needs to be collected and analyzed effectively to streamline the decision-making process. Big data analytics (BDA) are techniques that provide a way to analyze this huge quantity of data with the purpose of drawing conclusions about them by driving the business outcomes and real time decisions. With a wide range of data available in the healthcare sector including financial and clinical data, research and development, management and operational data and critical care units, big data in healthcare can generate meaningful insights to improve overall operational efficiency in the industry. There are various benefits for big data analytics in the health-care industry which encompasses advanced patient care; improved operational efficiency; evaluation of practitioner performance; reduced patient cost and researching cure for diseases. The main objective of this study is to outline the main challenges and opportunities of applying big data in health care and how it can help in transforming the healthcare industry towards the valuebased care.
Regular, 2020
Corona virus is an infectious disease that causes respiratory infections, producing fever, diffic... more Corona virus is an infectious disease that causes respiratory infections, producing fever, difficulty breathing, and dry cough, which may be more dangerous for people who suffer from chronic diseases. Wearable Devices (WD) have been recently adopted in a wide range of areas to show distinct potentials in the healthcare field. The different types of WDs can be one of the important steps towards improving patient care while reducing the cost based on artificial intelligence (AI) applications. These applications work on big data that arise from WDs despite the existence of various challenges such as user acceptance, security, ethics issues, big data, AI and interoperability. The purpose of this study is to drawthe possibility of utilizing the big data arising from integrating WDs with the electronic Medical records (EMR) through applying AI technologies which in turn will lead to the possibility of employing all of these technologies in predicting COVID-19 infection
International Journal of Advanced Computer Science and Applications, 2018
There are many features which appear on the surface of the sun. One of these features that appear... more There are many features which appear on the surface of the sun. One of these features that appear clearly are the dark threads in the Hydrogen alpha (Hα) spectrum solar images. These 'filaments' are found to have a definite correlation with Coronal Mass Ejections (CMEs). A CME is a large release of plasma into space. It can be hazardous to astronauts and the spacecraft if it is being ejected towards the Earth. Knowing the exact attributes of solar filaments may open the way towards predicting the occurrence of CMEs. In this paper, an efficient and fully automated algorithm for solar filament segmentation without compromising accuracy is proposed. The algorithm uses some statistical measures to design the thresholding equations and it is written in the C++ programming language. The square root of the range as a measure of variability of image intensity values is used to determine the size of the sliding window at run time. There are many previous studies in this area, but no single segmentation method that could precisely claim to be fully automatic exists. Samples were taken from several representative regions in low-contrast and high-contrast solar images to verify the viability and efficacy of the method.
Journal of Cancer Treatment and Research, 2017
Nowadays, many researchers try to find out a system that enables to detect and expect diseases ea... more Nowadays, many researchers try to find out a system that enables to detect and expect diseases early so as to find the appropriate precaution or medical treatment of it. One of the leading causes of death worldwide is Cancer. Most of the deaths from this disease are due to late prediction and detection. According to the American Cancer Society (ACS); lung cancer is the second most common cancer; it accounts for about 13% of all new cancers. It is expected to have a 221, 200 new cases of lung cancer in 2015 with 158, 040 estimated deaths from lung Cancer [1]. The main objective of this study is to reach the highest accuracy and speed of its predecessors and this is what has been obtained.
Journal of Signal and Information Processing, 2013
Radio astronomy radio telescope plays the role of a linear operator, affecting the function that ... more Radio astronomy radio telescope plays the role of a linear operator, affecting the function that describes the object of research, formation of image of a monitored object. This paper presents methods for reconstruction and correction of solar radio images using the algorithm of rejections, the updated Weiner-filter, and the method CLEAN designed by Hëgbomom (Pseudonym, 2009) for point sources. It is the process of numerical convolution in signal handling, an algorithm for separating weak-contrast formations on the solar which represents most points of the actual limb by using the ellipse equation. Consequently, the filling algorithm is applied by moving from the center to the ellipse points and filling each point by solar image data. Finally, a linear limb-darkening expression is used to remove the limb darkening. Different examples of the intermediate and final results are presented in addition to the developed algorithm.
Sustainability
The COVID-19 pandemic has created massive issues around the world. To ensure that education conti... more The COVID-19 pandemic has created massive issues around the world. To ensure that education continued during the crisis, educational institutions had to implement a variety of initiatives. This paper aims to examine the growth and country collaboration on social media (SM) research during the COVID-19 pandemic through a systematic review and investigate the impact of this body of work by citation and network analyses. The number of articles, keywords, and clusters of worldwide academic scholars working in the area was mapped using R studio and the VOS viewer tool. According to the study results, 519 articles have been retrieved from the Web of Science in the field of domain. The USA has produced the most publications, and Chen IH and Lin CY were the most prolific authors. Furthermore, the most studies on SM use in higher education were released in the International Journal of Environmental Research and Public Health. This research will help academic researchers, organizations, and p...
Uploads
Papers by Ibrahim A Atoum