MyMedR

Displaying all 6 publications

Abstract:

Sort:

Fulltext An Al-Biruni Earth Radius Optimization-Based Deep Convolutional Neural Network for Classifying Monkeypox Disease

Khafaga DS, Ibrahim A, El-Kenawy EM, Abdelhamid AA, Karim FK, Mirjalili S, et al.

Diagnostics (Basel), 2022 Nov 21;12(11).
PMID: 36428952 DOI: 10.3390/diagnostics12112892

Human skin diseases have become increasingly prevalent in recent decades, with millions of individuals in developed countries experiencing monkeypox. Such conditions often carry less obvious but no less devastating risks, including increased vulnerability to monkeypox, cancer, and low self-esteem. Due to the low visual resolution of monkeypox disease images, medical specialists with high-level tools are typically required for a proper diagnosis. The manual diagnosis of monkeypox disease is subjective, time-consuming, and labor-intensive. Therefore, it is necessary to create a computer-aided approach for the automated diagnosis of monkeypox disease. Most research articles on monkeypox disease relied on convolutional neural networks (CNNs) and using classical loss functions, allowing them to pick up discriminative elements in monkeypox images. To enhance this, a novel framework using Al-Biruni Earth radius (BER) optimization-based stochastic fractal search (BERSFS) is proposed to fine-tune the deep CNN layers for classifying monkeypox disease from images. As a first step in the proposed approach, we use deep CNN-based models to learn the embedding of input images in Euclidean space. In the second step, we use an optimized classification model based on the triplet loss function to calculate the distance between pairs of images in Euclidean space and learn features that may be used to distinguish between different cases, including monkeypox cases. The proposed approach uses images of human skin diseases obtained from an African hospital. The experimental results of the study demonstrate the proposed framework's efficacy, as it outperforms numerous examples of prior research on skin disease problems. On the other hand, statistical experiments with Wilcoxon and analysis of variance (ANOVA) tests are conducted to evaluate the proposed approach in terms of effectiveness and stability. The recorded results confirm the superiority of the proposed method when compared with other optimization algorithms and machine learning models.
Fulltext Optimizing HCV Disease Prediction in Egypt: The hyOPTGB Framework

Elshewey AM, Shams MY, Tawfeek SM, Alharbi AH, Ibrahim A, Abdelhamid AA, et al.

Diagnostics (Basel), 2023 Nov 13;13(22).
PMID: 37998575 DOI: 10.3390/diagnostics13223439

The paper focuses on the hepatitis C virus (HCV) infection in Egypt, which has one of the highest rates of HCV in the world. The high prevalence is linked to several factors, including the use of injection drugs, poor sterilization practices in medical facilities, and low public awareness. This paper introduces a hyOPTGB model, which employs an optimized gradient boosting (GB) classifier to predict HCV disease in Egypt. The model's accuracy is enhanced by optimizing hyperparameters with the OPTUNA framework. Min-Max normalization is used as a preprocessing step for scaling the dataset values and using the forward selection (FS) wrapped method to identify essential features. The dataset used in the study contains 1385 instances and 29 features and is available at the UCI machine learning repository. The authors compare the performance of five machine learning models, including decision tree (DT), support vector machine (SVM), dummy classifier (DC), ridge classifier (RC), and bagging classifier (BC), with the hyOPTGB model. The system's efficacy is assessed using various metrics, including accuracy, recall, precision, and F1-score. The hyOPTGB model outperformed the other machine learning models, achieving a 95.3% accuracy rate. The authors also compared the hyOPTGB model against other models proposed by authors who used the same dataset.
Fulltext Distributed controller clustering in software defined networks

Abdelaziz A, Fong AT, Gani A, Garba U, Khan S, Akhunzada A, et al.

PLoS One, 2017;12(4):e0174715.
PMID: 28384312 DOI: 10.1371/journal.pone.0174715

Software Defined Networking (SDN) is an emerging promising paradigm for network management because of its centralized network intelligence. However, the centralized control architecture of the software-defined networks (SDNs) brings novel challenges of reliability, scalability, fault tolerance and interoperability. In this paper, we proposed a novel clustered distributed controller architecture in the real setting of SDNs. The distributed cluster implementation comprises of multiple popular SDN controllers. The proposed mechanism is evaluated using a real world network topology running on top of an emulated SDN environment. The result shows that the proposed distributed controller clustering mechanism is able to significantly reduce the average latency from 8.1% to 1.6%, the packet loss from 5.22% to 4.15%, compared to distributed controller without clustering running on HP Virtual Application Network (VAN) SDN and Open Network Operating System (ONOS) controllers respectively. Moreover, proposed method also shows reasonable CPU utilization results. Furthermore, the proposed mechanism makes possible to handle unexpected load fluctuations while maintaining a continuous network operation, even when there is a controller failure. The paper is a potential contribution stepping towards addressing the issues of reliability, scalability, fault tolerance, and inter-operability.
Fulltext Prioritising Organisational Factors Impacting Cloud ERP Adoption and the Critical Issues Related to Security, Usability, and Vendors: A Systematic Literature Review

Salih S, Hamdan M, Abdelmaboud A, Abdelaziz A, Abdelsalam S, Althobaiti MM, et al.

Sensors (Basel), 2021 Dec 15;21(24).
PMID: 34960483 DOI: 10.3390/s21248391

Cloud ERP is a type of enterprise resource planning (ERP) system that runs on the vendor's cloud platform instead of an on-premises network, enabling companies to connect through the Internet. The goal of this study was to rank and prioritise the factors driving cloud ERP adoption by organisations and to identify the critical issues in terms of security, usability, and vendors that impact adoption of cloud ERP systems. The assessment of critical success factors (CSFs) in on-premises ERP adoption and implementation has been well documented; however, no previous research has been carried out on CSFs in cloud ERP adoption. Therefore, the contribution of this research is to provide research and practice with the identification and analysis of 16 CSFs through a systematic literature review, where 73 publications on cloud ERP adoption were assessed from a range of different conferences and journals, using inclusion and exclusion criteria. Drawing from the literature, we found security, usability, and vendors were the top three most widely cited critical issues for the adoption of cloud-based ERP; hence, the second contribution of this study was an integrative model constructed with 12 drivers based on the security, usability, and vendor characteristics that may have greater influence as the top critical issues in the adoption of cloud ERP systems. We also identified critical gaps in current research, such as the inconclusiveness of findings related to security critical issues, usability critical issues, and vendor critical issues, by highlighting the most important drivers influencing those issues in cloud ERP adoption and the lack of discussion on the nature of the criticality of those CSFs. This research will aid in the development of new strategies or the revision of existing strategies and polices aimed at effectively integrating cloud ERP into cloud computing infrastructure. It will also allow cloud ERP suppliers to determine organisations' and business owners' expectations and implement appropriate tactics. A better understanding of the CSFs will narrow the field of failure and assist practitioners and managers in increasing their chances of success.
A comprehensive review on processing, characteristics, and applications of cellulose nanofibrils/graphene hybrid-based nanocomposites: Toward a synergy between two-star nanomaterials

Trache D, Tarchoun AF, Abdelaziz A, Bessa W, Thakur S, Hussin MH, et al.

Int J Biol Macromol, 2024 Apr 18;268(Pt 2):131633.
PMID: 38641279 DOI: 10.1016/j.ijbiomac.2024.131633

Nanostructured materials are fascinating since they are promising for intensely enhancing materials' performance, and they can offer multifunctional features. Creating such high-performance nanocomposites via effective and mild approaches is an inevitable requirement for sustainable materials engineering. Nanocomposites, which combine two-star nanomaterials, namely, cellulose nanofibrils (CNFs) and graphene derivatives (GNMs), have recently revealed interesting physicochemical properties and excellent performance. Despite numerous studies on the production and application of such systems, there is still a lack of concise information on their practical uses. In this review, recent progress in the production, modification, properties, and emerging uses of CNFs/GNMs hybrid-based nanocomposites in various fields such as flexible energy harvesting and storage, sensors, adsorbents, packaging, and thermal management, among others, are comprehensively examined and described based on recent investigations. Nevertheless, numerous challenges and gaps need to be addressed to successfully introduce such nanomaterials in large-scale industrial applications. This review will certainly help readers understand the design approaches and potential applications of CNFs/GNMs hybrid-based nanocomposites for which new research directions in this emerging topic are discussed.
Fulltext Middle East and North Africa Registry to Characterize Rate of RAS Testing Status in Newly Diagnosed Patients with Metastatic Colorectal Cancer

Oukkal M, Bouzid K, Bounedjar A, Alnajar A, Taleb FA, Alsharm A, et al.

Turk J Gastroenterol, 2023 Feb;34(2):118-127.
PMID: 36445057 DOI: 10.5152/tjg.2022.22106

BACKGROUND: Rat sarcoma virus mutational status guides first-line treatment in metastatic colorectal cancer. This study was a multi center, multi-country ambispective, observational study in the Middle East and North Africa assessing regional rat sarcoma virus testing practices in newly diagnosed patients.
METHODS: The retrospective arm (2011-2014) included adults with metastatic colorectal cancer who had initiated first-line therapy with ≥1 post-baseline visit and survival data. The prospective arm (2014-2019) enrolled newly diagnosed patients with histologically proven metastatic colorectal cancer with ≥1 measurable lesion per Response Evaluation Criteria in Solid Tumors, and tissue availability for biomarker analysis. Data look-back and follow-up were 2 years; the rate of RAS mutation was evaluated.
RESULTS: RAS testing was ordered for patients in retrospective (326/417) and prospective (407/500) studies. In the former, testing was typically prescribed after first-line treatment initiation, significantly more in patients with stage IV disease (P < .005), resulting in the addition of targeted therapy (41.8% anti-epidermal growth factor receptor, 30.2% anti-vascular endothelial growth factor) in wild-type metastatic colorectal cancer, and significantly impacted the treatment of left-sided tumors (P = .037). In the latter, 58.4% were RAS wild-type; 41.6% were RAS mutant. Non-prescription of RAS testing was attributed to test unavailability, financial, or medical rea sons; predictors of testing prescription were older age, primary tumor in ascending colon, and high tumor grade. RAS status knowledge resulted in the addition of anti-vascular endothelial growth factor (20.4%) or anti-epidermal growth factor receptor therapy (21.2%).
CONCLUSION: Before 2014, RAS testing in patients with colorectal cancer in the Middle East and North Africa was often performed after first-line treatment. Testing is more routine in newly diagnosed patients, potentially shifting early treatment patterns.