جامعة المعرفة
المصدر المعتمد للمعلومات البحثية والمخرجات هو قاعدة بيانات سكوبس (Elsevier Scopus) مع تدقيق بيانات الباحثين من عمادة البحث العلمي.

Research outputs

المخرجات البحثية

مقالات ومراجعات وأوراق مؤتمرات وفصول كتب، مفهرسة برقم DOI ومربوطة بباحثي الجامعة.

مقالوصول مفتوح20251استشهاد· Semantic Scholar

MultiEpilepsyNet: An EEG and MRI data based multimodal seizure detection model using hybrid deep learning model

Brain Research Bulletin · مجلد 233 · 111645-111645

Epilepsy is a critical neurological disorder that requires accurate and privacy-preserving diagnostic solutions to enable early detection and effective management. However, existing approaches face key challenges, including reliance on centralized data, poor generalizability across modalities, suboptimal feature extraction, and vulnerability to noise. To address these issues, we propose MultiEpilepsyNet, a novel multimodal seizure detection framework that integrates federated learning with hybrid deep learning models. At its core, the system introduces SeizureFed-Net, a federated architecture that enables collaborative learning from EEG and MRI data while safeguarding patient privacy. For detection, we design SeizureShieldNet, a hybrid model that fuses the temporal learning capabilities of BBIDNet (Boosted BiLSTM Intrusion Detector Network) with the adaptive decision-making of FD-TMS (Fuzzy-DQN Threat Mitigation System) under uncertainty. To further enhance model efficiency, a Jackal-Wolf Hybrid Optimizer (JWHO)-a novel combination of Golden Jackal Optimization and Grey Wolf Optimizer-is employed for optimal feature subset selection. On the imaging side, MRI preprocessing is improved through EpiSkullNet+ +, a modified 3D UNet+ + architecture tailored for precise brain segmentation. Extensive experiments on two benchmark datasets demonstrate the superiority of our approach, achieving 99.36 % accuracy on the CHB-MIT EEG dataset and 99.38 % accuracy on an epilepsy MRI dataset. Beyond accuracy, MultiEpilepsyNet demonstrates improved robustness to missing modalities, reduced training overhead via federated aggregation, and enhanced privacy preservation compared to centralized deep learning models, thereby addressing critical barriers in practical clinical deployment. These outcomes highlight the effectiveness, scalability, and real-world clinical potential of the proposed framework for epilepsy diagnosis and management.

epilepsyseizure detectionmultimodal fusionEEG
مقالوصول مفتوح20251استشهاد· Semantic Scholar

Development and Validation of a Bilingual Reusable Learning Object to Enhance Mental Health Literacy on Neuroendocrine and Mental Health Disorders Among Youth in Saudi Arabia

Psychology Research and Behavior Management · مجلد Volume 18 · 2311-2322

Purpose: Youth in Saudi Arabia increasingly face mental health challenges such as anxiety, depression, and stress-related disorders. These issues are compounded by stigma, academic pressure, and limited access to mental health education. Mental health literacy (MHL) remains low, delaying recognition of symptoms and help-seeking. This study aimed to develop and validate a bilingual Reusable Learning Object (RLO) to enhance youth's understanding of mental health, with a focus on the neuroendocrine system's role in mood regulation. Methodology: The RLO was developed in English using the open-source Xerte software, guided by the ASPIRE framework (Aims, Storyboarding, Production, Implementation, Release, Evaluation). The 11-page interactive module covers key topics including the hypothalamic-pituitary-adrenal (HPA) axis, stress response, symptoms of common mental disorders, misconceptions, and self-help strategies. Multimedia and interactive elements such as animations, flash cards, hotspot images were used to enhance engagement. During RLO development, a panel of experts conducted iterative reviews to ensure the content accuracy and instructional quality. A 2-page of built-in Mental Health literacy instrument using a validated questionnaire was used for evaluation.The module was forward- and back-translated to produce an Arabic version, followed by content validation from six bilingual subject matter experts in Mental Health topics. Results: Expert reviewers were able to capture the RLO's clarity, educational value, and suitability for youth. Strengths included interactivity, visual appeal, and a manageable completion time (10-15 minutes). Recommendations included reducing cognitive load, improving conceptual flow, and enhancing feedback on quiz items. Minor technical and linguistic issues were also addressed. For content validation of the Mental Health literacy instrument, a score of S-VA/Ave was 0.761, indicating that most items were considered relevant by most experts. The low UA of 0.188 was addressed by modifying the RLO content and to preserve the English validated questionnaire integrity. Conclusion: This study presents a rigorously developed and validated bilingual RLO aimed at improving MHL among youth in Saudi Arabia.

mental health literacyreusable learning objectsyouth mental healthneuroendocrine system
مقالوصول مفتوح20251استشهاد· Semantic Scholar

Exploring phytochemicals as potential pharmacological inhibitors for NS1 protein of Kyasanur forest disease virus using virtual screening, molecular docking, and molecular simulation approach

PeerJ · مجلد 13 · e19954-e19954

Background: Kyasanur forest disease virus (KFDV) remains a significant public health challenge due to the limitations of existing vaccines, creating a critical need for effective antiviral treatments. KFDV is a tick-borne virus responsible for 400-500 new cases annually, with a mortality rate of 3-5%. The nonstructural protein 1 (NS1), which plays crucial roles in host cell interactions, immune evasion, and viral replication, represents a promising target for antiviral drug development. Objective: This study aims to identify potential antiviral compounds that inhibit the activity of KFDV NS1 protein using a computational pharmacological drug design approach. The objectives include determining the 3D structure of the NS1 protein through homology modeling, conducting virtual screening of phytochemicals to identify potential inhibitors, and performing molecular dynamics simulations to assess the stability and binding free energies of the selected compounds. Methods: The 3D structure of KFDV NS1 protein was predicted using homology modeling and validated using Ramachandran plot analysis. Virtual screening of phytochemicals from the Indian Medicinal Plants, Phytochemistry And Therapeutics (IMPPAT) database was performed to identify potential NS1 inhibitors. The top 15 compounds with the highest binding affinities were selected and subjected to absorption, distribution, metabolism, excretion, and toxicity (ADMET) analysis. Molecular dynamics simulations were conducted in duplicates for 200 ns to evaluate the stability of the ligand-NS1 complexes, and an additional independent simulation with randomized initial velocities was performed to ensure statistical robustness. Binding free energies were calculated using the molecular mechanics-generalized born surface area (MM-GBSA) method to determine the binding strength of each compound. Results: The 3D structure of the KFDV NS1 protein was determined using I-Tasser-MTD, Robetta, and Swiss Model servers, and a minimized model of I-Tasser, achieving an ERRAT score of 94.37, was selected. Virtual screening of 11,530 phytochemicals from the IMPPAT database identified the top 115 compounds after three screening phases. Out of the 15 screened compounds, L2, L3, and L5 demonstrated notable binding affinities of -9.34, -9.12, and -9.08 kcal/mol, respectively, compared to the FDA-approved antiviral dasabuvir, which had a binding affinity of -8.0 kcal/mol. Molecular dynamics simulations confirmed the stability of compounds L2 (IMPHY010294), L3 (IMPHY001281), L5 (IMPHY011162), and dasabuvir, with free-energy binding values of -62.97 ± 4.0, -77.22 ± 4.71, -62.07 ± 2.88, and -87.68 ± 4.31 kcal/mol, respectively. Conclusion: findings.

Kyasanur forest disease virusNS1 proteinantiviral drug designphytochemicals
مقالوصول مفتوح20251استشهاد· Semantic Scholar

Comprehensive impacts of black elderberry ( Sambucus nigra L. ) extract on mitigating acute heat stress, augmenting antioxidant defenses, and enhancing broiler chicken health and meat quality

Journal of Applied Animal Research · مجلد 53 (1)

Poultry genotypes’ low heat tolerance affects birds’ health, which results in major economic losses and calls for an immediate, consumer-friendly dietary plan. This study assessed black elderberry extract (BE) on 120-Cobb chickens, 35-days old, to mitigate the adverse-effects of acute heat stress on clinical and pathological parameters, antioxidant status, and meat quality. Birds were divided into four-groups: NEG: maintained at thermoneutral temperature (24 ± 1°C); 2) BE: administered 0.15 g/L BE extract for 12-h while kept at 24 ± 1°C; HSBE: maintained at 38 ± 1°C for 6-h and treated with BE extract (0.15 g/L); HS: maintained at 38 ± 1°C for 6-h. BE supplementation under heat stress significantly mitigated these effects, reducing rectal temperature and droppings moisture (p < 0.05), lowering both macroscopic and histological lesion severity at 3 and 12 h (p < 0.05), and improving meat quality traits—lower cooking and thawing losses, enhanced water-holding capacity, and better tenderness – while also diminished muscle malondialdehyde concentration, and elevated levels of polyunsaturated fatty acids (PUFA) and omega-3 PUFA, particularly alpha-linolenic acid (p < 0.05). The results suggest that the use of BE extract in the water of broiler chickens during periods of heat stress is beneficial, and further research on heat stress-reducing efficacy of BE is needed.

Sambucus nigraheat stressbroiler chickensantioxidant status
مقالمفتوح (مستودع)20251استشهاد· Semantic Scholar

Enhancing Diagnostic Precision: A Distribution-Based Compressed Denoising Scheme using Transfer Learning for Noise Reduction in Medical Imaging

Current Medical Imaging Formerly Current Medical Imaging Reviews · مجلد 21 · e15734056391923-e15734056391923

INTRODUCTION: Accurate interpretation of medical images is vital for diagnosis and treatment planning. However, noise in medical imaging significantly hampers this process, leading to potential diagnostic errors. Traditional denoising techniques often require large datasets or compromise diagnostic details. METHOD: This study proposes a Distribution-based Compressed Denoising Scheme (DCDS) leveraging transfer learning to enhance diagnostic precision. The framework analyzes pixel distributions to distinguish normal and noisy pixels using incremental and decremental distribution verification. A chest CT scan dataset with Gaussian-like noise was used to train the model, employing correlation mapping between training and target images for effective variance estimation. RESULT: Experimental analysis showed that DCDS significantly improves noise reduction, variance detection, and diagnostic precision. The peak signal-tonoise ratio improved across all evaluated ranges (24-32 dB), with a noise reduction rate exceeding 82% in optimal conditions. DCDS reduced mean error and analysis time, enhancing overall system efficiency. Transfer learning allowed for effective pixel classification and noise prediction with fewer data and computational resources. DISCUSSION: Compared to existing denoising methods, DCDS offers better generalization through statistical modeling and knowledge-sharing between training and learning states. However, current validation is limited to CT imaging with Gaussian noise. Broader modality testing and integration of perceptual and clinical grading metrics are needed. CONCLUSION: The DCDS framework presents a promising, lightweight, adaptive, and accurate solution for medical image denoising. It holds potential for realtime diagnostic support, but further optimization and clinical validation are necessary to ensure generalizability across diverse imaging modalities and noise types.

medical image denoisingtransfer learningchest CTGaussian noise
مقالوصول مفتوح20251استشهاد· Semantic Scholar

Co-administration of Spirulina and L-carnitine preserves ovarian reserve in a rat model of premature ovarian insufficiency via SIRT1 regulation of oxidative stress, inflammation, and apoptosis

Scientific Reports · مجلد 15 (1) · 32527-32527

This study aimed to assess the possible consequences of spirulina (SP) and/or L-carnitine (L-car) on the prevention of primordial follicular reserve depletion and the preservation of ovarian follicular structure and function in a rat model of premature ovarian insufficiency (POI). Forty healthy adult female Sprague-Dawley albino rats were randomly assigned into five equal-sized groups (n = 8): normal control, DOX group (2.5 mg/kg i.p.), SP group (500 mg/kg intragastric), L-car group (250 mg/kg i.p.), and SP + L-car group in the same previous doses. In comparison to the DOX group, administration of either SP or L-car significantly increased serum E2 and AMH levels along with a significant decrease in the FSH and LH levels (p < 0.05). The oxidative stress was significantly reduced. Ovarian expressions of NF-κB, iNOS, FOXO1, P53, and caspase-3 decreased significantly, while SIRT1, STAR, CYP17A1, HSD17B3, Nrf2, and mtDNA increased significantly. Histology revealed histoarchitecture improvement as the mean % of atretic follicles and degenerated corpora lutea was significantly reduced (p < 0.05). The combined treatments synergistically improved the parameters studied more than either treatment alone. The molecular docking results revealed the ability of both n-hexadecanoic acid and L-carnitine to activate SIRT1 and subsequent antioxidant, anti-inflammatory, and anti-apoptotic pathways. This ovoprotective effect is suggested to be mediated through activation of different SIRT1-mediated protective signaling pathways that remodel ovarian redox status, inflammation, and apoptosis, which may strengthen the potential role of SP and L-car as a chemotherapy adjuvant, reducing the negative health effects of early menopause after cancer therapy.

SpirulinaL-carnitinepremature ovarian insufficiencyovarian reserve
مقالوصول مغلق20251استشهاد· Semantic Scholar

Optimized Deep Learning for Intrusion Detection in Federated IoT Environments

Journal of Circuits Systems and Computers · مجلد 35 (07)

Current developments on the Internet of Things (IoT) have completely changed the landscape of Consumer Electronics (CE), enabling next-generation gadgets to be highly intelligent, networked and capable of utilizing large models. In addition to improving data accessibility, this improved connectivity between sensors, actuators and appliances allows autonomous control inside CE networks. Although deep learning models are highly effective in analyzing large amounts of data, controlling the intricacy of deep learning-based intrusion detection in low-latency IoT networks continues to be a formidable task. This paper presents a deep learning-based intrusion detection technique inspired by federated learning (FL), specifically designed for SDN-enabled CE networks. The application of the approach involves stringent training and testing protocols. In order to improve performance and handle the very complicated training data, the Pearson correlation coefficient (PCC) approach of feature selection (FS) is used in this work. Based on the UNSW-NB15 attack detection dataset, the results show that this approach performs better than other current security solutions, making it a promising option for next-generation smart CE networks. Comprehensive experimental evaluations demonstrated the value of the suggested intrusion detection system (IDS), which demonstrated exceptional intrusion detection accuracy in every domain under investigation.

intrusion detectionfederated learningInternet of Things securitysmart home networks
مقالوصول مفتوح20251استشهاد· Semantic Scholar

Towards a Lightweight Arabic Sign Language Translation System

Sensors · مجلد 25 (17) · 5504-5504

There is a pressing need to build a sign-to-text translation system to simplify communication between deaf and non-deaf people. This study investigates the building of a high-performance, lightweight sign language translation system suitable for real-time applications. Two Saudi Sign Language datasets are used for evaluation. We also investigate the effects of the number of signers and number of repetitions in sign language datasets. To this end, eight experiments are conducted in both signer-dependent and signer-independent modes. A comprehensive ablation study is presented to study the impacts of model components, network depth, and the size of the hidden dimension. The best accuracies achieved are 97.7% and 90.7% for the signer-dependent and signer-independent modes, respectively, using the KSU-SSL dataset. Similarly, the model achieves 98.38% and 96.22% for signer-dependent and signer-independent modes using the ArSL dataset.

Arabic Sign Languagesign language translationsign-to-text translationlightweight neural networks