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.

5 مُخرَج نتائج البحث عن «Workflow»

مقالمفتوح (مستودع)20266استشهاد· Semantic Scholar

Blockchain Consensus Mechanisms and Enhancement Techniques for Federated Learning-Based Intrusion Detection Systems in IoT Smart Homes

Journal of Reliable and Secure Computing · مجلد 2 (1) · 1-26

The rapid proliferation of smart home IoT devices has introduced unprecedented cybersecurity vulnerabilities, necessitating scalable and privacy-preserving intrusion detection systems (IDS). Federated Learning (FL) offers a promising decentralized approach by training models locally without sharing raw data, but it remains susceptible to poisoning attacks and relies on a vulnerable central aggregator. This paper presents a novel blockchain-enhanced FL framework tailored for smart home IDS, integrating multiple consensus mechanisms—Proof-of-Stake (PoS), Practical Byzantine Fault Tolerance (PBFT), and Proof-of-Authority (PoA)—for the first time in this context. Our approach uniquely combines differential privacy (DP) and secure aggregation (SA) within a blockchain-managed workflow to mitigate gradient inversion and membership inference attacks while ensuring tamper-resistant, decentralized trust. Experimental evaluation using the N-BaIoT dataset demonstrates that the proposed system achieves up to 88.3% detection accuracy with manageable latency (~200 ms/round) and formal privacy guarantees ($\varepsilon$=1.0 DP). The framework introduces 52.8% system overhead compared to vanilla FL—a reasonable trade-off for enhanced security and privacy. This work establishes a robust, transparent, and scalable security infrastructure for smart homes, effectively addressing the limitations of both centralized and conventional FL-based IDS.

blockchainfederated learningintrusion detection systemshome automation
مقالوصول مغلق2026

From Libraries to Language Models: Exploring PhD Students’ Digital Research Tool Adoption

Serials Review · 1-13

This study investigates the digital transformation of academic research practices among doctorate (PhD) scholars, focusing on the integration and use of Online Public Access Catalogs (OPACs), electronic resources (e-resources), and large language models (LLMs). Using a descriptive survey of 355 doctoral students, the research explores the frequency, purpose, and perceived effectiveness of these tools in academic workflows. The findings reveal that while e-resources are the most utilized platform for literature searches and academic writing, OPACs remain underused due to perceived usability challenges. LLMs are gradually being adopted, especially for grammar refinement and content drafting, though concerns regarding reliability and academic integrity remain. Factor analysis highlights intuitive interfaces and information reliability as critical dimensions shaping user experience. The results call for improved digital literacy initiatives, user-centric OPAC redesigns, and ethical AI integration strategies to support contemporary scholarly practices.

digital research toolstechnology adoptiondoctoral studentslanguage models
مقالوصول مفتوح2026

Development and validation of a predictive AI model for differential diagnosis of endodontic and non-endodontic orofacial pain: a comparative study

Scientific Reports · مجلد 16 (1)

Differentiating between endodontic and non-endodontic sources of orofacial pain is a diagnostic challenge owing to overlapping clinical presentations. Artificial intelligence (AI) offers a potential solution to improve the diagnostic accuracy of endodontics by analysing complex clinical and radiographic data. To evaluate the performance of an artificial intelligence (AI) model in distinguishing endodontic pain from non-endodontic pain and compare its diagnostic accuracy, sensitivity, and specificity with those of an expert panel. This cross-sectional diagnostic study included 224 participants (134 with endodontic pain and 90 without endodontic pain). Clinical and radiographic data were analysed using a random forest AI model trained on features including radiographic lesions, pain characteristics, and pulp vitality tests. Model performance metrics, including accuracy, sensitivity, specificity, and the area under the receiver operating characteristic (ROC) curve (AUC-ROC), were assessed across the training, validation, and test datasets. The model’s performance was compared to that of an expert panel using statistical tests. The AI model demonstrated an overall diagnostic accuracy of 91.8% on the test set, with sensitivity and specificity of 92.1% and 91.4%, respectively. The AI model showed significantly higher sensitivity (p = 0.03) than the expert panel (accuracy: 89.2%). Feature importance analysis identified radiographic lesions (34%), pain characteristics (28%), and pulp vitality test results (25%) as the most influential predictors. The AI model exhibited superior diagnostic accuracy compared with the expert panel, indicating its potential as a reliable tool for differentiating endodontic pain from non-endodontic sources. Incorporating AI into clinical workflows can enhance diagnostic precision and improve patient outcomes in endodontics.

endodontic painorofacial paindifferential diagnosisartificial intelligence
مقالوصول مفتوح2026

Global thermodynamic consistency: A linear-algebraic diagnostic framework

Results in Engineering · مجلد 32 · 112122-112122

Thermodynamic cycle models are routinely assembled from heterogeneous sources – steam-table lookups, manufacturer data sheets, handbook correlations, and hand-computed preliminary estimates – and an error introduced in any one source (a misread enthalpy, a sign error in a heat balance, a wrong coefficient-of-performance value) can propagate silently through every downstream calculation. Engineers currently guard against this by checking governing equations pairwise, but pairwise checking has a structural blind spot: a set of equations can pass every pairwise comparison and still be globally infeasible as a system. We develop a linear-algebraic diagnostic framework that closes this gap. The governing equations of a steady-state thermodynamic cycle – energy balances over turbines, compressors, boilers, condensers, and expansion devices, together with isentropic-process relations and the coefficient-of-performance definition – form a linear system A x = b whose state vector x collects enthalpies, heat transfer rates, and work quantities at each process node. We show that global inconsistency of this system is equivalent to infeasibility of A x = b , and that infeasibility is always witnessed by a vector in the left nullspace of A that is not orthogonal to b – an algebraically certifiable condition we call a nullspace inconsistency certificate , computable from a single thin SVD and fundamentally inaccessible to pairwise checking. Building on this certificate, we prove that pairwise consistency checks are provably insufficient to detect global thermodynamic inconsistency; we establish existence and uniqueness of a minimum-norm repair vector that returns the right-hand-side data to the nearest feasible point on the constraint manifold; we derive equation-localization weights that rank which governing equation is the primary source of a fault; and we construct a differentiable repair operator whose fixed points correspond to globally self-consistent cycle models. The complete detection-localization-repair pipeline runs in O ( kn 2 ) time via a thin SVD – negligible overhead for cycle models of practical size – and requires no information beyond the equations and data an engineer already has on hand. We demonstrate the framework on the Rankine steam-power cycle and the vapor-compression refrigeration cycle, where it correctly detects, localizes, and corrects hidden inconsistencies – including a 50 kJ kg − 1 enthalpy error in Rankine cycle steam tables and a simultaneous condenser-balance fault with an erroneous COP value in the refrigeration cycle – that pass all pairwise equation checks yet render the global model infeasible. We further discuss how the certificate behaves under measurement and property-estimation uncertainty, and compare the approach against residual-based checking, data-reconciliation, and optimization-based fault detection. The framework requires only the linear (or linearized) governing equations and standard property data already used in routine cycle calculations, making it directly deployable as an auditing layer in existing engineering workflows.

thermodynamic consistencylinear algebradiagnostic frameworkenergy balance
مراجعةوصول مفتوح2026

Deployment of Artificial Intelligence in Clinical Oral Pathology: Evidence Summary and Implementation Gaps

Analytical Cellular Pathology · مجلد 2026 (1) · e9281281-e9281281

BACKGROUND: Whole-slide imaging (WSI) has shifted pathology toward digital workflows, creating the foundation for applying artificial intelligence (AI) to diagnostic tasks. This review summarises validated AI applications in diagnostic pathology, with an emphasis on clinical performance, regulatory developments and the practical barriers that affect implementation. METHODS: A structured search of PubMed, Scopus and Google Scholar identified English-language, peer-reviewed studies from January 2020 to May 2025. Eligible studies applied AI to diagnostic, grading or prognostic tasks in human tissue, used a pathologist-confirmed reference standard and included external or multi-centre validation. RESULTS: More than 150,000 digital slides were represented across the included studies. Reported performance metrics demonstrated strong diagnostic accuracy across several validated applications. Large meta-analyses and externally validated studies reported sensitivity values exceeding 96% and specificity above 93% for selected cancer-detection tasks, while other studies demonstrated high agreement for Gleason grading (QWK up to 0.862) and biomarker quantification (Ki-67 ICC 0.98). CONCLUSION: AI has the capacity to strengthen diagnostic pathology by improving consistency, measurement and efficiency. Moving from experimental use to routine reporting will require broad validation across centres, enhanced model transparency, strong quality-assurance systems and close cooperation between developers and pathologists.

artificial intelligencewhole slide imagingdigital pathologyAI implementation barriers