Al-Razi University

Interpretable water and agricultural land cover in urban landscapes using CNN–ViT framework with Grad-CAM for agricultural sustainability

Abstract Accurate land-use and land-cover classification in hyper-arid environments is challenging because several surface types can exhibit overlapping spectral and spatial characteristics in Landsat imagery. These surfaces include water, irrigated agriculture, moist soil, barre...

Dual-model deep learning for detecting and classifying dental abscesses, cysts, and tumours on orthopantomograms: a histopathology-referenced diagnostic study

Differential diagnosis of periapical and intra-osseous jaw lesions is a recurring clinical challenge that still depends on invasive, costly histopathological examination. Deep learning applied to routine panoramic radiography offers a potential non-invasive triage aid, but most p...

Oxygen-Vacancy-Controlled Band-Gap Engineering in Fe/Co Co-doped La-Modified Bismuth Titanate: Integrated Experimental and First-Principles Analysis

Abstract Layered Aurivillius ferroelectrics offer a route to multifunctional band-gap engineering, yet the role of oxygen vacancies in band-edge reconstruction in Fe/Co-modified compositions remains poorly resolved. Here, oxygen annealing of Bi3.25La0.75Ti2.60(Fe0.50,Co0.50)0.40O...

Employing artificial intelligence technologies to enhance educational process quality in health education institutions in Yemen

Abstract This study aims to examine the role of employing artificial intelligence (AI) technologies in enhancing the quality of the educational process in university-level health education institutions within the Yemeni context. A descriptive analytical study design was adopted....