Results 191 to 200 of about 112,491 (292)
Prevalence and associated factors of eating disorders' risk among Alexandria University medical students. [PDF]
Hagag RA +4 more
europepmc +1 more source
An outline map of the city of Alexandria in ancient times, with buildings labeled and no topographical ...
Unknown
core
A Hybrid Transfer Learning Framework for Brain Tumor Diagnosis
A novel hybrid transfer learning approach for brain tumor classification achieves 99.47% accuracy using magnetic resonance imaging (MRI) images. By combining image preprocessing, ensemble deep learning, and explainable artificial intelligence (XAI) techniques like gradient‐weighted class activation mapping and SHapley Additive exPlanations (SHAP), the ...
Sadia Islam Tonni +11 more
wiley +1 more source
This paper introduces a resource‐aware Contrastive Scattering Meta‐Learning (CSML) framework for acoustic anomaly detection. By leveraging training‐free wavelet scattering and metric‐based meta‐learning, the model achieves competitive performance with only 50 K learnable parameters—a 98% reduction compared to state‐of‐the‐art frameworks—enabling ...
Rami Zewail, Bassem Mokhtar
wiley +1 more source
Polysomnographic arousal index and periodic limb movement index in patients undergoing coronary artery bypass grafting: an exploratory case-comparison study. [PDF]
Mekky J +7 more
europepmc +1 more source
Dielectric Elastomer Actuators as Safe and Effective Tools for Mechanostimulation of Human Cells
Replicating physiological forces is crucial for realistic cell models. Dielectric elastomer actuators (DEAs) offer a soft alternative, though their high voltages raised toxicity concerns. We demonstrate that DEA stimulation causes no cell damage, cell death or cell‐cycle disruption, while activating mechanosensitive responses.
Simon Holzer +6 more
wiley +1 more source
Trends in gastrointestinal cancers at a major tertiary hospital in Alexandria, Egypt: a 10-year retrospective study (2010-2019). [PDF]
Abdulla MM +4 more
europepmc +1 more source
The phase discontinuity problem—where the cyclic nature of phase angles causes catastrophic errors near the ±π boundary—is a fundamental obstacle in learning‐based reconfigurable intelligent surface (RIS) optimization. A phase‐aware hybrid CNN–LSTM framework resolves this by decomposing phase predictions into sine–cosine components, mapping circular ...
Seda Savaşçı Şen +3 more
wiley +1 more source
Finite element analysis of patient specific three-dimensional titanium plate versus conventional two miniplate fixation for mandibular angle fractures. [PDF]
Abd Elfattah AM +3 more
europepmc +1 more source
FluoAI is a two‐stage, label‐free method for quantifying nanomaterial‐induced cytotoxicity from conventional fluorescence microscopy images. Mask R‐CNN segmentation and DenseNet‐121 classification provide rapid live/dead classification matching human accuracy.
Ugur C. Topkiran +6 more
wiley +1 more source

