Abstract

Abstract

Latest developments in high-strength Magnetic Resonance Imaging (MRI) scanners with in-built high resolution, have dramatically enhanced the ability of clinicians to diagnose tumours and rare illnesses. However, their high-strength transient magnetic fields induce unwanted eddy currents in shielding components, which result in fast vibrations, noise, imaging artefacts and, ultimately, heat dissipation, boiling off the helium used to super-cool the magnets. Optimum MRI scanner design requires the capturing of complex electro-magneto-mechanical interactions with high fidelity computational tools. During production cycles, this is known to be extremely expensive due to the large number of configurations that need to be tested. There is an urgent need for the development of new cost-effective methods whereby previously performed computations can be assimilated as training solutions of a surrogate digital twin model to allow for real-time simulations. In this paper, a Reduced Order Modelling technique based on the Proper Generalised Decomposition method is presented for the first time in the context of MRI scanning design, with two distinct novelties. First, the paper derives from scratch the offline higher dimensional parametrised solution process of the coupled electro-magneto-mechanical problem at hand and, second, a regularised adaptive methodology is proposed for the circumvention of numerical singularities associated with the ill-conditioning of the discrete system in the vicinity of resonant modes. A series of numerical examples are presented in order to illustrate, motivate and demonstrate the validity and flexibility of the considered approach.

Abstract

Abstract

'''Diabetic retinopathy, a type of eye disease, is a danger for diabetics (DR). Manual labour, which is prone to inaccuracy and time consuming, makes dealing with this illness considerably more difficult. Normally computer-assisted diagnosis has appeared as a promising tool for the early identification and severity grading of DR. As technologies are revolutionizing day by day, in which the most advance technology deep learning's algorithm gives a tremendous support for healthcare fields. In this article propose an efficient classification of DR models such as Generative Adversarial Network with Deep Belief Network (GAN-DBN), this category the DR into different grades and to identify the severity. Obtaining medical data is also a tedious and challenging one because it is quite expensive and confidential, to overcome this the proposed model is act as a data augmentation model, moreover the features in the input data’s are reduced by Dimensionality reduction Module (DRM) based on Principal Component Analysis. Enhancing retinal fundus images using a median filter, morphological operation, and histogram equalization approaches. When compared to previous classification models, experimental results on fundus images using the MESSIDOR database reveal that the GAN-based DBN model obtained good processing performances with 99.2% accuracy in the suggested classification task.

Abstract

The deployment of communication base stations establishes an efficient information transmission network; however, implementing deployment in mountainous areas with complex terrain remains amajor challenge. To address the issues of large topographical variations, dispersed villages, and low coverage efficiency, this study focuses on application issues, develops a mountainous deployment environment model that incorporates terrain elevation increments and village exclusion zones. On this basis, a Differential Evolution algorithm with Multiple Mutation Strategies (MSM-DE) is proposed to improve the balance between global exploration and local exploitation. The algorithm introduces a probabilistic multi-mutation mechanism that dynamically selects among several mutation strategies according to population diversity, and an adaptive parameter memory archive that guides the search toward promising regions.These modifications enhance both convergence speed and robustness in complex terrain optimization. Three objectives—coverage rate, village coverage satisfaction, and signal security—are combined into a weighted multi-objective function, and experiments are performed under two deployment scenarios (fixed and random village distributions).The results demonstrate that MSM-DE achieves significantly faster convergence and higher coverage performance than benchmark DE variants, validating that the proposed mutation synergy and adaptive parameter control effectively strengthen the algorithm’s optimization capability and stability in mountainous base station deployment.

Abstract

A Urinary Tract Infection (UTI) is characterized by an infection affecting the urinary system, including the kidneys, bladder, urethra, and ureters, with clinical presentations including pyelonephritis, cystitis, and urethritis. While conventional diagnostic methods such as urinalysis and urine culture and sensitivity (C&S) remain widely used, they are limited by subjectivity, time-intensive processing, susceptibility to contamination and risks of false-positive or false-negative results. This study proposes a comprehensive deep learning (DL) and Internet of Things (IoMT) framework to automate the real-time detection and classification of UTIs using microscopic urine sediment images. The study employed 2 datasets (A and B). Dataset A, a clinically acquired dataset, comprises of 3345 images (normal, erythrocytes, fungi and pus) and Dataset B, a publicly accessible data comprises of 5377 images and 26,419 cropped microscopic images corresponding to 7 classes (casts, crystals, erythrocytes leukocytes, epithelial cells, epithelial nuclei, mycetes). A two-stage classification approach was implemented: a binary task to distinguish urine sediments from normal cases, followed by a multiclass task (clinical data and online data) to identify the specific infection type. All images underwent pre-processing, including normalization, resizing, noise removal, and augmentation to enhance feature visibility and model generalizability. The data were partitioned into training (65%), validation (25%), and test (10%) sets. Six state-of-the-art DL architectures, including ResNet50-V2, ResNet101-V2, Inception-V3, XceptionV2, Inception-ResNet-V2, and VGG19 were fine-tuned using transfer learning and evaluated using accuracy, precision, recall, F1-score, and confusion matrices. The proposed models were uploaded to a website to enable realtime detection (accessible via this link: https://uticlassification.app/). The proposed pipeline demonstrated strong performance in both classification tasks, underscoring the potential of deep learning as a reliable, rapid, and reproducible tool for automated urine sediment identification in clinical practice.