Abstract

Abstract

Breast cancer is one of the leading causes of death in women worldwide and early detection is critical to improving survival rates. In this study, we present a modified deep learning method for automatic feature detection for breast mass classification on mammograms. We propose to use EfficientNet, a Convolutional Neural Network (CNN) architecture that requires minimal parameters. The main advantage of EfficientNet is the small number of parameters, which allows efficient and accurate classification of mammogram images. Our experiments show that EfficientNet, with an overall accuracy of 86.5 percent, has the potential to be the basis for a fully automated and effective breast cancer detection system in the future. Our results demonstrate the potential of EfficientNet to improve the accuracy and efficiency of breast cancer detection compared to other approaches.

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.