In this study, a concatenated CNN model for pneumonia detection is proposed, combined with an image enhancement method based on fuzzy logic. The image enhancement process utilizes a novel refined fuzzification algorithm, which significantly improves image quality and feature extraction efficiency for the CCNN model. Four datasets were used for training: original images and images processed using fuzzy entropy, standard deviation, and histogram equalization. The results showed that using enhanced datasets notably increased the CCNN’s performance, with the fuzzy entropy–enhanced dataset yielding the best results. The proposed CCNN model achieved outstanding classification metrics, including 98.9% accuracy, 99.3% precision, 99.8% F1-score, and 99.6% recall. Experimental comparisons demonstrated that fuzzy logic–based image enhancement significantly outperforms traditional methods, providing higher diagnostic accuracy. This research highlights the effectiveness of integrating deep learning models with advanced image enhancement techniques for medical image analysis.
| Mualliflar | Бурибоев, А.Ш. |
|---|---|
| Jurnal | Рақамли технологияларнинг назарий ва амалий масалалари |
| Nashr sanasi | 2025-10-30 |
| Jild | 8 |
| Son | 4 |
| Betlar | 71-78 |
| Til | Rus |
| DOI | 10.62132/ijdt.v8i4.304 |
DOI: 10.62132/ijdt.v8i4.304 · Maqolaning asl sahifasi
классификация, нечеткая логика, фаззификация, данные, конкатенированная CNN, classification, fuzzy logic, fuzzification, data, concatenated CNN
The article presents a comprehensive mathematical model of radial filtration in a cylindrical filter, where the fluid flows from the outer layer toward the central cavity. The regions of free flow are described by the…
This article develops a model and numerical algorithm with second-order accuracy in time and spatial variables for solving problems of combined heat and moisture transfer during the storage and drying of heterogeneous…
This paper presents an intelligent video monitoring system with automatic fire detection. The system is based on YOLO deep learning algorithms and contour analysis, enabling real-time video stream processing. The…
High mortality in the acute and post-hospital periods of myocardial infarction underscores the relevance of accurately stratifying patient risk and assessing survival outcomes. This study compares two complementary…
This work is devoted to the description of certain cohomology groups with specific local conditions that possess the property of “local triviality.” It is proved that such groups are cyclic for certain classes of…
The paper considers the problem of deformation of a thin conductive plate under the action of a non-stationary magnetic field taking into account the Lorentz forces and Joule heat generation. A mathematical model is…
Experimental results of Faraday rotation spectra in the range of 1.8-3.65 eV were obtained for H2O, CCl4, dimethylaniline, benzene, nitrobenzene, o-toluidine, o-anisidine, m-chloroaniline and o-chloroaniline…
Understanding how daily behavioral patterns contribute to stress is increasingly important in a digitally saturated world. This study investigates the relationship between technology use, lifestyle behaviors, and stress…
In this paper, the electromagnetic properties of patch antennas with a ring-shaped open resonator based on various dielectric base (substrate) materials were electromagnetically modeled and analyzed. The study was…
The article considers a numerical method for solving a two-dimensional coupled dynamic thermoplastic boundary value problem based on deformation theory of plasticity. Discrete equations are compiled by the…
Рақамли технологияларнинг назарий ва амалий масалалари — barcha maqolalar