In this study, the task of classifying brain tumors based on magnetic resonance imaging was analyzed using deep learning approaches. The study compared convolutional neural networks and transformer-based models, including the Vision Transformer and DEiT architectures. The experiments were conducted on an open "Brain Tumor MRI Dataset" dataset, and the models were evaluated based on accuracy, precision, recall, and F1-score metrics. According to the results, the DEiT model demonstrated the highest efficiency, achieving 98.04% validation and 94.44% testing accuracy. The results obtained showed the superiority of transformer models due to their ability to effectively study global properties
| Mualliflar | Nishanov, Akhram Khasanovich, Zaripov, Fazil Makhsetovich, Qambarov, Bahriddin, Jurakulov, Nodirbek Sobirovich, Makhamatdinov, Abdul-Aziz Karamatdinovich |
|---|---|
| Jurnal | Al-Farg'oniy avlodlari |
| Nashr sanasi | 2026-06-08 |
| Son | 2 |
| Betlar | 357-363 |
| Til | Rus |
MRI, brain tumor, deep learning, CNN, Vision Transformer, DEiT, classification, MRI, brain tumor, deep learning, CNN, Vision Transformer, DEiT, classification
This article analyzes the use of steganography and digital watermarking (DW) methods in protecting copyright and intellectual property of digital multimedia data. General schemes for placing and extracting digital…
This article provides a comparative analysis of the symbolic and numerical computing capabilities of MathCad and Python programming environments for solving engineering optimization problems. Special attention is paid…
Note: This article analyzes the process of formation of aphthous lesions in the oral cavity based on mathematical modeling. The aphthous process is a complex biological phenomenon occurring in the oral mucosa, in which…
This paper discusses the protection of intellectual property using one of the key areas of steganography — digital watermarking and digital fingerprinting. The study examines the types of watermarks (robust, fragile…
This article evaluates noise removal and restoration errors using digital processing of ECG signals using wavelet types. As a result of the study, ECG signals were analyzed using second-order Daubechies wavelets, and…
This article provides an in-depth analysis of advanced algorithms for automatic object detection and classification in video imagery. The rapid advancements in artificial intelligence and deep learning have…
This paper proposes a neuro-fuzzy model based on Sugeno-type ANFIS for adaptive control of urban intersections. The model accounts for the state of not only the central intersection but also four adjacent intersections…
This article discusses in detail the theoretical foundations, structure and practical applications of fractal robot technology. The fractal concept is based on the principle of self-similarity, and this feature is…
An adaptive area contrast enhancement algorithm is proposed to solve the problem of low contrast in agricultural images. The algorithm automatically detects low contrast regions using local standard deviation and Sobel…
The article describes a PostgreSQL-based relational model for organizing automotive data on manufacturers, models, generations and trims. The analysis covers tables, enum types, foreign keys, temporal CHECK constraints…