检索结果-内蒙古大学图书馆

A lightweight attention-driven YOLOv5m model for improved brain tumor detection

computers in Biology and Medicine 2025年 188卷 109893-109893页

作者： Muksimova, Shakhnoza Umirzakova, Sabina Mardieva, Sevara Iskhakova, Nargiza Sultanov, Murodjon Cho, Young Im Department of Computer Engineering Gachon University Sujeong-gu Seongnam-si461-701 Korea Republic of Department of Information Systems and Technologies of the Tashkent State University of Economic Tashkent100066 Uzbekistan Department of Systematic and Practical Programming Tashkent University of Information Technologies named after Muhammad Al-Khwarizmi Tashkent100200 Uzbekistan

Brain tumors are regarded as one of the most lethal, devastating, and aggressive diseases, significantly reducing the life expectancy of affected individuals. For this reason, in pursuit of advancing brain tumor diagnostics, this study introduces a significant enhancement to the YOLOv5m model by integrating an Enhanced Spatial Attention (ESA) layer, tailored specifically for the analysis of magnetic resonance imaging (MRI) brain scans. Traditional brain tumor detection methods, heavily reliant on expert interpretation of MRI, are fraught with challenges such as high variability and the risk of human error. Our innovative approach leverages the ESA layer to acutely focus on salient features, significantly improving the method ability to differentiate between common classes of brain tumors—meningioma, pituitary, and glioma tumors. By processing spatial features with enhanced precision, the model minimizes false positives and maximizes detection reliability. Validated against a comprehensive dataset of 3064 T1-weighted contrast-enhanced MRI images from 233 patients, our modified YOLOv5m architecture demonstrates superior performance metrics compared to the standard model, highlighting its potential as a robust tool in clinical applications for automated and precise brain tumor diagnosis. © 2025 The Authors

关键词： Dynamic contrast enhanced MRI

来源：评论

学校读者我要写书评

暂无评论

Advanced convolutional neural network with attention mechanism for Alzheimer's disease classification using MRI

引用

computers in Biology and Medicine 2025年 190卷 110095-110095页

作者： Muksimova, Shakhnoza Umirzakova, Sabina Iskhakova, Nargiza Khaitov, Aziz Cho, Young Im Department of Computer Engineering Gachon University Sujeong-gu Gyeonggi-do Seongnam-si461-701 Korea Republic of Department of Systematic and Practical Programming Tashkent University of Information Technologies Named After Muhammad Al-Khwarizmi Tashkent100200 Uzbekistan Republican Scientific and Methodological Center for the Development of Education of the Republic of Uzbekistan Uzbekistan

This paper introduces a novel convolutional neural network model with an attention mechanism to advance Alzheimer disease (AD) classification using Magnetic Resonance Imaging (MRI). The model architecture is meticulously crafted to enhance feature extraction and selectively focus on crucial regions within brain images, thereby improving diagnostic accuracy. A unique component, the MRI Segmentation Block (MSB), is introduced to manage the skull stripping task effectively, highlighting the model ability to learn from complex, multilayered information. We have incorporated a detailed experimental evaluation of the MSB, demonstrating its superior performance in cranial debridement tasks compared to existing methods. The experiments involved a range of MRI scans, assessing the MSB's accuracy through metrics like the Dice Coefficient and Jaccard Index against ground truth annotations by expert radiologists. The results substantiate the MSB's effectiveness, setting a new benchmark for precision in medical imaging diagnostics. The proposed method integrates densely connected neural networks with a connection-wise attention model to extract multiscale features from MRI scans. Furthermore, the attention mechanism is fine-tuned to emphasize salient features significantly associated with various stages of Alzheimer's disease, thereby setting a new benchmark for precision in medical imaging diagnostics. Extensive experiments on the Alzheimer Disease Neuroimaging Initiative (ADNI) dataset demonstrate the superiority of our method over traditional and contemporary approaches, with our model achieving high accuracy and computational efficiency. This makes it suitable for clinical applications where resources are limited. This study represents a significant advancement in the diagnostic process for AD, with potential implications for improving patient outcomes in clinical settings. © 2025 The Authors

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Approach for Estimating Distances between Centers of Geometric Shapes based on Image Analysis and its Evaluation

Approach for Estimating Distances between Centers of Geometr...

引用

2021 International Conference on information Science and Communications technologies, ICISCT 2021

作者： Takhirov, Shakhzod Kudratov, Sultan Kubantsev, Konstantin Engineering University of California - Berkeley Department of Civil and Environmental BerkeleyCA United States Technologies and Programming Tashkent University of Information Technologies Department of Information and Computer Tashkent Uzbekistan

ISBN: (纸本)9781665432580

A digital image is usually stored as a two-dimensional matrix consisting of numerical values of the intensity of each color;for example, Red-Green-Blue (RGB). This fact allows a possibility of manipulation of the image data, including making measurements based on the images of a moving object. This paper presents a new approach for estimating distances between the centers of geometric shapes based on image analysis. The algorithm is based on determining the parameters of the matrices - the number of rows and columns of graphic images of target plates and creating vectors of the sums of their values. As a result of such manipulations, peaks (maxima, minima) are formed that coincide with the centers of the squares and circles displayed on the target plates. These peaks are the coordinates of the target centers. © 2021 IEEE.

关键词： Image analysis

来源：评论

学校读者我要写书评

暂无评论

On One Method of Constructing a Decision Rule in Pattern Recognition

On One Method of Constructing a Decision Rule in Pattern Rec...

引用

2021 International Conference on information Science and Communications technologies, ICISCT 2021

作者： Kasimova, Shoista Kasimov, Saidaminxon Tashkent University of Information Technologies after Name Mukhammad Al-Khwarizmi Information and Computer Technologies and Programming Department Tashkent Uzbekistan Tashkent University of Information Technologies after Name Mukhammad Al-Khwarizmi Information Security Department Tashkent Uzbekistan

ISBN: (纸本)9781665432580

The general problem of pattern recognition is to establish the theory and principles of building systems that share complex situations and events into classes. In this case, usually the number of possible situations in the classes is great and they are almost impossible to be remembered. The method of estimates' calculating contributes to a variety of scoring functions' building, which in turn, allows us to formulate and solve a wide class of multivariate data processing. In recent years more and more widely distributed methods of pattern recognition, in which the primary step is to calculate the balance of information and consideration of evidence. Based on the latest evidence being implemented, all further procedures until the distinction of classes or assign any object to one of the classes. © 2021 IEEE.

关键词： Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Traffic and road sign recognition using deep convolutional neural network

Traffic and road sign recognition using deep convolutional n...

引用

2021 International Conference on information Science and Communications technologies, ICISCT 2021

作者： Kuchkorov, Temurbek Khamzaev, Jamshid Allamuratova, Zamira Ochilov, Temur Tashkent University of Information Technologies Nmaed after Muhammad Al-Khwarizmi Department of Computer Systems Tashkent Uzbekistan Tashkent University of Information Technologies Nmaed after Muhammad Al-Khwarizmi Joint Faculty TUIT-BSUIR Department of Information-computer Technologies and Programming Tashkent Uzbekistan

ISBN: (纸本)9781665432580

Automatic road sign recognition is one of the most important steps to help a driver prevent accidents. In this paper, the deep convolutional neural network (Deep CNN) was used for the autonomous traffic and road signs detection and recognition system. The proposed system works in real-time recognition of the image of road signs. The contribution of this article is that it consists of a newly developed datasets for 42 different road signs using combination of existing datasets and collected local road signs. The images were taken from different angles and included other parameters and conditions. More than 30K images were collected to create the dataset, which is named Uzbekistan traffic and road signs (UZ-TRS-2021). The CNN architecture was used with various parameters to achieve the best recognition speed. Experimental results show that the proposed CNN architecture achieved 98% accuracy. © 2021 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Hydrogeological-Mathematical Model of Formation and Management of Resources and Quality of Fresh Underground Water of the Karakalpak Artesian Basin

Hydrogeological-Mathematical Model of Formation and Manageme...

引用

2021 International Conference on information Science and Communications technologies, ICISCT 2021

作者： Seitnazarov, Kuanish Aytanov, Anvar Kojametov, Ermuhammed Asenbaev, Nurbek Nukus Branch of Tashkent University of Information Technologies Named after Muhammad Al-Khwarizmi Faculty of 'Computer Engineering' Nukus Uzbekistan Tashkent University of Information Technologies Named after Muhammad Al-Khwarizmi Department of Computer Systems Tashkent Uzbekistan Tashkent University of Information Technologies Named after Muhammad Al-Khwarizmi Department of Information Computer Technologies and Programming Tashkent Uzbekistan Nukus Branch of Tashkent University of Information Technologies Named after Muhammad Al-Khwarizmi Department of Information Security Nukus Uzbekistan

ISBN: (纸本)9781665432580

This article discusses the problems of using groundwater resources of the Karakalpak artesian basin. The task of drawing up a geological and mathematical model of the operational resources of groundwater in the Karakalpak artesian basin for the rational use of fresh groundwater in the basin is set. This article discusses the problem of lack of fresh groundwater in the territory of the Republic of Karakalpakstan. A method of hydrogeological-mathematical model of exploitable groundwater resources for the correct use of fresh groundwater is proposed. © 2021 IEEE.

关键词： Hydrogeology

来源：评论

学校读者我要写书评

暂无评论

Analysis of Hardware and Software Tools for Implementation of Cognitive Radio Networks

Analysis of Hardware and Software Tools for Implementation o...

引用

2022 International Conference on information Science and Communications technologies, ICISCT 2022

作者： Reypnazarov, Ernazar Khujamatov, Halimjon Khasanov, Doston Allamuratova, Zamira Tashkent University of Information Technologies Named after Muhammad Al-Khwarizmi Tashkent Uzbekistan Tashkent University of Information Technologies Named after Muhammad Al-Khwarizmi The Computer Enjineering Faculty Tashkent Uzbekistan Tashkent University of Information Technologies Named after Muhammad Al-Khwarizmi Department of Data Communication Networks and Systems Tashkent Uzbekistan Tashkent University of Information Technologies Named after Muhammad Al-Khwarizmi Department of Information-Computer Technologies and Programming Tashkent Uzbekistan

ISBN: (纸本)9781665472296

This paper analyzes of the hardware and software tools for implementing a cognitive radio network. In particular, software-configurable radio modules, which are considered the main element of the cognitive network, were studied according to their main characteristics, among which the widely used ones were comparatively analyzed. As a result of the analysis, the HackRF One device was selected as the most preferred option for cognitive network research, and its working principles, structure, and characteristics were revealed in detail. It also provides information about the GNU Radio software environment and its capabilities, which are used to operate the HackRF One device. © 2022 IEEE.

关键词： Digital signal processing

来源：评论

学校读者我要写书评

暂无评论

Research of Energy Detection Method in Spectrum Sensing in Cognitive Radio Networks

Research of Energy Detection Method in Spectrum Sensing in C...

引用

2022 International Conference on information Science and Communications technologies, ICISCT 2022

作者： Reypnazarov, Ernazar Khujamatov, Halimjon Khasanov, Doston Allamuratova, Zamira Tashkent University of Information Technologies Named after Muhammad Al-Khwarizmi Tashkent Uzbekistan Computer Enjineering Faculty Tashkent University of Information Technologies Named after Muhammad Al-Khwarizmi Tashkent Uzbekistan Tashkent University of Information Technologies Named after Muhammad Al-Khwarizmi Department of Data Communication Networks and Systems Tashkent Uzbekistan Department of Information-Computer Technologies and Programming Tashkent University of Information Technologies Named after Muhammad Al-Khwarizmi Tashkent Uzbekistan

ISBN: (纸本)9781665472296

This paper presents the threshold value determination model, its implementation algorithm, and the characteristics of the threshold value depending on the probability of false signal detection, developed for the purpose of researching the method of energy determination in spectrum sensing in cognitive radio networks. Also, the main methods of single-band spectrum sensing in cognitive radio networks were initially studied in the article, and the main spectrum detection algorithms were comparatively analyzed. © 2022 IEEE.

关键词： Cognitive radio

来源：评论

学校读者我要写书评

暂无评论

METHOD OF DETECTION OF INTRUSIONS BASED ON STACKING META-ALGORITHM 5

METHOD OF DETECTION OF INTRUSIONS BASED ON STACKING META-ALG...

引用

5th IEEE KhPI Week on Advanced Technology, KhPIWeek 2024

作者： Gavrylenko, Svitlana Zozulia, Vladislav Khatsko, Nataliia Department of Computer Engineering and Programming National Technical University "Kharkiv Polytechnic Institute" Kharkiv Ukraine Department Information Systems and Technologies National Technical University «Kharkiv Polytechnic Institute» Kharkiv Ukraine

ISBN: (纸本)9798350384499

An analysis of modern computer network intrusion detection systems was carried out. The application of machine and deep learning methods for classification problems has been investigated. The UNSW-NB15 dataset, developed at the Australian Cyber Security Center's (ACCS) Cyber Range Laboratory, contains data on normal network operations and synthetic intrusions. Data pre-processing was performed, including class balancing using the SMOTEENN method and selection of informative features using the Recursive Feature Elimination method. The possibility of using the stacking meta-algorithm to detect intrusions into computer networks has been investigated. A new algorithm for generating packets of raw data is proposed, which generates two sets of training data: one for training basic models, the other for a meta-model. A study of the effectiveness of using Random Forest, ANN, K Nearest Neighbor methods and Support Vector Machine and Random Forest as a decision-making meta-model was conducted. The use of the stacking meta-algorithm with the proposed algorithm for forming packets of output data, as well as basic models and a meta-model, led to a significant improvement in the quality of the model. It was found that, on average, recall and f1 score increased by 55.6% and 37.4%, respectively, compared to raw data and other models. ©2024 IEEE.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence in Medicine for Chronic Disease Classification Using Machine Learning 16

Artificial Intelligence in Medicine for Chronic Disease Clas...

引用

16th IEEE International Conference on Application of information and Communication technologies, AICT 2022

作者： Rakhimov, Mekhriddin Akhmadjonov, Ravshanjon Javliev, Shahzod Tashkent University of Information Technologies Named after Muhammad Al-Khwarizmi Department of Artificial Intelligence Tashkent Uzbekistan Tashkent University of Information Technologies Named after Muhammad Al-Khwarizmi Department of System and Application Programming Tashkent Uzbekistan Tashkent University of Information Technologies Named after Muhammad Al-Khwarizmi Department of Computer System Tashkent Uzbekistan

ISBN: (纸本)9781665451628

Artificial intelligence (AI) systems in medicine are one of the most important modern trends in global healthcare. Artificial intelligence technologies are fundamentally changing the global healthcare system, making it possible to radically rebuild the system of medical diagnostics while reducing healthcare costs. AI is actively used in research to develop methods for diagnosing coronary heart disease (CHD). There are different types of CHD. Before treating a disease, it is necessary to determine which class of diseases it belongs to. Based on the feature space of the disease, it is possible to classify the type of CHD. Machine learning algorithms can solve this problem. The k-nearest neighbors (KNN) algorithm is a simple, easy-to-implement supervised machine learning algorithm that can be used to solve classification problems. The dataset is the more important part of the supervised machine learning algorithm for training. Gathering data is the most important step in solving any supervised machine learning problem. But choosing more important part from the collected data is one of the tasks to be solved. The main purpose of this study is to select more useful parametric attributes from the dataset to obtain a high F1-score of CHD classification. © 2022 IEEE.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：