检索结果-内蒙古大学图书馆

2023 International Russian Smart Industry Conference, SmartIndustryCon 2023

作者： Jumanov, Isroil I. Safarov, Rustam A. Djumanov, Olimjon I. Samarkand State University Intelligent Systems and Computer Technologies Samarkand Uzbekistan

ISBN: (纸本)9781665464291

A methodology for optimizing the identification, recognition and classification of micro-objects has been implemented using dynamic models for transforming the original image, synthesizing mechanisms for extracting redundant information structures and using histological, morphological, and texture characteristics of images. Implemented mechanisms for detecting, highlighting and correcting the values of distorted points by embedding new data, segmenting the contour, reducing redundant fragments, and setting variables. Identification algorithms have been developed that take into account the correlations of a set of points, the dynamics of their change, matrices of coordinates of points, deformation of segments and the selection of homogeneous areas of images. A comparative analysis of the effectiveness of the mechanisms for pre-processing images, recognition and classification based on testing pictures of medical diagnostics, and pollen grains in solving problems of selection and seed production of grain was carried out. Modified component schemes, and learning algorithms for a three-layer neural network. A generalized mechanism of identification is implemented in case of non-linearity of connections "inputs and outputs"under conditions of a priori insufficiency and uncertainty. Five types of neural network software modules were tested with supervised and unsupervised learning algorithms based on network learning with modified samples with vector quantization, clustering, and identification with "sliding windows". The efficiency of identification with filtrations in the presence of "noise", approximation of the reference points of the curve of the contour of images of micro-objects has been studied. © 2023 IEEE.

关键词： Dynamic models

来源：评论

学校读者我要写书评

暂无评论

Optimization of Identification of Micro-Objects with Blurring of Image Points

Optimization of Identification of Micro-Objects with Blurrin...

引用

2023 International Russian Automation Conference, RusAutoCon 2023

作者： Jumanov, Isroil I. Safarov, Rustam A. Samarkand State University Intelligent Systems and Computer Technologies Samarkand Uzbekistan

ISBN: (纸本)9798350345551

Scientific and methodological foundations have been developed for the identification and recognition of micro-objects in the systems of environmental protection and ecology, medicine, aimed at using redundant information structures of image components - histological, morphological, fractal, geometric, and other characteristics. The effectiveness of the mechanisms for identifying micro-objects according to the criteria of the minimum standard error, labor intensity, and cost of information processing has been studied. Implemented mechanisms for double threshold noise filtering, and detection of blurred image points for various practice conditions. A technique for gradient optimization of the micro-object identification functional, calculation of the weight coefficient of the image convolution kernel, and application of the Gauss, Laplace, Prewitt, Roberts, Sobel, and Canny operators is proposed. A software package for visualization, identification, recognition, and classification of images of micro-objects has been implemented, including a database of images, and subsystems for image pre-processing, filtering, identification, recognition, and classification. The operability of the software package was tested on the example of image processing of a large number of pollen grains and medical microorganisms. © 2023 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Optimization of Micro-object Identification Based on the Mellin Transform and the Use of Parallel Computing

Optimization of Micro-object Identification Based on the Mel...

引用

2023 International Russian Smart Industry Conference, SmartIndustryCon 2023

作者： Jumanov, Isroil I. Kholmonov, Sunatillo M. Samarkand State University Intelligent Systems and Computer Technologies Samarkand Uzbekistan

ISBN: (纸本)9781665464291

Scientific and methodological foundations for the optimal identification of non-stationary objects based on the use of neural networks have been developed. Models and algorithms for detection, extraction of hidden relationships, useful properties and patterns in data, formation of a database and knowledge bases are proposed. Mechanisms have been developed for using the statistical, dynamic and specific characteristics of images, unique features of three, five-layer neural networks and combined models for setting variables with typical recognition and classification tools. Have been developed computational schemes for determining and adjusting the weights of neurons, choosing a suitable activation function, coefficients of synaptic and interneuronal connections, rational neural network architecture, the number of layers and neurons in the layers of the network, a set of functions of nonlinear dependencies "inputs-outputs". Data pre-processing algorithms are implemented that perform the functions of informative features selection, segmentation, object image contour extraction, search based on methods with annealing, prohibition, and stochastic search. Tested neural networks of Hopfield, Hamming, Hebb, Kohonen, bidirectional associative memory were tested. Schemes for two and three-dimensional image reconstruction based on the synthesis of tools for calculating Mellin transform functions, initial values of centroids, and the formation of a suboptimal set of variables are proposed. The identification software package in C++ was developed and implemented in the CUDA parallel computing environment. © 2023 IEEE.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Fractal Measurement of Images Human Brain from MRI

Fractal Measurement of Images Human Brain from MRI

引用

2024 Cognitive Models and Artificial Intelligence Conference, AICCONF 2024

作者： Anarova, Shahzoda Jabbarov, Jamoliddin Uralova, Iroda Tashkent University of Information Technologies Department of Convergence of digital technologies Computer Engineering Faculty Tashkent Uzbekistan Department of Computer science and technology Intelligent systems and computer technologies Faculty Samarkand State University Samarkand Uzbekistan

ISBN: (纸本)9798400716928

This article is devoted to the determination of the fractal size of the damaged part of the human brain on the basis of images obtained from MRI (magnetic resonance imaging). There are various mathematical methods for determining the size of fractal structures, this article uses two variants of the cell counting method and describes the analysis of errors in determining the fractal size of the damaged part of the human brain. The article shows that the damaged part of the human brain has a fractal structure and that it has a fractal dimension. Fractal measurement has also been used to determine the size of the damaged part of the human brain, unlike common methods. In determining the fractal scale, cases of changes in human body organs were not taken into account. In the article, the determination of the size of the damaged part of the human brain is studied on the basis of mathematical formulas. Two different variants of the special cell counting method were used to calculate the fractal measurements, as well as the corresponding number of experimental results. In addition, these measurements were used to assess the extent to which patients suffered brain damage and to provide information on the practical application of these fractal measurements. © 2024 ACM.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

A graph-based method for identity resolution to assist police force investigative process

引用

Journal of Cyber Security Technology 2025年第2期9卷 127-150页

作者： Amirhosseini, Mohammad Hossein Kazemian, Hassan Phillips, Michael Department of Computer Science and Digital Technologies University of East London London United Kingdom Intelligent Systems Research Centre School of Computing and Digital Media London Metropolitan University London United Kingdom

The ability to prove an individual identity has become crucial in social, economic, and legal aspects of life. Identity resolution is the process of semantic reconciliation that determines whether a single identity is the same when being described differently. This paper introduces a novel graph-based methodology for identity resolution, designed to reconcile identities by analysing the similarity of attribute values associated with different identities within a policing dataset. The proposed methodology employs graph analysis techniques, including centrality measurement and community detection, to enhance the identity resolution process. This paper also presents a new identity model for identity resolution. SPIRIT policing dataset was used for testing the proposed methodology. This dataset is an anonymised dataset used in the SPIRIT project funded by EU Horizon. It contains 892 identity records and among these, two ’known’ identities utilize different names but actually represent the same individual. The presented method successfully recognised these two identities. Additionally, another experimental evaluation was conducted on a refined and extended version of the dataset and the false identities were successfully detected. This method can assist police forces in identifying criminals and fraudsters using fake identities and has applications across finance, marketing, and customer service. © 2024 The Author(s). Published by Informa UK Limited, trading as Taylor & Francis Group.

关键词： Statistical tests

来源：评论

学校读者我要写书评

暂无评论

Modeling and Simulating more efficient and reliable fuel cell vehicles through enhancing the integration of the 6kW PEM fuel cell stack with DC/DC boost converter and BLDC motor 33

Modeling and Simulating more efficient and reliable fuel cel...

引用

33rd Southern African Universities Power Engineering Conference, SAUPEC 2025

作者： Mtumka, Olona Krishnamurthy, Senthil Cape Peninsula University of Technology Bellville Center for Intelligent Systems and Emerging Technologies Department of Electrical Electronic and Computer Engineering Cape Town7530 South Africa

ISBN: (纸本)9798331535162

This study focuses on enhancing the integration of the PEM fuel cell, DC/DC boost converter, and BLDC motor, which help to develop more efficient and dependable fuel cell vehicles. The development of renewable energy sources for power generation has received much attention due to the depletion of fossil fuel supplies worldwide and economic difficulties. Fuel cells are one of the most efficient and cleanest power generation methods. Polymer electrolyte membrane (PEM) fuel cell is the preferred type of fuel cell for vehicles because of its high energy density, fast start-up, and lack of pollution. This paper aims to model and simulate a PEM fuel cell stack to power a Brushless DC (BLDC) motor for a fuel cell vehicle to reduce emissions in the transportation sectors. A boost converter is implemented to boost the output voltage of the PEM fuel cell stack to 100 V. The paper utilizes the trapezoidal commutation of the BLDC motor to drive the inverter. The trapezoidal commutation uses the six-switching technique to control the inverter's phase currents. The variation of fuel flow rate and drive cycle are included to observe the effect on the operation of the fuel cell stack. The paper presents the modeling and simulation of the PEM Fuel cell stack to improve power conversion, energy management, and vehicle control, helping to make fuel cell vehicles more viable for widespread adoption in the future. © 2025 IEEE.

关键词： Brushless DC motors

来源：评论

学校读者我要写书评

暂无评论

Optimization of Micro-Object Identification with Factorization and Correction Mechanisms for Distorted Image Points

Optimization of Micro-Object Identification with Factorizati...

引用

International Russian Smart Industry Conference (SmartIndustryCon)

作者： Isroil I. Jumanov Rustam A. Safarov Olimjon I. Djumanov Intelligent systems and computer technologies Samarkand state university Samarkand Uzbekistan

ISBN: (数字)9798331511241

ISBN: (纸本)9798331511258

The scientific and methodological foundations for the optimal identification of micro-objects with mechanisms for using information structural components, features, statistical and dynamic characteristics of images have been developed. Mechanisms for tracking, detecting and correcting distorted points, factorizing the structural components of the image, filtering, segmentation, tracking distorted points under conditions of a priori insufficiency, parametric uncertainty, and low reliability of information processing are proposed. Methods for converting the initial brightness of a point into homogeneous objects as a function of two variables have been studied and nonlinear optimization functionals have been used. Mechanisms for factorization of the structural components of the image in the form of an indicator of linear connectivity, “neighborhood relationship” of three separate algorithms have been implemented. An alternative image factorization algorithm has been developed. A comparative analysis of effectiveness was carried out. The effectiveness of the mechanisms for detecting and correcting distorted points was studied using the criterion of the probability of undetected errors, the root-mean-square error, according to Shannon's estimates, the average level of intensity of the points, and the total compactness parameter. Rank estimates of integral indicators of image factorization were obtained for 30 images with 100 tests. A software package for visualization, recognition, and classification of images of microobjects has been developed, the implementations of which have been tested using real medical diagnostic data.

关键词： Image segmentation Uncertainty Software packages Nonlinear distortion Brightness Noise Information processing Reliability Object recognition Optimization

来源：评论

学校读者我要写书评

暂无评论

Multi-Class Vehicle Detection and Classification with YOLO11 on UAV-Captured Aerial Imagery 7

Multi-Class Vehicle Detection and Classification with YOLO11...

引用

7th IEEE International Conference on Actual Problems of Unmanned Aerial Vehicles Development, APUAVD 2024

作者： Bakirci, Murat Dmytrovych, Petro Bayraktar, Irem Anatoliyovych, Oleh Tarsus University Unmanned/Intelligent Systems Lab Faculty of Aeronautics and Astronautics Mersin Turkey Ivan Franko National University of Lviv Faculty of Electronics and Computer Technologies Lviv Ukraine

ISBN: (纸本)9798331534141

Aerial imaging and object detection using unmanned aerial vehicle (UAV) systems pose unique challenges, including varying altitudes, dynamic backgrounds, and changes in lighting and weather conditions. These factors complicate the detection process, demanding robust and adaptive algorithms. Furthermore, the need for real-time processing in UAV applications imposes stringent requirements on computational efficiency and resource management. This study presents a comparative analysis of the cutting-edge object detection algorithm YOLO11, specifically tailored for vehicle detection in UAV-captured traffic images. Using a custom dataset derived from UAV aerial imaging, the algorithm was trained and evaluated to assess both its performance in terms of speed and accuracy, and the results were compared with YOLOv10. Experimental findings indicate that while YOLOv10 achieves slightly faster inference speeds, YOLO11 offers marginally better detection accuracy. © 2024 IEEE.

关键词： Adaptive algorithms

来源：评论

学校读者我要写书评

暂无评论

Challenges and Advances in UAV-Based Vehicle Detection Using YOLOv9 and YOLOv10 7

Challenges and Advances in UAV-Based Vehicle Detection Using...

引用

7th IEEE International Conference on Actual Problems of Unmanned Aerial Vehicles Development, APUAVD 2024

ISBN: (纸本)9798331534141

Aerial imaging and object detection with unmanned aerial vehicle (UAV) systems present unique challenges, including varying altitudes, dynamic backgrounds, and changes in lighting and weather conditions. These factors complicate the detection process, demanding robust and adaptive algorithms. Furthermore, the need for real-time processing in UAV applications imposes stringent requirements on computational efficiency and resource management. This study presents a comparative analysis of two cutting-edge object detection algorithms, YOLOv9 and YOLOv10, specifically tailored for vehicle detection in UAVcaptured traffic images. Leveraging a custom dataset derived from UAV aerial imaging, both algorithms were trained and evaluated to assess their performance in terms of speed and accuracy. The experimental results reveal that while YOLOv9 demonstrates a marginally superior inference speed, YOLOv10 excels slightly in detection accuracy. © 2024 IEEE.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Automatic extraction of lightweight and efficient neural network architecture of heavy convolutional architectures to predict microsatellite instability from hematoxylin and eosin histology in gastric cancer

引用

Neural Computing and Applications 2024年第25期36卷 15295-15321页

作者： Rostami, Habib Ashkpour, Maryam Behzadi-Khormouji, Hamed Mokhtari, Maral Khayati, Armin Keshavarz, Ahmad Talatian Azad, Saeed Tabesh, Yahya Computer Engineering Department Faculty of Intelligent Systems Engineering and Data Science Persian Gulf University Bushehr75168 Iran Artificial Intelligence and Intelligent Healthcare Lab Artificial Intelligence and Data Mining Research Group Faculty of Intelligent Systems Engineering and Data Science ICT Research Institute Persian Gulf University Bushehr75168 Iran Faculty of New Science and Technologies University of Tehran Tehran Iran Department of Computer Science Imec-IDLab University of Antwerp Sint-Pietersvliet 7 Antwerp2000 Belgium Shahid Faghihi Hospital Shiraz University of Medical Sciences Shiraz Iran Department of Computer Science Engineering and IT School of Electrical and Computer Engineering Shiraz University Shiraz Iran Electrical Engineering Department Faculty of Intelligent Systems Engineering and Data Science Persian Gulf University Bushehr75168 Iran IoT and Signal Processing Research Group Faculty of Intelligent Systems Engineering and Data Science ICT Research Institute Persian Gulf University Bushehr75168 Iran Department of Mathematical Sciences Sharif University of Technology Tehran Iran

Cancers have emerged as a significant concern due to their impact on public health and society. The examination and interpretation of tissue sections stained with Hematoxylin and Eosin (H&E) play a crucial role in disease assessment, particularly in cases like gastric cancer. Microsatellite instability (MSI) is suggested to contribute to the carcinogenesis of specific gastrointestinal tumors. However, due to the nonspecific morphology observed in H&E-stained tissue sections, MSI determination often requires costly evaluations through various molecular studies and immunohistochemistry methods in specialized molecular pathology laboratories. Despite the high cost, international guidelines recommend MSI testing for gastrointestinal cancers. Thus, there is a pressing need for a new diagnostic modality with lower costs and widespread applicability for MSI detection. This study aims to detect MSI directly from H&E histology slides in gastric cancer, providing a cost-effective alternative. The performance of well-known deep convolutional neural networks (DCNNs) and a proposed architecture are compared. Medical image datasets are typically smaller than benchmark datasets like ImageNet, necessitating the use of off-the-shelf DCNN architectures developed for large datasets through techniques such as transfer learning. Designing an architecture proportional to a custom dataset can be tedious and may not yield desirable results. In this work, we propose an automatic method to extract a lightweight and efficient architecture from a given heavy architecture (e.g., well-known off-the-shelf DCNNs) proportional to a specific dataset. To predict MSI instability, we extracted the MicroNet architecture from the Xception network using the proposed method and compared its performance with other well-known architectures. The models were trained using tiles extracted from whole-slide images, and two evaluation strategies, tile-based and whole-slide image (WSI)-based, were employed and comp

关键词： Network architecture

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：