检索结果-内蒙古大学图书馆

An Improved Unsupervised White Blood Cell Classification via Contrastive Learning 1

6th International Conference on Data Mining and Big Data, DMBD 2021

作者： Zhong, Yuning Huang, Maoye Fan, Haoyi Hu, Rong Li, Zuoyong College of Computer Science and Mathematics Fujian University of Technology Fuzhou350118 China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control College of Computer and Control Engineering Minjiang University Fuzhou350121 China School of Information Engineering Zhengzhou University Zhengzhou450001 China

ISBN: (数字)9789811674761

ISBN: (纸本)9789811674754

The classification and counting of white blood cells (WBCs, leukocytes) in blood smears are of great significance for clinicopathological diagnosis. Therefore, the classification of WBCs in the images is a basic task. Most of the existing WBCs classification methods are based on supervised learning, which highly depends on a large number of image labels. To cope with the challenge of image annotation, in this paper, we propose an unsupervised WBCs classification method, which combines the advantages of contrastive learning and a deep clustering algorithm. Specifically, the proposed method firstly employs contrastive learning to pre-train the feature encoder, which is able to improve the similarity of feature coding among the same kind of cell categories. Then, the classical clustering algorithm is used based on the pre-trained image features for unsupervised classification of WBCs. Finally, the high confidence clustering results are fed back to the pre-trained feature encoder, which can be used as the pseudo labels to form a closed loop. Experimental results on a dataset containing 574 leukocyte images demonstrate the effectiveness of the proposed method. © 2021, Springer Nature Singapore Pte Ltd.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

An optimized aes masking method for resisting side channel analysis 8th

An optimized aes masking method for resisting side channel a...

引用

8th International Conference on Computer Engineering and Networks, CENet 2018

作者： Jiao, Ge Li, Lang Zou, Yi College of Computer Science and Technology Hengyang Normal University HengyangHunan421002 China Hunan Provincial Key Laboratory of Intelligent Information Processing and Application HengyangHunan421002 China

ISBN: (纸本)9783030146795

In order to against the side channel analysis attack such as power, electromagnetic waves, and time attack, an optimized masking method is proposed for Advanced Encryption Standard (AES) algorithm in this paper. This scheme adopts random hamming distance mask and offset randomization strategy in the first two rounds, the last round and two rounds randomly selected in the middle of the AES algorithm to ensure the security of each intermediate value. The scheme then adopts fixed-value mask strategy in the five rounds in the middle, which can reduce the time and space consumption to recalculate S box, improve the efficiency of the algorithm and reduce the production cost. To compare with other defence methods, we build a power analysis platform and conduct extensive experiments. The experimental results show that our optimized AES masking method is more secure than the compared methods, and it is able to resist second-order correlation power analysis (CPA) attacks. © Springer Nature Switzerland AG 2020.

关键词： Hamming distance

来源：评论

学校读者我要写书评

暂无评论

Retinal Vessel Segmentation Based on UNet and Edge Detection

Retinal Vessel Segmentation Based on UNet and Edge Detection

引用

IEEE International Symposium on information (IT) in Medicine and Education, ITME

作者： Peixin Yan Zuoyong Li Rong Hu Xinrong Cao College of Computer Science and Mathematics Fujian University of Technology Fuzhou China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Colloge of Computer and Control Engineering Minjiang University Fuzhou China

Retinal vessel segmentation is important for the diagnosis of many diseases. The segmentation of microscopic vessels is one of the challenges because of the complex structure of retinal vessels, which makes it challenging to tell the vessels apart from the background. In order to improve the segmentation performance of retinal vessels, we use the edge detection method of HED to optimize the segmentation effect of UNet. Using Hybrid Dilated Convolution not only increases the perceptual field, but also avoids the loss of information continuity caused by the continuous use of dilated convolution. The Pyramid Pooling Module is used at the end of the encoder to compensate for the information loss caused by downsampling. Finally, the output of edge detection and image segmentation is combined as the final result. The model is evaluated in two mainstream datasets DRIVE and CHASE_DB1, and the experimental results show that the proposed model can improve the performance of retinal vessel segmentation.

关键词： Training Image segmentation Convolution Image edge detection Microscopy Feature extraction Retinal vessels

来源：评论

学校读者我要写书评

暂无评论

Insulator Defect Detection Based on YOLOv4-tiny with Improved Feature Fusion

Insulator Defect Detection Based on YOLOv4-tiny with Improve...

引用

IEEE International Symposium on information (IT) in Medicine and Education, ITME

作者： Yuning Zhong Rong Hu Zuoyong Li Yuanzheng Cai College of Computer Science and Mathematics Fujian University of Technology Fuzhou China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control College of Computer and Control Engineering Minjiang University Fuzhou China

Insulator exposed to a wild environment for long-term running usually suffers from the damage of natural calamities that makes them become one of the most fragile components in the whole power system. In this case, even a slight fault will seriously affect the power supply safety of the power grid. Therefore, it is critical to find and identify the faulty insulator efficiently and accurately. However, an insulator is quite a small component in comparison with a huge power system which makes it hard to visible with naked eyes. This characteristic leads to poor recognition accuracy for existing detection methods. In order to solve the above problems, we propose an insulator defect detection algorithm based on an improved YOLOv4-tiny model. It differs from existing insulator detection models, our algorithm applies the effective channel attention network to the feature extraction network of YOLOv4-tiny, which significantly enhances the feature extraction ability of the backbone network. These two-way features of the pyramid can be fully fused in the two-way feature fusion stages seamlessly. Experimental results show that compared with, our proposed algorithm outperforms Faster RCNN and YOLOv3 in average classification accuracy, missed detection, and false detection.

关键词： Fault diagnosis Power supplies Education Insulators Feature extraction Power grids Safety

来源：评论

学校读者我要写书评

暂无评论

Visual Language Model based Cross-modal Semantic Communication Systems

arXiv

引用

arXiv 2024年

作者： Jiang, Feibo Tang, Chuanguo Dong, Li Wang, Kezhi Yang, Kun Pan, Cunhua Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing Hunan Normal University Changsha China School of Information Science and Engineering Hunan Normal University Changsha China Changsha Social Laboratory of Artificial Intelligence Hunan University of Technology and Business Changsha China The Department of Computer Science Brunel University London United Kingdom The School of Computer Science and Electronic Engineering University of Essex ColchesterCO4 3SQ United Kingdom Changchun Institute of Technology China The National Mobile Communications Research Laboratory Southeast University Nanjing210096 China

Semantic Communication (SC) has emerged as a novel communication paradigm in recent years, successfully transcending the Shannon physical capacity limits through innovative semantic transmission concepts. Nevertheless, extant Image Semantic Communication (ISC) systems face several challenges in dynamic environments, including low semantic density, catastrophic forgetting, and uncertain Signal-to-Noise Ratio (SNR). To address these challenges, we propose a novel Vision-Language Model-based Cross-modal Semantic Communication (VLM-CSC) system. The VLM-CSC comprises three novel components: (1) Cross-modal Knowledge Base (CKB) is used to extract high-density textual semantics from the semantically sparse image at the transmitter and reconstruct the original image based on textual semantics at the receiver. The transmission of high-density semantics contributes to alleviating bandwidth pressure. (2) Memory-assisted Encoder and Decoder (MED) employ a hybrid long/short-term memory mechanism, enabling the semantic encoder and decoder to overcome catastrophic forgetting in dynamic environments when there is a drift in the distribution of semantic features. (3) Noise Attention Module (NAM) employs attention mechanisms to adaptively adjust the semantic coding and the channel coding based on SNR, ensuring the robustness of the CSC system. The experimental simulations validate the effectiveness, adaptability, and robustness of the CSC system. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Multiscale fast correlation filtering tracking algorithm based on a feature fusion model

Multiscale fast correlation filtering tracking algorithm bas...

引用

作者： null null null null null null null School of Computer and Communication Engineering and Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on Transportation Changsha University of Science and Technology Changsha China School of Information Science and Engineering Fujian University of Technology Fujian China Hunan Valin Lianyuan Iron & Steel Corporation Loudi China Electronics & Information School Yangtze University Jingzhou China Hunan Institute of Scientific and Technical Information Changsha China Technical Quality Department Hunan ZOOMLION Heavy Industry Intelligent Technology Corporation Limited Changsha China

关键词： Object tracking

来源：评论

学校读者我要写书评

暂无评论

CHARACTERIZATIONS OF COMPOSITION OPERATORS ON BLOCH AND HARDY TYPE SPACES

arXiv

引用

arXiv 2022年

作者： Chen, Shaolin Hamada, Hidetaka College of Mathematics and Statistics Hengyang Normal University Hunan Hengyang421002 China Hunan Provincial Key Laboratory of Intelligent Information Processing and Application 421002 China Faculty of Science and Engineering Kyushu Sangyo University 3-1 Matsukadai 2-Chome Higashi-ku Fukuoka813-8503 Japan

The main purpose of this paper is to investigate characterizations of composition operators on Bloch and Hardy type spaces. Initially, we use general doubling weights to study the composition operators from harmonic Bloch type spaces on the unit disc ⅅ to pluriharmonic Hardy spaces on the Euclidean unit ball Bn. Furthermore, we develop some new methods to study the composition operators from harmonic Bloch type spaces on ⅅ to pluriharmonic Bloch type spaces on ⅅ. Additionally, some application to new characterizations of the composition operators between pluriharmonic Lipschitz type spaces to be bounded or compact will be presented. The obtained results of this paper provide the improvements and extensions of the corresponding known *** Codes 31C10, 47B33, 32A35, 30H30 Copyright © 2022, The Authors. All rights reserved.

关键词： Harmonic functions

来源：评论

学校读者我要写书评

暂无评论

On Riesz type inequalities, Hardy-Littlewood type theorems and smooth moduli

arXiv

引用

arXiv 2022年

The purpose of this paper is to develop some methods to study Riesz type inequalities, Hardy-Littlewood type theorems and smooth moduli of holomorphic, pluriharmonic and harmonic functions in high-dimensional cases. Initially, we prove some sharp Riesz type inequalities of pluriharmonic functions on bounded symmetric domains. The obtained results extend the main results in (Trans. Amer. Math. Soc. 372 (2019) 4031–4051). Furthermore, some Hardy-Littlewood type theorems of holomorphic and pluriharmonic functions on John domains are established. Additionally, we also discuss the Hardy-Littlewood type theorems and smooth moduli of holomorphic, pluriharmonic and harmonic functions. Consequently, we improve and generalize the corresponding results in (Acta Math. 178 (1997) 143–167) and (Adv. Math. 187 (2004) 146–172).MSC Codes Primary 42A50, 42B30, 46E15, 31B05, 31C10, 32U05 Copyright © 2022, The Authors. All rights reserved.

关键词： Harmonic functions

来源：评论

学校读者我要写书评

暂无评论

A Flexible Two-Stage Constrained Multi-Objective Evolutionary Algorithm Based on Autonomic Regulation

SSRN

引用

SSRN 2022年

作者： Zou, Juan Luo, Jian Liu, Yuan Yang, Shengxiang Zheng, Jinhua Key Laboratory of Intelligent Computing and Information Processing Ministry of Education Computer science College of Xiangtan University Hunan Province Xiangtan China Faculty of Informational Engineering University of Xiangtan Xiangtan411105 China Hunan Provincial Key Laboratory of Intelligent Information Processing and Application Hengyang421002 China School of Computer Science and Informatics De Montfort University LeicesterLE1 9BH United Kingdom

The core element in solving constrained multi-objective problems (CMOPs) with evolutionary algorithms is simultaneously balancing objective optimization and constraint satisfaction. The di ffi culty of maintaining this balance increases significantly for existing algorithms when dealing with complex CMOPs because various complex feasible regions often make CMOPs with very di ff erent characteristics. To address this issue, we propose a more flexible two-stage evolutionary algorithm based on autonomic regulation (ARCMO), which can e ff ectively control evolutionary trends to adapt to complex CMOPs. Specifically, the first stage performs a fast global search and passes the population information to the second stage. The second stage consists of two dynamically complementary sub-processes: named exploration subprocess and convergence subprocess. The ratio of these two sub-processes is dynamically adjusted according to the information from the first stage to adapt to CMOPs with di ff erent complexities. Experiments on several recently proposed benchmark suites and real-world application problems show that ARCMO is more adaptable than the contender algorithms when solving di ff erent complex CMOPs. © 2022, The Authors. All rights reserved.

关键词： Evolutionary algorithms

来源：评论

学校读者我要写书评

暂无评论

A many-objective evolutionary algorithm based on rotation and decomposition

引用

Swarm and Evolutionary Computation 2021年 60卷

作者： Zou, Juan Liu, Jing Yang, Shengxiang Zheng, Jinhua Key Laboratory of Hunan Province for Internet of Things and Information Security Xiangtan University XiangtanHunan411105 China Key Laboratory of Intelligent Computing and Information Processing Ministry of Education Information Engineering College of Xiangtan University XiangtanHunan411105 China Hunan Provincial Key Laboratory of Intelligent Information Processing and Application Hengyang421002 China School of Computer Science and Informatics De Montfort University LeicesterLE1 9BH United Kingdom

Evolutionary algorithms have shown their promise in addressing multiobjective problems (MOPs). However, the Pareto dominance used in multiobjective optimization loses its effectiveness when addressing many-objective problems (MaOPs), which are defined as having more than three objectives. This is because the Pareto dominance loses its ability to distinguish between individuals. In this paper, a many-objective evolutionary algorithm based on rotation and decomposition is proposed (MaOEA-RD) to overcome the shortcoming of insufficient selection pressure caused by the Pareto dominance. First, the coordinates system is rotated and a hyperplane is established to distinguish between the nondominated individuals. Then, a novel individual selection mechanism incorporating decomposition is adopted to maintain the diversity of the population. In order to compensate for the deficiency of the predefined reference vectors, a reference vector adjustment mechanism is proposed. Experimental studies on several well-known benchmark problems show that the proposed algorithm is competitive compared with nine state-of-the-art many-objective algorithms. © 2020 Elsevier B.V.

关键词： Evolutionary algorithms

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：