检索结果-内蒙古大学图书馆

Adaptive consensus of two-time-scale multi-agent systems

INTERNATIONAL JOURNAL OF CONTROL 2021年第4期94卷 943-951页

作者： Wei, Li-Mei Yang, Wu Wang, Yan-Wu Guangxi Univ XingJian Coll Sci & Liberal Arts Nanning Guangxi Peoples R China Huazhong Univ Sci & Technol Sch Automat Wuhan 430074 Hubei Peoples R China Huazhong Univ Sci & Technol Minist Educ Key Lab Image Proc & Intelligent Control Wuhan Hubei Peoples R China Huazhong Univ Sci & Technol Sch Elect & Elect Engn Wuhan Hubei Peoples R China China Three Gorges Univ Hubei Prov Collaborat Innovat Ctr New Energy Micr Yichang Peoples R China

This paper studies the distributed consensus problem of a new class of multi-agent systems, where each agent is represented by the two-time-scale system. Two fully distributed, epsilon-dependent adaptive consensus protocols are designed, namely, the relative states based adaptive protocol and the relative outputs based adaptive protocol. By using the merit of the proposed epsilon-Lyapunov function, some sufficient consensus criteria in terms of well-conditioned linear matrix inequalities are derived. The upper bound of epsilon is also determined. A numerical example for the drying section of a paper converting machine with nine rolls verifies the effectiveness of the proposed results.

关键词： Consensus multi-agent systems two-time-scale feature fully distributed protocol adaptive control strategy

来源：评论

学校读者我要写书评

暂无评论

Attention-inception-based U-Net for retinal vessel segmentation with advanced residual

引用

COMPUTERS & ELECTRICAL ENGINEERING 2022年 98卷 107670-107670页

作者： Wang, Huadeng Xu, Guang Pan, Xipeng Liu, Zhenbing Tang, Ningning Lan, Rushi Luo, Xiaonan Guilin Univ Elect Technol Sch Informat & Commun Guilin 541004 Peoples R China Guilin Univ Elect Technol Guangxi Key Lab Image & Graph Intelligent Proc 1 Jinji Rd Guilin 541004 Guangxi Peoples R China Guangdong Prov Peoples Hosp Guangdong Acad Med Sci Dept Radiol Guangzhou 510080 Peoples R China Natl Local Joint Engn Res Ctr Satellite Nav & Loc Guilin 541004 Peoples R China Peoples Hosp Guangxi Zhuang Autonomous Reg Nanning 530022 Peoples R China

U-Net based methods have been widely used in retinal vessel segmentation tasks. But there are still some obstacles needing to be crossed, such as the loss of microvasculature details at the end of vessels, as well as the interference of the hard exudate produced by lesions. To address these issues, this paper proposes a novel AR-SA U-Net model that integrates residual block with dilated convolution, inception module and an scSE-based attention mechanism. The model also optimizes the upsampling of original U-Net by combining bilinear interpolation and transpose convolution to update their weights dynamically. The experimental results on three retinal vessel image datasets show that the proposed model can eliminate the influence of hard exudate produced by the lesions in the segmentation results, and the segmentation results are clear in detail with high performance. The accuracy of the proposed model on DRIVE, STARE and CHASE_DB1 is 96.11%, 97.78% and 96.79% respectively, which is 1.07%, 1.06% and 1.29% higher than that of original U-Net. The proposed model also shows strong generalization ability in non-fundus medical image datasets.

关键词： Retinal vessel segmentation U-Net Attention mechanism Inception module Residual block

来源：评论

学校读者我要写书评

暂无评论

Safety helmet detection method based on YOLO v4 16

Safety helmet detection method based on YOLO v4

引用

16th International Conference on Computational Intelligence and Security (CIS)

作者： Deng Benyang Lei Xiaochun Ye Miao Guilin Univ Elect Technol Sch Comp & Informat Secur Guilin 541004 Peoples R China Guangxi Key Lab Image & Graph Intelligent Proc Guilin 541004 Peoples R China Guilin Univ Elect Technol Sch Informat & Commun Guilin 541004 Peoples R China

ISBN: (纸本)9781665404457

In the actual production process, safety accidents caused by workers not wearing safety helmets often occur. In order to reduce safety accidents caused by wearing helmets, a helmet detection method based on improved YOLO v4 is proposed. By collecting a self-made data set of on-site construction site video, using the K-means algorithm to cluster the data set in getting appropriately a priori frame dimensional center and obtaining more targeted edge information. Subsequently, a multi-scale training strategy is used in the network training process to improve the adaptability of the model from different scales of detection. The experimental results show that, in the helmet wearing detection task, the model mAP value reached 92.89%, the detection speed reached 15f/s, and its detection accuracy and detection speed were improved compared with YOLO v4, which satisfies the real-time requirements of the helmet detection task.

关键词： safety helmet detection neural network target detection YOLO v4

来源：评论

学校读者我要写书评

暂无评论

Prior Knowledge-Based Probabilistic Collaborative Representation for Visual Recognition

引用

IEEE TRANSACTIONS ON CYBERNETICS 2020年第4期50卷 1498-1508页

作者： Lan, Rushi Zhou, Yicong Liu, Zhenbing Luo, Xiaonan Guilin Univ Elect Technol Guangxi Key Lab Intelligent Proc Comp Image & Gra Guilin 541004 Peoples R China South China Univ Technol Sch Comp Sci & Engn Guangzhou 510006 Peoples R China Univ Macau Dept Comp & Informat Sci Macau 999078 Peoples R China Guilin Univ Elect Technol Guangxi Key Lab Trusted Software Guilin 541004 Peoples R China

Collaborative representation is an effective way to design classifiers for many practical applications. In this paper, we propose a novel classifier, called the prior knowledge-based probabilistic collaborative representation-based classifier (PKPCRC), for visual recognition. Compared with existing classifiers which use the collaborative representation strategy, the proposed PKPCRC further includes characteristics of training samples of each class as prior knowledge. Four types of prior knowledge are developed from the perspectives of image distance and representation capacity. They adaptively accommodate the contribution of each class and result in an accurate representation to classify a query sample. Experiments and comparisons on four challenging databases demonstrate that PKPCRC outperforms several state-of-the-art classifiers.

关键词： Training Visualization Collaboration Probabilistic logic Databases Face recognition Correlation Collaborative representation prior knowledge representation-based classifier visual recognition

来源：评论

学校读者我要写书评

暂无评论

Hyperspectral image classification using multi-feature fusion

引用

OPTICS AND LASER TECHNOLOGY 2019年 110卷 176-183页

作者： Li, Fang Wang, Jie Lan, Rushi Liu, Zhenbing Luo, Xiaonan Guilin Univ Elect Technol Guangxi Coll Guilin 541004 Peoples R China Guilin Univ Elect Technol Univ Key Lab Intelligent Proc Comp Image & Graph Guilin 541004 Peoples R China Guilin Univ Elect Technol Guangxi Key Lab Trusted Software Guilin 541004 Peoples R China

Traditional hyperspectral image (HSI) classification methods typically use the spectral features and do not make full use of the spatial or other features of the HSI. To address this problem, this paper proposes a novel HSI classification method based on a multi-feature fusion strategy. The spectral-spatial features are first extracted by spectral-spatial feature learning (SSFL), which is a deep hierarchical architecture. Additionally, the texture features of the local binary pattern (LBP) image are applied and fused with the spectral-spatial features. Then, the kernel extreme learning machine (KELM) is used to classify the hyperspectral images. The results of a number of experiments show that the proposed method effectively improves the classification accuracy of hyperspectral images.

关键词： Hyperspectral image classification Spectral-spatial feature learning Local binary pattern Feature fusion Kernel extreme learning machine

来源：评论

学校读者我要写书评

暂无评论

Mitosis detection techniques in H&E stained breast cancer pathological images: A comprehensive review

引用

COMPUTERS & ELECTRICAL ENGINEERING 2021年 91卷 107038-107038页

作者： Pan, Xipeng Lu, Yinghua Lan, Rushi Liu, Zhenbing Qin, Zujun Wang, Huadeng Liu, Zaiyi Guilin Univ Elect Technol Guangxi Key Lab Image & Graph Intelligent Proc Guilin 541004 Peoples R China Guangdong Acad Med Sci Guangdong Prov Peoples Hosp Dept Radiol Guangzhou 510080 Peoples R China Guilin Univ Elect Technol Sch Elect Engn & Automat Guilin 541004 Peoples R China

Quantifying mitosis in pathological sections is of great significance in the pathological diagnosis of breast cancer as it is used to evaluate the aggressiveness of the tumor and to provide more comprehensive and reliable information for accurate diagnosis and treatment. In this paper, we summarized the current mainstream methods of mitosis detection and divided them into four categories, namely traditional methods, deep learning methods, methods combining deep learning with traditional methods and other methods. Each method is introduced, and the performance indicators achieved by some of these methods and their results are discussed, compared, and evaluated. We summarize some solutions to the problem of positive and negative sample imbalance in mitotic datasets. Through the review of the research methods in this field, the existing methods of mitosis research in breast cancer are summarized, and the future developments are prospected.

关键词： Breast cancer Mitosis Detection Machine learning Deep learning

来源：评论

学校读者我要写书评

暂无评论

Hyperspectral image Target Detection via Weighted Joint K-Nearest Neighbor and Multitask Learning Sparse Representation

引用

IEEE ACCESS 2020年 8卷 11503-11511页

作者： Ou, Xianfeng Zhang, Yiming Wang, Hanpu Tu, Bing Guo, Longyuan Zhang, Guoyun Xu, Zhi Hunan Inst Sci & Technol Sch Informat & Commun Engn Yueyang 414006 Peoples R China Hunan Inst Sci & Technol Machine Vis & Artificial Intelligence Res Ctr Yueyang 414006 Peoples R China Guilin Univ Elect Technol Guangxi Key Lab Images & Graph Intelligent Proc Guilin 541004 Peoples R China

Multitask sparse representation method improves the detection performance by constructing multiple associated sub-sparse representation tasks and jointly learning multiple sub-sparse representation tasks, and this method can make use of the spectral information. However, the using of spatial information needs to be improved. This paper designs a hyperspectral image target detection method which can both make use of spectral and spatial information, that is a weighted joint k-nearest neighbor and multitask learning sparse representation method (WJNN-MTL-SR) is proposed. This method mainly consists of the following steps:1) using multitask sparse representation to obtain the representation residuals. 2) weighted joint k-nearest neighbor is used into the joint region of test pixels to obtain the weighted joint Euclidean distance. 3) a decision function, combining the weighted joint Euclidean distance and residuals of the multitask sparse representation, is used to get target detection result. Experimental results demonstrate that the proposed method show better detection performance than state-of-the-art methods.

关键词： K-nearest neighbor sparse representation multitask learning hyperspectral image target detection

来源：评论

学校读者我要写书评

暂无评论

An LBP encoding scheme jointly using quaternionic representation and angular information

引用

NEURAL COMPUTING & APPLICATIONS 2020年第9期32卷 4317-4323页

作者： Lan, Rushi Lu, Huimin Zhou, Yicong Liu, Zhenbing Luo, Xiaonan South China Univ Technol Sch Comp Sci & Engn Guangzhou Peoples R China Guilin Univ Elect Technol Guangxi Key Lab Intelligent Proc Comp Image & Gra Guilin Peoples R China Kyushu Inst Technol Dept Mech & Control Engn Kitakyushu Fukuoka Japan Univ Macau Dept Comp & Informat Sci Macau Peoples R China Guilin Univ Elect Technol Guangxi Key Lab Trusted Software Guilin Peoples R China

Local descriptors play a crucial role in numerous computer vision and pattern recognition applications. This paper proposes a novel local descriptor, called the quaternionic local angular binary pattern (QlabP), for color image classification. QlabP is based on the quaternionic representation (QR) of color images such that it is able to handle all color components holistically as well as consider their relations. Using QR, the quaternionic angular information is further developed to account for more color characteristics. We provide two ways to derive the quaternionic angular information from different perspectives. A pattern encoding operation is finally conducted on the obtained angular information to obtain QlabP. The effectiveness of QlabP has successfully been evaluated by comparing with several state-of-the-art descriptors.

关键词： Quaternionic representation (QR) Local binary pattern (LBP) Quaternionic angular information image classification

来源：评论

学校读者我要写书评

暂无评论

Cascading and Residual Connected Network for Single image Superresolution

引用

WIRELESS COMMUNICATIONS & MOBILE COMPUTING 2021年第1期2021卷

作者： Huang, Kai Wang, Wenhao Pang, Cheng Lan, Rushi Li, Ji Luo, Xiaonan Guilin Univ Elect Technol Guangxi Key Lab Image & Graph Intelligent Proc Guilin 541004 Peoples R China Guilin Univ Elect Technol Natl Local Joint Engn Res Ctr Satellite Nav & Loc Guilin 541004 Peoples R China Guilin Huigu Inst Artificial Intelligence Ind Tec Guilin 541004 Peoples R China

Convolution neural networks facilitate the significant process of single image super-resolution (SISR). However, most of the existing CNN-based models suffer from numerous parameters and excessively deeper structures. Moreover, these models relying on in-depth features commonly ignore the hints of low-level features, resulting in poor performance. This paper demonstrates an intriguing network for SISR with cascading and residual connections (CASR), which alleviates these problems by extracting features in a small net called head module via the strategies based on the depthwise separable convolution and deformable convolution. Moreover, we also include a cascading residual block (CAS-Block) for the upsampling process, which benefits the gradient propagation and feature learning while easing the model training. Extensive experiments conducted on four benchmark datasets demonstrate that the proposed method is superior to the latest SISR methods in terms of quantitative indicators and realistic visual effects.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Connected Domain Algorithm Based on Asymmetric Square NAM 16

Connected Domain Algorithm Based on Asymmetric Square NAM

引用

16th International Conference on Computational Intelligence and Security (CIS)

作者： Cen Caichun He Jie Guo Hui WuZhou Univ Sch Elect & Informat Engn Wuzhou Peoples R China WuZhou Univ Guangxi Coll Wuzhou Peoples R China WuZhou Univ Univ Key Lab Image Proc & Intelligent Informat Sy Wuzhou Peoples R China

ISBN: (纸本)9781665404457

Aiming at the problem concerning low determination efficiency of sub-mode position caused by asymmetry in image segmentation with an algorithm in the asymmetric square NAM model image representation, with the aim to realize rapid image marking, the present study improves a peculiar rasterized array data structure, so as to make it satisfy geometric computation. Then, based on the neighbor search algorithm by employing SNAM, a connected domain marking algorithm based on SNAM is proposed. Through comparison of experimental results concerning handling of different binary images with the pixel scanning based connected domain marking algorithm, the connected domain marking algorithm based on quadtree scanning and the connected domain marking algorithm based on SNAM, it is proved that the connected domain marking algorithm based on asymmetric square NAM has high efficiency.

关键词： SNAM connected domain neighbor search

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：