检索结果-内蒙古大学图书馆

Revolutionary entrapment model of uniformly distributed swarm robots in morphogenetic formation

Defence Technology（防务技术） 2024年第1期31卷 496-509页

作者： Chen Wang Zhaohui Shi Minqiang Gu Weicheng Luo Xiaomin Zhu Zhun Fan Shantou University ShantouGuangdongChina National University of Defense Technology ChangshaChina Key Lab of Digital Signal and Image Processing of Guangdong Province China

This study proposes a method for uniformly revolving swarm robots to entrap multiple targets,which is based on a gene regulatory network,an adaptive decision mechanism,and an improved *** the gene regulatory network method,the robots can generate entrapping patterns according to the environmental input,including the positions of the targets and ***,an adaptive decision mechanism is proposed,allowing each robot to choose the most well-adapted capture point on the pattern,based on its *** robots employ an improved Vicsek-model to maneuver to the planned capture point smoothly,without colliding with other robots or *** proposed decision mechanism,combined with the improved Vicsek-model,can form a uniform entrapment shape and create a revolving effect around targets while entrapping *** study also enables swarm robots,with an adaptive pattern formation,to entrap multiple targets in complex *** robots can be deployed in the military field of unmanned aerial vehicles’(UAVs)entrapping multiple *** experiments demonstrate the feasibility and superiority of the proposed gene regulatory network method.

关键词： Swarm intelligence Revolutionary entrapment Flocking Robots Gene regulatory network Vicsek-model Entrapping multiple targets

来源：评论

学校读者我要写书评

暂无评论

Research on state monitoring of bridge cable based on optical fiber sensing technology 21

Research on state monitoring of bridge cable based on optica...

引用

21st International Conference on Optical Communications and Networks, ICOCN 2023

作者： Xu, Chunying Wu, Xinjie Liang, Ruixin Zhou, Yu Yang, Chengyu Wei, Chuliang College of Enineering Guangdong Province Shantou515013 China Guangdong Provincial Key Laboratory of Digital Signal and Image Processing China

ISBN: (纸本)9798350343502

In this paper, the strain and vibration of the bridge cable and its compensation device were monitored using fiber optic grating (FBG) sensing technology on the Zhoushan-Daishan Bridge in Zhoushan, Zhejiang Province. During the monitoring period, the bridge experienced two typhoon events. The strain and vibration signals were analyzed. The results showed that the typhoon 'Muifa' had a greater impact on the Zhoushan-Daishan Bridge than typhoon 'Hinnamnor'. And there was no movement of the expansion compensation device during the monitoring period. © 2023 IEEE.

关键词： Vibration analysis

来源：评论

学校读者我要写书评

暂无评论

Automatic Pavement Crack Detection Based on YOLOv5-AH 12

Automatic Pavement Crack Detection Based on YOLOv5-AH

引用

12th International Conference on CYBER Technology in Automation, Control, and Intelligent Systems, CYBER 2022

作者： Dong, Zhaohui Zhu, Guijie Fan, Zhun Liu, Jiacheng Li, Huanlin Cai, Yuwei Huang, Huaxing Shi, Ze Ning, Weibo Wang, Liu Guangdong Provincial Key Laboratory of Digital Signal and Image Processing College of Engineering Shantou University Shantou515063 China

ISBN: (数字)9781665472678

ISBN: (纸本)9781665472678

Object detection on pavement cracks plays a significant role in the overall condition assessment of the pavement. However, the automatic crack detection remains a tough work due to the complex background and the scale change. In order to solve the related issues, a deep learning model named YOLOv5-AH is proposed on the basis of the YOLOv5. We integrate convolutional block attention module (CBAM) to extract attention area, which can emphasize the crack features and suppress the background information. Moreover, we optimize the network architecture by adding one more prediction head to detect different-scale cracks. To further improved our proposed YOLOv5-AH, a series of advanced strategies are integrated into the model training including data augmentation. A pavement crack dataset in different enviroments is built by a mobile robot. The precision and recall of our crack detection method reach 0.924 and 0.988 respectively. The prediction speed of the model can achieve real-time effect (72FPS). © 2022 IEEE.

关键词： Crack detection

来源：评论

学校读者我要写书评

暂无评论

Predefined-Time Consensus Tracking Control of Multi-Agent Systems With Resilience to Communication Link Attacks

Predefined-Time Consensus Tracking Control of Multi-Agent Sy...

引用

2022 Chinese Automation Congress, CAC 2022

作者： Wang, Yani Liu, Yangyang Lu, Minyin Zou, An-Min College of Engineering Shantou University Shantou China Guangdong Provincial Key Laboratory of Digital Signal and Image Processing Shantou China

ISBN: (纸本)9781665465335

With consideration of communication link attacks, the distributed predefined-time consensus control issue of multi-agent systems is studied. First, a distributed resilient predefined-time observer is introduced to obtain an exact estimation of the states of the leader within predefined time. Second, a predefined-time consensus control protocol is proposed. The rigorous proof demonstrates that all follower agents can reach a common state within predefined time. At last a numerical example is presented to show the effectiveness of the resilient predefined-time controller. © 2022 IEEE.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

On Visualizing Music Storage Media for Modern Access to Historic Sources

On Visualizing Music Storage Media for Modern Access to Hist...

引用

24th Eurographics Conference on Visualization, EuroVis 2022

作者： Khulusi, R. Fricke, H. Image and Signal Processing Group Leipzig University Germany Research Center Digital Organology Leipzig University Germany

ISBN: (纸本)9783038681854

Finding a balance between conserving historic objects and using them for research is one of the big issues in historic collections. Digitization holds the opportunity to offer a safe and non-destructible access to historic objects, making them available for research. With this poster, we want to give insight into our planned visualization system, using close and distant reading access for visual analysis approaches and allowing musicologists novel approaches to normally fragile and endangered media. © 2022 The Author(s) Eurographics Proceedings © 2022 The Eurographics Association.

关键词：

来源：评论

学校读者我要写书评

暂无评论

MB-CapsNet: An Efficient Fusion of MobileNetV3 and Matrix Capsule Networks

MB-CapsNet: An Efficient Fusion of MobileNetV3 and Matrix Ca...

引用

2022 Chinese Automation Congress, CAC 2022

作者： Han, Wenxing Zou, An-Min Shantou University Guangdong Provincial Key Laboratory of Digital Signal and Image Processing Dept. of Electronic and Information Engineering Shantou China

ISBN: (纸本)9781665465335

The capsule network constructs the relationship between the part and the whole in an image through feature coding, which shows excellent performance in the image classification. However, the original capsule network is weak in extracting useful feature information, because it tends to explain all the information in a graph and the advantages of the capsule network cannot be reflected in the face of complex background datasets. By using MobileNetV3 as the backbone to replace the simple primary convolutional network layer, an improved capsule network named MB-CapsNet is proposed in this paper. The advanced network reducing the interference of invalid features to focus on effective features. At the same time, a variety of parameter sets are employed and extensive experiments are proceeded on four kinds of datasets. After that, an optimal network configuration is obtained which is suitable for different datasets. The experimental results illustrate that the advanced MB-CapsNet is more effectively than the original capsule network in the feature extraction, showing its advantages and potential in complex datasets. © 2022 IEEE.

关键词： image classification

来源：评论

学校读者我要写书评

暂无评论

ConvNextUNet: A small-region attentioned model for cardiac MRI segmentation

引用

Computers in Biology and Medicine 2024年 177卷 108592-108592页

作者： Zhang, Huiyi Cai, Zemin The Department of Electronic Engineering Shantou University Guangdong Shantou515063 China Key Laboratory of Digital Signal and Image Processing of Guangdong Province Guangdong Shantou515063 China

Cardiac MRI segmentation is a significant research area in medical image processing, holding immense clinical and scientific importance in assisting the diagnosis and treatment of heart diseases. Currently, existing cardiac MRI segmentation algorithms are often constrained by specific datasets and conditions, leading to a notable decrease in segmentation performance when applied to diverse datasets. These limitations affect the algorithm's overall performance and generalization capabilities. Inspired by ConvNext, we introduce a two-dimensional cardiac MRI segmentation U-shaped network called ConvNextUNet. It is the first application of a combination of ConvNext and the U-shaped architecture in the field of cardiac MRI segmentation. Firstly, we incorporate up-sampling modules into the original ConvNext architecture and combine it with the U-shaped framework to achieve accurate reconstruction. Secondly, we integrate Input Stem into ConvNext, and introduce attention mechanisms along the bridging path. By merging features extracted from both the encoder and decoder, a probability distribution is obtained through linear and nonlinear transformations, serving as attention weights, thereby enhancing the signal of the same region of interest. The resulting attention weights are applied to the decoder features, highlighting the region of interest. This allows the model to simultaneously consider local context and global details during the learning phase, fully leveraging the advantages of both global and local perception for a more comprehensive understanding of cardiac anatomical structures. Consequently, the model demonstrates a clear advantage and robust generalization capability, especially in small-region segmentation. Experimental results on the ACDC, LVQuan19, and RVSC datasets confirm that the ConvNextUNet model outperforms the current state-of-the-art models, particularly in small-region segmentation tasks. Furthermore, we conducted cross-dataset training and testin

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

Research on state monitoring of bridge cable based on optical fiber sensing technology

Research on state monitoring of bridge cable based on optica...

引用

International Conference on Optical Communications and Networks (ICOCN)

作者： Chunying Xu Xinjie Wu Ruixin Liang Yu Zhou Chengyu Yang Chuliang Wei College of Enineering Shantou Guangdong Province China Guangdong Provincial Key Laboratory of Digital Signal and Image Processing

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Cooperative Gene Regulatory Network Target Entrapping in GNSS-denied Environments 12

A Cooperative Gene Regulatory Network Target Entrapping in G...

引用

12th International Conference on CYBER Technology in Automation, Control, and Intelligent Systems, CYBER 2022

作者： Shi, Ze Fan, Zhun Ma, Peili Hong, Juncao Li, Wenji Zhu, Guijie Huang, Huaxing Cai, Yuwei Dong, Zhaohui Zhu, Xiaomin Guangdong Provincial Key Laboratory of Digital Signal and Image Processing College of Engineering Shantou University Shantou515063 China College of Systems Engineering National University of Defense Technology China

ISBN: (数字)9781665472678

ISBN: (纸本)9781665472678

In recent years, the use of gene regulatory network (GRN) to guide swarm robots for target-entrapping tasks has received increasing attention. Even though many GRN-based algorithms for swarm aggregation morphogenesis generation are designed and verified in two-dimensional space, they are not suit-able for target trapping in three-dimensional space with GNSS-denied environments. Therefore, we propose a cooperative GRN (Co-GRN), which can guide swarm robots to complete target-entrapping tasks in GNSS-denied three-dimensional environments. The average distance and enveloping strength are analysed in several simulated scenes, and the effectiveness and flexibility of the proposed method are verified. © 2022 IEEE.

关键词： Genes

来源：评论

学校读者我要写书评

暂无评论

Pipeline Leak Detection, Location and Repair 11

Pipeline Leak Detection, Location and Repair

引用

11th IEEE Annual International Conference on CYBER Technology in Automation, Control, and Intelligent Systems, CYBER 2021

作者： Lin, Peihan Li, Xiaoming Long, Zhoubin Ma, Peili Zhu, Guijie Wei, Jiahong Fan, Zhun Engineering College Shantou University Department of Key Lab of Digital Signal and Image Processing of Guangdong Province Shantou China

ISBN: (纸本)9781665425278

Pipeline leak-sealing under the high pressure and temperature condition is the way to repair a pipeline while the equipment is in continuous work in a power plant or chemical plant. At present, most of this work is carried out by operators with carrying heavy pipeline repairing tools. However, the medium transported by the pipeline is high temperature and high pressure, even acidic or corrosive, which is dangerous to the operators. In order to solve this issue, a pipeline leak-sealing robot is designed to replace the operators to perform pipeline leak-sealing tasks. Furthermore, we design and develop a caulking actuator for the pipeline leak-sealing task and applied a deep learning method to locate the leak points on the pipeline. The experimental results demonstrate that the caulking actuator achieves good performance to repair pipeline leaks, and the accuracy of the method for locating pipeline leaks meets the demand for leak location. © 2021 IEEE.

关键词： Chemical plants

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：