检索结果-内蒙古大学图书馆

2024 China Automation Congress, CAC 2024

作者： Zhao, Ming Pi, Han-Lin Zhang, Jiao-Yang Wang, Bo Liu, Lei Fan, Huijin National Key Laboratory of Multispectral Information Intelligent Processing Technology School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China

ISBN: (纸本)9798350368604

In this paper, we deal with the complex mission planning problem for unmanned aerial vehicles (UAVs) via a multiple objective hybrid neighborhood search approach, in which resource allocation, task assignment and flight profile selection are incorporated in a unified framework. Three objective functions, namely, the maximum completion time, the total energy consumption and the task payback are optimized. To address the coupled submissions simultaneously, we propose a Multi-Objective Hybrid Adaptive Large Neighborhood Search (MO-HALNS) algorithm which extends the conventional Adaptive Large Neighborhood Search (ALNS) algorithm to a muli-objective version by using a population-based approach. Additionally, an evolutionary mechanism is developed, thereby managing the Pareto-optimal fronts while reducing computational costs. Simulation results demonstrate the effectiveness and superiority of the proposed framework. © 2024 IEEE.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

Permittivity inversion of GPR images based on Deeplab 3

Permittivity inversion of GPR images based on DeepLab

引用

3rd International Conference on Artificial Intelligence and Computer Engineering, ICAICE 2022

作者： Liu, Hongwei Wang, Jinpeng Talukdar, Masud Yuan, Da Key Laboratory of Intelligent Information Processing Shandong Technology and Business University Yantai Shandong264005 China

ISBN: (纸本)9781510663473

Ground Penetrating Radar (GPR) is usually used to detect unknown underground structure information, but it is very difficult to extract the underground target structure information from original GPR signal. This paper aims to solve the inversion problem by deep learning method. The two-dimensional ground penetrating radar B-scan signal is converted into intuitive underground structure information by neural network. In this paper, the Deeplab network proposed by Google is improved to solve the problem of permittivity inversion of GPR signal images. We verify the network using simulated data, which is generated by Finite Difference Time Domain (FDTD) algorithm. Finally we quantitatively evaluate the performance of our network by comparing it with some existing deep learning inversion networks. © 2023 SPIE.

关键词： Permittivity

来源：评论

学校读者我要写书评

暂无评论

Controllability of neighborhood Corona product networks

引用

Science China(information Sciences) 2024年第12期67卷 327-328页

作者： Bo LIU Xuan LI Qiang ZHANG Junjie HUANG Housheng SU Ministry of Education Key Laboratory for Intelligent Analysis and Security Governance of Ethnic Languages School of Information Engineering Minzu University of China School of Mathematical Sciences Inner Mongolia University Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China School of Artificial Intelligence and Automation Huazhong University of Science and Technology

Controlling networks aims to study the models, structures,and related dynamics of complex networks. The primary problem of controlling networks is to determine whether they are controllable. Nowadays, controllability has been widely studied and applied to system engineering and control theory, power systems, aerospace, and quantum systems. Various classical criteria include the Gram matrix criterion, Kalman rank criterion, and PBH test.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Adaptive Tracking of Uncertain Markovian Jump Nonlinear Systems With Random Actuator Faults

Adaptive Tracking of Uncertain Markovian Jump Nonlinear Syst...

引用

2024 China Automation Congress, CAC 2024

作者： Zhang, Jiao-Yang Fan, Huijin Liu, Lei Wang, Bo National Key Laboratory of Multispectral Information Intelligent Processing Technology School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China

ISBN: (纸本)9798350368604

This article deals with the adaptive fault-tolerant tracking problem for uncertain Markovian jump nonlinear systems (MJNSs) in a stochastic framework. A joint and a scalar Markovian process are employed to describe behaviors of the unknown parameters and actuator faults, respectively, thereby characterizing uncertainties in a random manner. With the aid of the backstepping technique, an adaptive tracking controller as well as the corresponding parameter update laws is constructed by treating the regimes of all Markovian variables as constants. It is shown that with appropriate design parameters, the output tracking error can converge into a small adjustable residual set in the sense of mean quadratic value while all closed-loop signals are bounded in probability, regardless of infinite number of random abrupt jumps in both uncertain parameters and the control input. An illustrative example is provided to show the effectiveness of the theoretical results. © 2024 IEEE.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

Time-varying Formation-containment Tracking Control of Heterogeneous Multi-agent System under Denial of Service Attack and Sensor Fault

Time-varying Formation-containment Tracking Control of Heter...

引用

2024 China Automation Congress, CAC 2024

作者： Niu, Baojian Fan, Huijin Liu, Lei Wang, Bo National Key Laboratory of Multispectral Information Intelligent Processing Technology School of Artificial Intelligence and Automation Huazhong University of Science and Technology Hubei Wuhan China

ISBN: (纸本)9798350368604

In this paper, the problem of output-feedback time-varying formation-containment tracking control for heterogeneous multi-agent systems with sensor fault under distributed denial of service (DoS) attacks is studied. The leaders are non-cooperative, which are embedded with unknown input. Firstly, in order to estimate the sensor fault and the states of the followers, a distributed fault-detecting observer is designed. Secondly, in order to deal with distributed DoS attacks and the unknown input of the leaders, a leader state estimator is designed. Finally, a distributed output-feedback containment control law is proposed to realize the time-varying formation tracking of the convex hull of multiple leaders. It is proved that the proposed control scheme guarantees the exponential convergence of all errors of the multi-agent system, and the effectiveness and superiority of the proposed scheme are verified by simulation experiments. © 2024 IEEE.

关键词： Denial-of-service attack

来源：评论

学校读者我要写书评

暂无评论

A Dual-Branch Network Based on ViT and Mamba for Semantic Segmentation of Remote Sensing Image 2

A Dual-Branch Network Based on ViT and Mamba for Semantic Se...

引用

2nd IEEE International Conference on Signal, information and Data processing, ICSIDP 2024

作者： An, Ke Wang, Ying Chen, Liang Wang, Yupie Beijing Institute of Technology National Key Laboratory for Space-Born Intelligent Information Processing Beijing China Shanghai Academy of Spaceflight Technology Shanghai China

ISBN: (纸本)9798331515669

Semantic segmentation of remote sensing images has significant applications across various scenarios. The prevailing frameworks include Convolutional Neural Network (CNN) and Transformer. However, CNN is limited by the receptive field of convolutions, while the Transformer is constrained by computational complexity, which restricts attention calculations to local windows and fails to effectively address long-range dependency modeling. The efficient Mamba architecture, characterized by linear complexity, offers a promising solution to these challenges. Inspired by Mamba, we propose a dual-branch network based on ViT and Mamba. The Vision Transformer (ViT) branch incorporates the Swin Transformer to model spatial details while maintaining computational complexity within acceptable bounds. Complementarily, the Mamba branch efficiently captures global context and long-range dependencies. Additionally, to suppress noise and conflicting information arising from the fusion of features from different frameworks, we design the Cross-Model Fusion Module (CMFM) and the Cross-Model Relevance Loss (CMRLoss) to achieve semantic consistency in the fusion process. The comprehensive experimental findings on the commonly utilized GaoFen-2 and iSAID datasets clearly illustrate the advantages of our proposed approach compared to the leading methods in the field. © 2024 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

A joint sparse Bayesian learning for wideband DOA estimation

A joint sparse Bayesian learning for wideband DOA estimation

引用

2024 Conference on Spectral technology and Applications, CSTA 2024

作者： Zhao, Yonghong Liu, Jisong Wang, Junlong Dong, Shuxin Shannxi Key Laboratory of Complex System Control and Intelligent Information Processing Department of Automation and Information Engineering Xi'an University of Technology Shaanxi Xi'an710048 China

ISBN: (纸本)9781510683082

Wideband direction of arrival (DOA) estimation using sensor array is a noteworthy problem frequently occurring in many applications involving radar, sonar, and communication. We present a wideband DOA method based on a sparse Bayesian learning of multiple sub-bands jointly with the redundant dictionary matrix at the reference frequency. Explicitly enforcing the focusing operation and the singular value decomposition (SVD) to sensor measurements is motivated by a desire to decrease the computational complexity and storage capacity. A joint sparse Bayesian learning framework is proposed to deal with multiple sub-bands under one segment to obtain the DOA information. Moreover, the proposed method can be directly extended to multiple segments. Comparing to other wideband DOA estimation methods, the proposed method has the advantages of increased resolution, higher accuracy, and correlation of the sources, as well as not requiring the initial angles for the focusing matrix. Simulations are provided to show the effectiveness and improved performance of the proposed method. © 2024 SPIE.

关键词： Direction of arrival

来源：评论

学校读者我要写书评

暂无评论

Fine grained image recognition algorithm based on CNN-Transformer and paired interaction 4

Fine grained image recognition algorithm based on CNN-Transf...

引用

4th International Conference on Neural Networks, information and Communication Engineering, NNICE 2024

作者： Wang, Yu Zhang, Hong Wuhan University of Science and Technology Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial System Wuhan China

ISBN: (纸本)9798350394375

A new fine-grained image recognition algorithm (P-ResViT, Paired Interaction Res50-ViT) based on CNN-Transformer is proposed to address the issue of existing fine-grained image recognition methods based on convolutional neural networks (CNN) lacking attention mechanisms and difficulty in accurately locating key regions, as well as weak ability to extract contextual information and global features. This algorithm introduces paired interaction attention mechanisms to supplement external attention. This algorithm can utilize the self attention mechanism of the Vision Transformer and the external attention mechanism formed by paired image inputs during training to achieve precise positioning, while preserving the inductive bias and local feature extraction capabilities of CNN. Firstly, the fine-tuning improved ResNet-50 completes local feature extraction and obtains high-resolution feature maps. Secondly, the Transformer encodes the tokenized image blocks of the feature map as input sequences for extracting global context. Finally, the Transformer completes global feature extraction and outputs the classification sequence. In addition, two external attention mechanisms were introduced by inputting image pairs during training, including collaborative attention mechanisms for similar images and cross attention mechanisms for heterogeneous images, fully utilizing the correlation information between images. After experimental evaluation, the P-ResViT proposed in this article has reached advanced levels in three fine-grained image datasets CUB, CAR, and AIR. © 2024 IEEE.

关键词： Image recognition

来源：评论

学校读者我要写书评

暂无评论

EXPLORING THE COMMON APPEARANCE-BOUNDARY ADAPTATION FOR NIGHTTIME OPTICAL FLOW 12

EXPLORING THE COMMON APPEARANCE-BOUNDARY ADAPTATION FOR NIGH...

引用

12th International Conference on Learning Representations, ICLR 2024

作者： Zhou, Hanyu Chang, Yi Liu, Haoyue Yan, Wending Duan, Yuxing Shi, Zhiwei Yan, Luxin National Key Lab of Multispectral Information Intelligent Processing Technology School of Artificial Intelligence and Automation Huazhong University of Science and Technology China Huawei International Co. Ltd. China

We investigate a challenging task of nighttime optical flow, which suffers from weakened texture and amplified noise. These degradations weaken discriminative visual features, thus causing invalid motion feature matching. Typically, existing methods employ domain adaptation to transfer knowledge from auxiliary domain to nighttime domain in either input visual space or output motion space. However, this direct adaptation is ineffective, since there exists a large domain gap due to the intrinsic heterogeneous nature of the feature representations between auxiliary and nighttime domains. To overcome this issue, we explore a common-latent space as the intermediate bridge to reinforce the feature alignment between auxiliary and nighttime domains. In this work, we exploit two auxiliary daytime and event domains, and propose a novel common appearance-boundary adaptation framework for nighttime optical flow. In appearance adaptation, we employ the intrinsic image decomposition to embed the auxiliary daytime image and the nighttime image into a reflectance-aligned common space. We discover that motion distributions of the two reflectance maps are very similar, benefiting us to consistently transfer motion appearance knowledge from daytime to nighttime domain. In boundary adaptation, we theoretically derive the motion correlation formula between nighttime image and accumulated events within a spatiotemporal gradient-aligned common space. We figure out that the correlation of the two spatiotemporal gradient maps shares significant discrepancy, benefitting us to contrastively transfer boundary knowledge from event to nighttime domain. Moreover, appearance adaptation and boundary adaptation are complementary to each other, since they could jointly transfer global motion and local boundary knowledge to the nighttime domain. Extensive experiments have been performed to verify the superiority of the proposed method. © 2024 12th International Conference on Learning Representations,

关键词： Optical flows

来源：评论

学校读者我要写书评

暂无评论

Impact of COVID-19 on Residential and Non-residential Power Consumption: A Data-Driven Study 8

Impact of COVID-19 on Residential and Non-residential Power ...

引用

8th Asia Conference on Power and Electrical Engineering, ACPEE 2023

作者： Zhang, Qifan Cao, Xiu Chen, Yang Cao, Yixin Gao, Min Fudan University Shanghai Key Lab of Intelligent Information Processing Department of Computer Science Shanghai China

ISBN: (纸本)9798350345520

In the past few years, the COVID-19 pandemic has affected all aspects of people's daily life. In particular, people in large cities have also been greatly affected. How to accurately and timely evaluate and analyze the impact of COVID-19 on large cities in China is increasingly significant. Based on the four-year power consumption data of a large city in China, this paper examines COVID-19's impact from the perspective of residential and non-residential power *** address the discrepancies in climate and date information, we created COVID-19-Power, a framework that predicts the predicted power consumption of the city in 2020 without the outbreak of COVID-19, and then analyzes the difference in power consumption between the real situation and predicted results. For residential power consumption, we analyze the respective users' behavior citywide, in different districts, and with different historical power consumption habits clustered by the K-means algorithm. On the other hand, for non-residential consumption, we analyze the users citywide, in different regions and industries. The results showed that while the impact of the pandemic on resident power consumption has been small, it is significant for non-residential power consumption, which is independent of geographical location. The regional differences were mainly reflected in the main types of industries. Through these research results, we can understand in detail the impact of the pandemic on residents' lives and industries in China's large cities;Power enterprises can more precisely understand the impact of the pandemic on electrical load, so that power enterprises can adjust power supply strategies more effectively and pertinently. © 2023 IEEE.

关键词： COVID-19

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：