检索结果-内蒙古大学图书馆

Feature refinement attention U-net for enhanced liver segmentation

Engineering Applications of Artificial Intelligence 2025年 157卷

作者： Wang, Hui Liu, Desheng Zhao, Zhilei Wu, Yue Cekderi, Anil Baris State Key Laboratory of Intelligent Control and Decision of Complex Systems School of Automation Beijing Institute of Technology Beijing100081 China College of Information Science & Electronic Technology Jiamusi University Jiamusi154007 China

Developing efficient and accurate automated liver segmentation methods is of far-reaching significance for the prevention, diagnosis, treatment, and prognostic assessment of liver diseases. Artificial intelligence (AI) technology has shown immense potential in various computer vision tasks and has been increasingly adopted in medical image segmentation in recent years. However, conventional neural networks often exhibit limitations in capturing global context capture, constraining their performance in medical image segmentation. To address this challenge, we propose a Feature Refinement Attention U-Net (FRAttU-Net). The architecture is designed with two key components: a High and Low Frequency Feature Fusion and Enhancement Module (HLF3EM) between the encoder and decoder to integrate the multilevel features and enhance the high-level feature representation using edge cues, and an Otsu Density Refinement Module in the output layer to strengthen density information representation and improve the prediction accuracy. Extensive experiments demonstrate that FRAttU-Net achieves state-of-the-art accuracy, outperforming existing methods on multiple datasets. This performance advancement holds considerable potential in improving clinical decision-making in liver disease diagnosis and treatment planning. The code is available at: https://***/HUI623/FRAttU-Net. © 2025 Elsevier Ltd

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

A comprehensive survey on STP approach to finite games

arXiv

引用

arXiv 2021年

作者： Cheng, Daizhan Wu, Yuhu Zhao, Guodong Fu, Shihua Key Laboratory of Intelligent Control and Optimization for Industrial Equipment of Ministry of Education Dalian University of Technology China School of Mathematics and Statistics Shandong Normal University Jinan250014 China School of Mathematical Sciences Liaocheng University Shandong Liaocheng China Key Laboratory of Systems and Control Academy of Mathematics and Systems Sciences Chinese Academy of Sciences Beijing100190 China

Nowadays the semi-tensor product (STP) approach to finite games has become a promising new direction. This paper provides a comprehensive survey on this prosperous field. After a brief introduction for STP and finite (networked) games, a description for the principle and fundamental technique of STP approach to finite games is presented. Then several problems and recent results about theory and applications of finite games via STP are presented. A brief comment about the potential use of STP to artificial intelligence is also proposed. © 2021, CC BY.

关键词： Game theory

来源：评论

学校读者我要写书评

暂无评论

The Emerging intelligent Vehicles and intelligent Vehicle Carriers Collaborative systems

The Emerging Intelligent Vehicles and Intelligent Vehicle Ca...

引用

IEEE Symposium on intelligent Vehicle

作者： Zhipeng Shen Chao Huang Hailong Huang Yutong Wang Fei-Yue Wang Abbas Jamalipour Duc Truong Pham Ljubo Vlacic Andrey V. Savkin Department of Aeronautical and Aviation Engineering the Hong Kong Polytechnic University Hong Kong Department of Industrial and Systems Engineering the Hong Kong Polytechnic University Hong Kong State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China Institute of Engineering Macau University of Science and Technology Macau China School of Electrical and Information Engineering University of Sydney Sydney Australia Department of Mechanical Engineering University of Birmingham Birmingham UK Institute of Intelligent & Integrated Systems and the School of Engineering and Built Environment Griffith University Brisbane Australia School of Electrical Engineering and Telecommunications University of New South Wales Sydney Australia

ISBN: (数字)9798350348811

ISBN: (纸本)9798350348828

In this paper, we propose the innovative use of intelligent Vehicle Carriers (IVCs) as a key solution to address the energy constraints of small-scale unmanned intelligent Vehicles (IVs). IVCs function as both transporters and charging stations, significantly boosting the operational range and efficiency of IVs. Our research delves into the IV-IVC collaborative framework, highlighting the existing challenges, exploring potential solutions, and examining a range of applications. This study offers a visionary approach to revolutionizing intelligent transportation systems by leveraging the synergistic relationship between IVs and IVCs.

关键词： intelligent vehicles Collaboration Charging stations Boosting

来源：评论

学校读者我要写书评

暂无评论

Research on Attention-Based Predictive Model in Multi-Agent Reinforcement Learning

Research on Attention-Based Predictive Model in Multi-Agent ...

引用

Chinese Automation Congress (CAC)

作者： Weixin Hong Huaiyu Wu Zhen Shen Gang Xiong Bin Hu Xisong Dong Fei-Yue Wang The State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China The Beijing Engineering Research Center of Intelligent Systems and Technology Institute of Automation Chinese Academy of Sciences Beijing China The Guangdong Engineering Research Center of 3D Printing and Intelligent Manufacturing Cloud Computing Center Chinese Academy of Sciences Dongguan China

Agent actions planning is a challenging problem in multi-agent reinforcement learning. Recent methods typically build their predictive models by full connection layers, but the shortage of utilizing action and observation information in complex multi-agent environment limits the performance of those methods. To address this issue, we propose a novel predictive model based on self-attention mechanism which can effectively use information in the environment. Specifically, we use the MADDPG algorithm to make a dataset where the input is the observations and actions and the output is the predicted observations and rewards. We also introduce the multi-head attention mechanism into the predictive model so that the predictive model can better combine different information for prediction. We perform extensive experiments to assess the proposed method and compare it with the representative baseline approach. Results demonstrate that our method outperforms competitors with higher accuracy in different tasks. Our implementation will be publicly available.

关键词： Automation Reinforcement learning Predictive models Prediction algorithms Planning Task analysis

来源：评论

学校读者我要写书评

暂无评论

Stability and Stabilization of T-S Fuzzy systems with Sampled-Data controller: A Fuzzy-Related Matrix Injection Method

引用

IEEE Transactions on Fuzzy systems 2025年

作者： Xiong, Du Zhang, Chuan-Ke Jin, Li Fan, Yu-Long He, Yong China University of Geosciences School of Automation Wuhan430074 China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan430074 China Ministry of Education Engineering Research Center of Intelligent Technology for Geo-Exploration Wuhan430074 China

This paper addresses the stability and stabilization issues of Takagi-Sugeno (T-S) fuzzy systems under sampled-data control. In this paper, efforts are dedicated to developing a stability criterion and control strategy with high accuracy and low complexity, leveraging an improved looped functional and a fuzzy-related matrix injection method. First, an improved looped function containing quadratic information about the sampling sawtooth characteristic is employed to include as much system state information as possible in a simple form. In response to the nonlinear terms encountered in the functional derivatives, a fuzzy-related matrix injection method is proposed on the basis of linearization transformation. This method enables the unified treatment of reciprocally convex and quadratic terms, which is conducive to reducing estimation gaps. Based on the aforementioned techniques, stability and stabilization criteria for T-S fuzzy systems are derived. The efficacy and superiority of the proposed method are substantiated through rigorous theoretical analysis and illustrative instances. © 1993-2012 IEEE.

关键词： Sampled data control systems

来源：评论

学校读者我要写书评

暂无评论

Trajectory Tracking Strategy for Gliding Hypersonic Vehicle with Aileron Stuck at an Unknown Angle

引用

Journal of Beijing Institute of Technology 2019年第3期28卷 447-455页

作者： Haibo Ji Lei Wang School of Automation Beijing Institute of TechnologyBeijing 100081China State Key Laboratory of Intelligent Control and Decision of Complex Systems Ministry of EducationBeijing 100081China

A nonlinear robust trajectory tracking strategy for a gliding hypersonic vehicle with an aileron stuck at an unknown position is presented in this paper. First, the components of translational motion dynamics perpendicular to the velocity are derived, and then a guidance law based on a time-varying sliding mode method is used to realize trajectory tracking. Furthermore, the rotational equations of motion are separated into an actuated subsystem and an unactuated subsystem. And an adaptive time-varying sliding mode attitude controller is proposed based on the actuated subsystem to track the command attitude and the tracking performance and robustness are therefore enhanced. The proposed guidance law and attitude controller make the hypersonic vehicle fly along the reference trajectory even when the aileron is stuck at an unknown angle. Finally, a hypersonic benchmark platform is used to demonstrate the effectiveness of the proposed strategy.

关键词： trajectory tracking stuck aileron time-varying sliding mode

来源：评论

学校读者我要写书评

暂无评论

Precedence-constrained path planning of messenger UAV for air-ground coordination

引用

control Theory and Technology 2019年第1期17卷 13-23页

作者： Yulong DING Bin XIN Jie CHEN School of Automation Beijing Institute of Technology Beijing 700087 China Key Laboratory of Intelligent Control and Decision of Complex Systems Beijing Institute of Technology Beijing 100081 China Beijing Advanced Innovation Center for Intelligent Robots and Systems Beijing Institute of Technology Beijing 100081 China

This paper addresses an unmanned aerial vehicle (UAV) path planning problem for a team of cooperating heterogeneous vehicles composed of one UAV and multiple unmanned ground vehicles (UGVs). The UGVs are used as mobile actuators and scattered in a large area. To achieve multi-UGV communication and collaboration, the UAV serves as a messenger to fly over all task points to collect the task information and then flies all UGVs to transmit the information about tasks and UGVs. The path planning of messenger UAV is formulated as a precedence-constrained dynamic Dubins traveling salesman problem with neighborhood (PDDTSPN). The goal of this problem is to find the shortest route enabling the UAV to fly over all task points and deliver information to all requested UGVs. When solving this path planning problem, a decoupling strategy is proposed to sequentially and rapidly determine the access sequence in which the UAV visits task points and UGVs as well as the access location of UAV in the com mu nication n eighborhood of each task point and each UGV. The effectiveness of the proposed approach is corroborated through computational experiments on randomly generated instances. The computational results on both small and large in stances dem on strate that the proposed approach can generate high-quality solutions in a reasonable time as compared with two other heuristic algorithms.

关键词： Air-ground coordination curvature-constrained path planningz precedence constraints Dubins traveling salesman problem

来源：评论

学校读者我要写书评

暂无评论

Analytic Hierarchy Process（AHP） in Portfolio Selection Based on Information Granularity

Analytic Hierarchy Process（AHP） in Portfolio Selection Bas...

引用

第32届中国控制与决策会议

作者： Kaixin Zhao Yaping Dai Ye Ji Jiayi Sun School of Automation Beijing Institute of Technology State Key Laboratory of Intelligent Control and Decision of Complex Systems

Analytic Hierarchy Process（AHP） is a multi criteria decision-making method,which can describe and transform the qualitative problems quantitatively,and then get the quantitative analysis results in accordance with the causal relationship between decision *** this paper,a granular Analytic Hierarchy Process,which introduces the granularity mechanism,is proposed to solve the portfolio selection problem under the mean-risk *** the proposed method,the scale value of scheme layer is no longer limited to nine positive integers from 1 to 9,which gives granularity attributes to the comparison of advantages and disadvantages in a specific criterion layer between different *** proposed method reflects small differences between different alternative schemes through granularity attribute,so it can provide rich decision information for decision *** numeric examples from the real-world financial market（China Shanghai Stock Exchange） are provided to illustrate an essence of the proposed method.

关键词： Analytic Hierarchy Process（AHP） Portfolio Selection Information Granularity Decision-making

来源：评论

学校读者我要写书评

暂无评论

Local Map Construction Based on 3D-LiDAR and Camera

Local Map Construction Based on 3D-LiDAR and Camera

引用

Chinese control Conference (CCC)

作者： Hui Qin Jing Li Junzheng Wang Qingbin Wu Key Laboratory of Intelligent Control and Decision of Complex Systems School of Automation Beijing Institute of Technology Beijing

ISBN: (数字)9789881563903

ISBN: (纸本)9781728165233

The local map can update the local environment information in real time, which provides the environment information for the local dynamic planning of the robot. In this paper, a local cost map construction method based on 3D-LIDAR and camera is proposed. We use camera to detect lane lines in structured road and 3D-LIDAR to detect road boundaries in unstructured environment, and then use DS evidence reasoning to determine the current local road information. Dynamic obstacle information in the environment is obtained through 3D point cloud data segmentation, which is fused with the road information to get 3D point cloud information in the local range and generate local cost map according to it. Experiments show that the method in this paper can accurately extract the current road information whether in structured roads or unstructured roads. The fused local cost map can enable the robot to perform reasonable local planning and complete navigation on the current road.

关键词： Roads Three-dimensional displays Robots Planning Cameras Real-time systems Navigation

来源：评论

学校读者我要写书评

暂无评论

DBFCM: a Density-Based Fuzzy C-Means with Self-Regulated Fuzzy Clustering Parameters

DBFCM: a Density-Based Fuzzy C-Means with Self-Regulated Fuz...

引用

第三十九届中国控制会议

作者： Jiayi Sun Yaping Dai Kaixin Zhao School of Automation Beijing Institute of Technology State Key Laboratory of Intelligent Control and Decision of Complex Systems

As an interdisciplinary of fuzzy theory and clustering, Fuzzy C-Means（FCM） is widely applied for identifying categories with unlabeled data. However, its application to data which is hard to visualize rises the difficulty for users to determine the input parameters, especially for the number of clusters. In this paper, a kind of fuzzy clustering algorithm with self-regulated parameters named Density-Based Fuzzy C-Means（DBFCM） is proposed by integrating the idea of Density-Based Spatial Clustering of Application with Noise（DBSCAN） into FCM. Its advantage is using the inherit density characteristic of input data to self-determine the parameters of fuzzy clustering. The experimental results demonstrate that the proposed DBFCM can not only self-determine the proper parameters, but also accelerate the convergence process compared to the original FCM.

关键词： Machine Learning Fuzzy Clustering Fuzzy C-Means Parameter Self-Regulation

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：