检索结果-内蒙古大学图书馆

2024 systems of Signal Synchronization, Generating and Processing in Telecommunications, SYNCHROINFO 2024

作者： Pomogalova, A.V. Donskov, E.A. Elagin, V.S. Vladyko, A.G. The Bonch-Bruevich Saint-Petersburg State University of Telecommunications Infocommunication Systems Department Saint Petersburg Russia St. Petersburg Institute for Informatics and Automation of the Russian Academy of Sciences Laboratory of Computer Security Problems Department St. Petersburg Russia Saint-Petersburg State University of Telecommunications Faculty of Infocommunication Networks and Systems the Bonch-Bruevich Saint Petersburg Russia Saint-Petersburg State University of Telecommunications Faculty of Fundamental Training the Bonch-Bruevich Saint Petersburg Russia

ISBN: (纸本)9798350373448

The paper presents a study of response scenarios in an intelligent transport system, in which pedestrians are participants, to emergency situations and their prevention. Pedestrians are included in the VRU (Vulnerable Road Users) category within the general ITS architecture and are most susceptible to accidents due to the lack of movement control. Scenarios for interaction with such traffic participants may include not only rules for responding and providing assistance as soon as possible, but also identifying the initiator of the incident for the purpose of further control and prevention of situations of a similar nature. The authors of the work propose the use of blockchain technology to ensure data safety, as well as the option of building an ITS architecture with a module for monitoring incident data and timely response. The paper provides mathematical calculations of the possibility of using blockchain technology within the framework of the proposed concept and modeling. © 2024 IEEE.

关键词： blockchain distributed ledger technology emergency scenario Intelligent Transport System ITS V2X Vehicle-to-Everything VRU

来源：评论

学校读者我要写书评

暂无评论

A Parallel and Asynchronous Blob Shape Descriptor Implemented in CMOS Technology 33

A Parallel and Asynchronous Blob Shape Descriptor Implemente...

引用

33rd IEEE International Conference on Microelectronics, MIEL 2023

作者： Bogacki, P. Dlugosz, M. Talaska, T. Dlugosz, R. Aptiv Services Poland Kraków30-399 Poland Agh University of Science and Technology Institute of Telecommunications Faculty of Computer Science Electronics and Telecommunications Kraków30-059 Poland Poznan University of Technology Faculty of Control Robotics and Electrical Engineering Institute of Automation and Robotics Division of Signal Processing and Electronic Systems Poznan60-965 Poland Bydgoszcz University of Science and Technology Faculty of Telecommunication Computer Science and Electrical Engineering Bydgoszcz85-796 Poland

ISBN: (纸本)9798350347760

The paper presents a family of novel light blob shape descriptors for use in selected active safety algorithms used in Advanced Driver Assistance systems (ADAS). One of the motivations was to obtain a descriptor that would ensure low computational complexity. This makes it easy to implement both in software and hardware. One assumption is that the location of the center of a given light spot is approximately known. The principle of its operation is then to count white pixels in selected directions, starting from this central point. A key issue here is an efficient way of determining indexes of particular pixels belonging to the image patch, as well as the location of points representing places where the white area turns into black. In the case of a hardware implementation, this can be done using a parallel circuit operating in asynchronous mode, without the need for a control clock. © 2023 IEEE.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Research on Low Energy Software Defined Industrial Network Time Synchronization Method

Research on Low Energy Software Defined Industrial Network T...

引用

IEEE Conference on Industrial Electronics and Applications (ICIEA)

作者： Jianmou Li Yongxin Miao Yunxu Zhang Shibo Wang Yongbao Guan Shuai Shao State Grid YingKou Electric Power Supply Company China Yingkou Liaoning Key Laboratory of Networked Control Systems Chinese Academy of Sciences Shenyang Institute of Automation Chinese Academy of Sciences Shenyang Liaoning

ISBN: (数字)9798350360868

ISBN: (纸本)9798350360875

Industrial control networks are becoming increasingly complex, with various types of networks and devices interconnected, forming a heterogeneous industrial control network environment. In this environment, network time synchronization becomes the key to ensuring the reliable and stable operation of industrial networks and production manufacturing. However, traditional time synchronization algorithms suffer from the problem of frequent broadcasting with fixed cycles, resulting in high communication overhead and hindering the achievement of green and low-carbon production goals. Therefore, studying a low-energy industrial network time synchronization method has important practical significance. This article proposes a low-energy software defined industrial network time synchronization method to solve the communication overhead problem caused by traditional time synchronization algorithms with fixed cycle frequent broadcasts. This method is based on the software defined network concept, constructs a layered network topology, and is compatible with various time synchronization protocols according to application requirements. Considering the impact of dynamic link delay on time synchronization accuracy, low-power synchronous broadcasting was achieved by dynamically adjusting the time synchronization period of each layer of the network, and the time synchronization period was further optimized.

关键词： Energy consumption Accuracy Industrial control Software algorithms Production Broadcasting Software

来源：评论

学校读者我要写书评

暂无评论

Multiple Objective Scheduling Optimization Algorithm Based on Grey Wolf Optimization and Variable Neighborhood Search Algorithm

Multiple Objective Scheduling Optimization Algorithm Based o...

引用

Electronic Information Engineering and computer Technology (EIECT), International Conference on

作者： Jiannan Liu Wencheng Liu Ting Wang Shengnan Zhang School of Software Shenyang University of Technology Shenyang Liaoning China Key Laboratory of Networked Control Systems Chinese Academy of Sciences Shenyang China Chinese Academy of Sciences Shenyang Institute of Automation Shenyang China

ISBN: (数字)9798331528850

ISBN: (纸本)9798331528867

Multi-objective scheduling is a key problem in the field of scheduling optimization such as warehouse logistics. Aiming at the problems of insufficient local search ability and difficult multi-objective trade-off in the existing methods, this article proposes an improved GWO-VNS algorithm. According to existing research, significant enhancements in local search capability and multi-objective optimization performance are achieved by incorporating the variable neighborhood search algorithm and applying crossover and mutation operations. The comparative experimental results show that the IGD index of GWO-VNS algorithm is reduced by 33%, and the HV index is increased by 11%, which verifies its significant advantages in multi-objective scheduling problems.

关键词： Processor scheduling Search problems Scheduling Robustness Indexes Optimization Logistics Convergence

来源：评论

学校读者我要写书评

暂无评论

Abstraction-Based Synthesis of controllers for Approximate Opacity

Abstraction-Based Synthesis of Controllers for Approximate O...

引用

IEEE Conference on Decision and control

作者： Junyao Hou Siyuan Liu Xiang Yin Majid Zamani Department of Automation Key Laboratory of System Control and Information Processing Shanghai Jiao Tong University Shanghai China Division of Decision and Control Systems KTH Royal Institute of Technology Stockholm Sweden Department of Computer Science University of Colorado Boulder CO USA Department of Computer Science LMU Munich Munich Germany

Opacity is an important information-flow security property which characterizes the plausible deniability of certain “secret behaviors” in dynamical systems. In this paper, we study the problem of synthesizing controllers enforcing a notion of opacity over discrete-time control systems with continuous state sets. In this paper, we develop an abstraction-based approach to tackle the controller synthesis problem. Specifically, we adopt a notion of approximate opacity which is suitable for continuous-space control systems. We propose a notion of approximate initial-state opacity preserving alternating simulation relation which characterizes the closeness between two systems in terms of opacity preservation. We show that, based on this new notion of system relation, one can synthesize an opacity-enforcing controller for the abstract system which is finite and then refine it back to enforce opacity over the original control system. Finally, we present a method for constructing opacity-preserving finite abstractions for discrete-time control systems under some stability properties. Our results are illustrated on a two-room temperature control problem.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Asynchronous control of Positive Markov Jump systems: A Necessary and Sufficient Condition 10

Asynchronous Control of Positive Markov Jump Systems: A Nece...

引用

10th IEEE Data Driven control and Learning systems Conference, DDCLS 2021

作者： Fang, Mei Wang, Liqing Wu, Zheng-Guang College of Automation Harbin Engineering University Harbin150001 China State Key Laboratory of Industrial Control Technology Institute of Cyber-Systems and Control Zhejiang University Zhejiang Hangzhou310027 China

ISBN: (纸本)9781665424233

This paper deals with h -gain controller synthesis of positive Markov jump systems (PMJSs) with asynchronous modes. Thanks to the hidden Markov model, the closed-loop systems are modeled as hidden Markov jump systems (HMJSs). The definitions of positivity, mean stability, and h -gain are introduced for HMJSs. A necessary and sufficient condition is derived to ensure that the HMJSs are positive and mean stable with h -gain γ that can be solvable by linear programming strategy. Two numerical examples are listed to show the effectiveness of our results. © 2021 IEEE.

关键词： Hidden Markov models

来源：评论

学校读者我要写书评

暂无评论

SkinFormer: Learning Statistical Texture Representation with Transformer for Skin Lesion Segmentation

arXiv

引用

arXiv 2024年

作者： Xu, Rongtao Wang, Changwei Zhang, Jiguang Xu, Shibiao Meng, Weiliang Zhang, Xiaopeng The State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing China The Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China CASIA Beijing China The State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences China School of Artificial Intelligence Beijing University of Posts and Telecommunications China

Accurate skin lesion segmentation from dermoscopic images is of great importance for skin cancer diagnosis. However, automatic segmentation of melanoma remains a challenging task because it is difficult to incorporate useful texture representations into the learning process. Texture representations are not only related to the local structural information learned by CNN, but also include the global statistical texture information of the input image. In this paper, we propose a transFormer network (SkinFormer) that efficiently extracts and fuses statistical texture representation for Skin lesion segmentation. Specifically, to quantify the statistical texture of input features, a Kurtosis-guided Statistical Counting Operator is designed. We propose Statistical Texture Fusion Transformer and Statistical Texture Enhance Transformer with the help of Kurtosis-guided Statistical Counting Operator by utilizing the transformer’s global attention mechanism. The former fuses structural texture information and statistical texture information, and the latter enhances the statistical texture of multi-scale features. Extensive experiments on three publicly available skin lesion datasets validate that our SkinFormer outperforms other SOAT methods, and our method achieves 93.2% Dice score on ISIC 2018. It can be easy to extend SkinFormer to segment 3D images in the future. Our code is available at https://***/RongtaoXu/SkinFormer. Copyright © 2024, The Authors. All rights reserved.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Repetitive T-S Fuzzy Model-Based Iterative Learning control Law Design 63

Repetitive T-S Fuzzy Model-Based Iterative Learning Control ...

引用

63rd IEEE Conference on Decision and control, CDC 2024

作者： Maniarski, Robert Paszke, Wojciech Tao, Hongfeng Rogers, Eric Institute of Automation Electronic and Electrical Engineering University of Zielona Góra ul. Szafrana 2 Zielona Góra65-246 Poland Jiangnan University Key Laboratory of Advanced Process Control for Light Industry of Ministry of Education Wuxi214000 China University of Southampton School of Electronics and Computer Science SouthamptonSO17 1BJ United Kingdom

ISBN: (纸本)9798350316339

This paper develops an iterative learning control law for a class of nonlinear systems. The approach used to represent the nonlinear system dynamics is a Takagi-Sugeno fuzzy repetitive process that considers the two directions of information propagation. Then, the control action investigated is a state feedback control law combined with a PD-type feed-forward learning control law. Consequently, linear matrix inequality techniques can be used for control design. Furthermore, this approach allows the design of control action to satisfy the requirements on both the error convergence and the transient dynamics. Finally, an example demonstrates the properties of the new design. © 2024 IEEE.

关键词： State feedback

来源：评论

学校读者我要写书评

暂无评论

Context-Aware Clinical Diagnosis Prediction via Hierarchical Ontology Representation

Context-Aware Clinical Diagnosis Prediction via Hierarchical...

引用

Medical Artificial Intelligence (MedAI), IEEE International Conference on

作者： Bolin Zhu Chen Liu Jiaojiao Wang Xin Li School of Computer Science & Technology Beijing Institute of Technology Beijing China State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing China

In recent years, the extensive utilization of electronic medical records has led to the preservation of a large amount of historical patient information, culminating in the formation of Electronic Health Record (EHR) dataset. Through technologies such as deep learning and representation learning, EHR dataset has been employed for tasks in the medical field, such as disease prediction. However, the challenges of how to better learn the embeddings of medical codes and how to effectively model historical visit sequences remain significant issues in the field. Therefore, we introduce a novel disease prediction methodology grounded on hierarchical ontology representation and disease evolution. First, we incorporate medical ontology to obtain external prior knowledge and simultaneously utilize the co-occurrence relationships between diseases to construct a disease co-occurrence graph. By integrating information from both sources, we achieve the final embedding of the medical codes. Building on this foundation, we delve deeper into exploring the evolution and changes in diseases, specifying different sequence modeling methods, thereby acquiring the embeddings of the patients. The application of medical ontology is beneficial in mitigating data inadequacy, while the exploration of dynamic disease evolution enhances the effectiveness of predictive models. Experimental results on the MIMIC-III dataset indicate that the proposed method achieved superior performance in disease pre-diction tasks, thus validating the effectiveness of this approach.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Adaptive Neural Network Asymptotic Tracking control for Autonomous Surface Vehicles

Adaptive Neural Network Asymptotic Tracking Control for Auto...

引用

Industrial Cyber-Physical systems (ICPS)

作者： Yongchao Liu Qingzhi Wang Baozeng Fu Institute of Complexity Science School of Automation Qingdao University Qingdao China Shandong Key Laboratory of Industrial Control Technology Qingdao China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Southeast University Nanjing China

In this paper, an adaptive neural network asymptotic tracking control method is presented for autonomous surface vehicles (ASV) with unknown uncertainties. In the control design, a smooth function is integrated into backstepping construction, which can achieve asymptotic convergence. The neural networks are borrowed to approximate the lumped nonlinear functions encompassing the unknown dynamics. It can be proved that the tracking errors of ASV can asymptotically converge to zero and all signals of the ASV closed-loop system are bounded. We offer simulation images to exhibit the validity of the devised asymptotic control method of ASV.

关键词： Adaptation models Backstepping Uncertainty Adaptive systems control design Process control Artificial neural networks

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：