检索结果-内蒙古大学图书馆

American control conference (ACC)

作者： Zhang, Runyu (Cathy) Li, Weiyu Li, Na Harvard Univ John Paulson Sch Engn & Appl Sci Cambridge MA 02138 USA

ISBN: (纸本)9798350328066

This paper studies network LQR problems with system matrices being spatially-exponential decaying (SED) between nodes in the network. The major objective is to study whether the optimal controller also enjoys a SED structure, which is an appealing property for ensuring the optimality of decentralized control over the network. We start with studying the open-loop asymptotically stable system and show that the optimal LQR state feedback gain K is 'quasi'-SED in this setting, i.e. vertical bar vertical bar Left inverted perpendicularKrightinverted perpendicular(ij)vertical bar vertical bar similar to O (e -beta/poly ln(N) dist(i,j)). The decaying rate beta depends on the decaying rate and norms of system matrices and the open-loop exponential stability constants. Then the result is further generalized to unstable systems under a stabilizability assumption. Building upon the 'quasi'-SED result on K, we give an upper-bound on the performance of kappa-truncated local controllers, suggesting that distributed controllers can achieve near-optimal performance for SED systems. We develop these results via studying the structure of another type of controller, disturbance response control, which has been studied and used in recent online control literature;thus as a side result, we also prove the 'quasi'-SED property of the optimal disturbance response control which serves as a contribution on its own merit.

关键词： Decentralized control

来源：评论

学校读者我要写书评

暂无评论

Reinforcement learning based NSGA-ii for energy-delay trade-off in IAB mmWave Het-Nets

Reinforcement learning based NSGA-II for energy-delay trade-...

引用

IEEE International conference on Communications (IEEE ICC)

作者： Shang, Wen Friderikos, Vasilis Kings Coll London Dept Engn London WC2R 2LS England

ISBN: (纸本)9781538674628

This paper proposes efficient ways for constructing the energy-delay Pareto front in cache-enabled integrated access and backhauling (IAB) heterogeneous wireless network. More specifically, an improved non-dominated sorting genetic algorithm ii (NSGA-ii) is proposed which is coupled with the operator parameter control ability based on reinforcement learning, to solve the energy-delay trade-off in the multi-objective optimization problem. To estimate the effectiveness of the proposed scheme, key performance indicators that cover the convergence and distribution of the Pareto front solution set are conducted and analyzed. A wide set of numerical investigations show that the proposed algorithm can provide a more evenly distributed result than the state of the art techniques with a 15% gain compared to the nominal case which is the weighted-sum method. Furthermore, and maybe more importantly, the undesirable large gaps between solutions in the Pareto front which are caused by the weighting coefficient choices are avoided. By enabling the operator parameter control ability, the exploration and exploitation process of the proposed algorithm can be balanced, which prevents the frequently faced problems of early convergence and being trapped at a local optimum in the genetic algorithm. The proposed technique can have significant implications in improving the avoidable choices regarding the network operation, and compared with the traditional NSGA-ii, the proposed algorithm can provide a near-optimal solution set with 20% more diversity.

关键词： Multi-Objective Optimization network Optimization Reinforcement Learning NSGA-ii

来源：评论

学校读者我要写书评

暂无评论

Unveiling Graph Power: SegmentAnything and GCN Synergy for Instance Segmentation and Classification

Unveiling Graph Power: SegmentAnything and GCN Synergy for I...

引用

IEEE conference on Evolving and Adaptive Intelligent systems (IEEE EAIS)

作者： Scarrica, Vincenzo Mariano Staiano, Antonino Univ Naples Federico II Natl PhD Program AI Agrifood & Environm Corso Umberto I 40 I-80138 Naples Italy Univ Naples Parthenope Dept Sci & Technol Ctr Direz Isola C4 I-80143 Naples Italy

ISBN: (纸本)9798350366235;9798350366242

In this paper, we propose a novel approach to improve instance segmentation and classification tasks by incorporating SegmentAnything [1] before using graph neural network frameworks. Before experimentation, we ensure comprehensive data labeling using SegmentAnything for instance segmentation and Grounding DINO [2] for class annotation. Our study aims to evaluate the effectiveness of this integration by conducting a comparative analysis with the state-of-the-art Vision Transformer model [3]. Surprisingly, our experiments reveal that while the vision transformer has demonstrated remarkable performance in various tasks, it underperforms compared to our proposed approach on the same dataset. Our findings underscore the efficacy of integrating SegmentAnything with graph neural networks for instance segmentation and classification tasks, emphasizing the pivotal of those networks in advancing computer vision methodologies.

关键词： instance segmentation object classification graph neural networks transformers

来源：评论

学校读者我要写书评

暂无评论

Learning Imminent Throughput for Real-time Intersection control with Deep Neural network 26

Learning Imminent Throughput for Real-time Intersection Cont...

引用

IEEE 26th International conference on Intelligent Transportation systems (ITSC)

作者： Lin, Dianchao Li, Li Xue, Nian Wang, Lei Fuzhou Univ Sch Econ & Management Fujian Peoples R China Fuzhou Univ Sch Civil Engn Fujian Peoples R China NYU Tandon Sch Engn Dept Comp Sci & Engn New York NY USA Shanghai Maritime Univ Coll Transport & Commun Shanghai Peoples R China Tongji Univ Minist Educ Key Lab Rd & Traff Engn Shanghai Peoples R China

ISBN: (纸本)9798350399462

Imminent Throughput (ITP), the number of vehicles in a movement that can pass through an intersection given a unit of effective green time, serves as a crucial control input in many real-time optimization-based control schemes. The accuracy of ITP prediction can significantly influence control performance. If a movement with a green signal cannot discharge as many vehicles as predicted by the controller, its performance may be significantly reduced. However, most existing studies have focused on the design of control schemes while neglecting the importance of precise ITP prediction. These studies either assume that ITP can be accurately predicted or use traditional indices (e.g., saturation flow rate) or heuristic methods to predict ITP, resulting in relatively low accuracy. This paper proposes the use of a Deep Neural network (DNN) to predict ITP and demonstrates that the DNN with Multiple Classifications (NN-C) models can predict ITP with higher accuracy, lower mean absolute error, and lower root mean squared error than other prediction methods (regression, decision tree, and heuristic methods). Experiments also show that control performance can be improved with more accurate ITP predictions using the NN-C.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Research on the Servo System based on DBO-BPPID Algorithm 8

Research on the Servo System based on DBO-BPPID Algorithm

引用

8th International conference on Electrical, Mechanical and Computer Engineering, ICEMCE 2024

作者： Shen, Kai Han, Chongwei Zhang, Xuhui Zhang, Yue Northwest Institute of Mechanical and Electrical Engineering Xianyang China Shandong University School of Mechanical Electrical and Information Engineering Weihai China Shaanxi Normal University School of International Studies Xi'an China

ISBN: (纸本)9798331506230

Aiming at the requirements of high precision, strong robustness, and strong anti-disturbance ability of the anti-aircraft gun servo system, as well as the problems of internal parameter perturbation and external shooting torque interference, a BP neural network tuning PID control method based on the Dung Beetle Optimizer (DBO) is proposed. Firstly, the mathematical model of the artillery servo system is established, and the PID controller model is designed accordingly. Secondly, a BP neural network is added. A BP neural network can adjust PID parameters online through adaptive learning. However, the initial weights of the BP neural network are randomly selected, which makes it easy to fall into the local optimum during weight parameter training and affects the control performance of the system. Therefore, the DBO optimization algorithm is introduced to optimize the initial weights of the BP neural network by using DBO's good global search ability, so as to speed up network convergence and improve the control performance of the system. Finally, the simulation results show that the DBO-BP-PID control algorithm designed in this paper can well meet the control requirements of the artillery servo system and has a good application prospect in the field of intelligent artillery servo control. © 2024 IEEE.

关键词： Three term control systems

来源：评论

学校读者我要写书评

暂无评论

Evaluating Machine Learning Techniques for ICS Security: Insights from Dataset Limitations and Classifier performance 4

Evaluating Machine Learning Techniques for ICS Security: Ins...

引用

4th International Mobile, Intelligent, and Ubiquitous Computing conference

作者： Amer, Eslam Elboghdadly, Tamer Univ Portsmouth Sch Comp Portsmouth Hants England

ISBN: (纸本)9798350367782;9798350367775

The security of Industrial control systems (ICSs) is critical for the operation of essential infrastructure like energy, water, and transportation. However, ICS communication protocols often lack essential security features, making them vulnerable to advanced persistent threat (APT) attacks, as evidenced by cyberattacks like Stuxnet and Triton. One potential solution is deploying Intrusion Detection systems (IDS) to monitor network traffic and detect intrusions. While Machine Learning (ML) and Deep Learning (DL) have shown promise for IDS, testing these methods in real ICS environments is impractical due to the risk of disruptions and the challenge of labeling data without altering system functionality. This study compares the performance of several ML classifiers, including Logistic Regression, Decision Tree, XGBoost, Random Forest, ANN, LightGBM, and SVM, in detecting ICS cyberattacks. The classifiers generally performed well but showed variations depending on the type of attack. For instance, Decision Tree, Random Forest, and SVM excelled in detecting DDoS attacks, while performance dropped for PortScan attacks. LightGBM outperformed others across multiple attack types, with F-scores between 0.993 and 1.000. The study highlights the importance of comprehensive, labeled datasets for improving IDS effectiveness in ICS environments.

关键词： Intrusion Detection Anomaly Detection Industrial control systems Machine Learning

来源：评论

学校读者我要写书评

暂无评论

Research and Analysis of Electric control systems Based on Fuzzy Logic and Neural network Integration 4

Research and Analysis of Electric Control Systems Based on F...

引用

4th Asia-Pacific conference on Communications Technology and Computer Science, ACCTCS 2024

作者： Yang, Xuejian Xu, Yuanfei Zhang, Lei Yunnan Tobacca Corporation Dali Prefecture Yunnan Dali China China Tobacca Corporation Yunnan Company Yunnan Kunming China

ISBN: (纸本)9798350359985

With the rapid development of electrical engineering, electric control systems have entered a period of high-quality development. By focusing on fuzzy logic-based neural networks, new proposals should be submitted to meet the needs of intelligent and adaptive electric control systems. Based on the dynamic evolution of electrical control systems, we establish a theoretical analysis framework for modeling electric control systems according to fuzzy logic. It allows us to explain the integrated system state identification mechanism and performance optimization of electric control systems, including fuzzy logic and neural networks. In addition, we use numerical examples and practical deduction to explore the possibility of moving toward the high-quality development of electric control systems. The development of an electric control system is to provide electrical equipment with functions that meet expected standards. Managers are committed to continuously improving electric control systems' quality and equipment satisfaction. To this end, we have taken measures, including strengthening fuzzy logic control based on fuzzy rules and internal circulation, constructing a mechanism for interaction and learning between fuzzy logic and neural network quality perception, and establishing an evaluation system for electric control system and electrical equipment, to achieve high-quality development of electric control system, boost technological upgrading, and truly meet user needs. © 2024 IEEE.

关键词： Adaptive control systems

来源：评论

学校读者我要写书评

暂无评论

Kubernetes-Driven network Security for Distributed ACL Management 8

Kubernetes-Driven Network Security for Distributed ACL Manag...

引用

8th Cyber Security in networking conference

作者： Gupta, Tushar

ISBN: (纸本)9798331534110;9798331534103

Access control List (ACL) management in complex, distributed network environments poses significant challenges for organizations relying on heterogeneous infrastructures. This paper proposes a novel architecture leveraging Infrastructure as Code principles, containerization, and Kubernetes orchestration to automate and streamline ACL management at scale. Our solution incorporates a CI/CD pipeline for ACL generation, utilizing Capirca for platform-agnostic policy definition and Docker for consistent packaging. A Kubernetes Deployment controller manages the safe rollout of ACLs across diverse network devices, employing a phased approach with canary deployments. A Drift Detection controller ensures continuous compliance by monitoring and rectifying unauthorized changes. The architecture integrates with external systems like NetBox for efficient device inventory management. By automating the entire ACL lifecycle, our approach significantly reduces manual errors, enhances security posture, and improves operational efficiency. performance evaluation reveals strong scalability, with optimization opportunities for large-scale deployments. This work contributes to the evolving field of network security automation, offering a framework for managing network security policies in modern, complex infrastructures.

关键词： Access control Lists (ACLs) network Security Kubernetes Infrastructure as Code (IaC) Continuous Integration/Continuous Deployment (CI/CD)

来源：评论

学校读者我要写书评

暂无评论

Enhancing CNN-Based network Robustness Predictors Through Representation Recovery Against Information Noise

Enhancing CNN-Based Network Robustness Predictors Through Re...

引用

2024 IEEE International conference on systems, Man, and Cybernetics, SMC 2024

作者： Chen, Liang Huang, Wenli Wu, Chengpei Li, Junli College of Computer Science Sichuan Normal University Chengdu610066 China Ministry of Education Chengdu610068 China

ISBN: (纸本)9781665410205

Connectivity robustness and controllability robustness play a crucial role in maintaining the stability of complex network systems. Recently, complex network systems have faced an increasing number of malicious attacks and random failures, emphasizing the vital importance of assessing their performance. The CNN-based predictor serves as a powerful tool for evaluating the robustness of complex networks. However, the excellent performance of CNN-based predictors requires complete network data, which is often not available in real-world networks. In this paper, we investigate the recovery of losing information in networks. The main contributions can be summarized as follows: 1) Explore the impact of information loss in complex networks on CNN-based robustness prediction models. 2) Propose three recovery algorithms for addressing information loss, effectively improving the issue of losing network information. Extensive experiments demonstrate that in the presence of information loss in complex networks, CNN-based predictors exhibit higher prediction errors. However, through the application of recovery algorithms to recover losing information, a significant reduction in prediction errors is achieved. © 2024 IEEE.

关键词： Information leakage

来源：评论

学校读者我要写书评

暂无评论

Real-Time Target Tracking System With Spiking Neural networks Implemented on Neuromorphic Chips

引用

IEEE TRANSACTIONS ON CIRCUITS AND systems ii-EXPRESS BRIEFS 2023年第4期70卷 1590-1594页

作者： Liu, Kefei Cui, Xiaoxin Ji, Xiang Kuang, Yisong Zou, Chenglong Zhong, Yi Xiao, Kanglin Wang, Yuan Peking Univ Sch Integrated Circuits Key Lab Microelect Devices & Circuits Beijing 100871 Peoples R China Peking Univ Beijing Lab Future IC Technol & Sci Beijing 100871 Peoples R China

Real-time target tracking is a usual task for humans despite the neural delays during the nervous system's axonal transfer and neural processing. A plausible explanation is that the human brain employs predictive mechanisms to compensate for the delay. Inspired by the brain, this brief adopts a prediction network based on spiking neural networks (SNNs) to implement a real-time tracking task on a neuromorphic chip with low power consumption. The SNN-based prediction network outperforms the long short-term memory (LSTM) network on a small dataset and reduces 90% to 98% computations compared with LSTM. The quantized SNN-based network is deployed on a neuromorphic chip, and it takes 25ms and only 442 similar to 626nJ for a single prediction. The tracking performance of the system is also verified in real-life scenarios. Furthermore, the proposed real-time target tracking system can be easily ported to other neuromorphic platforms.

关键词： Neurons Target tracking Neuromorphics Voltage control Trajectory Task analysis Real-time systems Real-time tracking trajectory prediction spiking neural network neuromorphic chip

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：