检索结果-内蒙古大学图书馆

New Class Detection in Network Traffic Classification Using Confidence Information Embedded Cascade Structure

IEEE Transactions on Network Science and engineering 2025年第3期12卷 1692-1706页

作者： Lu, Haotian Dong, Yuning Wu, Zhiyuan Wei, Hua-Liang Lu, Guanming Nanjing University of Posts and Telecommunications School of Communications and Information Engineering Nanjing210003 China The University of Sheffield Department of Automatic Control and Systems Engineering SheffieldS1 3JD United Kingdom

Network traffic classification plays an important role in network management. With continued emergence of new applications, classifiers need to deal with unknown classes in an open set environment. However, the available open set flow recognition methods cannot well balance the performance of new class detection and the fine-grained classification of known classes. Moreover, these methods could pursue high accuracy at the cost of the classification speed. To address these problems, this paper proposes an unknown network traffic detection method based on confidence (difference) and a cascade structure, by analyzing the confidence distributions of both the known and new classes. The proposed method works as follows. Firstly, it uses a cascade structure to detect new class samples (having high confidence) which are difficult to identify using existing methods;secondly, it employs the maximum confidence difference to classify the new and known classes. In order to better detect new classes with high confidence, an algorithm is designed to select the pseudo-negative samples from the unlabelled dataset with an adaptive threshold. The proposed method is evaluated on real-world datasets. The results show that compared with the state-of-the-art methods, the proposed method can significantly improve the overall accuracy and the classification latency is also greatly reduced. © 2013 IEEE.

关键词： Data accuracy

来源：评论

学校读者我要写书评

暂无评论

Distributed Adaptive Tracking control for Fuzzy Nonlinear MASs Under Round-Robin Protocol

引用

IEEE Transactions on Fuzzy Systems 2025年第5期33卷 1488-1498页

作者： Fan, Sha Meng, Min Fu, Yukai Deng, Chao Nanjing University of Posts and Telecommunications College of Automation College of Artificial Intelligence Nanjing210023 China Tongji University Department of Control Science and Engineering College of Electronics and Information Engineering Shanghai200070 China Chinese Academy of Sciences State Key Laboratory of Robotics Shenyang Institute of Automation Shenyang110016 China Chinese Academy of Sciences Key Laboratory of Networked Control Systems Shenyang110016 China Nanjing University of Posts and Telecommunications Institute of Advanced Technology Nanjing210049 China

In this article, the cooperative fuzzy tracking control problem for a type of high-order nonlinear multi-agent systems under the Round-Robin (RR) communication protocol is solved. To effectively reduce the communication among agents, an RR communication protocol is first proposed, where each agent can communicate with only one neighbor at any given time. Based on the developed communication protocol, a hierarchical control approach is introduced, consisting of a distributed observer layer that utilizes information from both local and neighboring agents, and a decentralized control layer that operates solely based on local agent information. Specifically, a distributed observer is designed in the distributed observer layer to achieve the distributed observation objective by introducing a time-varying gain in the observer input. Furthermore, an improved distributed observer with the upper triangular form is constructed to produce a signal with high-order derivatives. In the decentralized control layer, fuzzy adaptive controllers are designed for all agents by using the backstepping technique. By using the Lyapunov stability theory, rigorous stability analysis shows that the cooperative fuzzy tracking control problem is solved under the developed hierarchical control approach. In the end, a simulation example is presented to demonstrate the validity of our proposed method. © 1993-2012 IEEE.

关键词： Protocols Observers Stability analysis Decentralized control Backstepping Vectors Symmetric matrices Network topology telecommunications System dynamics

来源：评论

学校读者我要写书评

暂无评论

Laser direct writing of flexible multifunctional airflow sensors on the Kevlar fabric

引用

Nano Research 2025年第1期18卷 443-454页

作者： Wei Wang Zi-Qing Chen Yong-Qi Li Yu-Long Wang Mei-Chen Liu Yun-Bo Ruan Yang Zhang Shu-Juan Liu Qiang Zhao College of Electronic and Optical Engineering and College of Flexible Electronics(Future Technology) Nanjing University of Posts and TelecommunicationsNanjing 210023China State Key Laboratory of Organic Electronics and Information Displays and Jiangsu Key Laboratory for Biosensors Institute of Advanced Materials(IAM)Nanjing University of Posts and TelecommunicationsNanjing 210023China Zhe Jiang Topsun Logistic Control CO. LTD.Yuhuan 317600China Department of Rehabilitation Medicine School of Acupuncture-Moxibustion and Tuina and School of Health Preservation and RehabilitationNanjing University of Chinese MedicineNanjing 210023China

The growing interest in flexible devices has emerged as a global trend due to their advantages in flexibility,lightweight structure,and wearability,addressing the limitations of traditional *** wearable airflow sensors have been previously reported,the development of flexible fabric-based airflow sensors capable of functioning in environments with open flames—critical for fire rescue operations—has yet to be explored,largely due to the poor fire resistance of conventional *** this work,we first present a flexible,wearable,and multifunctional airflow sensor with excellent fire-resistant properties,fabricated through a simple direct laser writing *** sensor maintains airflow detection capabilities even in the presence of open ***,the fabrication of fabric-based sensors involves complex procedures such as carbon materials doping or vapor-phase deposition,leading to lengthy preparation cycles and high ***,fabric-based devices are inherently prone to *** address these challenges,we introduce twice-vertical laser-induced graphene(TVLIG)as a sensitive and reliable component for fire-resistant airflow *** resulting TVLIG/Kevlar fabric can be integrated into various garments,particularly protective suits,to form sensitive and fire-resistant airflow sensors capable of detecting airflow velocity and direction in both two-dimensional(2D)and three-dimensional(3D)spaces during fire ***,the TVLIG patterns can be expanded to multifunctional platforms,such as glucose detection for injured individuals,offering further applications in rescue *** functional expansion reduces the burden on rescue personnel and streamlines device *** its outstanding sensing capabilities,fire resistance,and expandability,the developed flexible airflow sensor shows great potential for various real-world rescue scenarios,promising advancements in wearable sensing technology for rescue enginee

关键词： flexible airflow sensor direct laser writing twice-vertical laser-induced graphene fire accident rescue Kevlar fabric

来源：评论

学校读者我要写书评

暂无评论

MARS: Multi-Agent Deep Reinforcement Learning for Complex Environment Exploration

MARS: Multi-Agent Deep Reinforcement Learning for Complex En...

引用

Consumer Communications and Networking Conference, CCNC IEEE

作者： Francesco Gervino Andrea Eirale Marcello Chiaberge Alessio Sacco Guido Marchetto Claudio Casetti Department of Control and Computer Engineering Politecnico di Torino Italy Department of Electronics and Telecommunications Politecnico di Torino Italy

ISBN: (数字)9798331508050

ISBN: (纸本)9798331508067

Autonomous exploration of complex, unknown environments is a cutting-edge task not entirely solved by the scientific community. When an agent needs to explore a maze without any a priori information about the environment, the lack of proper destinations and explicit task objectives make traditional navigation policies inappropriate. While the literature presents some sporadic deterministic systems able to face the tasks, learning approaches still need an adequate investigation which could prove them to be more suitable and versatile for this purpose. In this paper, we present MARS, a path planner that exploits swarms of robots to optimize the exploration of complex unknown environments, such as mazes. To make the solution scalable, the proposed method exploits two cooperating modules: local and global planners. The local planner is modeled as a Markov Decision Process (MDP) and trained as a Reinforcement Learning (RL) multi-agent system. Each agent has access to image representations of a section of the global map, always centered in the robot reference frame, and decides the next navigation goal to complete the local exploration. The global planner is a deterministic system that recovers the navigation when a local solution is unavailable. The robots share the explored section with peers when they meet in a rendez-vous. We compared our approach to a single deterministic agent, a single RL agent and a close-to-optimal deterministic approach which deploys five greedy agents. The simulation results demonstrate MARS' efficiency, reaching near-optimal levels in significantly less time.

关键词： Mars Navigation Simulation Markov decision processes Image representation Deep reinforcement learning Robots Faces Multi-agent systems

来源：评论

学校读者我要写书评

暂无评论

Numerical simulation of piston rings in marine diesel engines considering thermal-fluid-structure factors: From normal to gas leakage conditions 24

Numerical simulation of piston rings in marine diesel engine...

引用

2024 International Conference on Industrial Automation and Robotics, IAR 2024

作者： Luo, Congcong Zhao, Minghang Fu, Song Zhang, Yan Han, Yan Huang, Qingqing Cui, Zhiquan Department of Mechanical Engineering Harbin Institute of Technology Shandong Weihai China School of Mechatronics Engineering Harbin Institute of Technology Heilongjiang Harbin China The Key Laboratory of Industrial Internet of Things and Networked Control Ministry of Education Chongqing University of Posts and Telecommunications Chongqing China School of Automotive Engineering Harbin Institute of Technology Shandong Weihai China

ISBN: (纸本)9798400711268

Worn piston rings disrupt the sealing performance of combustion chambers, reducing the compression ratio and combustion efficiency, thereby affecting engine power. Currently, limited in-depth simulations have been conducted on gas leakage of combustion chamber caused by piston ring faults. This paper presents a thermal-fluid-structure coupling simulation of a piston rings in a large marine diesel engine, focusing on the thermal parameter variations induced by its fault. The simulation results indicate that, under the given simulated conditions, the maximum deformation of the piston ring is 37.922 μm. As piston ring wear accumulates, both the velocity and pressure of gas leakage decrease, and the rate of decrease is diminished accordingly. Additionally, piston ring sticking may significantly raise gas pressure, resulting in a noticeable increase in the pressure drop at the inlet of ring-liner gap. © 2024 Copyright held by the owner/author(s).

关键词： Piston rings

来源：评论

学校读者我要写书评

暂无评论

Design and control of a Permanent Magnet Spherical Wheel Motor With a Radially Segmented Belt and a Virtual Shaft

引用

IEEE Transactions on Industrial Electronics 2025年

作者： Kim, Minki Lee, Kyu-Sung Electronics and Telecommunications Research Institute Seongnam-si13488 Korea Republic of Kongju National University Department of Electrical Electronics and Control Engineering Cheonan31080 Korea Republic of

A novel design for a permanent magnet spherical wheel motor (SWM) is proposed to enable controlled rotation direction while ensuring stable and precise rotational control. The proposed motor features a belt-shaped stator, which is derived from conventional motor systems but employs a belt-shaped structure, enhancing scalability and modularity. To regulate the rotation direction effectively, a virtual shaft mechanism is introduced, in which additional permanent magnets are placed orthogonally to the primary rotational direction, enabling controlled axis stabilization. A prototype SWM was developed with a single-phase, four-belt configuration and six stators per belt, and its operation was successfully demonstrated using Hall sensors, an FPGA-based controller, and parallel inverters. Under a 12 V dc-link and no-load conditions, the motor speed was controlled from 50 to 500 rpm by adjusting the PWM duty cycle. One of the key challenges in evaluating the motor’s performance was the lack of an established method for accurately measuring rotation direction and speed. To address this, we proposed and implemented two measurement approaches: 1) image processing-based tracking;and 2) tachometer-based speed detection. Using these measurement techniques, we further analyzed the motor’s behavior under a friction load of approximately 10 mN · m. The results demonstrated continuous 360-degree directional switching at 45-degree intervals, while maintaining a speed of 300 rpm. This article introduces a novel method for designing and controlling a permanent magnet SWM with adjustable rotation direction, demonstrating its feasibility for future mobility applications. © 1982-2012 IEEE.

关键词： Permanent magnets

来源：评论

学校读者我要写书评

暂无评论

G-Anomaly: A Pyramid Graph Transformer-based Vision-Language Model for General Industrial Anomaly Detection

引用

IEEE Transactions on Automation Science and engineering 2025年

作者： Li, Jiaqi Wen, Shuhuan Fang, Bin Yanshan University Key Lab of Industrial Computer Control Engineering of Hebei Province Qinhuangdao066004 China Beiing University of Posts and Telecommunications Department of Artificial intelligence Beijing China

Visual-language alignment is crucial for enhancing the domain adaptability of industrial anomaly detection models. However, the existing methods overlook the importance of structured image representation, fail to further distinguish topological differences between anomalies and the inherent textures of products, which reduces the accuracy of semantic matching. To address this problem, we propose a novel industrial anomaly detection model G-Anomaly, to preserve the topological structure of the sample images and further enhance the model’s domain adaptability. We designed Pyramid Graph Transformer as a visual encoder to extract multi-scale visual features, which can directly preserve the structural relationships between different regions of the image, and also optimize the over-smoothing issue present in deep graph networks, thereby retaining the distinguishability of anomalous nodes. Additionally, we design a Multi-level Domain Adapter that ensures semantic consistency of anomalous features across different scales and contexts by performing visual-language matching at various resolutions and levels of abstraction. This enhances the model’s domain adaptability for anomaly detection for a wide range of industrial products. We collect and craft an actual solar panel dataset PV_actual AD, and conduct extensive experiments on the public dataset MVTec AD as well as the actual solar panel dataset PV_actual AD. This has demonstrated that G-Anomaly not only performs well in standard testing environments but also exhibits robustness and domain adaptability for anomaly detection tasks in real-world scenarios. © 2025 IEEE. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Multi-Agent Distributed DQN and Transfer Learning for Energy-Efficient Power Management in Solar Energy-Harvested Small-Cell Networks

引用

IEEE Internet of Things Journal 2025年

作者： Cho, Hyebin Kim, Hyungsub Na, JeeHyeon Lim, Seung-Chan Lee, Howon Hankyong National University School of Electrical Electronic and Control Engineering Anseong17579 Korea Republic of Electronics and Telecommunications Research Institute Daejeon34141 Korea Republic of Hankyong National University School of ICT Robotics and Mechanical Engineering and IITC Anseong17579 Korea Republic of Ajou University Department of Electrical and Computer Engineering Suwon16499 Korea Republic of

The integration of solar energy harvesting into small-cell networks is a promising solution for achieving energy-efficient and sustainable wireless communications. However, the inherent variability and intermittency of solar energy, coupled with precise inter-cell interference management, significantly hinder efficient network operation. To resolve these challenges, we propose a multi-agent distributed deep Q-network (MA-DDQN) framework, where the distributed base stations learn the optimal transmit power control policies. To further enhance adaptability under varying solar conditions, we present a daily model transfer with a fine-tuning approach, enabling efficient deployment without extensive training overhead. Simulation results demonstrate that the proposed methods remarkably improve energy efficiency while maintaining robust adaptability under dynamic solar conditions, revealing their potential for sustainable small-cell network deployments. © 2014 IEEE.

关键词： Solar cell efficiency

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Different Sliding Mode control Approaches for Load Frequency control in Edge of the Grid System

引用

IET Generation, Transmission and Distribution 2025年第1期19卷

作者： Aich, Pritom Ahmed, Anis Shah, Rakibuzzaman Islam, Md Rabiul Roy, Naruttam Kumar Nasir, Ali Department of Electrical and Electronic Engineering Daffodil International University Dhaka Bangladesh Department of Electrical and Electronic Engineering Khulna University of Engineering & Technology Khulna Bangladesh Federation University Australia Mt HelenVIC Australia School of Electrical Computer and Telecommunications Engineering University of Wollongong WollongongNSW Australia Control and Instrumentation Engineering Department King Fahd University of Petroleum and Minerals Dhahran Saudi Arabia Interdisciplinary Research Center for Intelligent Manufacturing and Robotics King Fahd University of Petroleum and Minerals Dhahran Saudi Arabia

The integration of renewable energy sources (RESs) at the edge of the grid plays a contributory role in advancing the transition to a sustainable energy future. However, this transition introduces significant variability, which challenges the maintenance of frequency stability in power systems. To address the impacts of RES variability, various robust control strategies have been developed. This paper compares the performance of different advanced sliding mode control (SMC) approaches, i.e., super twisting (ST) algorithm-based second order sliding mode control (STSOSMC), second order sliding mode control (SOSMC), double integral sliding mode control (DISMC) and integral sliding mode control (ISMC) with conventional sliding mode control (SMC) for load frequency control with stochastic RESs such as biogas generators (BG) and wind-based doubly fed induction generators (DFIG). The impact of the advanced sliding mode controllers on the voltage and rotor angle stability of the system is also explored. The efficacy of the controllers is tested under different load disturbances, considering nonlinearities such as communication delay (CD), sensor inaccuracy (SI), governor dead band (GDB), and generation rate constraint (GRC). The results demonstrate that STSOSMC achieves superior frequency regulation with minimal chattering and outperforms other controllers in terms of settling time, overshooting, and undershooting in frequency deviation. The result also demonstrates the effectiveness of STSOSMC in managing the variability and disturbances of RESs. Therefore, it could be considered the most robust control mechanism from the edge of the grid system with high penetration of RESs. © 2025 The Author(s). IET Generation, Transmission & Distribution published by John Wiley & Sons Ltd on behalf of The Institution of engineering and Technology.

关键词： Robust control

来源：评论

学校读者我要写书评

暂无评论

Topological Dictionary Learning

arXiv

引用

arXiv 2025年

作者： Grimaldi, Enrico Battiloro, Claudio Di Lorenzo, Paolo Department of Computer Control and Management Engineering Sapienza University of Rome Via Ariosto 25 Rome00185 Italy Biostatistics Department of Harvard University 655 Huntington Ave BostonMA02115 United States Department of Information Engineering Electronics and Telecommunications Sapienza University of Rome Via Eudossiana 18 Rome00184 Italy

The aim of this paper is to introduce a novel dictionary learning algorithm for sparse representation of signals defined over combinatorial topological spaces, specifically, regular cell complexes. Leveraging Hodge theory, we embed topology into the dictionary structure via concatenated sub-dictionaries, each as a polynomial of Hodge Laplacians, yielding localized spectral topological filter frames. The learning problem is cast to jointly infer the underlying cell complex and optimize the dictionary coefficients and the sparse signal representation. We efficiently solve the problem via iterative alternating algorithms. Numerical results on both synthetic and real data show the effectiveness of the proposed procedure in jointly learning the sparse representations and the underlying relational structure of topological signals. © 2025, CC BY.

关键词： Topology

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：