检索结果-内蒙古大学图书馆

HKB-YOLO: transmission line fire detection method based on hierarchical feature fusion

International Journal of Security and Networks 2024年第4期19卷 188-198页

作者： Ying, Zhilei Meng, Yanan Chen, Ruoxi Lou, Jianlou School of Information and Control Engineering Jilin Institute of Chemical Technology Jilin 132022 China Department of Automation Jilin Institute of Chemical Technology Jilin 132022 China School of Computer Engineering Northeast Electric Power University Jilin 132012 China

Timely transmission line fire inspections are vital for power system safety. Although deep learning models are widely used for flame detection, struggle with small target recognition due to background interference and are vulnerable to input data perturbations, posing security risks. This study introduces a hierarchical feature fusion method based on the you only look once Version 8 (YOLOV8) framework. It employs high-performance GPU network version 2 (HGNetV2) to enhance small-target feature extraction while reducing computational complexity. A spatial pyramid pooling-fast module with large separable kernel attention is designed to highlight key features and suppress background noise. The proposed bidirectional slim neck structure (BiSlimneck) reduces feature loss. Adversarial training enhances the model’s robustness. Experimental results show a 1.4% accuracy improvement, with a reduction in parameters and complexity by 18.3% and 21.6%, respectively. After adversarial training, the accuracy of the network in the face of attacks increased by 10% compared to the pre-training. Copyright © 2024 Inderscience Enterprises Ltd.

关键词： Premixed flames

来源：评论

学校读者我要写书评

暂无评论

Decentralized Game-based Auction Algorithm for Scheduling Robotic Chargers to Service EVs with Uncertain Demands

IEEE Transactions on Intelligent Vehicles

引用

IEEE Transactions on Intelligent Vehicles 2024年 1-14页

作者： Fang, Qiuyang Zhang, Jianlei Wang, Chen Xie, Guangming Zhang, Chunyan Department of Automation College of Computer and Control Engineering Nankai University Tianjin China National Engineering Research Center of Software Engineering Peking University Beijing China State Key Laboratory for Turbulence and Complex Systems Intelligent Biomimetic Design Lab College of Engineering Peking University Beijing China

In this study, we introduce a novel auction-based algorithm modeled as a decentralized coalition formation game, designed for the complex requirements of large-scale multi-robot task allocation under uncertain demand. This context is particularly illustrative in scenarios where robots are tasked to charge electric vehicles. The algorithm begins by partitioning a composite task sequence into distinct subsets based on spatial similarity principles. Subsequently, we employ a coalition formation game paradigm to coordinate the assembly of robots into cooperative coalitions focused on these distinct subsets. To mitigate the impact of unpredictable task demands on allocations, our approach utilizes the conditional value-at-risk to assess the risk associated with task execution, along with computing the potential revenue of the coalition with an emphasis on risk-related outcomes. Additionally, integrating consensus auctions into the coalition formation framework allows our approach to accommodate assignments for individual robot-task pairings, thus preserving the stability of individual robotic decision autonomy within the coalition structure and assignment distribution. Simulative analyses on a prototypical parking facility layout confirm that our algorithm achieves Nash equilibrium within the coalition structure in polynomial time and demonstrates significant scalability. Compared to competing algorithms, our proposal exhibits superior performance in resilience, task execution efficiency, and reduced overall task completion times. The results demonstrate that our approach is an effective strategy for solving the scheduling challenges encountered by multi-robot systems operating in complex environments. IEEE

关键词： Polynomial approximation

来源：评论

学校读者我要写书评

暂无评论

Uncertainty and its Effect on Optimal Multidrug control of Hemodynamic Variables

Uncertainty and its Effect on Optimal Multidrug Control of H...

引用

2024 American control Conference, ACC 2024

作者： Popescu, Teodora Birs, Isabela R. Othman, Ghada Ben Yumuk, Erhan Mihai, Marcian Hegedus, Erwin Copot, Dana De Keyser, Robin Ionescu, Clara M. Muresan, Cristina I. Technical University of Cluj-Napoca Department of Automation Cluj-Napoca Romania Ghent University Research Group on Dynamical Systems and Control Department of Electromechanics Systems and Metal Engineering Tech Lane Science Park 125 Gent9052 Belgium Istanbul Technical University Department of Control and Automation Engineering Maslak Istanbul34469 Turkey

ISBN: (纸本)9798350382655

Computer aided control in biomedical applications is gaining more and more popularity due to numerous research studies that have proven the efficiency of automatic control over manual dosing, which is highly susceptible to human errors. Optimal drug dosing is best achieved using automatic control, which triggers important benefits in terms of both costs and patient side-effects. However, mathematical models for patients are highly susceptible to large modeling uncertainty. A predictive control algorithm is designed in this paper for optimal multidrug control of hemodynamic variables. Improved closed loop performance is obtained compared to similar control strategies, for ± 30% modeling uncertainty. The simulation results demonstrate that predictive control is a feasible solution for optimal drug dosing. An analysis of the closed loop performance for significant patient variability shows that controllers tuned using a nominal patient model often fail to achieve desired robustness. To limit the effect of modeling uncertainty, the prediction model should be updated using an online identification tool to extract patient features. © 2024 AACC.

关键词： Predictive control systems

来源：评论

学校读者我要写书评

暂无评论

Data-driven consensus control of fully distributed event-triggered multi-agent systems

引用

Science China(Information Sciences) 2023年第5期66卷 147-161页

作者： Yifei LI Xin WANG Jian SUN Gang WANG Jie CHEN School of Automation Beijing Institute of Technology The State Key Lab of Autonomous Intelligent Unmanned Systems Beijing Institute of Technology Beijing Institute of Technology Chongqing Innovation Center Department of Control Science and Engineering Tongji University

This study investigates the consensus control issue in discrete-time linear multi-agent systems(MASs) using data-driven control under undirected communication networks. To alleviate the communication burden, an adaptive event-triggered control strategy involving only local information is proposed and a model-based stability condition is derived that guarantees the asymptotic consensus of MASs. Furthermore,a data-based consensus condition for unknown MASs is established by combining a data-based system representation with the model-based stability condition, using only pre-collected noisy input-state data instead of the accurate system information a priori. Specifically, both model-based and data-driven event-triggered controllers can be utilized without requiring any global information. The validity and correctness of the controllers and associated theoretical results are demonstrated via numerical simulations.

关键词： distributed control event-triggered control data-driven control discrete-time MASs

来源：评论

学校读者我要写书评

暂无评论

A Real-Time Semantic Segmentation Method Based on Transformer for Autonomous Driving

引用

Computers, Materials & Continua 2024年第12期81卷 4419-4433页

作者： Weiyu Hao Jingyi Wang Huimin Lu Donald Bren School of Information and Computer Sciences University of CaliforniaIrvineCA 92612USA Department of Control Engineering Kyushu Institute of TechnologyKitakyushu804-8550Japan School of Automation Southeast UniversityNanjing210096China

While traditional Convolutional Neural Network(CNN)-based semantic segmentation methods have proven effective,they often encounter significant computational challenges due to the requirement for dense pixel-level predictions,which complicates real-time *** address this,we introduce an advanced real-time semantic segmentation strategy specifically designed for autonomous driving,utilizing the capabilities of Visual *** leveraging the self-attention mechanism inherent in Visual Transformers,our method enhances global contextual awareness,refining the representation of each pixel in relation to the overall *** enhancement is critical for quickly and accurately interpreting the complex elements within driving sce-narios—a fundamental need for autonomous *** experiments conducted on the DriveSeg autonomous driving dataset indicate that our model surpasses traditional segmentation methods,achieving a significant 4.5%improvement in Mean Intersection over Union(mIoU)while maintaining real-time *** paper not only underscores the potential for optimized semantic segmentation but also establishes a promising direction for real-time processing in autonomous navigation *** work will focus on integrating this technique with other perception modules in autonomous driving to further improve the robustness and efficiency of self-driving perception frameworks,thereby opening new pathways for research and practical applications in scenarios requiring rapid and precise decision-making *** experimentation and adaptation of this model could lead to broader implications for the fields of machine learning and computer vision,particularly in enhancing the interaction between automated systems and their dynamic environments.

关键词： Visual transformer semantic segmentation autonomous driving

来源：评论

学校读者我要写书评

暂无评论

One-Variable Attack on the Industrial Fault Classification System and Its Defense

引用

engineering 2022年第12期19卷 240-251页

作者： Yue Zhuo Yuri A.W.Shardt Zhiqiang Ge State Key Laboratory of Industrial Control Technology College of Control Science and EngineeringZhejiang UniversityHangzhou 310027China Department of Automation Engineering Technische Universität IlmenauIlmenau D-98684Germany

Recently developed fault classification methods for industrial processes are mainly ***,models based on deep neural networks have significantly improved fault classification accuracy owing to the inclusion of a large number of data ***,these data-driven models are vulnerable to adversarial attacks;thus,small perturbations on the samples can cause the models to provide incorrect fault *** recent studies have demonstrated the vulnerability of machine learning methods and the existence of adversarial *** paper proposes a black-box attack method with an extreme constraint for a safe-critical industrial fault classification system:Only one variable can be perturbed to craft adversarial ***,to hide the adversarial samples in the visualization space,a Jacobian matrix is used to guide the perturbed variable selection,making the adversarial samples in the dimensional reduction space invisible to the human *** the one-variable attack(OVA)method,we explore the vulnerability of industrial variables and fault types,which can help understand the geometric characteristics of fault classification *** on the attack method,a corresponding adversarial training defense method is also proposed,which efficiently defends against an OVA and improves the prediction accuracy of the *** experiments,the proposed method was tested on two datasets from the Tennessee–Eastman process(TEP)and steel plates(SP).We explore the vulnerability and correlation within variables and faults and verify the effectiveness of OVAs and defenses for various classifiers and *** industrial fault classification systems,the attack success rate of our method is close to(on TEP)or even higher than(on SP)the current most effective first-order white-box attack method,which requires perturbation of all variables.

关键词： Adversarial samples Black-box attack Industrial data security Fault classification system

来源：评论

学校读者我要写书评

暂无评论

Bayesian Filtering for High-Dimensional State-Space Models With State Partition and Error Compensation

引用

IEEE/CAA Journal of Automatica Sinica 2024年第5期11卷 1239-1249页

作者： Ke Li Shunyi Zhao Biao Huang Fei Liu Key Laboratory of Advanced Process Control for Light Industry(Ministry of Education) Institute of AutomationJiangnan UniversityWuxi 214122China Department of Chemical and Materials Engineering University of AlbertaEdmonton AB T6G 2G6Canada

In the era of exponential growth of data availability,the architecture of systems has a trend toward high dimensionality,and directly exploiting holistic information for state inference is not always computationally *** paper proposes a novel Bayesian filtering algorithm that considers algorithmic computational cost and estimation accuracy for high-dimensional linear *** high-dimensional state vector is divided into several blocks to save computation resources by avoiding the calculation of error covariance with immense *** that,two sequential states are estimated simultaneously by introducing an auxiliary variable in the new probability space,mitigating the performance degradation caused by state ***,the computational cost and error covariance of the proposed algorithm are analyzed analytically to show its distinct features compared with several existing *** results illustrate that the proposed Bayesian filtering can maintain a higher estimation accuracy with reasonable computational cost when applied to high-dimensional linear systems.

关键词： filtering estimation error

来源：评论

学校读者我要写书评

暂无评论

Fusing Multi-scale Binary Convolution with Joint Attention Face Expression Recognition Algorithm 19th

Fusing Multi-scale Binary Convolution with Joint Attention ...

引用

19th Chinese Intelligent Systems Conference, CISC 2023

作者： Qin, Minbo Li, Lin Automation Division Department of Control Science and Engineering University of Shanghai for Science and Technology Shanghai200093 China

ISBN: (纸本)9789819968855

Addressing the challenges of wild facial expression datasets being affected by illumination and pose variations, and the expression features being dispersed across multiple easily overlooked facial regions, this paper proposes a facial expression recognition network called Binary and Joint Attention Network. Firstly, The multi-scale binary convolution module integrates texture features of different granularities. Subsequently, the proposed Multi-head Joint Attention module focusing on multiple distinct facial areas through multiple attention heads. Lastly, the inter-attention map loss is designed to prevent attention overlap while assisting in classification. Experimental results on multiple datasets, including SFEW2.0, RAF-DB, FER2013, demonstrate that the proposed network can effectively recognize various facial expressions. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Local binary pattern

来源：评论

学校读者我要写书评

暂无评论

Proximity Estimation with Position Adjustment for Autonomous Industrial Inspection

Proximity Estimation with Position Adjustment for Autonomous...

引用

2024 International Conference on Artificial Intelligence of Things and Systems, AIoTSys 2024

作者： Zhou, Ziyi Huang, Ping Zheng, Song Xu, Zhezhuang Zhuang, Zixiong College of Electrical Engineering and Automation Fuzhou Univ. and Key Lab. of Industrial Automation Control Technology and Information Processing Education Department of Fujian Province Fuzhou350000 China

ISBN: (纸本)9798331507886

Due to the similarity in appearance and dense deployment of devices in industrial environments, relying solely on machine vision makes it challenging for inspection robots to accurately identify similar devices. Although wireless signals from industrial internet of things (IoT) can serve as identification features, signal fluctuations impact the accuracy and efficiency of recognition. To address this issue, this paper proposes a proximity estimation algorithm with position adjustment for autonomous industrial inspection. The algorithm considers the spatial relationships between nodes and the topological relationship between the signal strength and variations among the nodes. By analyzing the topological relationship between the signal strength and variations among the nodes, the robot autonomously adjusts its position and selects the proximal node based on the spatial topology relationship between them. We have built an inspection platform using quadruped robots to evaluate the effectiveness of the experiments. The experimental results demonstrate that the algorithm further improves the efficiency of identifying proximal devices while ensuring the estimation accuracy of the algorithm. © 2024 IEEE.

关键词： Topology

来源：评论

学校读者我要写书评

暂无评论

Optimal Multi-agent Collision-Free Path Planning with Temporal Logic Constraints 5th

Optimal Multi-agent Collision-Free Path Planning with Tempo...

引用

5th Chinese Conference on Swarm Intelligence and Cooperative control, CCSICC 2021

作者： Zheng, Yiwei Liu, Zhaocong Lai, Aiwen Yu, Xiao Lan, Weiyao Department of Automation Xiamen University Fujian Xiamen361005 China The Science and Technology on Space Intelligent Control Laboratory Beijing Institute of Control Engineering Beijing100094 China Department of Mechanical and Automation Engineering The Chinese University of Hong Kong Hong Kong

ISBN: (纸本)9789811939976

In this paper, we present a novel optimal multi-agent collision-free path planning algorithm (OMPATL) for the problem of multi-robot path planning with temporal logic constraints. Given a high-level mission specification in the form of linear temporal logic (LTL), OMPATL can automatically synthesize a set of trajectories for the multi-agent system (MAS), which achieves the collision avoidance among agents and minimizes the cost of the maximum traveling time between successive satisfactions. To synthesize the optimal trajectories, the motion of all agents, together with the mission area, is modeled as a weighted team transition system (TS) with a set of atomic propositions (APs). If the collision avoidance were not required, the optimal trajectories would be easily synthesized by an algorithm such as shortest paths. However, once the multi-agent systems are required to be safety-critical and collision-free, these trajectories may become infeasible. In OMPATL, a strategy is proposed for adding a set of transitions including "wait" and "go-back" to each individual TS based on the optimal run which does not consider collision avoidance. Then, the states and transitions with collisions can be removed such that the optimal collision-free trajectories are founded by the synthesis algorithm. The synthesized run balances collision avoidance, mission fulfillment, and optimality. The optimal run is synthesized offline and online adjustments are not needed. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Motion planning

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：