检索结果-内蒙古大学图书馆

Asilomar Conference on Signals, Systems & computers

作者： Hsiang-Yu Chu Hongbo Zhao Markus Flierl Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm Sweden Department of Control Science and Engineering Harbin Institute of Technology Harbin China

ISBN: (数字)9798350354058

ISBN: (纸本)9798350354065

Deep convolutional networks can solve various complex tasks in the field of image processing. However, adversarial attacks have been shown to have the ability of fooling deep learning models. Adversarial training is one commonly used strategy to improve the robustness of deep learning models against adversarial examples, which is performed by incorporating adversarial examples into the training process. Traditionally, during this process, cross-entropy loss is used as the loss function. In order to improve the robustness of deep learning models against adversarial examples, we propose in this paper two new methods of adversarial training by applying the principle of Maximal Coding Rate Reduction (MCR 2 ). We evaluate the performance of different adversarial training methods by comparing the clean accuracy and adversarial accuracy. It is shown that adversarial training with the MCR 2 loss function yields a more robust network than the traditional adversarial training method. In our experiments, adversarial accuracies are improved by up to 10%. The two loss functions are discussed by using a model.

关键词： Training Deep learning Hands Accuracy Image coding Computational modeling Robustness Data models Encoding Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Sailing Through Point Clouds: Safe Navigation Using Point Cloud Based control Barrier Functions

arXiv

引用

arXiv 2024年

作者： Dai, Bolun Khorrambakht, Rooholla Krishnamurthy, Prashanth Khorrami, Farshad Control/Robotics Research Laboratory Electrical & Computer Engineering Department Tandon School of Engineering New York University BrooklynNY11201 United States

The capability to navigate safely in an unstructured environment is crucial when deploying robotic systems in real-world scenarios. Recently, control barrier function (CBF) based approaches have been highly effective in synthesizing safety-critical controllers. In this work, we propose a novel CBF-based local planner comprised of two components: Vessel and Mariner. The Vessel is a novel scaling factor based CBF formulation that synthesizes CBFs using only point cloud data. The Mariner is a CBF-based preview control framework that is used to mitigate getting stuck in spurious equilibria during navigation. To demonstrate the efficacy of our proposed approach, we first compare the proposed point cloud based CBF formulation with other point cloud based CBF formulations. Then, we demonstrate the performance of our proposed approach and its integration with global planners using experimental studies on the Unitree B1 and Unitree Go2 quadruped robots in various environments. © 2024, CC BY.

关键词： Robot programming

来源：评论

学校读者我要写书评

暂无评论

Robust Frequency Regulation for Dual-Area Interconnected Grids Using Hybrid controller: A Comparative Study 3

Robust Frequency Regulation for Dual-Area Interconnected Gri...

引用

3rd IEEE International Conference on Smart Technologies for Power, Energy and control, STPEC 2023

作者： Wazir, Awadh Ba Alhussainy, Abdullah A. Alobaidi, Abdulraheem H. Altaf, Aatif Kumar, Anil Kumar, Mahendra Alghamdi, Sultan King Abdulaziz University Faculty of Engineering Department of Electrical and Computer Engineering Jeddah Saudi Arabia King Abdulaziz University Center of Research Excellence in Renewable Energy and Power Systems Jeddah Saudi Arabia Dr. B R Ambedkar National Institute of Technology Jalandhar Instrumentation and Control Engineering Department Punjab Jalandhar India

ISBN: (纸本)9798350304732

This paper introduces a robust controller designed for load frequency control in a dual-area integrated power grid. Here, the suggested controller is a blend of a fuzzy logic controller with an integral controller. The parameters of the integral controller and frequency bias settings are optimized to enhance the dynamic response of the proposed controller. To attain this, three distinct optimization algorithms are employed, i.e., genetic algorithm, simulated annealing, and pattern search. A new objective function using settling time, settling-max, and settling-min with a suitable weight factor is used to improve the parameters estimation process. A comparative analysis is performed using the proposed approach and classical-I controller under two cases considering several load disturbance scenarios. Furthermore, the suggested hybrid controller is evaluated and compared with similar models in the literature. As expected, the proposed controller exhibits superior performance. © 2023 IEEE.

关键词： Fuzzy logic controller integral controller load frequency control optimization technique parameter estimation

来源：评论

学校读者我要写书评

暂无评论

Complex Network Pinning control based on Adjacency Degree and Resistance Distance Algorithm 3

Complex Network Pinning Control based on Adjacency Degree an...

引用

3rd International Conference on Green Communication, Network, and Internet of Things, CNIoT 2023

作者： Zhong, Hao Jia, Haoran Jia, Yanting Sun, Haiyi School of Computer Science and Engineering Shenyang Jianzhu University Shenyang China School of Electrical and Control Engineering Shenyang Jianzhu University Shenyang China Office of Academic Affairs Shenyang Jianzhu University Shenyang China Department of Science Shenyang Jianzhu University Shenyang China

ISBN: (纸本)9781510668867

In this paper, a new strategy for pinning control node selection is proposed, namely: pinning control strategy based on ADRD (Adjacency Degree and Resistance Distance) algorithm. Firstly, the model of the undirected network and the sufficient conditions to achieve synchronization are given. Secondly, the steps of the pinning control strategy based on the ADRD algorithm are specifically given and applied to dolphins network, and by comparing the pinning control strategy based on the resistance distance, it is concluded that: the pinning control strategy based on the ADRD algorithm is better than the pinning control strategy based on the resistance distance. Finally, the correctness and effectiveness of the method are verified by numerical simulation. © 2023 SPIE.

关键词： Complex networks

来源：评论

学校读者我要写书评

暂无评论

Insulation condition forewarning of form-wound winding for electric aircraft propulsion based on partial discharge and deep learning neural network

引用

High Voltage 2021年第2期6卷 302-313页

作者： Yalin Wang Jiandong Wu Tao Han Kiruba Haran Yi Yin Department of Electrical Engineering Shanghai Jiao Tong UniversityShanghaiChina Key Laboratory of Control of Power Transmission and Conversion(SJTU) Ministry of EducationShanghaiChina Department of Electrical and Computer Engineering University of Illinois Urbana-ChampaignUrbanaIllinoisUSA Department of Instrument Science and Engineering Shanghai Jiao Tong UniversityShanghaiChina

Form-wound windings in electric machines designed for electric aircraft propulsion face reliability challenges due to the severe operating environment,such as high temperature and low *** study proposes a forewarning method for insulation condition monitoring of form-wound windings based on partial discharge(PD)and deep learning neural *** PD features are extracted from the PD profile,which provides information about physics-of-failure and reflects the degree of insulation *** algorithm fusion extracted from auto-encoder and long short-term recurrent neural network is proposed to synthesize one failure precursor from these three features and make multi-time-step prediction through historical data to provide *** electrical and thermal accelerated ageing test is performed on the form-wound windings at 0.2 atm to simulate working environment of electric *** proposed method is validated on the accelerated ageing dataset and shows better prediction accuracy than some existing time-series prediction methods,indicating the advantages of the proposed ***,an on-line hardware setup using a deep learning processor is rec-ommended to implement the forewarning *** proposed approach has the potential to be widely applied to other insulation systems and contribute to work on condition monitoring.

关键词： network processor neural

来源：评论

学校读者我要写书评

暂无评论

Pinning control of Complex Networks Based on the entropy of Betweenness centrality and Node strength 3

Pinning Control of Complex Networks Based on the entropy of ...

引用

3rd International Conference on Green Communication, Network, and Internet of Things, CNIoT 2023

作者： Sun, Haiyi Cai, Liang Lv, Chenxinxiao Jia, Yanting Department of Science Shenyang Jianzhu University Shenyang China School of Computer Science and Engineering Shenyang Jianzhu University Shenyang China School of Electrical and Control Engineering Shenyang Jianzhu University Shenyang China Office of academic affairs Shenyang Jianzhu University Shenyang China

ISBN: (纸本)9781510668867

In order to solve the problem of pinning node selection in undirected weighted networks, a pinning control strategy based on the entropy of betweenness centrality and node strength is proposed in this paper. Firstly, a complex network model is given where each node is the same dynamical system, secondly, sufficient conditions for the synchronization of this network are given, and specific steps of the betweenness centrality and node strength entropy-based pinning control strategy are proposed and applied to different networks. Finally, by comparing the neighborhood information entropy-based pinning control strategy, it is found that in order to synchronize the network, the number of key nodes pinned by the proposed pinning control strategy is smaller than the neighborhood information entropy-based pinning control strategy under different coupling strengths. © 2023 SPIE.

关键词： Complex networks

来源：评论

学校读者我要写书评

暂无评论

Synergy-driven multi-modal prompting for weakly supervised semantic segmentation

引用

Neurocomputing 2025年 646卷

作者： Zhao, Yaping Liu, Chengyun Wang, Zhenyan Peng, Xiaona Chen, Zhenxue Wu, Q.M. Jonathan School of Control Science and Engineering Shandong University Jinan250061 China Department of Electrical and Computer Engineering University of Windsor WindsorN9B 3P4 Canada

Weakly supervised semantic segmentation has advanced rapidly by using weak labels, significantly reducing costs and labor demands. Current methods often rely on class activation maps (CAMs) from classifiers as supervision signals, but these tend to focus on highly discriminative regions, resulting in incomplete coverage. To address this, we leverage the cross-modal consistency of CLIP's language and vision encoders, enabling natural integration of textual and visual features for improved image classification and localization. We propose SDMMPS, which uses Text-synergized visual multimodal prompts and contrastive learning to enhance object recognition and localization. The model consists of three stages: Firstly, generating initial CAMs with a traditional classification network as a foundation for optimization. Secondly, creating "multi-modal prompts" by integrating CLIP's text embeddings via a mapping function for richer semantic information. Finally, applying a prompt-driven suppression strategy to refine the focus on target regions while suppressing the background. Extensive experiments were conducted on PASCAL VOC 2012 and MS COCO 2014, achieving state-of-the-art performance. Code will be released soon. © 2025 Elsevier B.V.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

A Study on Impact-Aware Aerial Robots Colliding with the Environment at Non-Vanishing Speed

A Study on Impact-Aware Aerial Robots Colliding with the Env...

引用

International Conference on Unmanned Aircraft Systems (ICUAS)

作者： Gayatri Indukumar Alessandro Saccon Antonio Franchi Chiara Gabellieri Robotics and Mechatronics Department Electrical Engineering Mathematics and Computer Science (EEMCS) Faculty University of Twente Enschede The Netherlands Department of Mechanical Engineering Eindhoven University of Technology Eindhoven The Netherlands Department of Computer Control and Management Engineering Sapienza University of Rome Rome Italy

ISBN: (数字)9798331513283

ISBN: (纸本)9798331513290

Enabling aerial robots to handle dynamic contacts happening at non-vanishing speeds can enlarge the range of their applications. In this work, we propose an impactaware strategy to allow aerial multirotor robots to recover from impacts. The method leverages a reactive strategy not requiring low-level changes to the motion controller commonly implemented onboard quadrotors, which might be not viable or not desirable for most users. Extensive simulation tests show that the proposed strategy considerably increases the tolerated velocity at impact in tasks in which the robot either picks an object up or collides against an object to clear its way. Preliminary experimental results using Crazyflie UAVs are also presented.

关键词： Trajectory tracking Dynamics Lead Autonomous aerial vehicles Stability analysis Robustness computer crashes Trajectory Robots Quadrotors

来源：评论

学校读者我要写书评

暂无评论

Integration of ANN for Accurate Estimation and control in Wastewater Treatment 28

Integration of ANN for Accurate Estimation and Control in Wa...

引用

28th IEEE International Conference on Emerging Technologies and Factory Automation, ETFA 2023

作者： Ţiru, Andreea Elena Vasiliev, Iulian Diaconu, Larisa Vilanova, Ramon Voipan, Daniel Ratnaweera, Harsha Dunǎrea de Jos University of Galaţi Department of Automatic Control and Electrical Engineering Galaţi Romania Autonomous University of Barcelona Department of Automation Systems and Advanced Control Research Barcelona Spain Dunǎrea de Jos University of Galaţi Department of Computer Science and Information Technology Galaţi Romania Ås Norway

ISBN: (纸本)9798350339918

The management of wastewater is a significant global concern that calls for innovative solutions to lessen its negative effects on the environment. Conventional techniques of treating wastewater need improvement in order to deal with newly discovered contaminants, which highlights the importance of providing precise estimates of process performance and resource requirements. The worsening water shortage situation requires a paradigm shift in which wastewater is viewed as a useful resource. It is possible to create an economy that is both sustainable and circular by treating and recycling wastewater, putting less pressure on freshwater supplies, and leaving as little of an environmental footprint as possible. This study investigates the use of Artificial Neural Networks (ANNs) as software estimators in the treatment of wastewater, with a particular emphasis on predicting ammonium concentrations in effluent. In order to deal with imbalanced time-series data, the research introduces innovative data pretreatment strategies. These techniques include a Sliding Window protocol, Data Normalization, and a K-Fold training scheme. This illustrates the potential of ANNs to revolutionize wastewater treatment procedures and drive developments in this field. The suggested method demonstrates higher performance when estimating pollutant concentrations, showing the ability of ANNs to do so. © 2023 IEEE.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Adaptive Fractional-Order Sliding Mode control for Mobile Robots: A PSO-Based Optimization Framework

Adaptive Fractional-Order Sliding Mode Control for Mobile Ro...

引用

IEEE SSD International Multi-Conference on Systems, Signals and Devices

作者： M. Nasir R. Fareh J. Ghommam Om Gad S. Khadraoui M. Bettayeb Department of Electrical Engineering University of Sharjah Sharjah UAE Department of Electrical and Computer Engineering Sultan Qaboos University Oman Control and Energy Management Laboratory (CEM Lab) Ecole National d'Ingenieur de Sfax Tunisia

ISBN: (数字)9798331542726

ISBN: (纸本)9798331542733

This study presents an adaptive fractional sliding mode control (AFSMC) strategy for finite-time trajectory tracking of differential drive mobile robots (DDMR) in the presence of system uncertainties and external disturbances. The proposed control strategy employs a fractional-order sliding surface and an optimized reaching law to ensure finite-time convergence of tracking errors while retaining robustness against external disturbances. Particle Swarm Optimization (PSO) is employed for offline parameter tuning, where its capability to efficiently handle a large parameter space makes it an ideal choice for optimizing the control system, ensuring both enhanced performance and computational feasibility. Simulation tests comparing the AFSMC with a conventional SMC show that the AFSMC exhibits higher tracking accuracy, robustness, and precise linear and angular velocity tracking. The results demonstrate the AFSMC's resilience to disturbances and minimal steady-state error, even under challenging conditions.

关键词： Adaptive systems Uncertainty Accuracy Torque Trajectory tracking Robustness Mobile robots Sliding mode control Optimization Tuning

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：