检索结果-内蒙古大学图书馆

IEEE International Conference on Communications in China (ICCC)

作者： Ningning Yu Jiajun Wu Chengwei Zhou Zhiguo Shi Jiming Chen Key Laboratory of Collaborative Sensing and Autonomous Unmanned Systems of Zhejiang Province Zhejiang University Hangzhou China State Key Laboratory of Industrial Control Technology Zhejiang University Hangzhou China

ISBN: (数字)9798350378412

ISBN: (纸本)9798350378429

As the explosive increase of drone classes, most existing radio frequency (RF) based drone detection methods belong to the supervised learning approaches, which brings the risk of misclassifying unknown classes. To address this problem, an open set signal recognition method for unknown drone detection is proposed to deal with such a scenario where testing classes do not exactly match training classes. In particular, dilated convolution layers with multi-level receptive fields are used in the process of signal semantic construction, which facilitates feature extraction by jointly exploiting the image-transmission signals and the flight control signals of drones. Besides, an outlier analysis-based classifier is designed in the semantic classification process, which relaxes the necessity of manually setting the bounding thresholds. Furthermore, a newly established real-world dataset DroneRFaSpectra is also released, which includes 12 drone classes with a total number of 8334 samples. Experimental results demonstrate that the proposed method outperforms the compared detection methods, achieving the highest detection rate of 99.26% for unknown drones.

关键词： Training Convolution Semantics Supervised learning Process control Feature extraction Explosives

来源：评论

学校读者我要写书评

暂无评论

Distributed Pose-graph Optimization with Multi-level Partitioning for Collaborative SLAM

arXiv

引用

arXiv 2024年

作者： Li, Cunhao Guo, Guanghui Yi, Peng Hong, Yiguang The Department of Control Science and Engineering Tongji University Shanghai China The Department of Control Science and Engineering National Key Laboratory of Autonomous Intelligent Unmanned Systems Frontiers Science Center for Intelligent Autonomous Systems Ministry of Education Tongji University Shanghai China

The back-end module of Distributed Collaborative Simultaneous Localization and Mapping (DCSLAM) requires solving a nonlinear Pose Graph Optimization (PGO) under a distributed setting, also known as SE(d)-synchronization. Most existing distributed graph optimization algorithms employ a simple sequential partitioning scheme, which may result in unbalanced subgraph dimensions due to the different geographic locations of each robot, and hence imposes extra communication load. Moreover, the performance of current Riemannian optimization algorithms can be further accelerated. In this letter, we propose a novel distributed pose graph optimization algorithm combining multi-level partitioning with an accelerated Riemannian optimization method. Firstly, we employ the multilevel graph partitioning algorithm to preprocess the naive pose graph to formulate a balanced optimization problem. In addition, inspired by the accelerated coordinate descent method, we devise an Improved Riemannian Block Coordinate Descent (IRBCD) algorithm and the critical point obtained is globally optimal. Finally, we evaluate the effects of four common graph partitioning approaches on the correlation of the inter-subgraphs, and discover that the Highest scheme has the best partitioning performance. Also, we implement simulations to quantitatively demonstrate that our proposed algorithm outperforms the state-of-the-art distributed pose graph optimization protocols1 Copyright © 2024, The Authors. All rights reserved.

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

Cross-Subject Depression Level Classification Using EEG Signals with a Sample Confidence Method

arXiv

引用

arXiv 2025年

作者： Zhang, Zhong-Yi Xu, Chen-Yang Zhao, Li-Xuan Hou, Hui-Rang Meng, Qing-Hao Tianjin Key Laboratory of Process Measurement and Control Institute of Robotics and Autonomous Systems School of Electrical and Information Engineering Tianjin University Tianjin300072 China

Electroencephalogram (EEG) is a non-invasive tool for real-time neural monitoring, widely used in depression detection via deep learning. However, existing models primarily focus on binary classification (depression/normal), lacking granularity for severity assessment. To address this, we proposed the DepL-GCN, i.e., Depression Level classification based on GCN model. This model tackles two key challenges: (1) subjectivity in depression-level labeling due to patient self-report biases, and (2) class imbalance across severity categories. Inspired by the model learning patterns, we introduced two novel modules: the sample confidence module and the minority sample penalty module. The former leverages the L2-norm of prediction errors to progressively filter EEG samples with weak label alignment during training, thereby reducing the impact of subjectivity;the latter automatically upweights misclassified minority-class samples to address imbalance issues. After testing on two public EEG datasets, DepL-GCN achieved accuracies of 81.13% and 81.36% for multi-class severity recognition, outperforming baseline models. Ablation studies confirmed both modules’ contributions. We further discussed the strengths and limitations of regression-based models for depression-level recognition. Copyright © 2025, The Authors. All rights reserved.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

PAGNet: Pluggable Adaptive Generative networks for Information Completion in Multi-Agent Communication

arXiv

引用

arXiv 2025年

作者： Zhang, Zhuohui Cheng, Bin Wang, Zhipeng Zhou, Yanmin Li, Gang Lu, Ping He, Bin Chen, Jie Department of Control Science & Engineering Tongji University Shanghai201804 China National Key Laboratory of Autonomous Intelligent Unmanned Systems Shanghai201203 China

For partially observable cooperative tasks, multiagent systems must develop effective communication and understand the interplay among agents in order to achieve cooperative goals. However, existing multi-agent reinforcement learning (MARL) with communication methods lack evaluation metrics for information weights and information-level communication modeling. This causes agents to neglect the aggregation of multiple messages, thereby significantly reducing policy learning efficiency. In this paper, we propose pluggable adaptive generative networks (PAGNet), a novel framework that integrates generative models into MARL to enhance communication and decision-making. PAGNet enables agents to synthesize global states representations from weighted local observations and use these representations alongside learned communication weights for coordinated decision-making. This pluggable approach reduces the computational demands typically associated with the joint training of communication and policy networks. Extensive experimental evaluations across diverse benchmarks and communication scenarios demonstrate the significant performance improvements achieved by PAGNet. Furthermore, we analyze the emergent communication patterns and the quality of generated global states, providing insights into operational mechanisms. Copyright © 2025, The Authors. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Soft Safety Analysis of Interconnected systems

引用

IEEE Transactions on Automatic control 2024年

作者： Zhang, Weihao Zhao, Di Liang, Shu Tongji University Department of Control Science and Engineering Shanghai Institute of Intelligent Science and Technology Shanghai201804 China Tongji University National Key Laboratory of Autonomous Intelligent Unmanned Systems Frontiers Science Center for Intelligent Autonomous Systems Shanghai201804 China

This paper introduces the concept of soft safety for nonlinear dynamical systems, examined from an input-output perspective, and establishes criteria for verifying soft safety in interconnected systems. Diverging from traditional safety approaches that enforce rigid/hard constraints on system states, our proposal involves integrating soft barrier functions with respect to system inputs and outputs to characterize soft safety. Particularly, when the soft barrier function takes a quadratic form with a constant QSR multiplier - later extended to a dynamic multiplier - we further define QSR safety for a class of nonlinear systems subject to quadratic constraints on input-output signals. The paper presents methods for analyzing QSR safety in both open-loop systems with state-space representations and interconnected systems, with these methods subsequently employed to design QSR soft safe systems meeting prescribed safety and stability requirements. Numerical and simulation examples are provided to illustrate the rationality of the concept and the efficacy of the results. © 1963-2012 IEEE.

关键词： State space methods

来源：评论

学校读者我要写书评

暂无评论

Prescribed Time Performance Security Tracking control of Quadrotors Under Unknown Attacks

Prescribed Time Performance Security Tracking Control of Qua...

引用

第43届中国控制会议

作者： Liping Wang Hailong Pei Key Laboratory of Autonomous Systems and Networked Control Ministry of EducationGuangdong Engineering Technology Research Center of Unmanned Aerial Vehicle SystemsSouth China University of Technology

ISBN: (数字)9789887581581

ISBN: (纸本)9798350366907

This paper investigates the prescribed time performance security tracking control problem of quadrotors under unknown attacks. First,by using a prescribed time performance function and coordinate transformation,the tracking error can remain within a given region in a prescribed time. In the backstepping design process,a first-order sliding mode differentiator is given to surmount the problem of "the explosion of complexity",and the Nussbaum function is developed to deal with the unknown attacks problem. A prescribed time performance security attitude tracking control method is designed to prove the boundedness of the closed-loop signals. Finally,the simulation results are enumerated to state the superiority and effectiveness of the designed control method.

关键词： quadrotor unmanned aerial vehicles unknown deception attack backstepping Nussbaum function

来源：评论

学校读者我要写书评

暂无评论

A Hierarchical Deep Reinforcement Learning Strategy for Collective Pursuit-Evasion Game with Partial Observations

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2025年

作者： Wang, Xiaoxiao Yi, Peng Hong, Yiguang Tongji University Shanghai Research Institute for Intelligent Autonomous Systems Shanghai200092 China Tongji University School of Electronics and Information Shanghai200070 China Tongji University Control Science and Engineering Department Shanghai200070 China National Key Laboratory of Autonomous Intelligent Unmanned Systems China Ministry of Education Frontiers Science Center for Intelligent Autonomous Systems China

This paper addresses the problem of Collective Pursuit-Evasion Game (C-PEG) with partial observation, aiming to enhance cooperation among cluster pursuers, reduce the game space, and optimize the overall pursuer strategy efficiency in complex dynamic environments. Firstly, we consider a distributed communication model suitable for cluster collaboration and model the multi-agent cooperative task as a Collective Decentralized Partially Observable Markov Decision Process (C-Dec POMDP). Then we propose a Hierarchical Regularization Game Multi-agent Deep Deterministic Policy Gradient (HRG-MADDPG) algorithm, which includes High-Level Strategy (HLS) and Low-Level Strategy (LLS). The HLS takes the current observation from the pursuers’ sensors and the pursuers’ status as inputs, and outputs target allocation strategies for the coalitions and individuals to guide the LLS in executing specific pursuit tasks. The LLS is further divided into centralized training and decentralized execution phases. In the centralized training phase, the guiding strategy provided by the HLS and the introduced regularization auxiliary term are combined to promote decision-making through the fusion of favorable situations and auxiliary terms. In the decentralized execution phase, a reliable policy improvement method based on partially observable information is designed. All in all, the HRG-MADDPG algorithm provides a reliable method for collective pursuit-evasion. It is trained in a single environment and further validated in multiple different test environments. Simulation results confirm the effectiveness of the proposed method, showing the adaptability, scalability, and rapid responsiveness of the proposed framework in various practical applications. © 2020 IEEE.

关键词： Hierarchical systems

来源：评论

学校读者我要写书评

暂无评论

A method based on YOLOv4 and classic image processing methods to detect defects about distance in strain clamps 2

A method based on YOLOv4 and classic image processing method...

引用

2nd International Conference on Energy, Power, and Electrical Technology, ICEPET 2023

作者： Du, Qiliang Lin, Jiashuo Qu, Fengrui Tian, Lianfang School of Automation Science and Engineering South China University of Technology Guangzhou510641 China Sino-Singapore International Joint Research Institute Guangzhou510555 China Key Laboratory of Autonomous Systems and Network Control of Ministry of Education Guangzhou510641 China Research Institute of Modern Industrial Innovation South China University of Technology Zhuhai519170 China

ISBN: (纸本)9781510668270

Strain clamps of transmission lines are the main part of transmission lines, which play the role of bearing tensile force and transmitting current in the transmission line. In this paper, we focus on the distance between the end of steel anchor and strand in the strain clamps. We propose a method using YOLOv4 and classic image processing methods to measure the distance referred to above, according to which we can judge whether the strain clamps have defects about distance. We first got the bounding boxes of the end of steel anchor and strand in the strain clamps by YOLOv4, thus calculating the distance between the two bounding boxes. Meanwhile, we used classic image processing methods to get the diameter of the steel anchor. Finally, we calculated the ratio of the two distances mentioned above to determine whether the defect exists. We achieve good performance in the detection of distance defects in strain clamps with high accuracy through the research in this paper. © 2023 SPIE. All rights reserved.

关键词： Electric lines

来源：评论

学校读者我要写书评

暂无评论

Use Anchor-Free Based Object Detectors to Detect Surface Defects

Use Anchor-Free Based Object Detectors to Detect Surface Def...

引用

TEPEN International Workshop on Fault Diagnostics and Prognostics, TEPEN-IWFDP 2024

作者： Liu, Jiaxue Zhang, Chao Li, Jianjun College of Mechanical Engineering Inner Mongolia University of Science and Technology Baotou014000 China Inner Mongolia Autonomous Region Key Laboratory of Intelligent Diagnosis and Control of Electromechanical Systems Baotou014010 China College of Information Engineering Inner Mongolia University of Science and Technology Baotou014000 China

ISBN: (纸本)9783031702341

Many anchor-based object detectors have limitations in the detection process because of the presence of anchors. Therefore, in recent years, many researchers have shifted their focus to designing anchor-free object detectors. In this paper, we initially employ several common anchor-free detectors (CenterNet, FCOS, YOLOX-S, and YOLOV8-S) to detect surface defects in the hot-rolled strip datasets from Northeastern University (NEU-DET). Following experimental comparisons, YOLOV8-S demonstrates the best detection performance (mAP is 78.04% and the FPS is 8.45). Secondly, we utilize transfer learning to mitigate the overfitting problem that large models can induce on small datasets. Finally, we conduct a large number of experimental comparisons to verify the effectiveness of the model. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Transfer learning

来源：评论

学校读者我要写书评

暂无评论

Deterministic Learning-Based Robust Practical Output Regulation for Second-Order Nonlinear systems

Deterministic Learning-Based Robust Practical Output Regulat...

引用

Complex systems and Intelligent Science (CSIS-IAC), International Annual Conference on

作者： Qingxi Hu Wei Liu Key Laboratory of Autonomous Systems and Networked Control of Ministry of Education School of Automation Science and Engineering South China University of Technology Guangzhou China

ISBN: (数字)9798331504755

ISBN: (纸本)9798331504762

This article intends to investigate the semi-global robust practical output regulation problem for a class of second-order nonlinear systems with parametric and non-parametric uncertainties based on deterministic learning method. First, by constructing the internal models, the robust output regulation problem is transformed into the semi-global robust practical stabilization problem. Second, we propose an adaptive neural control (ANC) strategy to solve the stabilization problem and utilize the radial basis function neural networks (RBF NNs) to identify unknown dynamic. Moreover, under the persistently exciting (PE) property, the unknown dynamics can be identified and the learned knowledge is saved as some constant NN weights. Finally, we design an deterministic learning-based adaptive neural control (DLANC) law with the learned knowledge to solve the output regulation problem and improve control performance.

关键词： Learning systems Uncertainty Adaptive systems Process control Artificial neural networks Radial basis function networks Regulation Nonlinear dynamical systems Complex systems Convergence

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：