检索结果-内蒙古大学图书馆

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Zhang, Zhiyong Liu, Ruyu Wang, Chaochao Zhang, Xianchao Zhang, Jianhua Liu, Xiufeng School of Computer Science and Engineering Tianjin University of Technology Tianjin China School of Information Science and Technology Hangzhou Normal University Hangzhou China Provincial Key Laboratory of Multimodal Perceiving and Intelligent Systems Jiaxing University Zhejiang China Department of Technology Management and Economics Technical University of Denmark Lyngby Denmark

ISBN: (纸本)9798350368741

Getting dense, uniform, time-series point cloud data is critical for effective rendering. However, due to the limited computational power of edge devices, existing methods cannot achieve real-time results, which affects the visual quality of the consumer experience. To effectively address this issue, this paper presents a self-supervised adversarial upsampling method for point cloud video streams called SPR-GAN. In the generator, we design the Temporal Iterative Graph module to learn local features for each frame and captures long-range spatial information using three iterations of graph convolution operations. Then the Contextual Temporal Fusion module is developed to merge information between different frames, synthesizing temporal information and enriching the dynamic feature representation of the point cloud. Meanwhile, in the discriminator, we introduce the Efficient Shape module. Through dynamic graph convolution operations and stacked learning, it significantly improves the resolution efficiency of global shape information in point clouds. The final experiments show that the proposed method exhibits high practicality and superiority. The model achieves a good result on both the D-FAUST and DeformingThing4D-Animals datasets. © 2025 IEEE.

关键词： point cloud sequence Point cloud upsampling self-supervised temporal aggregation

来源：评论

学校读者我要写书评

暂无评论

Improved High-Speed Thermal Analysis Based on Two-Step Simulation for High-Frequency Transformers 14

Improved High-Speed Thermal Analysis Based on Two-Step Simul...

引用

14th Annual IEEE Applied Power Electronics Conference and Exposition, APEC 2025

作者： Yi, Zheyuan Sun, Kai Li, Qiang Liu, Zengyang Tsinghua University State Key Laboratory of Power System Department of Electrical Engineering Beijing China Delta Electronics Shanghai Co. Ltd. Shanghai China University Blacksburg Center for Power Electronics Systems The Bradley Department of Electrical and Computer Engineering Virginia Polytechnic Institute and State BlacksburgVA United States

ISBN: (纸本)9798331516116

Thermal analysis is a crucial and time-consuming step in the optimization design process of high-frequency transformers (HFTs). This paper proposes an improved thermal analysis method based on heat dissipation-conduction two-step simulation, significantly reducing the computation time while ensuring the accuracy of thermal analysis. Simulation results validate the accuracy and of the proposed method and demonstrate that the proposed method saves 82% of computation time for a single thermal analysis case compared to direct CFD. Experimental results further verify the accuracy of the proposed method. An exemplary application of the proposed method in the optimization design of the HFT illustrates a 98% reduction in computation time for thermal analysis during the optimization process. © 2025 IEEE.

关键词： Thermal modeling

来源：评论

学校读者我要写书评

暂无评论

Intelligent Cooperative Sensing for Connected and Autonomous Vehicles: An Improved Decision Transformer Approach

引用

IEEE Internet of Things Journal 2025年第11期12卷 15424-15437页

作者： Pincan Zhao Changle Li Xinrui Zhang F. Richard Yu Yuchuan Fu State Key Laboratory of Integrated Services Networks Xidian University Xi’an China School of Information Technology Carleton University Ottawa ON Canada Department of Systems and Computer Engineering Carleton University Ottawa ON Canada

Effective sensing capabilities are crucial for the safe and reliable operation of Connected and autonomous vehicles (CAVs). While traditional approaches focus on enhancing onboard sensors, the integration of road sensor networks (RSNs) into the CAV ecosystem presents a promising solution to improve sensing performance, but also introduces significant challenges, including heterogeneous sensing requirements, inconsistencies in multisource sensor data, and efficient resource utilization. To address these challenges, this article proposes a novel cooperative sensing framework that leverages multisource and multilevel sensing information from RSNs to optimize CAV sensing performance in resource-constrained scenarios. We develop an improved decision transformer (DT)-based approach that dynamically adapts to diverse driving conditions and efficiently fuses sensor data at various abstraction levels. To tackle the issue of long-delayed rewards, we introduce a reshaped reward function and a bi-level optimization framework that enables effective propagation of rewards along decision sequences. An advanced gradient approximation technique is employed to efficiently solve the optimization problem. Extensive simulations demonstrate the superior performance of our improved DT approach compared to state-of-the-art reinforcement learning (RL) methods in terms of sensing accuracy, coverage, and data efficiency under various traffic conditions.

关键词： Connected vehicles Fuses Thermal sensors Sensor fusion Transformers Data models Sensors Resource management Optimization Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

Equilibrium-Independent Control of Continuous-Time Nonlinear systems Via the LPV Framework

引用

IEEE Transactions on Automatic Control 2025年

作者： Koelewijn, Patrick J. W. Weiland, Siep Toth, Roland Eindhoven University of Technology Control Systems Group Department of Electrical Engineering Eindhoven Netherlands Institute for Computer Science and Control Systems and Control Laboratory Budapest Hungary

In this paper, we consider the analysis and control of continuous-time nonlinear systems to ensure universal shifted stability and performance, i.e., stability and performance w.r.t. each forced equilibrium point of the system. This "equilibrium-free"concept is especially beneficial for control problems that require the tracking of setpoints and rejection of persistent disturbances, such as input loads. In this paper, we show how the velocity form, i.e., the time-differentiated dynamics of the system, plays a crucial role in characterizing these properties and how the analysis of it can be solved by the application of Linear Parameter-Varying (LPV) methods in a computationally efficient manner. Furthermore, by leveraging the properties of the velocity form and the LPV framework, a novel controller synthesis method is presented which ensures closed-loop universal shifted stability and performance. The proposed controller design is verified experimentally on a real system. Additionally, we compare the proposed method to a standard LPV control design, demonstrating the improved stability and performance guarantees of the new approach. © 1963-2012 IEEE.

关键词： Equilibrium independent dissipativity linear parameter-varying systems output feedback stability of nonlinear systems

来源：评论

学校读者我要写书评

暂无评论

ON INFINITE-HORIZON MINIMUM ENERGY CONTROL

arXiv

引用

arXiv 2025年

作者： Belabbas, Mohamed-Ali Chen, Xudong Electrical and Computer Engineering Department and Coordinated Science Laboratory University of Illinois Urbana-Champaign United States Electrical and Systems Engineering Washington University in St. Louis United States

We address the infinite-horizon minimum energy control problem for linear time-invariant finite-dimensional systems (A, B). We show that the problem admits a solution if and only if (A, B) is stabilizable and A does n... 详细信息

关键词： Linear time-invariant system

来源：评论

学校读者我要写书评

暂无评论

Data-Driven Incentive Mechanisms for Federated Learning in Vehicular Networks

引用

IEEE Transactions on Vehicular Technology 2025年

作者： Fathi, Faeze Montazeri, Mina N.araabi, Babak Du, Hongyang Niyato, Dusit Kebriaei, Hamed University of Tehran School of Ece College of Engineering Tehran Iran Urban Energy Systems Laboratory Dübendorf8600 Switzerland Nanyang Technological University School of Computer Science and Engineering The Energy Research Institute @ Ntu Interdisciplinary Graduate Program Singapore Nanyang Technological University School of Computer Science and Engineering Singapore School of Computer Science Tehran Iran

Centralized machine learning algorithms in vehicular networks face privacy and resource constraints. Federated Learning (FL) addresses these by enabling collaborative model training without sharing raw data. To incentivize vehicle participation despite resource constraints, we propose a contract between Roadside Units (RSUs) and vehicles, specifying required computation resources and rewards based on local data quality. The contract is designed to maximize the utility of the RSU, subject to constraints that ensure the participation of the vehicles in the task and truthful reporting of their data quality parameter. However, designing an optimal contract with classical methods is limited to specific utility functions. To extend the design methodology of optimal contracts to a broader range of utility functions, our study proposes a deep learning-based solution. Specifically, we present a novel application of Deep Neural Networks (DNNs), marking the first instance of applying DNNs in contract theory-based incentive mechanisms to achieve nearoptimal contracts. We design the DNN's structure to inherently satisfy specific constraints of the optimization problem, enhancing its efficiency and accuracy in determining the optimal contract. We utilize an augmented Lagrangian method to approximate the optimal contract in federated learning tasks. A case study on traffic sign recognition demonstrates the applicability and effectiveness of our method. Comparing our approach with the well-known generative diffusion model shows that in the FL scenarios, the DNN results are closer to the optimal contract compared to those of the generative diffusion model. © 1967-2012 IEEE.

关键词： Traffic signs

来源：评论

学校读者我要写书评

暂无评论

On Space-Filling Input Design for Nonlinear Dynamic Model Learning: A Gaussian Process Approach

arXiv

引用

arXiv 2025年

作者： Liu, Yuhan Kiss, Máté Tóth, Roland Schoukens, Maarten Control Systems Group Department of Electrical Engineering Eindhoven University of Technology Eindhoven5600 MB Netherlands Systems and Control Laboratory HUN-REN Institute for Computer Science and Control Budapest1111 Hungary

While optimal input design for linear systems has been well-established, no systematic approach exists for nonlinear systems, where robustness to extrapolation/interpolation errors is prioritized over minimizing estimated parameter variance. To address this issue, we develop a novel identification-oriented space-filling input design strategy for efficient covering of a well-defined region of interest. By placing a Gaussian Process (GP) prior on the joint input-state space, the proposed strategy leverages the GP posterior variance to construct a space-filling promoting input design cost function from the Bayesian point of view. This accordingly enables maximization of the coverage in the region of interest, thereby facilitating the generation of informative datasets. Furthermore, we theoretically prove that minimization of the cost function indicates the space-filling behavior. The effectiveness of the proposed strategy is demonstrated on both an academic example and a mass-spring-damper system, highlighting its potential practical impact on efficient exploration in identification scenarios for nonlinear dynamical systems. © 2025, CC BY-NC-SA.

关键词： Cost functions

来源：评论

学校读者我要写书评

暂无评论

Self-Supervised Reflective Learning Through Self-Distillation and Online Clustering for Speaker Representation Learning

引用

IEEE Transactions on Audio, Speech and Language Processing 2025年 33卷 1535-1550页

作者： Danwei Cai Zexin Cai Ze Li Ming Li Department of Electrical and Computer Engineering Duke University Durham NC USA Suzhou Municipal Key Laboratory of Multimodal Intelligent Systems Digital Innovation Research Center Duke Kunshan University Kunshan China School of Computer Science Wuhan University Wuhan China

Speaker representation learning is crucial for voice recognition systems, with recent advances in self-supervised approaches reducing dependency on labeled data. Current two-stage iterative frameworks, while effective, suffer from significant computational overhead due to repeated rounds of clustering and training. They also struggle with noisy pseudo labels that can impair model learning. This paper introduces self-supervised reflective learning (SSRL), an improved framework that addresses these limitations by enabling continuous refinement of pseudo labels during training. Through a teacher-student architecture and online clustering mechanism, SSRL eliminates the need for iterative training rounds. To handle label noise, we incorporate noisy label modeling and pseudo label queues that maintain temporal consistency. Experiments on VoxCeleb show SSRL's superiority over current two-stage iterative approaches, surpassing the performance of a 5-round method in just a single training round. Ablation studies validate the contributions of key components like noisy label modeling and pseudo label queues. Moreover, consistent improvements in pseudo labeling and the convergence of cluster counts demonstrate SSRL's effectiveness in deciphering unlabeled data. This work marks an important advancement in efficient and accurate self-supervised speaker representation learning through the novel reflective learning paradigm.

关键词： Training Representation learning Iterative methods Noise Adaptation models Noise measurement Predictive models Speech processing Robustness Convergence

来源：评论

学校读者我要写书评

暂无评论

Design of Distributed Nonlinear Observers Without Using Global Inputs

引用

IEEE Transactions on Automatic Control 2025年

作者： Cao, Ganghui Wang, Jinzhi Polycarpou, Marios M. Peking University State Key Laboratory for Turbulence and Complex Systems Department of Mechanics and Engineering Science College of Engineering Beijing100871 China University of Cyprus KIOS Research and Innovation Center of Excellence and the Department of Electrical and Computer Engineering Nicosia1678 Cyprus

This paper investigates the design of distributed observers for a class of nonlinear systems. The designed distributed observers reside in a network of sensor nodes. The communication links in the network enable each sensor node to estimate all states of the nonlinear system, even though each one can only collect a small portion of the system's outputs. However, all inputs of the system are still needed at each node to carry out a correct state estimation. For this problem, the paper further proposes a distributed nonlinear observer without using global inputs, in which each sensor node only needs partial input information of the nonlinear system. © 1963-2012 IEEE.

关键词： Nonlinear simulations

来源：评论

学校读者我要写书评

暂无评论

Symbiotic Control of Uncertain Dynamical systems: Harnessing Synergy Between Fixed-Gain Control and Adaptive Learning Architectures

引用

IEEE Transactions on Automatic Control 2025年

作者： Yucelen, Tansel Sarsilmaz, Selahattin Burak Yildirim, Emre University of South Florida Department of Mechanical Engineering Laboratory for Autonomy Control Information and Systems TampaFL33620 United States Utah State University Department of Electrical and Computer Engineering LoganUT84322 United States

Both fixed-gain control and adaptive learning architectures aim to mitigate the effects of uncertainties. In particular, fixed-gain control offers more predictable closed-loop system behavior but requires the knowledge of uncertainty bounds. In contrast, while adaptive learning does not necessarily require such knowledge, it often results in less predictable closed-loop system behavior compared to fixed-gain control. To this end, this paper presents a novel symbiotic control framework that offers the strengths of fixed-gain control and adaptive learning architectures. Specifically, this framework synergistically integrates these architectures to mitigate the effects of uncertainties in a more predictable manner as compared to adaptive learning alone and it does not require any knowledge on such uncertainties. Both parametric and nonparametric uncertainties are considered, where we utilize neural networks to approximate the unknown uncertainty basis for the latter case. Counterintuitively, the proposed framework has the ability to achieve a desired level of closed-loop system behavior even with an insufficient number of neurons (e.g., when the neural network approximation error is large) or in the face of injudiciously selected adaptive learning parameters (e.g., high leakage term parameters). © 1963-2012 IEEE.

关键词： Closed loop control systems

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：