检索结果-内蒙古大学图书馆

Multi-Time-Scale Variational Mode Decomposition-Based Robust Fault Diagnosis of Railway Point Machines Under Multiple Noises

引用

Chinese Journal of Electronics 2024年第3期33卷 814-822页

作者： Junqi LIU Tao WEN Guo XIE Yuan CAO Clive Roberts Shaanxi Key Laboratory of Complex System Control and Intelligent Information Processing Xi'an University of Technology The School of Electronic and Information Engineering Beijing Jiaotong University Birmingham Centre for Railway Research and Education University of Birmingham

The fault diagnosis of railway point machines(RPMs) has attracted the attention of engineers and *** have studies considered diverse noises along the *** fulfill this aspect,a multi-time-scale variational mode decomposition(MTSVMD) is proposed in this paper to realize the accurate and robust fault diagnosis of RPMs under multiple *** decomposes condition monitoring signals after coarse-grained processing in varying *** this manner,the information contained in the signal components at multiple time scales can construct a more abundant feature space than at a single *** the experimental validation,a random position,random type,random number,and random length(4R) noise-adding algorithm helps to verify the robustness of the *** adequate experimental results demoristrate the superiority of the proposed MTSVMD-based fault diagnosis.

关键词： Railway point machines Fault diagnosis Multi-time-scale Variational mode decomposition

来源：评论

学校读者我要写书评

暂无评论

Research on solving time-dependent Schrodinger equation for higher-order FDTD based on spatial filtering

Research on solving time-dependent Schrodinger equation for ...

引用

2023 International Applied Computational Electromagnetics Society Symposium, ACES-China 2023

作者： Ding, Wenjie Xie, Guoda Huang, Zhixiang Ministry of Education The Key Laboratory of Intelligent Computing and Signal Processing Hefei China Hefei China

ISBN: (纸本)9781733509657

Combining the spatial filtering (SF) technique with FDTD(2, q) method (2 and q denote the temporal differential order and spatial differential order, respectively), a novel SF-FDTD(2, q) method with more relaxed Courant-Friedrichs-Lewy (CFL) condition is proposed and used for solving 3D time-dependent Schrödinger equation. Then, the correctness of the SF-FDTD(2, q) method is validated by calculating eigenfrequencies of the 3D quantum well model. © 2023 Applied Computational Electromagnetics Society (ACES).

关键词： Computational electromagnetics

来源：评论

学校读者我要写书评

暂无评论

Relaxing Distillation Constraints for Improved New Class Learning in Continual Semantic Segmentation

Relaxing Distillation Constraints for Improved New Class Lea...

引用

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

作者： Ti, Zheng Hao, Xuze Chen, Renhai College of Intelligence and Computing Tianjin University Tianjin China School of Computer Science Shanghai Key Laboratory of Intelligent Information Processing Fudan University Shanghai China

ISBN: (纸本)9798350368741

Continual Semantic Segmentation (CSS) aims to continuously learn new classes while mitigating catastrophic forgetting. Existing CSS methods primarily address this challenge through knowledge distillation. While they focus on maintaining stability for old classes, this emphasis often restricts plasticity in learning new ones. In this work, we propose two plug-and-play methods to better balance stability and plasticity. First, for feature map distillation, we replace pixel-level constraints with statistical information extraction within a window, improving the learning of new classes while preserving structural integrity to overcome forgetting. Second, we use relative ranks of predictions to replace exact probabilistic values to loosen the constraints in the logit distribution of old classes. Extensive experiments demonstrate that our methods outperform state-of-the-art methods when integrating into several baselines across various CSS scenarios. © 2025 IEEE.

关键词： Continual Learning Knowledge Distillation Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning based intelligent Routing for Multi-service Traffic SDN 5

Deep Reinforcement Learning based Intelligent Routing for Mu...

引用

5th International Academic Exchange Conference on Science and Technology Innovation, IAECST 2023

作者： Wang, Lingjiao Li, Jiachen Xiang Tan University Key Laboratory of Intelligent Computing and Information Processing Ministry of Education China Xiang Tan University School of Automation and Electronic Information China

ISBN: (纸本)9798350357738

The development of network has imposed higher requirements on QoS (Quality of Service) for routing, and the emergence of traffic classification techniques, software defined networking (SDN), and programmable network devices has made it possible to quickly identify user needs and route for service traffic requirements. Deep reinforcement learning routing algorithms for existing QoS compliant routing algorithms perform poorly in terms of generalizability. A deep graph reinforcement learning intelligent routing algorithm DDGL applied to SDN scenarios is proposed, which uses GNN to extract the link feature information of SDN data plane for deep reinforcement learning routing decision making, and comprehensively takes into account the performance metrics such as latency, packet loss, throughput, and bandwidth, to improve the algorithm generalization ability and enhance the SDN routing performance. © 2023 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Design of Microstrip Type Broadband Directional Coupler

Design of Microstrip Type Broadband Directional Coupler

引用

2023 International Applied Computational Electromagnetics Society Symposium, ACES-China 2023

作者： Yan, Hang Wu, Xianliang Wang, Ruikang Wang, Gang Anhui University Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Hefei China

ISBN: (纸本)9781733509657

A microstrip line broadband directional coupler is designed based on microstrip line theory. The bandwidth of the coupler is extended by using a cascade of multiple coupled lines. The isolation of the directional coupler is greatly improved by covering the microstrip line with a dielectric layer [1] and by loading the branching compensation capacitor to compensate for the odd-even mode phase velocity difference. Simulation results of ANSYS HFSS 2019 show that the return loss (S11) is greater than 20 dB, the insertion loss (S21) is less than 1.7 dB, the coupling degree (S31) is about -6dB(±0.8dB), the isolation degree (S41) is greater than 23.4dB, and the minimum directionality is greater than 17dB during 700 MHz-3700 MHz. The physical size of coupler is 18 mm × 60mm, which meets the design requirements of 6dB coupler. © 2023 Applied Computational Electromagnetics Society (ACES).

关键词： Directional couplers

来源：评论

学校读者我要写书评

暂无评论

Trajectory optimization for UAV-enabled relaying with reinforcement learning

引用

Digital Communications and Networks 2025年第1期11卷 200-209页

作者： Chiya Zhang Xinjie Li Chunlong He Xingquan Li Dongping Lin School of Electronic and Information Engineering Harbin Institute of TechnologyShenzhenChina Guangdong Key Laboratory of Intelligent Information Processing Shenzhen UniversityShenzhenChina Peng Cheng Laboratory(PCL) ShenzhenChina National Mobile Communications Research Laboratory Southeast UniversityNanjingChina Shenzhen Institute of Information Technology ShenzhenChina Guangdong-Hong Kong Joint Laboratory for Big Data Imaging and Communication Shenzhen UniversityShenzhenChina

In this paper,we investigate the application of the Unmanned Aerial Vehicle(UAV)-enabled relaying system in emergency communications,where one UAV is applied as a relay to help transmit information from ground users to a Base Station(BS).We maximize the total transmitted data from the users to the BS,by optimizing the user communication scheduling and association along with the power allocation and the trajectory of the *** solve this non-convex optimization problem,we propose the traditional Convex Optimization(CO)and the Reinforcement Learning(RL)-based ***,we apply the block coordinate descent and successive convex approximation techniques in the CO approach,while applying the soft actor-critic algorithm in the RL *** simulation results show that both approaches can solve the proposed optimization problem and obtain good ***,the RL approach establishes emergency communications more rapidly than the CO approach once the training process has been completed.

关键词： Unmanned aerial vehicle Emergency communications Trajectory optimization Convex optimization Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A Range-Based Node Localization Scheme for UWASNs Considering Noises and Aided With Neurodynamics Model

引用

IEEE/CAA Journal of Automatica Sinica 2023年第11期10卷 2168-2170页

作者： Lijuan Wang Xiujuan Du Chong Li School of Computer Qinghai Normal UniversityQinghai Provincial Key Laboratory of IoTXining 810008 the State Key Laboratory of Tibetan Intelligent Information Processing and Application Xining 810008 Academy of Plateau Science and Sustainability Xining 810008China

Dear Editor,This letter focuses on the node localization problem in underwater acoustic sensor networks(UWASNs) with the time-dependent property and various noise disturbances. A range-based localization scheme aided with an integral-feedback-based neurodynamics(IND)model is proposed and referred to as IND-RS, which has the stability against the internal perturbations encountered during the solving process.

关键词： dynamics underwater networks

来源：评论

学校读者我要写书评

暂无评论

An anti-occlusion tracking algorithm based on mask strategy and adaptive response fusion 12

An anti-occlusion tracking algorithm based on mask strategy ...

引用

SPIE 12th International Symposium on Multispectral Image processing and Pattern Recognition, MIPPR 2023

作者： Duan, Zhongyu Huang, Shixiang Yue, Zhongmu Tian, Tian Tian, Jinwen National Key Laboratory of Multispectral Information Intelligent Processing Technology Huazhong University of Science and Technology Wuhan China

ISBN: (数字)9781510674943

ISBN: (纸本)9781510674936

In long-Term target tracking, target occlusion is an important factor that affects the performance of the tracker, and it is also an inevitable problem in long-Term target tracking. Therefore, it is necessary to adopt corresponding strategies for target occlusion to improve the robustness of the tracker in corresponding scenarios. In response to the problem of target loss in complex background scenarios such as target occlusion in current filtering based tracking algorithms, this paper studies the use of masking strategies and adaptive response fusion methods to improve the accuracy and robustness of tracking *** experimental results demonstrate the effectiveness of various strategies in resisting occlusion in tracking algorithms. The experimental results of the overall algorithm indicate that the algorithm can effectively solve occlusion problems while balancing accuracy, speed, and robustness. © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.

关键词： Target tracking

来源：评论

学校读者我要写书评

暂无评论

Clustering for Bivariate Functional Data

引用

Acta Mathematicae Applicatae Sinica 2024年第3期40卷 613-629页

作者： Shi-yun CAO Yan-qiu ZHOU Yan-ling WAN Tao ZHANG School of Science Guangxi University of Science and TechnologyLiuzhou 545006China School of Marxism Guangxi University of Science and TechnologyLiuzhou 545006China Key Laboratory of Intelligent Information Processing and Graph Processing Guangxi University of Science and TechnologyLiuzhou 545006China

In this paper,we consider the clustering of bivariate functional data where each random surface consists of a set of curves recorded repeatedly for each *** k-centres surface clustering method based on marginal functional principal component analysis is proposed for the bivariate functional data,and a novel clustering criterion is presented where both the random surface and its partial derivative function in two directions are *** addition,we also consider two other clustering methods,k-centres surface clustering methods based on product functional principal component analysis or double functional principal component *** results indicate that the proposed methods have a nice performance in terms of both the correct classification rate and the adjusted rand *** approaches are further illustrated through empirical analysis of human mortality data.

关键词： bivariate functional data -centres surface clustering functional principal component analysis partial derivative function

来源：评论

学校读者我要写书评

暂无评论

An Adaptive Parallel Gaussian Homotopy Approach for Zeroth-Order Optimization

An Adaptive Parallel Gaussian Homotopy Approach for Zeroth-O...

引用

2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024

作者： Zhou, Bingyi Wang, Guoyou Huazhong University of Science and Technology National Key Laboratory of Multispectral Information Intelligent Processing Technology Wuhan China

ISBN: (纸本)9781665410205

The Gaussian homotopy method is a classical optimization approach for solving nonconvex problems. It applies Gaussian smoothing to a given problem, using varying smoothing factors to generate a series of proxy problems that are easier to solve, subsequently addressing them gradually from simpler to more complex ones. Traditional Gaussian homotopy methods typically utilize a predefined sequence or parameter to update a single smoothing factor serially. However, this sequential updating process is inefficient and unsuitable for parallel homotopy pipelines. Moreover, the utilization of predefined sequences or parameters leads to a lack of adaptability. To address the abovementioned challenges, we propose an adaptive parallel Gaussian homotopy optimization method. Initially, we introduce an adaptive model called Scaling. This model is formulated as a scaler that concurrently adjusts multiple smoothing factors, with each factor aligning to a homotopy level. It can be integrated easily into serial and parallel homotopy pipelines. Furthermore, we establish a collaborative training regimen to jointly train the Scaling model and a parallel homotopy model, named continuation path learning (CPL) [1] model. Throughout the training process, the Scaling model furnishes CPL with multiple scaled smoothing factors and updates CPL implicitly. Extensive experiments demonstrate that the proposed Gaussian homotopy approach performs competitively. © 2024 IEEE.

关键词： Gaussian distribution

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：