检索结果-内蒙古大学图书馆

IET International Radar Conference 2023, IRC 2023

作者： Cao, Yice Zhu, Dayi Wu, Zhenhua Chen, Jie Huang, Zhixiang Yang, Lixia Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education School of Electronics and Information Engineering Anhui University Hefei230601 China 38th Research Institute China Electronics Technology Group Corporation Hefei230088 China

ISBN: (纸本)9781839539954

Gathering reliable labeled samples for polarimetric synthetic aperture (PolSAR) image classification is laborious. Moreover, applying a trained classifier to new domains often leads to noticeable performance degradation due to domain disparities. Therefore, this paper proposes the novel complex-valued cross-domain (CD) few-shot learning classification (CCFSLC) method for PolSAR images to address these issues. Firstly, the transferrable knowledge learning module (TKLM) with a complex-valued feature encoder (CVFE) is trained using source data with sufficient labeled samples. Then, the deep few-shot learning module (DFSLM), constructed using the pre-trained CVFE, is trained by episodes in both source and target domains, with only minimal target labeled samples. Meanwhile, the adversarial domain adaptation module (ADAM) is employed to eliminate domain shift. The proposed CCFSLC mainly focuses on exploring discriminative information from raw PolSAR data, while reducing the domain gap to recognize novel categories in unseen domains with only a few annotated samples. Experiments on typical PolSAR datasets validate the effectiveness of the proposed method. © The Institution of Engineering & Technology 2023.

关键词： Polarimeters

来源：评论

学校读者我要写书评

暂无评论

On book thickness parameterized by the vertex cover number

引用

Science China(information Sciences) 2022年第4期65卷 112-113页

作者： Yunlong LIU Jie CHEN Jingui HUANG School of Information Science and Engineering Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing Hunan Normal University

Dear editor,Book thickness for graphs forms a major theme in graph theory and has a broad application in the fields of sorting permutations, fault tolerant VLSI design, parallel computing, and others. The book Thickness problem, even if the vertex order is taken as part of the input, was shown to be NP-complete in general [1, 2]. Just because of this, parameterized algorithms have been proposed to deal with it [3].

关键词： Book Thickness Vertex Cover Number Linear Order 1-page embedding graph kernel

来源：评论

学校读者我要写书评

暂无评论

Heterophilic Graph Representation Learning Based on Multi-Order information Extraction and High and Low Pass Filters 10

Heterophilic Graph Representation Learning Based on Multi-Or...

引用

10th IEEE Smart World Congress, SWC 2024

作者： Wu, Ling Li, Xinyu Yang, Yingjie Guo, Kun Zhang, Qishan Fuzhou University College of Computer and Data Science Fuzhou China Fujian Key Laboratory of Network Computing and Intelligent Information Processing China De Montfort University School of Computer Science and Informatics Leicester United Kingdom Shanghai International Studies University College of Economics and Humanities Shanghai China

ISBN: (纸本)9798331520861

Real-world networks can be divided into homophilic and heterophilic graphs. Significantly, many nodes tend to be heterophilic in a homophilic graph. Graph representation learning in heterophilic graphs has attracted considerable significance in recent years as it breaks the homophily assumption and achieves higher-quality graph embeddings. However, existing heterophilic graph representation learning methods often mix attribute and topological information, neglecting the mutual exclusion between attribute information and topological information. Furthermore, algorithms in heterogeneous graphs usually rely on specific matrix structures to capture high-order information, which may restrict the applicability of these methods. To tackle these issues, this paper proposes a GNN-based strategy for Heterophilic graph Representation Learning based on Multi-order information extraction and High and Low pass filters (HRLMHL). First, we designed two relatively independent modules to learn attribute information and topological information, respectively, to address the issue of mismatch. Second, we built a multi-order information extraction module to extract multi-order similarity features, thereby achieving the learning of high-order graph information. Experiments on real datasets show that the node classification accuracy is superior to that of the state-of-the-art methods on most datasets. © 2024 IEEE.

关键词： Contrastive Learning

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

International Conference on Acoustics, Speech, and Signal processing (ICASSP)

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

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

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.

关键词： Semantic segmentation Semantics Signal processing Feature extraction Probabilistic logic information retrieval Acoustics Data mining Speech processing

来源：评论

学校读者我要写书评

暂无评论

Dual-layer Broadband High-gain Circularly Polarized Patch Antenna with L-shaped Stub

Dual-layer Broadband High-gain Circularly Polarized Patch An...

引用

2023 IEEE International Workshop on Electromagnetics: Applications and Student Innovation Competition, iWEM 2023

作者： Li, Wen Xue, Wei Li, Yingsong Loh, Tian Hong Chung, Kwok L. Harbin Engineering University College of Information and Communication Engineering Harbin150001 China Anhui University The Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Hefei China National Physical Laboratory Electromagnetic and Eletrochemical Technologies Department Middlesex United Kingdom Huizhou University School of Computing Science and Engineering Huizhou516007 China

ISBN: (纸本)9798350336740

This paper introduced a dual-layer broadband high-gain circularly polarized (CP) antenna. The proposed broadband CP antenna consists of the radiating patch and couping structure, which is made up of opening slot patch and L-shaped stub. An axial-ratio bandwidth of 26 % (4.36-5.66 GHz) is shown by this proposed dual-layer CP patch antenna with a simulated -10-dB reflection coefficient bandwidth of 37 % (4.23-6.15 GHz). The broadband characteristics offered by this CP antenna are promising for a wide range of future applications. © 2023 IEEE.

关键词： Microstrip antennas

来源：评论

学校读者我要写书评

暂无评论

Blockchain-based Transaction Scheme for Massive MIMO Channel Estimation 11

Blockchain-based Transaction Scheme for Massive MIMO Channel...

引用

11th International Conference on Networks, Communication and computing, ICNCC 2022

作者： Huang, Yu Zhi, Hui Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education Anhui University Hefei230601 China School of Electronic and Information Engineering Anhui University Hefei230601 China

ISBN: (纸本)9781450398039

In wireless communication systems, accurate channel estimation is essential to ensure the performance of wireless communication systems. Massive Multiple Input Multiple Output (M-MIMO) systems have a dramatic increase in the number of channels to be estimated due to the large number of antennas, which poses a great challenge to the computing resources of the base station, and one solution is offloading these computing tasks of channel estimation to other computing nodes with more computing resources (such as servers). However, in real life, computing nodes are not willing to participate in channel estimation because of their equipment and operation cost. In order to solve this problem, this paper introduces blockchain technology and designs a blockchain-based transaction scheme for channel estimation (BTS-CE) to solve the problem of computing resources transaction for massive MIMO channel estimation, and designs the specific process of the scheme. In order to solve the problem that computing nodes cannot complete the computation task due to failure or malicious disconnection, a task allocation model is designed to assign a computation task to multiple computation nodes. The security of the transactions is guaranteed through the blockchain. Practical Byzantine Fault Tolerance (PBFT) consensus mechanism cannot be applied to the public chain due to its low performance caused by a large number of nodes participating in consensus, this problem is solved by selecting some active nodes as consensus nodes. Simulation results show that improved PBFT(IPBFT) is lower in transaction delay and higher in throughput than PoW consensus mechanism. © 2022 ACM.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

A preconditioned iteration method for solving saddle point problems

arXiv

引用

arXiv 2024年

作者： Zhang, Juan Luo, Yiyi Hunan Key Laboratory for Computation and Simulation in Science and Engineering Key Laboratory of Intelligent Computing and Information Processing of Ministry of Education School of Mathematics and Computational Science Xiangtan University China

This paper introduces a preconditioned method designed to comprehensively address the saddle point system with the aim of improving convergence efficiency. In the preprocessor construction phase, a technical approach for solving the approximate inverse matrix of sparse matrices is presented. The effectiveness of the proposed method is demonstrated through numerical examples, emphasizing its efficacy in approximating the inverse matrix. Furthermore, the preprocessing technology includes a low-rank processing step, effectively reducing algorithmic complexity. Numerical experiments validate the effectiveness and feasibility of PSLR-GMRES in solving the saddle point system. © 2024, CC BY.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-based AP Selection Method in Software-defined Networks 5

Deep Learning-based AP Selection Method in Software-defined ...

引用

5th IEEE International Conference on Electronic information and Communication Technology, ICEICT 2022

作者： Duan, Miaomiao Zhi, Hui Yang, Lixia Anhui University Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Hefei230601 China School of Electronic and Information Engineering Anhui University Hefei230601 China

ISBN: (数字)9781665472111

ISBN: (纸本)9781665472111

In the Software Defined Network (SDN), the terminal has been connected to the network in the process when an access point failure or damage, if the access point is not properly selected, it will lead to a decline in the quality of service applications. To address this problem, most traditional AP selection methods use access point selection based on received signal strength without take into account the channel and channel capacity of the access point access, while this paper uses Deep Neural Networks (DNN)-based access point (AP) selection method and considers the channel and channel capacity as part of the parameters. In the SDN controller, the received signal strength, throughput, number of connected devices, channel, and the channel capacity and access point performance quality are used as the input and label of the DNN, respectively. The analysis and simulation results show that the algorithm can select AP with better performance quality compared with the traditional AP selection method based on received signal strength, and the correct rate is significantly improved by 5% when compared with the AP selection method based on feedforward neural network. Meanwhile, the DNN-based access point selection method in SDN achieves flexible control of network traffic and balances the load of access points in the network. © 2022 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Comments and extensions on "State-equivalent form and minimum-order compensator design for rectangular descriptor systems"

arXiv

引用

arXiv 2025年

作者： Shi, Shuo Zhang, Juan Hunan Key Laboratory for Computation and Simulation in Science and Engineering Key Laboratory of Intelligent Computing and Information Processing Ministry of Education School of Mathematics and Computational Science Xiangtan University Xiangtan411105 China

This technical note presents a counterexample showing that the equivalence conditions proposed by Geng et al. (IEEE Trans. Automat. Control, 2024), which use a minimum-order compensator (MOC) to achieve desired designs, including generalized regularity or both generalized regularity and free of impulse, are sufficient but not necessary. Furthermore, revised equivalence conditions are introduced, along with an equivalence condition ensuring the closed-loop system remains generalized regular, impulse-free, and stable using MOC. Additionally, it is shown that output feedback can replace the MOC, achieving the same design without increasing dimensionality. These findings are validated through a circuit *** Codes 93B05, 93B52, 15A03 Copyright © 2025, The Authors. All rights reserved.

关键词： Feedback

来源：评论

学校读者我要写书评

暂无评论

Open-vocabulary 3D Semantic Understanding via Affinity Neural Radiance Fields

Open-vocabulary 3D Semantic Understanding via Affinity Neura...

引用

Next Generation Data-driven Networks (NGDN), International Conference on

作者： Yujie Fan Huan Luo Computer and Data Science Fuzhou University Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University Fuzhou China

ISBN: (数字)9798350388374

ISBN: (纸本)9798350388381

Three-dimensional semantic understanding using only several multi-view images can largely reduce the communication burden on the network. In addition, while point clouds are extensively studied for 3D scene understanding, utilization of multi-view image data offers rich visual details and texture information. However, challenges persist in lifting 2D semantic features to 3D space and leveraging language for segmentation. Inspired by recent advancements, this paper proposes a method that combines CLIP features and SAM masks to create a feature field capable of segmenting objects via natural language text across 2D multi-view and 3D Gaussian splatting. It offers a promising function for extracting 3D assets for game engines and the metaverse. Our method involves mask generation from video frames, extracting physical scales via RGB Nerf with masks, and organizing hierarchical information for semantic comprehension. In the training process, affinity features maintain scale properties and guide CLIP feature generation with auto weights blending for semantic robustness. A straightforward 3D splatting CLIP feature approach and canonical text methodology enhance query robustness across 2D multi-view and 3D splatting through relevance score calculation based on text CLIP features for inference. Experimental results demonstrate promising improvements in semantic understanding of 3D scenes.

关键词： Training Image segmentation Vocabulary Visualization Three-dimensional displays Semantics Natural languages Neural radiance field Feature extraction Robustness

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：