检索结果-内蒙古大学图书馆

Dual Averaging for Distributed Unbalanced Optimization with Delayed Information

IEEE Transactions on Signal and Information processing over Networks 2025年 11卷 366-377页

作者： Huang, Qing Fan, Yuan Cheng, Songsong Anhui University Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Electrical Engineering and Automation Anhui Hefei230601 China

In this paper, we study a category of distributed constrained optimization problems where each agent has access to local information, communicates with its neighbors, and cooperatively minimizes the aggregated cost functions over time-varying unbalanced graphs. To address the considered problems, we propose a distributed dual averaging algorithm based on a row-stochastic weighted matrix (DDAR), which improves the robustness of network topology compared to conventional push-sum algorithms. Moreover, we develop a modified version of DDAR with delayed information (DDARD), which considers the delays of both network communication and gradient calculation, enhancing the algorithm's flexibility in communication and iteration. Our analysis demonstrates that the DDAR and DDARD achieve the optimal value at rates of O(N/(1-λ)√T) and O(τ2N/(1-λ}})√T}), respectively. Finally, the theoretical results are confirmed by simulation on a logistic regression problem. © 2015 IEEE.

关键词： Cost functions

来源：评论

学校读者我要写书评

暂无评论

RECONSTRUCTION-BASED A POSTERIORI ERROR ESTIMATES FOR THE L1 METHOD FOR TIME FRACTIONAL PARABOLIC PROBLEMS

引用

Journal of Computational Mathematics 2025年第2期43卷 345-368页

作者： Jiliang Cao Aiguo Xiao Wansheng Wang Department of Mathematics Shanghai Normal UniversityShanghai 200234China Hunan Key Laboratory for Computation and Simulation in Science and Engineering&Key Laboratory of Intelligent Computing and Information Processing of Ministry of Education Xiangtan UniversityXiangtan 411105China

In this paper,we study a posteriori error estimates of the L1 scheme for time discretizations of time fractional parabolic differential equations,whose solutions have generally the initial *** derive optimal order a posteriori error estimates,the quadratic reconstruction for the L1 method and the necessary fractional integral reconstruction for the first-step integration are *** using these continuous,piecewise time reconstructions,the upper and lower error bounds depending only on the discretization parameters and the data of the problems are *** numerical experiments for the one-dimensional linear fractional parabolic equations with smooth or nonsmooth exact solution are used to verify and complement our theoretical results,with the convergence ofαorder for the nonsmooth case on a uniform *** recover the optimal convergence order 2-αon a nonuniform mesh,we further develop a time adaptive algorithm by means of barrier function recently *** numerical implementations are performed on nonsmooth case again and verify that the true error and a posteriori error can achieve the optimal convergence order in adaptive mesh.

关键词： Time fractional parabolic differential equations A posteriori error estimates Ll method Fractional integral reconstruction Quadratic reconstruction

来源：评论

学校读者我要写书评

暂无评论

Underwater target recognition based on adaptive multi-feature fusion network

引用

Multimedia Tools and Applications 2025年第10期84卷 7297-7317页

作者： Pan, Xiaoying Sun, Jia Feng, TianHao Lei, MingZhu Wang, Hao Zhang, WuXia Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Xi’an710121 China Xi’an Key Laboratory of Big Data and Intelligent Computing Xi’an710121 China School of Computer Science and Technology Xi’an University of Post & Telecommunications Xi’an710121 China

Due to the complexity of the underwater environment, underwater acoustic target recognition is more challenging than ordinary target recognition, and has become a hot topic in the field of underwater acoustics research. In recent years, deep learning has been widely used in underwater recognition due to its powerful feature learning capabilities. However, most deep learning-based underwater target recognition methods use only the time-frequency domain features of signals, ignoring the frequency domain image features of signals. Additionally, they only use simple summation or splicing strategies to fuse and discriminate the extracted features, which leads to limited improvement in the accuracy of underwater target recognition. To address these issues, this paper proposes an underwater target recognition method based on an adaptive multi-feature fusion network. The method consists of a data pre-processing module, a multi-dimensional feature extraction module, and an adaptive multi-feature fusion module. In the multi-dimensional feature extraction module, the long short time memory network (LSTM) and the one-dimensional convolutional neural network (1DCNN) are used to extract the time-frequency features of the underwater signal. Furthermore, the two-dimensional convolutional neural network (2DCNN) is used to extract the image features in the frequency domain. The adaptive multi-feature fusion module uses an attention mechanism for adaptive weighted fusion to make full use of the learned features. The effectiveness of the proposed method is validated on the ShipEar dataset, and the recognition accuracy reaches 94.92%, which is higher than other existing methods. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Phase Retrieval System Based on Refractive Index Change 4

Phase Retrieval System Based on Refractive Index Change

引用

4th International Computational Imaging Conference, CITA 2024

作者： Cheng, Hong Zhang, Hongyi Wang, Li Fenzhang Li, Shuhan Key Laboratory of Intelligent Computing & Signal Processing Anhui University Anhui Province Hefei230601 China

ISBN: (纸本)9781510688834

The phase recovery method based on the Transport of Intensity Equation is widely used in the field of microscopic imaging of biological cells. When using this method for phase recovery, the CCD is always moved to acquire intensity images at different out-of-focus positions, which introduces mechanical errors, it also causes errors when using the traditional FFT method. Based on this, this paper proposes a phase recovery system based on refractive index change: firstly, an image acquisition system with a refractive index medium is built, and two intensity images with different refractive index are acquired;the intensity-phase equation based on refractive index change is established, and the "maximum intensity" assumption method is introduced to solve this equation. Then, we can obtain high-precision phase results without moving the CCD. In this paper, the feasibility and accuracy of this technique are confirmed by numerical simulation and optical experiment respectively. © 2025 SPIE.

关键词： Refractive index

来源：评论

学校读者我要写书评

暂无评论

JDC-GCN: joint diversity and consistency graph convolutional network

引用

Neural computing and Applications 2025年 1-17页

作者： Lin, Renjie Yao, Jie Wang, Shiping Guo, Wenzhong College of Computer and Data Science Fuzhou University Fuzhou350116 China Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University Fuzhou350116 China

In real-world scenarios, multi-view data comprises heterogeneous features, with each feature corresponding to a specific view. The objective of multi-view semi-supervised classification is to enhance classification performance by leveraging the inherent complementary and consistent information present within diverse views. Nevertheless, many existing frameworks primarily focus on assigning suitable weights to different views while neglecting the importance of consistent information. In this paper, a multi-view semi-supervised classification framework called joint diversity and consistency graph convolutional network (JDC-GCN) is proposed. Firstly, the structure of graph convolutional network is introduced to the multi-view semi-supervised classification, capable of propagating the label information over the topological structure of multi-view data. Secondly, the proposed JDC-GCN captures the complementary and consistent information from multiple views through two indispensable sub-modules, Diversity-GCN and Consistency-GCN, respectively. Finally, the attention mechanism is leveraged to dynamically adjust the weights of various views, allowing us to measure the significance of heterogeneous features and the consistent graph without introducing additional parameters. Comprehensive experiments on eight multi-view datasets are conducted to validate the effectiveness of the JDC-GCN algorithm. The results show that the proposed method exhibits superior classification performance compared to other state-of-the-art methods. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

PRPFD: Polynomial Resampling Particle Filter Based Deconvolution Approach for Resting-State BOLD-fMRI Data Analysis 24

PRPFD: Polynomial Resampling Particle Filter Based Deconvolu...

引用

5th International Symposium on Artificial Intelligence for Medicine Science, ISAIMS 2024

作者： Luo, Yunying Zeng, Weiming Key Laboratory for Digital Imaging Processing and Intelligent Computing School of Information Engineering Shanghai Maritime University Shanghai China

ISBN: (纸本)9798400717826

Functional Magnetic Resonance Imaging (fMRI) stands out in brain science research due to its non-invasive, non-intrusive, radiation-free, high spatial resolution, and precise localization advantages. However, the BOLD-fMRI signals it generates exhibit a several-second delay compared to neural activity, making it unable to reflect brain neural activity directly. This discrepancy may lead to differences from the actual situation. Therefore, this study aims to enhance the deconvolution of fMRI by refining existing methods to reconstruct the brain’s neural signals more faithfully. Building upon the foundation of particle filtering deconvolution, this paper introduced a novel approach to deconvolving resting-state fMRI data: the polynomial resampling particle filtering deconvolution (PRPFD). They adapted the particle distribution better to match the actual state through weight computation and resampling. We performed a simulation-based experiment to validate the feasibility of our approach. Besides, we validated the performance of our method using group data, focusing on both effective connectivity and functional connectivity, providing strong evidence for the usability and stability of our approach, and compared our method with other deconvolution techniques, demonstrating improvements in accuracy and computational efficiency. © 2024 Copyright held by the owner/author(s).

关键词： Polynomials

来源：评论

学校读者我要写书评

暂无评论

An Improved Compressive Sensing-Based Model for Efficient Analysis of Monostatic Electromagnetic Scattering Problems

引用

IEEE Microwave and Wireless Technology Letters 2025年第4期35卷 388-391页

作者： Qi, Qi Fan, Yunuo Cao, Xinyuan Liu, Yi Kong, Meng Huang, Zhixiang Wu, Xianliang Hefei Normal University Anhui Province Key Laboratory of Simulation Calculation and Design for Electronic Information System Hefei230601 China Anhui University Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Hefei230601 China

To further accelerate the analysis of monostatic electromagnetic (EM) scattering problems of objects, an improved compressive sensing (CS)-based model is proposed. First, an orthogonal subspace spanned by the wide-angle induced currents is identified by means of the wide-angle incident sources. Then, the sparse transform of the induced currents is replaced by the subspace projection. In addition, an optimal number of measurements is determined, only slightly larger than the dimension of the subspace. Finally, the recovery algorithm is simplified to the least-squares method to solve the resulting overdetermined system. Compared with the traditional CS-based model, the proposed model significantly improves the efficiency of the recovery step and optimizes both the requirement for and the way of determining the number of measurements. © 2023 IEEE.

关键词： Least squares approximations

来源：评论

学校读者我要写书评

暂无评论

Glare-SNet: Unsupervised Glare Suppression Balance Network 27th

Glare-SNet: Unsupervised Glare Suppression Balance Network

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Li, Pei Zuo, Chengyu Wei, Wangjuan Pan, Xiaoying Wang, Zhanhao School of Computer Science and Technology Xi’an University of Posts and Telecommunications Xi’an710121 China Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Xi’an China Shaanxi Key Laboratory of Intelligent Media Computing and interaction Xi’an China Xi’an Key Laboratory of Big Data and Intelligent Computing Xi’an China

ISBN: (纸本)9783031781681

In light of the problems associated with glare and halo effects in low-light images, as well as the inadequacy of existing processing algorithms in handling details, a glare suppression balance network based on unsupervised learning has been designed and implemented in this study. A network that perceives brightness through light decomposition has been proposed, and an illumination learning network has been designed. The idea of integration has been employed to form an unsupervised glare suppression balance network, aiming to tackle the issues of glare and the accompanying halo effects. Through objective and subjective evaluations of real images, it has been proven that the method introduced in this paper surpasses other methods in suppressing glare and enhancing the overall quality of low-light images. Furthermore, it has been shown to exhibit good performance and effectiveness in target detection. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Image enhancement

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

Multi-objective Balanced Task Offloading in Vehicular Networks Based on Edge computing 27th

Multi-objective Balanced Task Offloading in Vehicular Networ...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Wang, Lingjiao Meng, Lingwei Guo, Hua Xiangtan University Hunan Xiangtan411105 China Key Laboratory of Intelligent Computing and Information Processing of Ministry of Education Xiangtan University Hunan Xiangtan411105 China

ISBN: (纸本)9783031783821

The increasing number of vehicular networking devices and application demands has made the limited computing and communication resources a significant challenge. The heuristic task offloading strategy mechanism was proposed to improve the efficiency of task offloading in vehicular networks. This strategy mechanism utilized the Nondominated Sorting Genetic Fireworks Algorithm (NSGFA) based on the characteristics of the problem, integrated consideration of the multi-target balance between system offloading costs and load balancing. Experimental data results demonstrate that this method performs well in reducing latency, energy consumption, and load balancing, effectively enhancing the quality of service for vehicular network users. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Computation offloading

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：