检索结果-内蒙古大学图书馆

arXiv 2020年

作者： Hatamian, Faezeh Nejati Ravikumar, Nishant Vesal, Sulaiman Kemeth, Felix P. Struck, Matthias Maier, Andreas Department of Image Processing and Medical Technology Fraunhofer Institute for Integrated Circuits IIS Erlangen Germany Pattern Recognition Lab Department of Computer Science Friedrich-Alexander University Erlangen-Nrnberg Erlangen Germany School of Computing LICAMM Leeds Institute of Cardiovascular and Metabolic Medicine School of Medicine University of Leeds United Kingdom

Cardiovascular diseases are the most common cause of mortality worldwide. Detection of atrial fibrillation (AF) in the asymptomatic stage can help prevent strokes. It also improves clinical decision making through the delivery of suitable treatment such as, anticoagulant therapy, in a timely manner. The clinical significance of such early detection of AF in electrocardiogram (ECG) signals has inspired numerous studies in recent years, of which many aim to solve this task by leveraging machine learning algorithms. ECG datasets containing AF samples, however, usually suffer from severe class imbalance, which if unaccounted for, affects the performance of classification algorithms. Data augmentation is a popular solution to tackle this problem. In this study, we investigate the impact of various data augmentation algorithms, e.g., oversampling, Gaussian Mixture Models (GMMs) and Generative Adversarial Networks (GANs), on solving the class imbalance problem. These algorithms are quantitatively and qualitatively evaluated, compared and discussed in detail. The results show that deep learning-based AF signal classification methods benefit more from data augmentation using GANs and GMMs, than oversampling. Furthermore, the GAN results in circa 3% better AF classification accuracy in average while performing comparably to the GMM in terms of f1-score. Copyright © 2020, The Authors. All rights reserved.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Towards a unified quadrature framework for large-scale kernel machines

arXiv

引用

arXiv 2020年

作者： Liu, Fanghui Huang, Xiaolin Chen, Yudong Suykens, Johan A.K. KU Leuven LeuvenB-3001 Belgium Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai200240 China Institute of Medical Robotics Shanghai Jiao Tong University Shanghai200240 China School of Operations Research and Information Engineering Cornell University IthacaNY14850 United States

In this paper, we develop a quadrature framework for large-scale kernel machines via a numerical integration representation. Considering that the integration domain and measure of typical kernels, e.g., Gaussian kernels, arc-cosine kernels, are fully symmetric, we leverage deterministic fully symmetric interpolatory rules to efficiently compute quadrature nodes and associated weights for kernel approximation. The developed interpolatory rules are able to reduce the number of needed nodes while retaining a high approximation accuracy. Further, we randomize the above deterministic rules by the classical Monte-Carlo sampling and control variates techniques with two merits: 1) The proposed stochastic rules make the dimension of the feature mapping flexibly varying, such that we can control the discrepancy between the original and approximate kernels by tuning the dimnension. 2) Our stochastic rules have nice statistical properties of unbiasedness and variance reduction with fast convergence rate. In addition, we elucidate the relationship between our deterministic/stochastic interpolatory rules and current quadrature rules for kernel approximation, including the sparse grids quadrature and stochastic spherical-radial rules, thereby unifying these methods under our framework. Experimental results on several benchmark datasets show that our methods compare favorably with other representative kernel approximation based methods. Copyright © 2020, The Authors. All rights reserved.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

image reconstruction for brain CT slices

引用

Chinese Journal of Systems Engineering and Electronics 2004年第3期000卷

Different modalities in biomedical images, like CT, MRI and PET scanners, provide detailed cross-sectional views of human anatomy. This paper introduces three-dimensional brain reconstruction based on CT slices. It contains filtering, fuzzy segmentation, matching method of contours, cell array structure and image animation. Experimental results have shown its validity. The innovation is matching method of contours and fuzzy segmentation algorithm of CT slices.

关键词： filter AFCM segmentation contour cell array structure animation

来源：评论

学校读者我要写书评

暂无评论

Novel blind source separation algorithm using Gaussian mixture density function

引用

Chinese Journal of Systems Engineering and Electronics 2004年第4期000卷

The blind source separation (BSS) is an important task for numerous applications in signal processing, communications and array processing. But for many complex sources blind separation algorithms are not efficient because the probability distribution of the sources cannot be estimated accurately. So in this paper, to justify the ME(maximum enteropy) approach, the relation between the ME and the MMI(minimum mutual information) is elucidated first. Then a novel algorithm that uses Gaussian mixture density to approximate the probability distribution of the sources is presented based on the ME approach. The experiment of the BSS of ship-radiated noise demonstrates that the proposed algorithm is valid and efficient.

关键词： blind source separation(BSS) maximum entropy(ME) minimum mutual information (MMI) Gaussian mixture density

来源：评论

学校读者我要写书评

暂无评论

Semantics-based pre-fetching for reducing WWW latency

引用

Chinese Journal of Systems Engineering and Electronics 2004年第4期000卷

A semantics-based pre-fetching model is presented. This model predicts future requests based on latent intention that the user's current access path implies in semantics, rather than on temporal relationships, which oversomes the limitation of previous pre-fetching approaches. The hidden Markov model (HMM) was employed for mining actual intention from access patterns. Experimental results show that the proposed pre-fetching model has better general performance.

关键词： Web pre-fetching latent intention hidden Markov model

来源：评论

学校读者我要写书评

暂无评论

Abundant Semantic Information Module for Object Detection

Abundant Semantic Information Module for Object Detection

引用

Algorithms, High Performance Computing and Artificial Intelligence (AHPCAI), International Conference on

作者： Taida Wu Qishen Li Qiufeng Li Jun Gao School of Information Engineering Nanchang Hangkong University Nanchang Jiangxi China Key Laboratory of Jiangxi Province for Image Processing and Pattern Recognition Nanchang Jiangxi China School of Software Nanchang Hangkong University Nanchang Jiangxi China Key Laboratory of Nondestructive Testing (Ministry of Education) Nanchang Hangkong University Nanchang Jiangxi China

Nowadays, with the high-speed iteration of convolution neural network, the efficient object detector emerges one after another. As an important branch of computer vision, object detection aims to detect where and what the object is. However, nowadays, many detector cannot extract abundant semantic information to discriminate the location and size of the objects, resulting in poor performance of the network. In this paper, a new module is proposed, named Abundant Semantic Information Module (ASIM), to enrich and expand the semantic information of the object with more and larger receptive fields. In ASIM, we blend the extracted feature maps to different degrees with different blending factors and fuse them so that all object information is given full attention. Compared to the baseline method, a wealth of experiments show that our module has achieved a significant performance improvement.

关键词： Location awareness Fuses High performance computing Semantics Neural networks Object detection Detectors

来源：评论

学校读者我要写书评

暂无评论

Low-light image enhancement model based on self-calibration illumination and color adjustment

Low-light image enhancement model based on self-calibration ...

引用

Algorithms, High Performance Computing and Artificial Intelligence (AHPCAI), International Conference on

作者： Guiwen Zhang Qishen Li Qiufeng Li Taida Wu School of Information Engineering Nanchang Hangkong University Nanchang Jiangxi China Key Laboratory of Jiangxi Province for Image Processing and Pattern Recognition Nanchang Jiangxi China School of Software Nanchang Hangkong University Nanchang Jiangxi China Key Laboratory of Nondestructive Testing (Ministry of Education) Nanchang Hangkong University Nanchang Jiangxi China

to improve the clarity of objects in a dark-light environment, and to facilitate the identification and detection of targets behind. People perceive the color and brightness of a point not only depending on the pixel value of the point but also the absolute light entering the human eye is related to the color and brightness around the point. The self-calibration model we used considers the surrounding information, which avoids the information pollution, such as large regions of dark background information. In this model, we introduce a heterogeneous convolution filter, which makes reasonable use of different parts of the filter. Through this operation, information from multiple different scale spaces can be fused, and the field of view when applying the convolution layer is greatly increased without increasing the hyper-parameters, thus producing a more distinctive feature representation. Then the self-calibration model is combined with the backbone reinforcement network, which can not only retain the information of the original scale space but also efficiently collect the latent space information to guide the feature transformation in the original space. After the different channels of the image are processed separately, the dependency between the channels can be established by using the heterogeneous convolution filter. Finally, the test on the ExDark data set proves that our dark target enhancement effect has been significantly improved.

关键词： Training Pollution image color analysis Convolution Brightness Lighting Information filters

来源：评论

学校读者我要写书评

暂无评论

Modeling Inter-Intra Heterogeneity for Graph Federated Learning

arXiv

引用

arXiv 2024年

作者： Yu, Wentao Chen, Shuo Tong, Yongxin Gu, Tianlong Gong, Chen School of Computer Science and Engineering Nanjing University of Science and Technology China Center for Advanced Intelligence Project RIKEN Japan State Key Laboratory of Complex & Critical Software Environment Beihang University China Jinan University China Department of Automation Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University China

Heterogeneity is a fundamental and challenging issue in federated learning, especially for the graph data due to the complex relationships among the graph nodes. To deal with the heterogeneity, lots of existing methods perform the weighted federation based on their calculated similarities between pairwise clients (i.e., subgraphs). However, their inter-subgraph similarities estimated with the outputs of local models are less reliable, because the final outputs of local models may not comprehensively represent the real distribution of subgraph data. In addition, they ignore the critical intra-heterogeneity which usually exists within each subgraph itself. To address these issues, we propose a novel Federated learning method by integrally modeling the Inter-Intra Heterogeneity (FedIIH). For the inter-subgraph relationship, we propose a novel hierarchical variational model to infer the whole distribution of subgraph data in a multi-level form, so that we can accurately characterize the inter-subgraph similarities with the global perspective. For the intra-heterogeneity, we disentangle the subgraph into multiple latent factors and partition the model parameters into multiple parts, where each part corresponds to a single latent factor. Our FedIIH not only properly computes the distribution similarities between subgraphs, but also learns disentangled representations that are robust to irrelevant factors within subgraphs, so that it successfully considers the inter- and intra- heterogeneity simultaneously. Extensive experiments on six homophilic and five heterophilic graph datasets in both non-overlapping and overlapping settings demonstrate the effectiveness of our method when compared with nine state-of-the-art methods. Specifically, FedIIH averagely outperforms the second-best method by a large margin of 5.79% on all heterophilic datasets. Code is available at https://***/blgpb/FedIIH. Copyright © 2024, The Authors. All rights reserved.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Remote Sensing image Object Detection Method with Feature Denoising Fusion Module

Remote Sensing Image Object Detection Method with Feature De...

引用

IEEE Advanced Information Technology, Electronic and Automation Control Conference (IAEAC)

作者： Penghui Chen Qishen Li Qiufeng Li Zhongyu Wu School of Information Engineering Nanchang Hangkong University Nanchang Jiangxi China Key Laboratory of Jiangxi Province for Image Processing and Pattern Recognition Nanchang Jiangxi China School of Software Nanchang Hangkong University Nanchang Jiangxi China Key Laboratory of Nondestructive Testing (Ministry of Education) Nanchang Hangkong University Nanchang Jiangxi China

Remote sensing object detection is an important research area in computer vision, widely applied in both military and civilian domains. However, challenges in remote sensing image object detection such as large image sizes, complex backgrounds, and significant variations in target scales are prevalent. To address these issues, this paper proposes a new Feature Denoising and Fusion Module (FDFM) aimed at enhancing the accuracy and robustness of object detection. This module comprises a Multi-Scale Denoising Submodule(MDS) and an Attention Optimization Submodule(AOS). The Multi-Scale Denoising Module aims to suppress lower-level texture noise by utilizing higher-level semantic features before the fusion process, reducing the impact of lower-level noise on subsequent multi-scale feature fusion. Meanwhile, the Attention Optimization Module seeks to enhance the precision of self-attention computations within the Multi-Scale Denoising Module without increasing the parameter count. The efficacy of this method was evaluated on public datasets DOTA, VisDrone, VOC and COCO, showing improvements in comparison to baseline models.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Edge-Aware Graph Attention Network for Ratio of Edge-User Estimation in Mobile Networks

Edge-Aware Graph Attention Network for Ratio of Edge-User Es...

引用

International Conference on pattern recognition

作者： Jiehui Deng Sheng Wan Xiang Wang Enmei Tu Xiaolin Huang Jie Yang Chen Gong PCA Lab the Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai China Hong Kong Polytechnic University Hong Kong SAR China

Estimating the Ratio of Edge-Users (REU) is an important issue in mobile networks, as it helps the subsequent adjustment of loads in different cells. However, existing approaches usually determine the REU manually, which are experience-dependent and labor-intensive, and thus the estimated REU might be imprecise. Considering the inherited graph structure of mobile networks, in this paper, we utilize a graph-based deep learning method for automatic REU estimation, where the practical cells are deemed as nodes and the load switchings among them constitute edges. Concretely, Graph Attention Network (GAT) is employed as the backbone of our method due to its impressive generalizability in dealing with networked data. Nevertheless, conventional GAT cannot make full use of the information in mobile networks, since it only incorporates node features to infer the pairwise importance and conduct graph convolutions, while the edge features that are actually critical in our problem are disregarded. To accommodate this issue, we propose an Edge-Aware Graph Attention Network (EAGAT), which is able to fuse the node features and edge features for REU estimation. Extensive experimental results on two real-world mobile network datasets demonstrate the superiority of our EAGAT approach to several state-of-the-art methods.

关键词： Deep learning Fuses Estimation Switches pattern recognition

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：