检索结果-内蒙古大学图书馆

A NONLOCAL KRONECKER-BASIS-REPRESENTATION METHOD FOR LOW-DOSE CT SINOGRAM RECOVERY

Journal of Computational Mathematics 2024年第4期42卷 1080-1108页

作者： Jian Lu Huaxuan Hu Yuru Zou Zhaosong Lu Xiaoxia Liu Keke Zu Lin Li Shenzhen Key Laboratory of Advanced Machine Learning and Applications College of Mathematics and StatisticsShenzhen UniversityShenzhen 518060China National Center for Applied Mathematics Shenzhen(NCAMS) Shenzhen 518055China Department of Industrial and Systems Engineering University of Minnesota Twin CitiesMinneapolisMN55455USA Department of Applied Mathematics The Hong Kong Polytechnic UniversityHong Kong SARChina School of Electronic Engineering Xidian UniversityXi'an 710071China

Low-dose computed tomography(LDCT)contains the mixed noise of Poisson and Gaus-sian,which makes the image reconstruction a challenging *** order to describe the statistical characteristics of the mixed noise,we adopt the sinogram preprocessing as a stan-dard maximum a posteriori(MAP).Based on the fact that the sinogram of LDCT has non-local self-similarity property,it exhibits low-rank *** conventional way of solving the low-rank problem is implemented in matrix forms,and ignores the correlations among similar patch *** avoid this issue,we make use of a nonlocal Kronecker-Basis-Representation(KBR)method to depict the low-rank problem.A new denoising model,which consists of the sinogram preprocessing for data fidelity and the nonlocal KBR term,is developed in this *** proposed denoising model can better illustrate the generative mechanism of the mixed noise and the prior knowledge of the ***-merical results show that the proposed denoising model outperforms the state-of-the-art algorithms in terms of peak-signal-to-noise ratio(PSNR),feature similarity(FSIM),and normalized mean square error(NMSE).

关键词： Low-dose computed tomography Kronecker-basis-representation Low-rank imation.Noise-generating-mechanism

来源：评论

学校读者我要写书评

暂无评论

A Novel ECG Signal Classification Algorithm Based on Common and Specific Components Separation 2nd

A Novel ECG Signal Classification Algorithm Based on Common ...

引用

2nd International Conference on Pattern Recognition and Artificial Intelligence, ICPRAI 2020

作者： Huang, Jianfeng Huang, Chao Yang, Lihua Zhang, Qian School of Financial Mathematics and Statistics Guangdong University of Finance Guangzhou China College of Mathematics and Statistics Shenzhen Key Laboratory of Advanced Machine Learning and Applications Shenzhen University Shenzhen China Guangdong Province Key Laboratory of Computational Science School of Mathematics Sun Yat-sen University Guangzhou China

ISBN: (纸本)9783030598297

Electrocardiography (ECG) signal classification is a challenging task since the characteristics of ECG signals vary significantly for different patients. In this paper, we propose a new method for ECG signal classification based on the separation of common and specific components of a signal. The common components are obtained via Canonical Correlation Analysis (CCA). After removing the common components from the signal, we map the specific components to a lower dimensional feature space for classification. We first establish a basic model in the binary classification setting and then extend it to a more general version. Numerical experiments results on the MIT-BIH Arrhythmia Database are presented and discussed. © 2020, Springer Nature Switzerland AG.

关键词： Electrocardiography

来源：评论

学校读者我要写书评

暂无评论

Jantzen conjecture for singular characters

arXiv

引用

arXiv 2021年

作者： Xiao, Wei College of Mathematics and Statistics Shenzhen Key Laboratory of Advanced Machine Learning and Applications Shenzhen University Guangdong Shenzhen518060 China

We show that the Jantzen filtration of a Verma module (possibly singular) coincides with its radical filtration. It implies that the Jantzen Conjecture on Verma modules holds for all infinitesimal characters, while the regular case was settled by Beilinson and Bernstein by geometric methods and reproved by Williamson by an algebraic approach. The coincidence between Jantzen filtration and radical filtration is also generalized to the case of parabolic Verma modules by Shan’s results. Copyright © 2021, The Authors. All rights reserved.

关键词： Algebra

来源：评论

学校读者我要写书评

暂无评论

Kernel Non-Negative Matrix Factorization Using Self-Constructed Cosine Kernel

Kernel Non-Negative Matrix Factorization Using Self-Construc...

引用

International Conference on Computational Intelligence and Security

作者： Huihui Qian Wen-Sheng Chen Binbin Pan Bo Chen College of Mathematics and Statistics Shenzhen University China Shenzhen Key Laboratory of Advanced Machine Learning and Applications Shenzhen University China

ISBN: (纸本)9781665404457;9781665447119

Kernel-based non-negative matrix factorization (KNMF) can non-linearly extract non-negative features for image-data representation and classification. However, different kernel functions would lead to different performance. This means that selecting an appropriate kernel function plays an important role in KNMF algorithms. In this paper, we construct a novel Mercer kernel function, called cosine kernel function, which has the advantages of translation invariance and robustness to noise. Based on the self-constructed cosine kernel, we further propose a cosine kernel-based NMF (CKNMF) approach. The iterative formulas of CKNMF are deduced using the gradient descent method. We empirically validate that our CKNMF algorithm is convergent. Compared with some state of the art kernel-based algorithms, experimental results indicate that the proposed CKNMF algorithm achieves superior performance on face recognition.

关键词： Face recognition Feature extraction Robustness Classification algorithms Security Iterative methods Kernel

来源：评论

学校读者我要写书评

暂无评论

Distributed Network Flow to Solve Constrained Linear Matrix Equation

Distributed Network Flow to Solve Constrained Linear Matrix ...

引用

International Workshop on advanced Computational Intelligence (IWACI)

作者： Yiyuan Chai Jiqiang Feng Chen Xu Sitian Qin Shenzhen Key Laboratory of Advanced Machine Learning and Applications Shenzhen University Shenzhen China Harbin Institute of Technology Weihai China

In this paper, a novel network flow is presented from a distributed perspective, which aims to solve classical Stein equation. With the coefficient matrices of appropriate dimensions, each agent only access to several row information. That is to say, a standard decomposition method is presented extensively, and then a distributed optimization problem to search least squares solution is proposed by introducing substitutive variables. We show the equivalence between solutions of distributed optimization problem and least squares solution of original Stein equation. Related convex analysis results show that the state solutions of the designed distributed network flow converge to the least squares solution of Stein equation. Finally, numerical results provide the viability of the designed distributed network flow.

关键词： Computational modeling Search problems Convex functions Mathematical model Matrix decomposition Optimization Standards

来源：评论

学校读者我要写书评

暂无评论

JANTZEN COEFFICIENTS AND SIMPLICITY OF GENERALIZED VERMA MODULES

arXiv

引用

arXiv 2020年

作者： Xiao, Wei Zhang, Ailin College of Mathematics and Statistics Shenzhen Key Laboratory of Advanced Machine Learning and Applications Shenzhen University Guangdong Shenzhen518060 China

The main purpose of this paper is to establish new tools in the study of Op. We introduce the Jantzen coefficients of generalized Verma modules. They come from the Jantzen's simplicity criteria for generalized Verma modules and have a deep relation with the structure of Op. We develop a reduction process to compute those coefficients by considering basic generalized Verma modules. These modules are induced from maximal parabolic subalgebras and have maximal nontrivial singularity. The classification of such modules is also obtained in this paper. As the first application of our results, we give a refinement of Jantzen's simplicity criteria for generalized Verma *** Codes 17B10, 22E47 Copyright © 2020, The Authors. All rights reserved.

关键词： Algebra

来源：评论

学校读者我要写书评

暂无评论

A Combined Regularizer Based Image Inpainting

A Combined Regularizer Based Image Inpainting

引用

2019 International Conference on advanced Electrical, Mechatronics and Computer Engineering(AEMCE 2019)

作者： Yu HAN Chen HU Bin XIE Wei-qiang ZHANG Shenzhen Key Laboratory of Advanced Machine Learning and Applications College of Mathematics and StatisticsShenzhen University College of Information Engineering Shenzhen University

As a significant topic in computer vision, image inpainting aims to recover the natural pattern of an image in which pixels have been partially removed or occluded. To achieve this task, the traditional method uses a convex total variation(TV) regularizer. However, as the TV regularizer has to be solved by iteration, image inpainting results obtained from classical methods have the over smoothness tendency and the staircase effect when iteration number increases. To solve the problem, in this paper we introduce a new regularizer to achieve better image inpainting. The new regularizer is a weighted combination of the classical TV regularizer and a nonconvex regularizer. To solve our new model efficiently, a new algorithm is also proposed which is based on the primal-dual algorithm and the iteratively reweighting method. Numerical results demonstrate that our proposed image inpainting model is more effective than classical TV regularizer based models.

关键词： Image inpainting Total variation Primal-dual algorithm Variation models

来源：评论

学校读者我要写书评

暂无评论

Enhanced Image Restoration Via Supervised Target Feature Transfer

Enhanced Image Restoration Via Supervised Target Feature Tra...

引用

IEEE International Conference on Image Processing

作者： Yuzhao Chen Tao Dai Xi Xiao Jian Lu Shu-Tao Xia Tsinghua Shenzhen International Graduate School Tsinghua University Shenzhen China Shenzhen Key Laboratory of Advanced Machine Learning and Applications Shenzhen University China

ISBN: (数字)9781728163956

ISBN: (纸本)9781728163963

Deep learning has obtained remarkable success for image restoration. However, most existing deep image restoration models are trained by minimizing the pixel-level reconstruction error between restored images and target images (ground truth), while neglecting the rich information from the intermediate feature layers, thus hindering the representational power of networks. To address this problem, we propose a Supervised Target Feature Transfer (STFT) framework to enhance the power of feature expression of the deep image restoration models. Specifically, we introduce a self-supervised antoencoder-based target feature extractor to extract compact feature representation of target images, which serves as supervision signals to train the deep backbone models at the same time. With such feature-level supervised information, deep backbone model can be enhanced by transfer learning of such target features. Moreover, we theoretically analyze our STFT training strategies and demonstrate that it imposes learnable prior information on the backbone restoration model. Extensive experiments demonstrate the effectiveness of our proposed framework compared with the state-of-the-art image restoration models.

关键词： Feature extraction Image restoration Training Image reconstruction Task analysis Image resolution machine learning

来源：评论

学校读者我要写书评

暂无评论

BLOCKS OF THE CATEGORY Op IN TYPE E

arXiv

引用

arXiv 2020年

作者： Jieren, Hu Xiao, Wei Zhang, Ailin College of Computer Science and Software Engineering Shenzhen University ShenzhenGuangdong518060 China College of Mathematics and statistics Shenzhen Key Laboratory of Advanced Machine Learning and Applications Shenzhen University Shenzhen Guangdong518060 China College of Mathematics and statistics Shenzhen Key Laboratory of Advanced Machine Learning and Applications Shenzhen University Shenzhen Guangdong518060 China

关键词：

来源：评论

学校读者我要写书评

暂无评论

Fakd: Feature-Affinity Based Knowledge Distillation for Efficient Image Super-Resolution

Fakd: Feature-Affinity Based Knowledge Distillation for Effi...

引用

IEEE International Conference on Image Processing

作者： Zibin He Tao Dai Jian Lu Yong Jiang Shu-Tao Xia Tsinghua Shenzhen International Graduate School Tsinghua University Shenzhen China Shenzhen Key Laboratory of Advanced Machine Learning and Applications Shenzhen University China

ISBN: (数字)9781728163956

ISBN: (纸本)9781728163963

Convolutional neural networks (CNNs) have been widely used in image super-resolution (SR). Most existing CNN-based methods focus on achieving better performance by designing deeper/wider networks, while suffering from heavy computational cost problem, thus hindering the deployment of such models in mobile devices with limited resources. To relieve such problem, we propose a novel and efficient SR model, named Feature Affinity-based Knowledge Distillation (FAKD), by transferring the structural knowledge of a heavy teacher model to a lightweight student model. To transfer the structural knowledge effectively, FAKD aims to distill the second-order statistical information from feature maps and trains a lightweight student network with low computational and memory cost. Experimental results demonstrate the efficacy of our method and the effectiveness over other knowledge distillation based methods in terms of both quantitative and visual metrics.

关键词： Knowledge engineering Computational modeling Correlation Image resolution Task analysis Feature extraction Mathematical model

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：