检索结果-内蒙古大学图书馆

Retinal vessel segmentation with constrained-based nonnegative matrix factorization and 3D modified attention U-Net

EURASIP JOURNAL ON IMAGE AND VIDEO PROCESSING 2021年第1期2021卷 6-6页

作者： Yu, Yang Zhu, Hongqing East China Univ Sci & Technol Sch Informat Sci & Engn 130 Meilong Rd Shanghai 200237 Peoples R China

Due to the complex morphology and characteristic of retinal vessels, it remains challenging for most of the existing algorithms to accurately detect them. This paper proposes a supervised retinal vessels extraction scheme using constrained-based nonnegative matrix factorization (NMF) and three dimensional (3D) modified attention U-Net architecture. The proposed method detects the retinal vessels by three major steps. First, we perform Gaussian filter and gamma correction on the green channel of retinal images to suppress background noise and adjust the contrast of images. Then, the study develops a new within-class and between-class constrained NMF algorithm to extract neighborhood feature information of every pixel and reduce feature data dimension. By using these constraints, the method can effectively gather similar features within-class and discriminate features between-class to improve feature description ability for each pixel. Next, this study formulates segmentation task as a classification problem and solves it with a more contributing 3D modified attention U-Net as a two-label classifier for reducing computational cost. This proposed network contains an upsampling to raise image resolution before encoding and revert image to its original size with a downsampling after three max-pooling layers. Besides, the attention gate (AG) set in these layers contributes to more accurate segmentation by maintaining details while suppressing noises. Finally, the experimental results on three publicly available datasets DRIVE, STARE, and HRF demonstrate better performance than most existing methods.

关键词： nonnegative matrix factorization Retinal vessel segmentation Within-class and between-class constrained 3 Dimension Attention U-Net

来源：评论

学校读者我要写书评

暂无评论

Community Detection Based on Modularized Deep nonnegative matrix factorization

引用

INTERNATIONAL JOURNAL OF PATTERN RECOGNITION AND ARTIFICIAL INTELLIGENCE 2021年第2期35卷

作者： Huang, Jin Zhang, Tinghua Yu, Weihao Zhu, Jia Cai, Ercong South China Normal Univ Sch Comp Sci Guangzhou Peoples R China

Community detection is a well-established problem and nontrivial task in complex network analysis. The goal of community detection is to discover community structures in complex networks. In recent years, many existing works have been proposed to handle this task, particularly nonnegative matrix factorization-based method, e.g. HNMF, BNMF, which is interpretable and can learn latent features of complex data. These methods usually decompose the original matrix into two matrixes, in one matrix, each column corresponds to a representation of community and each column of another matrix indicates the membership between overall pairs of communities and nodes. Then they discover the community by updating the two matrices iteratively and learn the shallow feature of the community. However, these methods either ignore the topological structure characteristics of the community or ignore the microscopic community structure properties. In this paper, we propose a novel model, named Modularized Deep nonnegative matrix factorization (MDNMF) for community detection, which preserves both the topology information and the instinct community structure properties of the community. The experimental results show that our proposed models can significantly outperform state-of-the-art approaches on several well-known dataset.

关键词： Community detection nonnegative matrix factorization modularity deep matrix factorization

来源：评论

学校读者我要写书评

暂无评论

Embedding regularized nonnegative matrix factorization for structural reduction in multi-layer networks

引用

APPLIED SOFT COMPUTING 2021年 112卷 107781-107781页

作者： Huang, Zhihao Dou, Zengfa Ma, Xiaoke Xidian Univ Sch Comp Sci & Technol Xian Shaanxi Peoples R China China Elect Technol Grp Corp Res Inst 20 Xian Shaanxi Peoples R China

A variety of complex systems from nature and society, ranging from biological to technological systems, can be effectively modeled by networks. The multiplex character of real-world systems leads to distinct types of interactions that are categorized as edges belonging to various layers. And, the topological analysis of multi-layer networks discovers graph patterns that are critical for revealing the mechanisms of systems. An essential prerequisite of successful multi-layer networks analysis is how to remove the redundancy of networks, i.e., structural reduction of multi-layer networks. The current algorithms quantify the distance among various layers by using either the topological structure or the representative vectors, which fail to fully characterize the relationship among various layers, leading to low accuracy. To overcome this problem, we propose a nonnegative matrix factorization algorithm for multi-layer networks reduction (NMF-MNR), which jointly factorizes the topological structure and graph representation of various layers. Specifically, we adopt the network embedding to obtain low-dimensional graph representation of each layer, and then jointly decompose the adjacency matrix and graph representation to extract the feature matrix for each layer, which provides a better way to characterize layers of networks. The experimental results on both artificial and real-world networks demonstrate that NMF-MNR is more accurate and robust than state-of-the-art approaches. (C) 2021 Elsevier B.V. All rights reserved.

关键词： Multi-layer networks Structural reduction nonnegative matrix factorization Network embedding

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Secure Watermarking Scheme Using nonnegative matrix factorization and FastWalsh-Hadamard Transform

引用

JOURNAL OF APPLIED SECURITY RESEARCH 2020年第2期15卷 185-198页

作者： Abdallah, Emad E. Otoom, Ahmed Fawzi Abdallah, Alaa E. Bsoul, Mohammad Awwad, Sari Hashemite Univ Fac Prince Al Hussein Bin Abdallah II Informat Te POB 150459 Zarqa 13115 Jordan

We present a robust and unnoticeable secure image watermarking approach using nonnegative matrix factorization (NMF) and Fast Walsh-Hadamard Transform (FWHT). The core idea of the proposed scheme consist of four key steps: The original cover image is divided into small blocks. The NMF is then applied to each block separately, followed by using the FWHT to the generated weight matrix. Finally, the singular values of the watermark image are distributed over the transformed blocks. The experimental results certainly show enhanced visual imperceptibility and exceptional resiliency against various types of attacks.

关键词： Watermarking fast hadamard transform nonnegative matrix factorization robustness to attacks

来源：评论

学校读者我要写书评

暂无评论

Source apportionment of atmospheric particle number concentrations with wide size range by nonnegative matrix factorization (NMF)

引用

ENVIRONMENTAL POLLUTION 2021年 289卷 117846页

作者： Liang, Chun-Sheng Yue, Dingli Wu, Hao Shi, Jin-Sen He, Ke-Bin Lanzhou Univ Collaborat Innovat Ctr West Ecol Safety Lanzhou 730000 Peoples R China Guangdong Environm Monitoring Ctr State Environm Protect Key Lab Reg Air Qual Monit Guangzhou 510308 Peoples R China Lanzhou Univ Coll Atmospher Sci Minist Educ Key Lab Semiarid Climate Change Lanzhou 730000 Peoples R China Tsinghua Univ Sch Environm State Key Joint Lab Environm Simulat & Pollut Con Beijing 100084 Peoples R China State Environm Protect Key Lab Sources & Control Beijing 100084 Peoples R China Chengdu Univ Informat Technol Sch Elect Engn China Meteorol Adm Atmospher Sounding Key Lab Chengdu 610225 Peoples R China

Quantifying the sources of atmospheric particles is essential to air quality control but remains challenging, especially for the source apportionment of particles based on number concentration with wide size range. Here, particle number concentrations (PNC) with size range 19-20,000 nm involving four modes Nucleation, Aitken, Accumulation, and Coarse are used to do source apportionment of PNC at the Guangdong Atmospheric Supersite (Heshan) during July-October 2015 by nonnegative matrix factorization (NMF) with 6 factors. For July 2015, separated source apportionments for three different size ranges from collocated instruments nano scanning mobility particle sizer (NSMPS), SMPS, and aerodynamic particle sizer (APS) and for two different size ranges (below and above 100 nm) show similar quantitative source information with that for the one whole size range. The mean absolute difference of contribution percentages of total particle number concentrations (TPNC) based on 5 unique apportioned sources is 5.6 % (4.3-7.6 %) for the instrument segregated apportionment and 4.2 % (0-5.3 %) for the size range segregated apportionment respectively, relative to the one whole apportionment. Moreover, the contribution percentages of TPNC are close to the weighted sum of contribution percentages of all size bins, with a mean absolute difference of 1.1 % (0-3.4 %). In both these two aspects, the consistency among different technical paths proves the matrix factorization by NMF is practically desirable and the simplicity of reducing some steps or calculations saves time. Besides, dust can be identified with the wide size range including larger than 3000 nm. Six apportioned sources in the 4 months are Accumulation (32.4 %), Nucleation (20.0 %), Aitken (15.2 %), traffic (14.6 %), dust (10.6 %), and Coarse (7.1 %). Therefore, NMF would serve as a promising tool for PNC source apportionment with wide size range and conducting the apportionment with the whole size range in one matrix factor

关键词： Source apportionment Particle number concentrations nonnegative matrix factorization Particle number size distributions Receptor model Particle sizer

来源：评论

学校读者我要写书评

暂无评论

Detecting dynamic community by fusing network embedding and nonnegative matrix factorization

引用

KNOWLEDGE-BASED SYSTEMS 2021年 221卷 106961-106961页

作者： Li, Dongyuan Zhong, Xiaoxiong Dou, Zengfa Gong, Maoguo Ma, Xiaoke Xidian Univ Sch Comp Sci & Technol Xian Shaanxi Peoples R China Peng Cheng Lab Shenzhen Guandong Peoples R China China Elect Technol Grp Corp Res Inst 20 Xian Shaanxi Peoples R China Xidian Univ Sch Elect Engn Xian Shaanxi Peoples R China

Many systems in nature and society, ranging from types of cancers to engineering, can be modeled as temporal networks. Identification of dynamic communities is fundamental for investigating the mechanisms of systems. Compared with community detection in static networks, dynamic community detection is challenging because it simultaneously leverages clustering accuracy with clustering drift. Current methods employ the temporal smoothness framework to balance these two items, but the inaccuracy and complexity of these methods have been criticized. To overcome these issues, a novel algorithm called NE2NMF for dynamic community detection is proposed by fusing Network Embedding based Evolutionary nonnegative matrix factorization. Specifically, we use third-order smoothness to characterize clustering drift by fusing snapshots of previous, current, and subsequent time steps, thereby improving the accuracy of the characterization of dynamic communities. Moreover, to reduce time complexity, we decompose the network embedding matrix, rather than the adjacency matrix of each snapshot on the basis of the equivalence between evolutionary non-negative matrix factorization (ENMF) and network embedding. Results demonstrate that NE2NMF outperforms state-of-the-art approaches in terms of accuracy and robustness. (c) 2021 Elsevier B.V. All rights reserved.

关键词： Dynamic community detection Temporal networks nonnegative matrix factorization Network embedding Trace optimization

来源：评论

学校读者我要写书评

暂无评论

Structured nonnegative matrix factorization for traffic flow estimation of large cloud networks

引用

COMPUTER NETWORKS 2021年 201卷 108564-108564页

作者： Atif, Syed Muhammad Gillis, Nicolas Qazi, Sameer Naseem, Imran Karachi Inst Econ & Technol Grad Sch Sci & Engn Karachi 75190 Sindh Pakistan Karachi Inst Econ & Technol Coll Engn Karachi 75190 Sindh Pakistan Univ Mons Fac Polytech Dept Math & Operat Res Rue Houdain 9 B-7000 Mons Belgium Univ Western Australia Sch Elect Elect & Comp Engn 35 Stirling Highway Crawley WA 6009 Australia

Network traffic matrix estimation is an ill-posed linear inverse problem: it requires to estimate the unobservable origin destination traffic flows, X, given the observable link traffic flows, Y, and a binary routing matrix, A, which are such that Y = AX. This is a challenging but vital problem as accurate estimation of OD flows is required for several network management tasks. In this paper, we propose a novel model for the network traffic matrix estimation problem which maps high-dimension OD flows to low-dimension latent flows with the following three constraints: (1) nonnegativity constraint on the estimated OD flows, (2) autoregression constraint that enables the proposed model to effectively capture temporal patterns of the OD flows, and (3) orthogonality constraint that ensures the mapping between low-dimensional latent flows and the corresponding link flows to be distance preserving. The parameters of the proposed model are estimated with a training algorithm based on Nesterov accelerated gradient and generally shows fast convergence. We validate the proposed traffic flow estimation model on two real backbone IP network datasets, namely Internet2 and GEANT. Empirical results show that the proposed model outperforms the state-of-the-art models not only in terms of tracking the individual OD flows but also in terms of standard performance metrics. The proposed model is also found to be highly scalable compared to the existing state-of-the-art approaches.

关键词： Network traffic matrix estimation nonnegative matrix factorization Nesterov accelerated gradient Autoregressive model Graph embedding Distance preserving transformation

来源：评论

学校读者我要写书评

暂无评论

Structural features with nonnegative matrix factorization for metamorphic malware detection

引用

COMPUTERS & SECURITY 2021年 104卷 102216-102216页

作者： Ling, Yeong Tyng Sani, Nor Fazlida Mohd Abdullah, Mohd Taufik Hamid, Nor Asilah Wati Abdul Univ Malaysia Sarawak Fac Comp Sci & Informat Technol Sarawak Malaysia Univ Putra Malaysia Fac Comp Sci & Informat Technol Dept Comp Sci Serdang Selangor Malaysia

Metamorphic malware is well known for evading signature-based detection by exploiting various code obfuscation techniques. Current metamorphic malware detection approaches require some prior knowledge during feature engineering stage to extract patterns and behaviors from malware. In this paper, we attempt to complement and extend previous techniques by proposing a metamorphic malware detection approach based on structure analysis by using information theoretic measures and statistical metrics with machine learning model. In particular, compression ratio, entropy, Jaccard coefficient and Chi-square tests are used as feature representations to reveal the byte information existing in malware binary file. Furthermore, by using nonnegative matrix factorization, feature dimension can be reduced. The experimental results show the Jaccard coefficient on hexadecimal byte as feature representation is effective for Windows metamorphic malware detection with an accuracy rate and F-score as high as 0.9972 and 0.9958, respectively. Whereas for Linux morphed malware detection, the Chi-square statistic test shows as effective feature representation with an accuracy rate and F-score as high as 0.9878 and 0.9901, respectively. Overall, the proposed feature representations and the technique of dimension reduction can be useful for detecting metamorphic malware. ? 2021 Elsevier Ltd. All rights reserved.

关键词： Metamorphic malware Compression ratio Entropy Jaccard coefficient Chi-square nonnegative matrix factorization

来源：评论

学校读者我要写书评

暂无评论

Maximum Likelihood Estimation Based nonnegative matrix factorization for Hyperspectral Unmixing

引用

REMOTE SENSING 2021年第13期13卷 2637-2637页

作者： Jiang, Qin Dong, Yifei Peng, Jiangtao Yan, Mei Sun, Yi Hubei Univ Fac Math & Stat Hubei Key Lab Appl Math Wuhan 430062 Peoples R China Anhui Univ Finance & Econ Sch Finance Bengbu 233030 Peoples R China

Hyperspectral unmixing (HU) is a research hotspot of hyperspectral remote sensing technology. As a classical HU method, the nonnegative matrix factorization (NMF) unmixing method can decompose an observed hyperspectral data matrix into the product of two nonnegative matrices, i.e., endmember and abundance matrices. Because the objective function of NMF is the traditional least-squares function, NMF is sensitive to noise. In order to improve the robustness of NMF, this paper proposes a maximum likelihood estimation (MLE) based NMF model (MLENMF) for unmixing of hyperspectral images (HSIs), which substitutes the least-squares objective function in traditional NMF by a robust MLE-based loss function. Experimental results on a simulated and two widely used real hyperspectral data sets demonstrate the superiority of our MLENMF over existing NMF methods.

关键词： hyperspectral unmixing maximum likelihood estimation nonnegative matrix factorization

来源：评论

学校读者我要写书评

暂无评论

PIXEL-WISE LINEAR/NONLINEAR nonnegative matrix factorization FOR UNMIXING OF HYPERSPECTRAL DATA

PIXEL-WISE LINEAR/NONLINEAR NONNEGATIVE MATRIX FACTORIZATION...

引用

IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Zhu, Fei Honeine, Paul Chen, Jie Tianjin Univ Ctr Appl Math Tianjin 300072 Peoples R China Normandie Univ UNIROUEN LITIS F-76000 Rouen France Northwestern Polytech Univ Sch Marine Sci & Technol Xian 710072 Peoples R China

ISBN: (纸本)9781509066315

Nonlinear spectral unmixing is a challenging and important task in hyperspectral image analysis. The kernel-based bi-objective nonnegative matrix factorization (Bi-NMF) has shown its usefulness in nonlinear unmixing;However, it suffers several issues that prohibit its practical application. In this work, we propose an unsupervised nonlinear unmixing method that overcomes these weaknesses. Specifically, the new method introduces into each pixel a parameter that adjusts the nonlinearity therein. These parameters are jointly optimized with endmembers and abundances, using a carefully designed objective function by multiplicative update rules. Experiments on synthetic and real datasets confirm the effectiveness of the proposed method.

关键词： Hyperspectral data analysis nonlinear unmixing unsupervised learning kernel methods nonnegative matrix factorization

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：