检索结果-内蒙古大学图书馆

9th IEEE International Workshop on Computational Advances in Multi-Sensor Adaptive Processing (CAMSAP)

作者： Wolnick, Daniel Grey Ibrahim, Shahana Marrinan, Tim Fu, Xiao Oregon State Univ Sch EECS Corvallis OR USA Pacific Northwest Natl Lab Seattle WA USA

ISBN: (纸本)9798350344523

Deep neural networks (DNN) heavily rely on labeled data for supervised training. However, acquiring accurate labels is often a challenging task. Moreover, DNNs easily overfit to noisy labels, hindering the generalization ability. Modeling the label noise using a "confusion matrix" is a widely adopted strategy under such circumstances. A recent work dealt with this problem using a regularizer that is reminiscent of minimum-volume enclosing simplex (MVES)-based matrix factorization. MVES is known for its identifiability of the latent factors, which in turn helps accurately estimate the confusion matrix and rectify its negative effects when training DNNs. However, MVES is highly sensitive to outliers due to its geometric nature. To overcome this limitation, we take insight from the robustification of MVES in the literature to come up with an outlier-resilient noisy label learning criterion. Consequently, when some data samples deviate from the model assumptions, the proposed criterion automatically downweights such outlying data, thereby steering DNN towards identifying the correct model parameters. Our experiment results provide support for the effectiveness of the proposed criterion.

关键词： noisy labels deep learning volume minimization nonnegative matrix factorization

来源：评论

学校读者我要写书评

暂无评论

Metamorphic malware detection using structural features and nonnegative matrix factorization with hidden markov model

引用

JOURNAL OF COMPUTER VIROLOGY AND HACKING TECHNIQUES 2022年第3期18卷 183-203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 Serdang Selangor Malaysia

Metamorphic malware modifies its code structure using a morphing engine to evade traditional signature-based detection. Previous research has shown the use of opcode instructions as feature representation with Hidden Markov Model in the context of metamorphic malware detection. However, it would be more feasible to extract a file feature at fine-grained level. In this paper, we propose a novel detection approach by generating structural features through computing a stream of byte chunks using compression ratio, entropy, Jaccard similarity coefficient and Chi-square statistic test. nonnegative matrix factorization is also considered to reduce the feature dimensions. We then use the coefficient vectors from the reduced space to train Hidden Markov Model. Experimental results show there is different performance between malware detection and classification among the proposed structural features.

关键词： Hidden Markov model Metamorphic malware nonnegative matrix factorization Structural feature

来源：评论

学校读者我要写书评

暂无评论

引用

INTERDISCIPLINARY SCIENCES-COMPUTATIONAL LIFE SCIENCES 2022年第1期14卷 45-54页

作者： Zhu, Ya-Li Yuan, Sha-Sha Liu, Jin-Xing Qufu Normal Univ Sch Comp Sci Rizhao Peoples R China Rizhao Huilian Zhongchuang Inst Intelligent Techn Rizhao 276826 Peoples R China

In traditional sequencing techniques, the different functions of cells and the different roles they play in differentiation are often ignored. With the advancement of single-cell RNA sequencing (scRNA-seq) techniques, scientists can measure the gene expression value at the single-cell level, and it is helping to understand the heterogeneity hidden in cells. One of the most powerful ways to find heterogeneity is using the unsupervised clustering method to get separate subpopulations. In this paper, we propose a novel clustering method Similarity and Dissimilarity Regularized nonnegative matrix factorization (SDCNMF) that simultaneously impose similarity and dissimilarity constraints on low-dimensional representations. SDCNMF both considers the similarity of closer cells and the dissimilarity of cells that are farther away. It can not only keep the similar cells getting closer in low-dimensional space, but also can push the dissimilar cells away from each other. We test the validity of our proposed method on five scRNA-seq datasets. Clustering results show that SDCNMF is better than other comparative methods, and the gene markers we find are also consistent with previous studies. Therefore, we can conclude that SDCNMF is effective in scRNA-seq data analysis.

关键词： nonnegative matrix factorization Dimension reduction Single-cell RNA sequencing Clustering

来源：评论

学校读者我要写书评

暂无评论

Fusion High-Order Information with nonnegative matrix factorization Based Community Infomax for Community Detection 16th

Fusion High-Order Information with Nonnegative Matrix Factor...

引用

16th International Conference on Knowledge Science, Engineering and Management (KSEM)

作者： Li, Ying Chen, Guohua Tang, Yong Zhang, Nini South China Normal Univ Sch Comp Sci Guangzhou Peoples R China South China Normal Univ Network Ctr Guangzhou Peoples R China Pazhou Lab Guangzhou Peoples R China

ISBN: (纸本)9783031402883;9783031402890

Community detection plays an important role in understanding the structures and functions of complex networks. Due to their simplicity, flexibility, effectiveness, and better interpretability, nonnegative matrix factorization (NMF)-based methods have been widely employed for community detection. However, most existing NMF-based community detection algorithms are shallow methods and their performance is limited when facing complex real-world networks. On the other view, the high-order information of the graph can provide more abundant structure information for community detection. Considering those questions, we propose a novel high-order NMF-based community detection method called HGI-NMF, which is composed of three modules: multi-hops graph attention encoders, graph-levelmutual information, and NMF-based community mutual information. This approach first encodes the high-order graph structure with an attention encoder and then uses the readout function, discriminator and graph, and community-level mutual information to jointly optimize our model. The experimental results show that our model outperforms state-of-the-art community detection methods.

关键词： Community detection nonnegative matrix factorization Graph neural networks Mutal information

来源：评论

学校读者我要写书评

暂无评论

nonnegative matrix factorization over Continuous Signals using Parametrizable Functions

引用

NEUROCOMPUTING 2020年 416卷 256-265页

作者： Hautecoeur, Cecile Glineur, Francois Catholic Univ Louvain CORE & ICTEAM Inst B-1348 Louvain La Neuve Belgium

nonnegative matrix factorization is a popular data analysis tool able to extract significant features from nonnegative data. We consider an extension of this problem to handle functional data, using parametrizable nonnegative functions such as polynomials or splines. Factorizing continuous signals using these parametrizable functions improves both the accuracy of the factorization and its smoothness. We introduce a new approach based on a generalization of the Hierarchical Alternating Least Squares algorithm. Our method obtains solutions whose accuracy is similar to that of existing approaches using polynomials or splines, while its computational cost increases moderately with the size of the input, making it attractive for large-scale datasets. (C) 2020 Elsevier B.V. All rights reserved.

关键词： nonnegative matrix factorization Hierarchical alternating least squares (HALS) Functional nonnegative matrix factorization (projection on) nonnegative polynomials (projection on) nonnegative splines

来源：评论

学校读者我要写书评

暂无评论

nonnegative matrix factorization for link prediction in directed complex networks using PageRank and asymmetric link clustering information

引用

EXPERT SYSTEMS WITH APPLICATIONS 2020年 148卷 113290-113290页

作者： Chen, Guangfu Xu, Chen Wang, Jingyi Feng, Jianwen Feng, Jiqiang Shenzhen Univ Coll Elect & Informat Engn Shenzhen Peoples R China Shenzhen Univ Coll Math & Stat Shenzhen Peoples R China

The aim of link prediction is to predict missing links in current networks or new links in future networks. Almost all the existing directed link prediction algorithms only take into account the links direction formation but ignored the abundant network topological information such as local and global structures. Therefore, how to preserve both local and global structure information is an important issue for directed link prediction. To solve this problem, in this paper, we are motivated to propose a novel nonnegative matrix factorization via Asymmetric link clustering and PageRank model, namely NMF-AP. Specifically, we utilize the PageRank algorithm to calculate the influence score of the node, which captures the global network structure information. While we employ the asymmetric link clustering method to calculate the link clustering coefficient score, which preserves the local network structure information. By jointly optimizing them in the nonnegative matrix factorization model, our model can preserve both the local and global information at the same time. Besides, we provide an effective the multiplicative updating rules to learn the parameter of NMF-AP. Extensive experiments are conducted on ten real-world directed networks, experiment results demonstrate that the method NMF-AP outperforms state-of-the-art link prediction methods. (C) 2020 Elsevier Ltd. All rights reserved.

关键词： Link prediction nonnegative matrix factorization PageRank Asymmetric link clustering

来源：评论

学校读者我要写书评

暂无评论

scNMF-Impute: imputation for single-cell RNA-seq data based on nonnegative matrix factorization

scNMF-Impute: imputation for single-cell RNA-seq data based ...

引用

2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023

作者： Wang, Juan Zhang, Na-Na Shang, Jun-Liang Liu, Jin-Xing Qufu Normal University School of Computer Science Rizhao276826 China

ISBN: (纸本)9798350337488

Single-cell RNA sequencing (scRNA-seq) data are collected at an unheard-of rate thanks to the advancement of high-throughput sequencing technologies. However, due to the limitations of current technology, scRNA-seq is sometimes unable to capture the expressed genes, resulting in a large number of zero counts (also known as dropout events) in the data. These dropout events can cause data loss in the gene expression matrix and severely hampers the accuracy of downstream analysis. To address this problem, in this paper, we propose a new imputation method called scNMF-impute. The scNMF-impute method imputes the dropout events and performs dimensionality reduction under the framework of nonnegative matrix factorization (NMF). To effectively identify the location of the dropout and recover the value of the dropout, we explicitly model the dropout events as a matrix. Therefore, the gene expression matrix without dropout is represented as the sum of the original data matrix and the dropout matrix. In addition, to reduce the influence of dropout on factorization, we introduce the similarity information between genes into the NMF model. The introduction of gene similarity information can ensure the accurate recovery of data structures obscured by dropout events in the gene expression matrix. We conducted extensive experiments on simulated datasets and real scRNA-seq datasets to verify the effectiveness of scNMF-impute and other state-of-the-art methods. The results show that scNMF-impute can accurately calculate missing data and restore true gene expression, thus improving the accuracy of existing clustering methods and obtaining more accurate cell clustering results. © 2023 IEEE.

关键词： Dropout event Gene expression Imputation nonnegative matrix factorization scRNA-seq datasets

来源：评论

学校读者我要写书评

暂无评论

A novel nonnegative matrix factorization-based model for attributed graph clustering by incorporating complementary information

引用

EXPERT SYSTEMS WITH APPLICATIONS 2024年 242卷

作者： Jannesari, Vahid Keshvari, Maryam Berahmand, Kamal Wichita State Univ Dept Ind Syst & Mfg Wichita KS USA Wichita State Univ Dept Elect Engn & Comp Sci Wichita KS USA Queensland Univ Technol Dept Sci & Engn Brisbane Australia

Attributed graph clustering is a prominent research area, catering to the increasing need for understanding real -world systems by uncovering exhaustive meaningful latent knowledge from heterogeneous spaces. Therefore, the critical challenge of this problem is the strategy used to extract and integrate meaningful heterogeneous information from structure and attribute sources. To this end, in this paper, we propose a novel nonnegative matrix factorization (NMF)-based model for attributed graph clustering. In this method, firstly, we filter structure and attribute spaces from noise and irrelevant information for clustering by applying Symmetric NMF and NMF during the clustering task, respectively. Then, to overcome the heterogeneity of discovered partitions from spaces, we suggest a new regularization term to inject the complementary information from the attribute partition into the structure by transforming them into their pairwise similarity spaces, which are homogeneous. Simultaneously, by setting orthogonality constraints on the discovered communities, we encourage the representation of distinct and non-overlapping communities within the attributed graph. Finally, we collect all these terms in a unified framework to learn a meaningful partition containing consensus and complementary information from structure and attributes. Then a new iterative multiplicative updating strategy is proposed to solve the proposed model, and its convergence is proven theoretically. Our experiments on the nine popular real-world networks illustrate the supremacy of our methods among eleven widely recognized and stat-of-the-arts attributed graph clustering methods in terms of accurately matching the ground truth and quality-based metrics.

关键词： Attributed network clustering nonnegative matrix factorization Heterogeneous information And information consistency

来源：评论

学校读者我要写书评

暂无评论

WSNMF: Weighted Symmetric nonnegative matrix factorization for attributed graph clustering

引用

NEUROCOMPUTING 2024年 566卷

作者： Berahmand, Kamal Mohammadi, Mehrnoush Sheikhpour, Razieh Li, Yuefeng Xu, Yue Queensland Univ Technol Fac Sci Sch Comp Sci Brisbane Australia Univ Kurdistan Dept Comp Engn Sanandaj Iran Ardakan Univ Fac Engn Dept Comp Engn POB 184 Ardakan Iran

In recent times, Symmetric nonnegative matrix factorization (SNMF), a derivative of nonnegative matrix factorization (NMF), has surfaced as a promising technique for graph clustering. Nevertheless, when applied to attributed graph clustering, it confronts notable challenges. These include the disregard for attributed information, the oversight of geometric data point structures, and the inability to discriminate irrelevant features and data outliers. In response, we introduce an innovative extension of SNMF termed Weighted Symmetric nonnegative matrix factorization (WSNMF). This method introduces node attribute similarity to compute a weight matrix, effectively bridging the gap for attributed graph clustering. Our approach incorporates graph regularization and sparsity constraints to uphold the geometric structure of data points and discern irrelevant features and data outliers. Additionally, we present an updating rule to address optimization complexities and validate algorithmic convergence. Rigorous experimentation on real-world and synthetic networks, employing well-established metrics including F-measure, RI, Modularity, Density, and entropy, substantiates the performance enhancement offered by WSNMF.

关键词： Attributed networks Attributed graph clustering nonnegative matrix factorization Symmetric nonnegative matrix factorization

来源：评论

学校读者我要写书评

暂无评论

Deep self-reconstruction driven joint nonnegative matrix factorization model for identifying multiple genomic imaging associations in complex diseases

引用

JOURNAL OF BIOMEDICAL INFORMATICS 2024年 156卷 104684页

作者： Deng, Jin Wei, Kai Fang, Jiana Li, Ying South China Agr Univ Coll Math & Informat Guangzhou 510642 Peoples R China Chinese Acad Sci Univ Chinese Acad Sci Shanghai Inst Nutr & Hlth CAS Key Lab Computat BiolBiomed Big Data Ctr Shanghai Peoples R China Shanghai Inst Technol Shanghai 201418 Peoples R China

Objective: Comprehensive analysis of histopathology images and transcriptomics data enables the identification of candidate biomarkers and multimodal association patterns. Most existing multimodal data association studies are derived from extensions of the joint nonnegative matrix factorization model for identifying complex data associations, which can make full use of clinical prior information. However, the raw data were usually taken as the input without considering the underlying complex multi-subspace structure, influencing the subsequent integration analysis results. Methods: This study proposed a deep-self reconstructed joint nonnegative matrix factorization (DSRJNMF) model to use self-expressive properties to reconstruct the raw data to characterize the similarity structure associated with clinical labels. Then, the sparsity, orthogonality, and regularization constraints constructed from prior information are added to the DSRJNMF model to determine the sparse set of biologically relevant features across modalities. Results: The algorithm has been applied to identify the imaging genetic association of triple negative breast cancer (TNBC). Multilevel experimental results demonstrate that the proposed algorithm better estimates potential associations between pathological image features and miRNA-gene and identifies consistent multimodal imaging genetic biomarkers to guide the interpretation of TNBC. Conclusion: The propose method provides a novel idea of data association analysis oriented to complex diseases.

关键词： Histopathology image Genetic variation nonnegative matrix factorization Triple negative breast cancer Association pattern

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：