非负矩阵分解方法识别电能质量扰动信号

利用相空间重构及非负矩阵分解(NMF)相结合的方法,对电压暂降、电压暂升、电压尖峰、电压中断、暂态谐波及暂态振荡6类电能扰动信号进行分类识别研究。利用相空间重构法构造扰动信号轨迹,并将其转化为图像。从图像处理的角度出发,利用NMF在人脸、指纹图像识别应用中的基本原理,对不同的相空间重构轨迹图进行特征提取,分类识别其所对应的电能质量扰动信号。该方法可避免由于扰动信号的复杂性而难以获得扰动信号稳定特征提取的困难,具有训练时间短、所需训练样本少、识别过程可视化便于分析等特点。仿真实验结果表明其能够较好地识别电能质量扰动,是提供了扰动信号检测与分类的算法。     

Discriminant Nonnegative Tensor Factorization Algorithms

Nonnegative matrix factorization (NMF) has proven to be very successful for image analysis, especially for object representation and recognition. NMF requires the object tensor (with valence more than one) to be vectorized. This procedure may result in information loss since the local object structure is lost due to vectorization. Recently, in order to remedy this disadvantage of NMF methods, nonnegative tensor factorizations (NTF) algorithms that can be applied directly to the tensor representation of object collections have been introduced. In this paper, we propose a series of unsupervised and supervised NTF methods. That is, we extend several NMF methods using arbitrary valence tensors. Moreover, by incorporating discriminant constraints inside the NTF decompositions, we present a series of discriminant NTF methods. The proposed approaches are tested for face verification and facial expression recognition, where it is shown that they outperform other popular subspace approaches.      

采用SVD-NMF的管道泄漏信号去噪算法

在管道泄漏检测中,压力信号中的噪声干扰会降低传统互相关法的定位精度。传统的去噪算法对环境的适应性差,去噪效果不理想。为此,提出了一种奇异值分解SVD( Singular Value Decomposition)与非负矩阵分解NMF( Nonnegative Matrix Factorization)相结合的管道泄漏信号去噪算法。该方法首先通过奇异值分解确定非负矩阵分解的阶数并对其初始化;然后,采用改进的非负矩阵分解算法对原信号进行迭代分解,获得去噪信号;最后,对去噪信号进行处理后通过互相关计算时延,并结合泄漏信号的传播速度实现泄漏定位。大量实验结果表明,SVD￣NMF算法能够显著降低迭代次数,提高去噪速度;同时在泄漏检测中,能够达到去除噪声干扰,提高定位精度的目的。     

基于约束NMF的欠定盲信号分离算法*

提出一种约束非负矩阵分解方法用于解决欠定盲信号分离问题。非负矩阵分解直接用于求解欠定盲信号分离时,分解结果不唯一,无法正确分离源信号。本文在基本非负矩阵分解算法基础上,对分解得到的混合矩阵施加行列式约束,保证分解结果的唯一性;对分解得到的源信号同时施加稀疏性约束和最小相关约束,实现混合信号的唯一分解,提高源信号分离性能。仿真实验证明了本文算法的有效性。     

Source separation using regularized NMF with MMSE estimates under GMM priors with online learning for the uncertainties

We propose a new method to incorporate priors on the solution of nonnegative matrix factorization (NMF). The NMF solution is guided to follow the minimum mean square error (MMSE) estimates of the weight combinations under a Gaussian mixture model (GMM) prior. The proposed algorithm can be used for denoising or single-channel source separation (SCSS) applications. NMF is used in SCSS in two main stages, the training stage and the separation stage. In the training stage, NMF is used to decompose the training data spectrogram for each source into a multiplication of a trained basis and gains matrices. In the separation stage, the mixed signal spectrogram is decomposed as a weighted linear combination of the trained basis matrices for the source signals. In this work, to improve the separation performance of NMF, the trained gains matrices are used to guide the solution of the NMF weights during the separation stage. The trained gains matrix is used to train a prior GMM that captures the statistics of the valid weight combinations that the columns of the basis matrix can receive for a given source signal. In the separation stage, the prior GMMs are used to guide the NMF solution of the gains/weights matrices using MMSE estimation. The NMF decomposition weights matrix is treated as a distorted image by a distortion operator, which is learned directly from the observed signals. The MMSE estimate of the weights matrix under the trained GMM prior and log-normal distribution for the distortion is then found to improve the NMF decomposition results. The MMSE estimate is embedded within the optimization objective to form a novel regularized NMF cost function. The corresponding update rules for the new objectives are derived in this paper. The proposed MMSE estimates based regularization avoids the problem of computing the hyper-parameters and the regularization parameters. MMSE also provides a better estimate for the valid gains matrix. Experimental results show that the proposed regularized NMF algorithm improves the source separation performance compared with using NMF without a prior or with other prior models.     

Nonlinear nonnegative matrix factorization based on Mercer kernel construction

Generalizations ofnonnegative matrix factorization (NMF) in kernel feature space, such as projected gradient kernel NMF (PGKNMF) and polynomial Kernel NMF (PNMF), have been developed for face and facial expression recognition recently. However, these existing kernel NMF approaches cannot guarantee the nonnegativity of bases in kernel feature space and thus are essentially semi-NMF methods. In this paper, we show that nonlinear semi-NMF cannot extract the localized components which offer important information in object recognition. Therefore, nonlinear NMF rather than semi-NMF is needed to be developed for extracting localized component as well as learning the nonlinear structure. In order to address the nonlinear problem of NMF and the semi-nonnegative problem of the existing kernel NMF methods, we develop the nonlinear NMF based on a self-constructed Mercer kernel which preserves the nonnegative constraints on both bases and coefficients in kernel feature space. Experimental results in face and expressing recognition show that the proposed approach outperforms the existing state-of-the-art kernel methods, such as KPCA, GDA, PNMF and PGKNMF.     

基于改进非负矩阵分解的手背静脉识别算法

为提高手背静脉识别过程中特征的有效性,提出了一种基于改进非负矩阵分解（NMF）的识别算法．首先,静脉图像经过分块后,将每一块子图像的像素均值与平均梯度幅值作为图像原始特征;其次,将所有训练样本原始特征形成的特征矩阵进行非负矩阵分解,其中对分解后的系数向量加以稀疏性与可区分性约束,从而形成改进的非负矩阵分解模型;再次,基于梯度投影法对提出的非负矩阵分解模型进行求解,获取新的特征基与特征向量;最后,利用最近邻匹配算法对特征向量进行分类,实现身份的识别．实验结果表明,提出的识别算法可获得较高的识别率,处理过程具有较好实时性．     

基于非负矩阵分解与相似性分析的运动目标检测

提出一种结合修正的非负矩阵分解与向量相似性分析进行运动目标检测的方法。该方法首先使用修正后的非负矩阵分解算法从连续图像序列中恢复出背景图像，然后分析待检测帧像素点与恢复出来的背景模型之间的相似性，根据相似性的高低区分背景与前景。为了减少计算量，降低动态背景对检测结果的干扰，该方法在进行相似性分析之前，通过核密度估计的方法对运动区域进行估计。实验结果表明，该方法能够较为精确地恢复出背景图像，并有效地检测出运动目标。     

How color break‐up occurs in the human‐visual system: The mechanism of the color break‐up phenomenon

Abstract— In the present set of experiments, we examined the mechanisms underlying color break‐up (CBU), a phenomenon observed when images produced with a color‐sequential projector are viewed. The perceived position of CBU was measured during fast eye movement, saccade with static and briefly flashed stimuli. Results showed that CBU did not simply correspond to the locus of the stimulus on the retina during saccades, because the width of the CBU perception was narrower than the distance of the eye movements. This effect was thought to be related to visual stability, which allows objects to be perceived as stationary even when the eyes move and the retinal image changes position. Visual stability is assumed to operate by compensating for the change in retinal image position using eye‐position signals; however, this compensation is imperfect during saccades. Thus, incomplete compensation results in a CBU perception that is of a narrower width than the amplitude of the saccade. In conclusion, CBU cannot be simulated with moving video cameras because it results largely from the mechanisms of visual perception. Large inter‐individual differences in perception of CBU were also found. This observation also supports the idea that CBU depends on the mechanism of perception.     

融合先验信息的非负矩阵分解社区发现算法*

针对复杂网络社区发现问题,为了获得更准确、可解释性的社区划分结果,提出融合先验信息的半监督非负矩阵分解算法,给出优化目标的求解方法.文中算法利用先验信息直接约束社区指示矩阵,构造优化目标函数,获得更有意义的社区划分结果.真实数据集上的实验表明该算法的有效性,减小先验信息的融入对利用非负矩阵分解进行节点重要性等属性分析工作带来的不利影响,并且适用于加权和非加权等不同的网络.     

Object‐oriented distributed computing based on remote class reference

Java RMI, Jini and CORBA provide effective mechanisms for implementing a distributed computing system. Recently many numeral libraries have been developed that take advantage of Java as an object‐oriented and portable language. The widely‐used client‐server method limits the extent to which the benefits of the object‐oriented approach can be exploited because of the difficulties arising when a remote object is the argument or return value of a remote or local method. In this paper this problem is solved by introducing a data object that stores the data structure of the remote object and related access methods. By using this data object, the client can easily instantiate a remote object, and use it as the argument or return value of either a local or remote method. Copyright © 2003 John Wiley & Sons, Ltd.     

Food safety inspection using “from presence to classification” object-detection model

With multiresolution decomposition and forest representation of wavelet transforms, we implemented a “from presence to classification” object-detection model. Three aspects of this model are studied. First, the presence of an object is quickly detected with fewer data manipulations at the coarsest resolution; secondly, object classification with high accuracy is fulfilled at the full resolution; and thirdly, the propagation in the coarse-to-fine process is studied in terms of coefficient propagation within a coefficient tree. We applied this model to internal deboned poultry inspection. As soon as the presence of a hazardous object was detected at a coarse resolution, a signal was actuated to reject the chicken fillet containing foreign inclusions before packing. Only with small foreign inclusions did we need to resort to finer resolution analysis.     

Nonnegative matrix factorization with the Itakura-Saito divergence: with application to music analysis

This letter presents theoretical, algorithmic, and experimental results about nonnegative matrix factorization (NMF) with the Itakura-Saito (IS) divergence. We describe how IS-NMF is underlaid by a well-defined statistical model of superimposed gaussian components and is equivalent to maximum likelihood estimation of variance parameters. This setting can accommodate regularization constraints on the factors through Bayesian priors. In particular, inverse-gamma and gamma Markov chain priors are considered in this work. Estimation can be carried out using a space-alternating generalized expectation-maximization (SAGE) algorithm; this leads to a novel type of NMF algorithm, whose convergence to a stationary point of the IS cost function is guaranteed. We also discuss the links between the IS divergence and other cost functions used in NMF, in particular, the Euclidean distance and the generalized Kullback-Leibler (KL) divergence. As such, we describe how IS-NMF can also be performed using a gradient multiplicative algorithm (a standard algorithm structure in NMF) whose convergence is observed in practice, though not proven. Finally, we report a furnished experimental comparative study of Euclidean-NMF, KL-NMF, and IS-NMF algorithms applied to the power spectrogram of a short piano sequence recorded in real conditions, with various initializations and model orders. Then we show how IS-NMF can successfully be employed for denoising and upmix (mono to stereo conversion) of an original piece of early jazz music. These experiments indicate that IS-NMF correctly captures the semantics of audio and is better suited to the representation of music signals than NMF with the usual Euclidean and KL costs.     

Incremental subspace learning via non-negative matrix factorization

In this paper we introduce an incremental non-negative matrix factorization (INMF) scheme in order to overcome the difficulties that conventional NMF has in online processing of large data sets. The proposed scheme enables incrementally updating its factors by reflecting the influence of each observation on the factorization appropriately. This is achieved via a weighted cost function which also allows controlling the memorylessness of the factorization. Unlike conventional NMF, with its incremental nature and weighted cost function the INMF scheme successfully utilizes adaptability to dynamic data content changes with a lower computational complexity. Test results reported for two video applications, namely background modeling in video surveillance and clustering, demonstrate that INMF is capable of online representing data content while reducing dimension significantly.     

Choose your “buddy icon” carefully: The influence of avatar androgyny, anthropomorphism and credibility in online interactions

In both online and offline interactions, the visual representation of people influences how others perceive them. In contrast to the offline body, an online visual representation of a person is consciously chosen and not stable. This paper reports the results of a 2 step examination of the influence of avatars on the person perception process. Specifically, this project examines the reliance on visual characteristics during the online perception process, and the relative influence of androgyny, anthropomorphism and credibility. In the first step, 255 participants fill out a survey where they rated a set of 30 static avatars on their credibility, androgyny, and anthropomorphism. The second step is a between subjects experiment with 230 participants who interact with partners represented by one of eight avatars (high and low androgyny, and anthropomorphism by high and low credibility). Results show that the characteristics of the avatar are used in the person perception process. Causal modeling techniques revealed that perceptions of avatar androgyny influence perceptions of anthropomorphism, which influences attributions of both avatar and partner credibility. Implications of these results for theory, future research, and users and designers of systems using avatars are discussed.     

基于线性投影结构的非负矩阵分解

非负矩阵分解(Non-negative matrix factorization, NMF)是一个近年来非常流行的非负数据处理方法, 它常用于维数约减、特征提取和数据挖掘等. NMF定义中采用的数学模型基于非线性投影结构构造, 这决定了NMF降维需借助计算量很大的迭代操作来实现. 此外, 由此模型提取的NMF特征常不稀疏, 这与NMF的设计期望相差甚远. 为一并解决上述两个问题, 本文提出了一个新的模型---基于线性投影结构的NMF (Linear projection-based NMF, LPBNMF), 并构造了一个单调的LPBNMF算法. 从数学的角度看, LPBNMF可理解为实现NMF的一种特殊方式. LPBNMF降维通过线性变换来完成, 它所采用的数学模型的自身结构特点决定了由其得到的特征一定非常稀疏. 大量的比较实验表明, PBNMF的降维效率显著高于NMF, LPBNMF特征明显比NMF特征更稀疏和局部化. 最后, 基于AR人脸数据库的实验揭示, LPBNMF特征比NMF、LDA以及PCA等特征更适合于用最近邻分类法处理有遮挡人脸识别问题.     

CdF<Subscript>2</Subscript>:Ga crystal application for dynamic joint transform correlator

Dynamical holographic joint transform correlator that uses cadmium fluoride crystal with gallium bistable impurity centers to generate real-time matched filters is proposed. Optical scheme features and the correlator performance are presented. Output correlation signals of object discrimination both experimentally obtained and theoretically calculated are demonstrated. Industrial object recognition illustrates possible practical application of the correlator proposed. The article is published in the original.     

应用非负矩阵分解和RBPNN模型的掌纹识别方法

提出一种基于非负矩阵分解（NMF）和径向基概率神经网络的掌纹识别方法。NFM是一种有效的图像局部特征提取算法,用于图像分类时能得到较高的识别率。考虑PolyU掌纹图像数据库,应用NMF、局部NMF（LNMF）、稀疏NMF（SNMF）和具有稀疏度约束的NMF（NMFSC）算法分别对掌纹图像进行特征提取,并对提取到的局部特征基图像进行分析对比;在特征提取的基础上,应用径向基概率神经网络（RBPNN）模型对掌纹特征进行分类,分类结果表明了RBPNN模型对掌纹特征具有较好的识别能力。实验对比结果证明了基于RBPNN的NMF掌纹识别方法在掌纹识别中的有效性,具有一定的理论研究意义和实用性。     

Improving non-negative matrix factorizations through structured initialization

In this paper we explore a recent iterative compression technique called non-negative matrix factorization (NMF). Several special properties are obtained as a result of the constrained optimization problem of NMF. For facial images, the additive nature of NMF results in a basis of features, such as eyes, noses, and lips. We explore various methods for efficiently computing NMF, placing particular emphasis on the initialization of current algorithms. We propose using Spherical K-Means clustering to produce a structured initialization for NMF. We demonstrate some of the properties that result from this initialization and develop an efficient way of choosing the rank of the low-dimensional NMF representation.     

Enhanced clustering of biomedical documents using ensemble non-negative matrix factorization

Searching and mining biomedical literature databases are common ways of generating scientific hypotheses by biomedical researchers. Clustering can assist researchers to form hypotheses by seeking valuable information from grouped documents effectively. Although a large number of clustering algorithms are available, this paper attempts to answer the question as to which algorithm is best suited to accurately cluster biomedical documents. Non-negative matrix factorization (NMF) has been widely applied to clustering general text documents. However, the clustering results are sensitive to the initial values of the parameters of NMF. In order to overcome this drawback, we present the ensemble NMF for clustering biomedical documents in this paper. The performance of ensemble NMF was evaluated on numerous datasets generated from the TREC Genomics track dataset. With respect to most datasets, the experimental results have demonstrated that the ensemble NMF significantly outperforms classical clustering algorithms of bisecting K-means, and hierarchical clustering. We compared four different methods for constructing an ensemble NMF. For clustering biomedical documents, this research is the first to compare ensemble NMF with typical classical clustering algorithms, and validates ensemble NMF constructed from different graph-based ensemble algorithms. This is also the first work on ensemble NMF with Hybrid Bipartite Graph Formulation for clustering biomedical documents.