non-negative matrix factorization (NMF) is a new feature extraction method. But the learned feature vectors are not directly suitable for further analysis such as object recognition using the nearest neighbor classifi...
详细信息
non-negative matrix factorization (NMF) is a new feature extraction method. But the learned feature vectors are not directly suitable for further analysis such as object recognition using the nearest neighbor classifier in contrast to traditional principal component analysis (PCA) because the learned bases are not orthonormal to each other. This paper investigates how to improve the accuracy of recognition based on this new method from two viewpoints. One is to adopt a Riemannian metric like distance for the learned feature vectors instead of Euclidean distance. The other is to first orthonormalize the learned bases and then to use the projections of data based on the orthonormalized bases for further recognition. Experiments on the USPS database demonstrate the proposed methods can improve accuracy and even outperform PCA. We believe that the proposed methods can make NMF used as widely as PCA. (C) 2004 Elsevier B.V. All rights reserved.
BACKGROUND: Little is known about neural oscillatory dynamics in first-episode psychosis. Pathophysiology of functional connectivity can be measured through network activity of alpha oscillations, reflecting long-rang...
详细信息
BACKGROUND: Little is known about neural oscillatory dynamics in first-episode psychosis. Pathophysiology of functional connectivity can be measured through network activity of alpha oscillations, reflecting long-range communication between distal brain regions. METHODS: Resting magnetoencephalographic activity was collected from 31 individuals with first-episode schizophrenia spectrum psychosis and 22 healthy control individuals. Activity was projected to the realistic cortical surface, based on structural magnetic resonance imaging. The first principal component of activity in 40 Brodmann areas per hemisphere was Hilbert transformed within the alpha range. non-negative matrix factorization was applied to single-trial alpha phase-locking values from all subjects to determine alpha networks. Within networks, energy and entropy were compared. RESULTS: Four cortical alpha networks were pathological in individuals with first-episode schizophrenia spectrum psychosis. The networks involved the bilateral anterior and posterior cingulate;left auditory, medial temporal, and cingulate cortex;right inferior frontal gyrus and widespread areas;and right posterior parietal cortex and widespread areas. Energy and entropy were associated with the Positive and negative Syndrome Scale total and thought disorder factors for the first three networks. In addition, the left posterior temporal network was associated with positive and negative factors, and the right inferior frontal network was associated with the positive factor. CONCLUSIONS: Machine learning network analysis of resting alpha-band neural activity identified several aberrant networks in individuals with first-episode schizophrenia spectrum psychosis, including the left temporal, right inferior frontal, right posterior parietal, and bilateral cingulate cortices. Abnormal long-range alpha communication is evident at the first presentation for psychosis and may provide clues about mechanisms of dysconnectivity in psychosis a
One class classification is widely used in many applications. Only one target class is well characterized by instances in the training data in one class classification, and no instance is available for other non-targe...
详细信息
One class classification is widely used in many applications. Only one target class is well characterized by instances in the training data in one class classification, and no instance is available for other non-target classes, or few instances are present and they cannot form statistically representative samples for the negative concept. A two-step paradigm employing nonnegativematrixfactorization (NMF) and support vector data description (SVDD) for one class classification training of nonnegative data is developed. Firstly, a projected gradient based NMF method is used to find the hiding structure from the training instances and the training instances are projected into a new feature space. Secondly, SVDD is employed to perform one class classification training with the projected feature data. Classification examples demonstrate that the proposed method is superior to principal component analysis (PCA) based SVDD method and other standard one class classifiers. (c) 2012 International Journal of Computer Science Issues.
This paper investigates a non-negative matrix factorization (NMF)-based approach to the semi-supervised single-channel speech enhancement problem where only non-stationary additive noise signals are given. The propose...
详细信息
ISBN:
(纸本)9781629934433
This paper investigates a non-negative matrix factorization (NMF)-based approach to the semi-supervised single-channel speech enhancement problem where only non-stationary additive noise signals are given. The proposed method relies on sinusoidal model of speech production which is integrated inside NMF framework using linear constraints on dictionary atoms. This method is further developed to regularize harmonic amplitudes. Simple multiplicative algorithms are presented. The experimental evaluation was made on TIMIT corpus mixed with various types of noise. It has been shown that the proposed method outperforms some of the state-of-the-art noise suppression techniques in terms of signal-to-noise ratio.
作者：
Yang, ZekunUCL
Dept Comp Sci 66-72 Gower St London England
Considering the complexity of clustering text datasets in terms of informal user generated content and the fact that there are multiple labels for each data point in many informal user generated content datasets, this...
详细信息
ISBN:
(纸本)9781450363532
Considering the complexity of clustering text datasets in terms of informal user generated content and the fact that there are multiple labels for each data point in many informal user generated content datasets, this paper focuses on non-negative matrix factorization (NMF) algorithms for Overlapping Clustering of customer inquiry and review data, which has seldom been discussed in previous literature. We extend the use of Semi-NMF and Convex-NMF to Overlapping Clustering and develop a procedure of applying Semi-NMF and Convex-NMF on Overlapping Clustering of text data. The developed procedure is tested based on customer review and inquiry datasets. The results of comparing Semi-NMF and Convex-NMF with a baseline model demonstrate that they have advantages over the baseline model, since they do not need to adjust parameters to obtain similarly strong clustering performances. Moreover, we compare different methods of picking labels for generating Overlapping Clustering results from Soft Clustering algorithms, and it is concluded that thresholding by mean method is a simpler and relatively more reliable method compared to maximum n method.
We propose the Logistic non-negative matrix factorization for decomposition of binary data. Binary data are frequently generated in e.g. text analysis, sensory data, market basket data etc. A common method for analysi...
详细信息
ISBN:
(纸本)9789897581649
We propose the Logistic non-negative matrix factorization for decomposition of binary data. Binary data are frequently generated in e.g. text analysis, sensory data, market basket data etc. A common method for analysing non-negative data is the non-negative matrix factorization, though this is in theory not appropriate for binary data, and thus we propose a novel non-negative matrix factorization based on the logistic link function. Furthermore we generalize the method to handle missing data. The formulation of the method is compared to a previously proposed logistic matrixfactorization without non-negativity constraint on the features. We compare the performance of the Logistic non-negative matrix factorization to Least Squares non-negative matrix factorization and Kullback-Leibler (KL) non-negative matrix factorization on sets of binary data: a synthetic dataset, a set of student comments on their professors collected in a binary term-document matrix and a sensory dataset. We find that choosing the number of components is an essential part in the modelling and interpretation, that is still unresolved.
In recent years non-negativefactorization (NMF) methods of a reduced image data representation attracted the attention of computer vision community. These methods are considered as a convenient part-based representat...
详细信息
ISBN:
(纸本)9780819464514
In recent years non-negativefactorization (NMF) methods of a reduced image data representation attracted the attention of computer vision community. These methods are considered as a convenient part-based representation of image data for recognition tasks with occluded objects. In the paper two novel modifications of the NMF are proposed which utilize the matrix sparseness control used by Hoyer. We have analyzed the influence of sparseness on recognition rates (RR) for various dimensions of subspaces generated for two image databases. We have studied the behaviour of four types of distances between a projected unknown image object and feature vectors in NMF-subspaces generated for training data. For occluded ORL face data, Euclidean and diffusion distances perform better than Riemannian ones, not following the overall expactation that Euclidean metric is suitable only for orthogonal basis vectors. In the case of occluded USPS digit data, the RR obtained for the modified NMF algorithm show in comparison to the conventional NMF algorithms very close values for all four distances over all dimensions and sparseness constraints. In this case Riemannian distances provide higher RR than Euclidean and diffusion ones. The proposed modified NMF method has a relevant computational benefit, since it does not require calculation of feature vectors which are explicitly generated in the NMF optimization process.
Cochlear implants (CIs) require efficient speech processing to maximize information transfer to the brain, especially in noise. Since speech information in CI is coded in the waveform envelope which is non-negative an...
详细信息
ISBN:
(纸本)9781479903566
Cochlear implants (CIs) require efficient speech processing to maximize information transfer to the brain, especially in noise. Since speech information in CI is coded in the waveform envelope which is non-negative and is highly correlated to firing of auditory neurons, a novel CI processing strategy is proposed in which sparse constraint non-negative matrix factorization (NMF) is applied to the envelope matrix of 22 frequency channels in order to improve the CI performance in noisy environments. The proposed strategy is evaluated by subjective speech reception threshold (SRT) experiments and subjective quality rating tests at three SNRs. Compared to the default commercially available CI processing strategy, the advanced combination encoder (ACE), the NMF algorithm significantly enhanced speech intelligibility and improved speech quality in the 0 dB and 5 dB for normal hearing subjects with vocoded speech, but not in the 10 dB.
Principal component analysis has been used to remove illumination and shadow effects from images and videos. Likewise, it has also been used to remove noise from ground penetrating radar images to enhance the buried o...
详细信息
ISBN:
(纸本)9781728119045
Principal component analysis has been used to remove illumination and shadow effects from images and videos. Likewise, it has also been used to remove noise from ground penetrating radar images to enhance the buried object signature. This is a preprocessing step aiming to increase the performance of detection and classification algorithms. There are a vast number of methods used for the same purpose apart from principal component analysis like non-negative matrix factorization. In literature, however, non-negative matrix factorization has not been applied for ground penetrating radar images as frequent as principal component analysis. In this paper Nestrov's non-negative matrix factorization algorithm is used for the first time to improve signal to clutter ratio of ground penetrating radar image. It is shown that Nestrov's non-negative matrix factorization algorithm yields better results compared to fast principal component pursuit algorithm.
non-negative matrix factorization (NMF) has been shown to be useful for a variety of practical applications. To meet the requirements of various applications, some extensions of NMF have been proposed as well. This pa...
详细信息
ISBN:
(纸本)9783642342882
non-negative matrix factorization (NMF) has been shown to be useful for a variety of practical applications. To meet the requirements of various applications, some extensions of NMF have been proposed as well. This paper presents a short survey on some recent developments of NMF on both the algorithms and applications. Some potential improvements of NMF are also suggested for future study.
暂无评论