Regularized NNLS Algorithms for Nonnegative Matrix Factorization with Application to Text Document Clustering

Zdunek, Rafał

doi:10.1007/978-3-642-20320-6_77

Cited by 4 publications

(2 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the ordinary cone representations (20) and 21of the MCD model, improper uniform (non-informative) prior distributions are actually implied for parameters β and α, with β ≥ 0 and α ≥ 0. However, in the proposed regularised MSCD-l 2 and MSCD-l 1 , multivariate folded distributions are in fact utilised as the priors for the estimation of β in (22) and (24) and α in (23) and (25), as we shall show below.…”

Section: B Regularised Cone-based Estimators Of Coefficient Vectorsmentioning

confidence: 99%

“…We compare the proposed methods MSCD-l 2 and MSCD-l 1 with four types of target detectors: 1) the classical baseline methods ACE and CEM, which are not affected by the dualwindow scheme; 2) the cone representation-based detector MCD in (20) and 21; 3) the subspace detectors OSP [6] and MSD [7]; and 4) the sparse representation-based detectors STD [10] and SRBBH [11]. For the proposed MSCD-l 2 and MSCD-l 1 , we adopt the MATLAB codes provided by [23] and on http://www.yelab.net/software/SLEP/ to solve the l 2 -norm regularised cone model (18) and the l 1 -norm regularised cone model (19), respectively.…”

Section: E Xperimentsmentioning

confidence: 99%

See 1 more Smart Citation

Matched Shrunken Cone Detector (MSCD): Bayesian Derivations and Case Studies for Hyperspectral Target Detection

Wang

Zhu

Fukui

et al. 2017

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

Hyperspectral images (HSIs) possess non-negative properties for both hyperspectral signatures and abundance coefficients, which can be naturally modeled using cone-based representation. However, in hyperspectral target detection, cone-based methods are barely studied. In this paper, we propose a new regularized cone-based representation approach to hyperspectral target detection, as well as its two working models by incorporating into the cone representation l-norm and l-norm regularizations, respectively. We call the new approach the matched shrunken cone detector (MSCD). Also important, we provide principled derivations of the proposed MSCD from the Bayesian perspective: we show that MSCD can be derived by assuming a multivariate half-Gaussian distribution or a multivariate half-Laplace distribution as the prior distribution of the coefficients of the models. In the experimental studies, we compare the proposed MSCD with the subspace methods and the sparse representation-based methods for HSI target detection. Two real hyperspectral data sets are used for evaluating the detection performances on sub-pixel targets and full-pixel targets, respectively. Results show that the proposed MSCD can outperform other methods in both cases, demonstrating the competitiveness of the regularized cone-based representation.

show abstract