• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권6호
• /
• pp.2634-2648
• /
• 2020

In this paper, an adaptive sparse singular value decomposition (ASSVD) algorithm is proposed to estimate the signal matrix when only one data matrix is observed and there is high dimensional white noise, in which we assume that the signal matrix is low-rank and has sparse singular vectors, i.e. it is a simultaneously low-rank and sparse matrix. It is a structured matrix since the non-zero entries are confined on some small blocks. The proposed algorithm estimates the singular values and vectors separable by exploring the structure of singular vectors, in which the recent developments in Random Matrix Theory known as anisotropic Marchenko-Pastur law are used. And then we prove that when the signal is strong in the sense that the signal to noise ratio is above some threshold, our estimator is consistent and outperforms over many state-of-the-art algorithms. Moreover, our estimator is adaptive to the data set and does not require the variance of the noise to be known or estimated. Numerical simulations indicate that ASSVD still works well when the signal matrix is not very sparse.

• ETRI Journal
• /
• 제36권1호
• /
• pp.167-170
• /
• 2014

In this letter, we propose an unsupervised framework for speech noise reduction based on the recent development of low-rank and sparse matrix decomposition. The proposed framework directly separates the speech signal from noisy speech by decomposing the noisy speech spectrogram into three submatrices: the noise structure matrix, the clean speech structure matrix, and the residual noise matrix. Evaluations on the Noisex-92 dataset show that the proposed method achieves a signal-to-distortion ratio approximately 2.48 dB and 3.23 dB higher than that of the robust principal component analysis method and the non-negative matrix factorization method, respectively, when the input SNR is -5 dB.

• ETRI Journal
• /
• 제39권1호
• /
• pp.21-29
• /
• 2017

This paper addresses the problem of unsupervised speech separation based on robust non-negative matrix factorization (RNMF) with ${\beta}$-divergence, when neither speech nor noise training data is available beforehand. We propose a robust version of non-negative matrix factorization, inspired by the recently developed sparse and low-rank decomposition, in which the data matrix is decomposed into the sum of a low-rank matrix and a sparse matrix. Efficient multiplicative update rules to minimize the ${\beta}$-divergence-based cost function are derived. A convolutional extension of the proposed algorithm is also proposed, which considers the time dependency of the non-negative noise bases. Experimental speech separation results show that the proposed convolutional RNMF successfully separates the repeating time-varying spectral structures from the magnitude spectrum of the mixture, and does so without any prior training.

• 방송공학회논문지
• /
• 제16권5호
• /
• pp.782-792
• /
• 2011

In this paper, we address a new fast DCT-II/DFT/HWT hybrid transform architecture for digital video and fusion mobile handsets based on Jacket-like sparse matrix decomposition. This fast hybrid architecture is consist of source coding standard as MPEG-4, JPEG 2000 and digital filtering discrete Fourier transform, and has two operations: one is block-wise inverse Jacket matrix (BIJM) for DCT-II, and the other is element-wise inverse Jacket matrix (EIJM) for DFT/HWT. They have similar recursive computational fashion, which mean all of them can be decomposed to Kronecker products of an identity Hadamard matrix and a successively lower order sparse matrix. Based on this trait, we can develop a single chip of fast hybrid algorithm architecture for intelligent mobile handsets.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권12호
• /
• pp.6043-6062
• /
• 2019

Low-rank matrix decomposition has shown its capability in many applications such as image in-painting, de-noising, background reconstruction and defect detection etc. In this paper, we consider the texture background of rail track images and the sparse foreground of the defects to construct a low-rank matrix decomposition model with block sparsity for defect inspection of rail tracks, which jointly minimizes the nuclear norm and the 2-1 norm. Similar to ADM, an alternative method is proposed in this study to solve the optimization problem. After image decomposition, the defect areas in the resulting low-rank image will form dark stripes that horizontally cross the entire image, indicating the preciselocations of the defects. Finally, a two-stage defect extraction method is proposed to locate the defect areas. The experimental results of the two datasets show that our algorithm achieved better performance compared with other methods.

• 대한수학회논문집
• /
• 제11권4호
• /
• pp.1175-1185
• /
• 1996

We study the computation of sparse null bases of equilibrium matrices in the context of structural optimization and incompressible fluid flow. In our approach we emphasize the parallel computatin and examine the applications. New block decomposition and node ordering schemes are suggested, and numerical examples are considered.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제18권5호
• /
• pp.1163-1185
• /
• 2024

With the sharp increase in the volume of literature data, researchers must spend considerable time and energy locating desired papers. A paper recommendation is the means necessary to solve this problem. Unfortunately, the large amount of data combined with sparsity makes personalizing papers challenging. Traditional matrix decomposition models have cold-start issues. Most overlook the importance of information and fail to consider the introduction of noise when using side information, resulting in unsatisfactory recommendations. This study proposes a paper recommendation method (PR-SLSMF) using document-level representation learning with citation-informed transformers (SPECTER) and low-rank and sparse matrix factorization; it uses SPECTER to learn paper content representation. The model calculates the similarity between papers and constructs a weighted heterogeneous information network (HIN), including citation and content similarity information. This method combines the LSMF method with HIN, effectively alleviating data sparsity and cold-start issues and avoiding topic drift. We validated the effectiveness of this method on two real datasets and the necessity of adding side information.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권1호
• /
• pp.53-76
• /
• 2020

The synchronous phasor measurement algorithm is the core content of the phasor measurement unit. This manuscript proposes a dynamic synchronous phasor measurement algorithm based on compressed sensing theory. First, a dynamic signal model based on the Taylor series was established. The dynamic power signal was preprocessed using a least mean square error adaptive filter to eliminate interference from noise and harmonic components. A Chirplet overcomplete dictionary was then designed to realize a sparse representation. A reduction of the signal dimension was next achieved using a Gaussian observation matrix. Finally, the improved orthogonal matching pursuit algorithm was used to realize the sparse decomposition of the signal to be detected, the amplitude and phase of the original power signal were estimated according to the best matching atomic parameters, and the total vector error index was used for an error evaluation. Chroma 61511 was used for the output of various signals, the simulation results of which show that the proposed algorithm cannot only effectively filter out interference signals, it also achieves a better dynamic response performance and stability compared with a traditional DFT algorithm and the improved DFT synchronous phasor measurement algorithm, and the phasor measurement accuracy of the signal is greatly improved. In practical applications, the hardware costs of the system can be further reduced.

• 전자공학회논문지
• /
• 제51권9호
• /
• pp.21-29
• /
• 2014

오늘날 수많은 사용자와 제한된 메모리 공간 때문에 빅 데이터(big data)를 위한 메모리 공간 문제가 중요한 이슈로 부상하고 있다. 대규모 MIMO 시스템에서 Toeplitz 채널은 전력효율 문제뿐아니라 성능 개선에 커다란 역할을 할 수 있다. 본 논문에서는 행렬 벡터화(vectorization)에 기반한 Toeplitz 채널 분해를 제안하고, 이때 대규모 MIMO 시스템을 위한 채널에 Toeplitz 행렬을 사용하며, 또 Toeplitz Jackrt행렬이 푸리에 고속 변환(FFT)처럼 Cooley-Tukey sparse 행렬로 분해됨을 보인다.

• 한국전자파학회논문지
• /
• 제11권3호
• /
• pp.337-344
• /
• 2000

파수영역에서 모멘트법의 엄피던스 행렬의 특정을 관찰하고 이를 웨이블릿 변환을 이용하여 효율적으로 표현 하는 방법을 연구하였다. 영상 선호처리 분야에서 자주 사용되는 이차원 쿼드트리(2-D Quadtree)방법(행렬의 $\phi$ 부분에만 웨이블릿 변환을 적용하는 방법)을 적용하여 모멘트 행렬을 성기게 만들었다. 웨이블릿이 적용된 모멘트 행렬을 CG( Conjugate-Gradient)법을 이용하여 모멘트 법의 계산량과 메모리를 줄였다. 수치적 결과는 정사 각형 실린더의 경우 임피던스 행렬의 0이 아닌 값이 O($N^{1.6}$)으로 증가하는 것을 관찰하였다.