• 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.

• The Korean Journal of Applied Statistics
• /
• 제27권6호
• /
• pp.923-932
• /
• 2014

The Hurdle model can to analyze zero-inflated count data. This model is a mixed model of the logit model for a binary component and a truncated Poisson model of a truncated count component. We propose a new hurdle model with a general heterogeneous random effects covariance matrix to analyze longitudinal zero-inflated count data using modified Cholesky decomposition. This decomposition factors the random effects covariance matrix into generalized autoregressive parameters and innovation variance. The parameters are modeled using (generalized) linear models and estimated with a Bayesian method. We use these methods to carefully analyze a real dataset.

• The Journal of the Korea Contents Association
• /
• 제12권9호
• /
• pp.357-368
• /
• 2012

The purpose of this study is to empirically examine the impact of enterprise R&D investment on international trade in Korea under the new Normal Era. In order to test whether the time series data of trade variables are stationary or not, we put in operation unit root test and cointegration test. Based on VECM (Vector Error Correction Model), we also apply impulse response functions and variance decomposition to estimate the dynamic effects in the short-run and long-run. The results show that the relationship between enterprise R&D investment and international trade (export and import) exists in the long-run as well as in the short-run. The results of applying impulse response functions and variance decomposition also indicate that the impact of enterprise R&D investment on international trade is positive, and a significant portion of fluctuations in the trade variable is explained by enterprise R&D investment. Therefore, enterprise R&D investment must be continuously increased to improve economic growth with promoting trading competition power in Korea under the new Normal Era.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 한국퍼지및지능시스템학회 2000년도 추계학술대회 학술발표 논문집
• /
• pp.305-309
• /
• 2000

In this paper, we presents a new methodology for face recognition after analysing conventional ICA(Independent Component Analysis) based approach. In the literature we found that ICA based methods have followed the same procedure without any exception, first PCA(Principal Component Analysis) has been used for feature extraction, next ICA learning method has been applied for feature enhancement in the reduced dimension. However, it is contradiction that features are extracted using higher order moments depend on variance, the second order statistics. It is not considered that a necessary component can be located in the discarded feature space. In the new methodology, features are extracted using the magnitude of kurtosis(4-th order central moment or cumulant). This corresponds to the PCA based feature extraction using eigenvalue(2nd order central moment or variance). The synergy effect of PCA and ICA can be achieved if PCA is used for noise reduction filter. ICA methodology is analysed using SVD(Singular Value Decomposition). PCA does whitening and noise reduction. ICA performs the feature extraction. Simulation results show the effectiveness of the methodology compared to the conventional ICA approach.

• Journal of Fisheries and Marine Sciences Education
• /
• 제28권1호
• /
• pp.127-136
• /
• 2016

The purpose of this research is to conduct a comparative study on the characteristics of daily volatility spillovers across the stock markets of Korea, China, and Japan. We employ generalized spillover definition and measurement developed by Diebold & Yilmaz (2009, 2012). The sample period is January 5, 1993 to September 25, 2015. From a static full-sample analysis, we find that 8.60% of forecast error variance comes from volatility spillovers. From a 250-day rolling-sample analysis, we discover that there exist significant volatility fluctuations in the stock markets of Korea, China and Japan, expecially during the Asian Financial Crisis (1998-1999) and the US Credit Crisis (2008-2009) after the collapse of Lehman Brothers. From the net directional spillovers across three countries, we come upon that there is neither a definite leader nor a significant follower during the sample period.

• Journal of Korea Multimedia Society
• /
• 제21권7호
• /
• pp.737-744
• /
• 2018

This paper presents a study on the performance of the higher-order moments for speech/music classification. For a successful speech/music classifier, extracting features that allow direct access to the relevant speech or music specific information is crucial. In addition to the conventional variance-based features, we utilize the higher-order moments of features, such as skewness and kurtosis. Moreover, we investigate the subband decomposition parameters in extracting features, which improves classification accuracy. Experiments on two speech/music datasets, which are publicly available, were performed and show that the higher-order moment features can improve classification accuracy when combined with the conventional variance-based features.

• Korea Trade Review
• /
• 제46권5호
• /
• pp.115-130
• /
• 2021

The main purpose of this study is to analyze the causal relationship between import-export goods and transportation modes. To this end, five major commodity groups were selected from 2010 to 2018 such as Machinery and transport equipment (SITC 7), manufactured goods classified chiefly by material (SITC 6), chemicals and related products, n.e.s. (SITC 5), mineral, fuels, lubricants, and related materials (SITC 3), and miscellaneous manufactured articles (SITC 8). And using the panel VECM, the difference between transportation modes such as ports and airports was compared and analyzed through panel granger causality, Impulse response function, Forecasting error variance decomposition. As a result, it is confirmed that the causal relationship between major product groups and transportation modes showed different causal relationships depending on the characteristics of port and air transportation.

• Proceedings of the IEEK Conference
• /
• 대한전자공학회 2001년도 하계종합학술대회 논문집(4)
• /
• pp.187-190
• /
• 2001

In this paper, we present a novel digital watermarking technique based on the concept of multiresolution decomposition and Human Visual System(HVS). Proposed watermarking is to embed watermark by quantization, that is to construct ‘perceptually lossless’quantization matrix, by using a quantization factor for each level and orientation and variance within a band. We compare our approach with another wavelet domain watermarking methods. Simulation results show the superior performance of robustness for variety image distortions.

• Communications for Statistical Applications and Methods
• /
• 제12권3호
• /
• pp.653-657
• /
• 2005

Eigenstructure of a spatial design matrix of Matheron's variogram estimator in $R^1$ is derived. It is shown that the spatial design matrix in $R^1$ with n/2$\le$h < n has a nice spectral decomposition. The mean, variance, and covariance of this estimator are obtained using the eigenvalues of a spatial design matrix. We also found that the lower bound and the upper bound of the normalized Matheron's variogram estimator.

• Journal of Broadcast Engineering
• /
• 제23권4호
• /
• pp.519-525
• /
• 2018

This paper deals with noise suppression of multi-channel data captured by microphone array using multi-channel Wiener filter. Multi-channel Wiener filter does not rely on information about the direction of the target speech and can be partitioned into an MVDR (Minimum Variance Distortionless Response) spatial filter and a single channel spectral filter. The acoustic transfer function between the single speech source and microphones can be estimated by subspace decomposition of multi-channel Wiener filter. The errors are incurred in the estimation of the acoustic transfer function due to the errors in the estimation of correlation matrices, which in turn results in speech distortion in the MVDR filter. To alleviate the speech distortion in the MVDR filter, diagonal loading is applied. In the experiments, database with seven microphones was used and MFCC distance was measured to demonstrate the effectiveness of the diagonal loading.