• The Korean Journal of Applied Statistics
• /
• v.28 no.5
• /
• pp.871-883
• /
• 2015

Vector autoregressive (VAR) models in high dimension suffer from noisy estimates, unstable predictions and hard interpretation. Consequently, the sparse vector autoregressive (sVAR) model, which forces many small coefficients in VAR to exactly zero, has been suggested and proven effective for the modeling of high dimensional time series data. This paper studies coupling measures to select non-zero coefficients in sVAR. The basic idea based on the simulation study reveals that removing the effect of other variables greatly improves the performance of coupling measures. sVAR model coefficients are asymmetric; therefore, asymmetric coupling measures such as Granger causality improve computational costs. We propose two asymmetric coupling measures, filtered-cross-correlation and filtered-Granger-causality, based on the filtered residuals series. Our proposed coupling measures are proven adequate for heavy-tailed and high order sVAR models in the simulation study.

• Korean Journal of Child Studies
• /
• v.35 no.5
• /
• pp.135-154
• /
• 2014

This study examined the causal relationships between parenting stress and self-efficacy of Korean mothers with an infant according to employment status using the second through fourth wave data of the Panel Study of Korean Children (PSKC). Autoregressive cross-lagged modeling was performed to test the longitudinal reciprocal relationships between the two constructs. Our results indicated that both maternal parenting stress and self-efficacy were consistent over time. The results also indicated that there was a significant cross-lagged effect of maternal parenting stress on their self-efficacy, rather than vice versa. No differences between working and non-working mothers were found in the relationship between the two constructs.

• Journal of Information Processing Systems
• /
• v.15 no.5
• /
• pp.1201-1210
• /
• 2019

Stock price is characterized as being mutable, non-linear and stochastic. These key characteristics are known to have a direct influence on the stock markets globally. Given that the stock price data often contain both linear and non-linear patterns, no single model can be adequate in modelling and predicting time series data. The autoregressive integrated moving average (ARIMA) model cannot deal with non-linear relationships, however, it provides an accurate and effective way to process autocorrelation and non-stationary data in time series forecasting. On the other hand, the neural network provides an effective prediction of non-linear sequences. As a result, in this study, we used a hybrid ARIMA and neural network model to forecast the monthly closing price of the Shanghai composite index and Shenzhen component index.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 2006.05a
• /
• pp.1221-1226
• /
• 2006

The use of Artificial Neural Networks (ANN) has received increasing attention in the analysis and prediction of financial time series. Stationarity of the observed financial time series is the basic underlying assumption in the practical application of ANN on financial time series. In this paper, we will investigate whether it is feasible to relax the stationarity condition to non-stationary time series. Our result discusses the range of complexities caused by non-stationary behavior and finds that overfitting by ANN could be useful in the analysis of such non-stationary complex financial time series.

• The Journal of the Convergence on Culture Technology
• /
• v.7 no.1
• /
• pp.640-645
• /
• 2021

The deep learning based end-to-end TTS system consists of Text2Mel module that generates spectrogram from text, and vocoder module that synthesizes speech signals from spectrogram. Recently, by applying deep learning technology to the TTS system the intelligibility and naturalness of the synthesized speech is as improved as human vocalization. However, it has the disadvantage that the inference speed for synthesizing speech is very slow compared to the conventional method. The inference speed can be improved by applying the non-autoregressive method which can generate speech samples in parallel independent of previously generated samples. In this paper, we introduce FastSpeech, FastSpeech 2, and FastPitch as Text2Mel technology, and Parallel WaveGAN, Multi-band MelGAN, and WaveGlow as vocoder technology applying non-autoregressive method. And we implement them to verify whether it can be processed in real time. Experimental results show that by the obtained RTF all the presented methods are sufficiently capable of real-time processing. And it can be seen that the size of the learned model is about tens to hundreds of megabytes except WaveGlow, and it can be applied to the embedded environment where the memory is limited.

• Journal of the Korean Statistical Society
• /
• v.24 no.1
• /
• pp.149-160
• /
• 1995

We consider the problem of optimal adaptive estiamtion of the euclidean parameter vector $\theta$ of the univariate non-linerar autogressive time series model ${X_t}$ which is defined by the following system of stochastic difference equations ; $X_t = \sum^p_{i=1} \theta_i \cdot T_i(X_{t-1})+e_t, t=1, \cdots, n$, where $\theta$ is the unknown parameter vector which descrives the deterministic dynamics of the stochastic process ${X_t}$ and ${e_t}$ is the sequence of white noises with unknown density $f(\cdot)$. Under some general growth conditions on $T_i(\cdot)$ which guarantee ergodicity of the process, we construct a sequence of adaptive estimatros which is locally asymptotic minimax (LAM) efficient and also attains the least possible covariance matrix among all regular estimators for arbitrary symmetric density.

• Journal of Welding and Joining
• /
• v.17 no.6
• /
• pp.100-107
• /
• 1999

In this paper, we deal with the speckle noise reduction and parameter estimation of ultrasonic NDT(non-destructive test) signals obtained during weld inspection of piping. The overall approach consists of three major steps, namely, speckle noise analysis, proposition of wavelet domain AR(autoregressive) model and flaw detection by proposed model parameter. The data are first processed whereby signals obtained using vertical and angle beam transducer. Correlation properties of speckle noise are then analyzed using multiresolution analysis in wavelet domain. The parameter estimation curve obtained using the proposed model is classified a flaw in weld region where is contaminated by severe speckle noise and also clear flaw signal is obtained through CA-CFAR threshold estimator that is a nonlinear post-processing method for removing the noise from reconstructed ultrasonic signal.

• Journal of Information Technology Applications and Management
• /
• v.29 no.4
• /
• pp.17-33
• /
• 2022

This study measures the internal and external competitiveness of 35 OECD countries in the insurance industry. We analyze whether variables related to the Fourth Industrial Revolution affect international competitiveness by applying a nonlinear autoregressive distributed lag model. As a result, the competitiveness of life insurance foreign companies in internal is showing positive responses in high income inequality countries. In addition, insurance companies in countries with low income inequality have shown high performance in external. The non-life insurance industry is less sensitive to shocks than life insurance. This is because non-life insurance is a more dangerous industry than life insurance and there are many restrictions on policies and regulations. The reason is that non-life insurance is a more dangerous industry than life insurance and there are many restrictions on policies and regulations.

• Journal of the Korean Statistical Society
• /
• v.36 no.2
• /
• pp.257-274
• /
• 2007

This paper considers the tests for the presence of smooth transition non-linearity in the partially nonstationary vector autoregressive model. The transition parameters cannot be identified under the null hypothesis of linearity, and therefore this paper develops the tests for smooth transition nonlinearity, the associated asymptotic theory and the bootstrap inference. The Monte Carlo simulation evidence shows that the bootstrap inference generates moderate size and power performances.

• Proceedings of the Korean Statistical Society Conference
• /
• 2002.11a
• /
• pp.3-9
• /
• 2002

In financial time series, the autoregressive conditional heteroscedastic (ARCH) models have been widely used for modeling conditional variances. In many cases, non-normality or heavy-tailed distributions of the data have influenced the estimation methods under normality assumption. To solve this problem, a robust function for the conditional variances of the errors is proposed and compared the relative efficiencies of the estimators with other conventional models.