• Asia-Pacific Journal of Atmospheric Sciences
• /
• v.54 no.4
• /
• pp.611-622
• /
• 2018

Observed climate data are processed under the assumption that their time series are stationary, as in multi-step temperature and precipitation prediction, which usually leads to low prediction accuracy. If a climate system model is based on a single prediction model, the prediction results contain significant uncertainty. In order to overcome this drawback, this study uses a method that integrates ensemble prediction and a stepwise regression model based on a mean-valued generation function. In addition, it utilizes empirical mode decomposition (EMD), which is a new method of handling time series. First, a non-stationary time series is decomposed into a series of intrinsic mode functions (IMFs), which are stationary and multi-scale. Then, a different prediction model is constructed for each component of the IMF using numerical ensemble prediction combined with stepwise regression analysis. Finally, the results are fit to a linear regression model, and a short-term climate prediction system is established using the Visual Studio development platform. The model is validated using temperature data from February 1957 to 2005 from 88 weather stations in Guangxi, China. The results show that compared to single-model prediction methods, the EMD and ensemble prediction model is more effective for forecasting climate change and abrupt climate shifts when using historical data for multi-step prediction.

• Korean Management Science Review
• /
• v.10 no.2
• /
• pp.27-42
• /
• 1993

Markov chain models can be used to predict the state of the system in the future. We extend the existing Markov chain models in two ways. For the stationary model, we propose a procedure that obtains the transition probabilities by appling the empirical Bayes method, in which the parameters of the prior distribution in the Bayes estimator are obtained on the collaternal micro data. For non-stationary model, we suggest a procedure that obtains a time-varying transition probabilities as a function of the exogenous variables. To illustrate the effectiveness of our extended models, the models are applied to the macro and micro time-series data generated from actual survey. Our stationary model yields reliable parameter values of the prior distribution. And our non-stationary model can predict the variable transition probabilities effectively.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2018.10a
• /
• pp.398-402
• /
• 2018

비정상(non-stationary) 장기 시계열 안에서도, 단기적으로 추세의 변화가 일시적인 것인지, 아니면 구조적으로 변한 것인지를 적시에 판단하는 것은 중요하다. 이는 시계열 추세의 변화를 상시 감지하여, 변화에 맞는 적정한 수준의 대응을 할 필요가 있기 때문이다. 본 연구에서는 장기 시계열이 주어진 상황에서, 단위근 검정법을 기반으로 단기적으로 구조변화를 감지하여, 이러한 변화가 얼마나 지속될 것인지를 시각적으로 판단할 수 있는 방법을 제시하고자 한다.

• Communications for Statistical Applications and Methods
• /
• v.29 no.2
• /
• pp.225-238
• /
• 2022

In this paper, we propose a clustering method for advanced metering infrastructure (AMI) data in Korea. As AMI data presents non-stationarity, we consider time-dependent frequency domain principal components analysis, which is a proper method for locally stationary time series data. We develop a new clustering method based on time-varying eigenvectors, and our method provides a meaningful result that is different from the clustering results obtained by employing conventional methods, such as K-means and K-centres functional clustering. Simulation study demonstrates the superiority of the proposed approach. We further apply the clustering results to the evaluation of the electricity price system in South Korea, and validate the reform of the progressive electricity tariff system.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.58 no.1
• /
• pp.173-180
• /
• 2009

It is difficult to predict non-stationary or chaotic time series which includes the drift and/or the non-linearity as well as uncertainty. To solve it, we propose an effective prediction method which adopts data preprocessing and multiple model TS fuzzy predictors combined with model selection mechanism. In data preprocessing procedure, the candidates of the optimal difference interval are determined based on the correlation analysis, and corresponding difference data sets are generated in order to use them as predictor input instead of the original ones because the difference data can stabilize the statistical characteristics of those time series and better reveals their implicit properties. Then, TS fuzzy predictors are constructed for multiple model bank, where k-means clustering algorithm is used for fuzzy partition of input space, and the least squares method is applied to parameter identification of fuzzy rules. Among the predictors in the model bank, the one which best minimizes the performance index is selected, and it is used for prediction thereafter. Finally, the error compensation procedure based on correlation analysis is added to improve the prediction accuracy. Some computer simulations are performed to verify the effectiveness of the proposed method.

• The Korean Journal of Applied Statistics
• /
• v.1 no.1
• /
• pp.57-67
• /
• 1987

In time series analysis, we usually require the assumption that time series are stationary. But we may often encounter time series whose parameter values subject to change. Inthis paper w propose a method which can detect the variance change point in anAR(1) model which is subjct to changesat non-predictable time points. Proposed method is compared with other methods using the simulated and real data.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.37 no.2
• /
• pp.27-34
• /
• 2014

In this paper, we investigate the statistical correlation of the time series for temperature measured at the heat box in the automobile drying process. We show, in terms of the sample variance, that a significant non-linear correlation exists in the time series that consist of absolute temperature changes. To investigate further the non-linear correlation, we utilize the volatility, an important concept in the financial market, and induce volatility time series from absolute temperature changes. We analyze the time series of volatilities in terms of the de-trended fluctuation analysis (DFA), a method especially suitable for testing the long-range correlation of non-stationary data, from the correlation perspective. We uncover that the volatility exhibits a long-range correlation regardless of the window size. We also analyze the cross correlation between two (inlet and outlet) volatility time series to characterize any correlation between the two, and disclose the dependence of the correlation strength on the time lag. These results can contribute as important factors to the modeling of forecasting and management of the heat box's temperature.

• 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 Statistical Society Conference
• /
• 2002.11a
• /
• pp.265-272
• /
• 2002

An Integer-valued autoregressive integrated (INARI) model is introduced to eliminate stochastic trend and seasonality from time series of count data. This INARI extends the previous integer-valued ARMA model. We show that it is stationary and ergodic to establish asymptotic normality for conditional least squares estimator. Optimal estimating equations are used to reflect categorical and serial correlations arising from panel count data and variations arising from three random processes for obtaining observation into estimation. Under regularity conditions for martingale sequence, we show asymptotic normality for estimators from the estimating equations. Using cancer mortality data provided by the U.S. National Center for Health Statistics (NCHS), we apply our results to estimate the probability of cells classified by 4 causes of death and 6 age groups and to forecast death count of each cell. We also investigate impact of three random processes on estimation.

• Publications of The Korean Astronomical Society
• /
• v.30 no.2
• /
• pp.605-607
• /
• 2015

The development of time-frequency analysis techniques allow astronomers to successfully deal with the non-stationary time series that originate from unstable physical mechanisms. We applied a recently developed time-frequency analysis method, the Hilbert-Huang transform (HHT), to two non-stationary phenomena: the superorbital modulation in the high-mass X-ray binary SMC X-1 and the quasi-periodic oscillation (QPO) of the AGN RE J1034+396. From the analysis of SMC X-1, we obtained a Hilbert spectrum that shows more detailed information in both the time and frequency domains. Then, a phase-resolved analysis of both the spectra and the orbital profiles was presented. From the spectral analysis, we noticed that the iron line production is dominated by different regions of this binary system in different superorbital phases. Furthermore, a pre-eclipse dip lying at orbital phase ~0:6-0:85 was discovered during the superorbital transition state. We further applied the HHT to analyze the QPO of RE J1034+396. From the Hilbert spectrum and the O-C analysis results, we suggest that it is better to divide the evolution of the QPO into three epochs according to their different periodicities. The correlations between the QPO periods and corresponding fluxes were also different in these three epochs. The change in periodicity and the relationships could be interpreted as the change in oscillation mode based on the diskoseismology model.