• 한국지능시스템학회논문지
• /
• 제21권6호
• /
• pp.730-736
• /
• 2011

본 연구는 순차적인 시계열 자료들에서 가장 최근의 추세가 반영될 수 있는 패턴분류 모델을 설계하였다. 의사결정을 지원하는 데이터마이닝 패턴분류 모델을 설계할 때 통계 기법과 인공지능 기법을 융합한 모델들이 기존의 모델보다 우수함을 입증하였다. 특히 퍼지이론과 융합된 패턴분류 모델들의 적중률이 상대적으로 더 향상되었다. 예를 들어, 통계적 이론을 기반으로 한 SVM모델과 퍼지소속함수와의 결합, 혹은 신경망과 FCM을 결합한 모델들의 성능이 우수하였다. 실험에서 사용한 패턴분류 모델들은 BPN, PNN, FNN, FCM, SVM, FSVM, Decision Tree, Time Series Analysis, Regression Analysis 등이다. 그리고 데이터베이스는 시계열 속성을 지닌 금융시장의 경제지표 DB(한국, KOSPI200 데이터베이스)와 병원 응급실의 부정맥환자에 대한 심전도 DB(미국 MIT-BIH 데이터베이스)들을 사용하였다.

• 물과 미래
• /
• 제23권1호
• /
• pp.99-107
• /
• 1990

수자원 개발계획 및 목공구조물의 합리적 설계를 위해서는 과거의 수문관측자료에 의거한 해석이 필요하며, 일반적인 수문현상은 무작위적인 인자가 포함되기 때문에 이를 고려한 통계적 기법, 즉 추계학적 해석기법이 필요하다고 하겠다. 본 연구에서는 남한강 상류의 동일유역 4개 지점(단양, 정선, 영월, 평창)의 월유량 자료를 일변량 AR(1), AR(2)모형과 다변량 AR(1), AR(2)모형에 적용하여 각 모형의 통계적 특성치를 분석하고, 월유량을 모의발생시켜, 일변량 모형과 다변량 모형을 비교하였다. 각각의 모형에 의한 모의발생 계열의 비교, 분석을 통하여 볼 때, 단일지점만을 고려하는 일변량 모형에 비해 지점간의 공선형성을 고려하는 다변량 모형이 동일유역의 월유량 해석에 있어서 더 적합함을 알 수 있었다.

• Communications for Statistical Applications and Methods
• /
• 제30권4호
• /
• pp.369-388
• /
• 2023

In this paper, we develop the two-step procedure that detects and estimates the position of structural changes for multivariate nonstationary time series, either on mean parameters or second-order structures. We first investigate the presence of mean structural change by monitoring data through the aggregated cumulative sum (CUSUM) type statistic, a sequential procedure identifying the likely position of the change point on its trend. If no mean change point is detected, the proposed method proceeds to scan the second-order structural change by modeling the multivariate nonstationary time series with a multivariate locally stationary Wavelet process, allowing the time-localized auto-correlation and cross-dependence. Under this framework, the estimated dynamic spectral matrices derived from the local wavelet periodogram capture the time-evolving scale-specific auto- and cross-dependence features of data. We then monitor the change point from the lower-dimensional approximated space of the spectral matrices over time by applying the dynamic principal component analysis. Different from existing methods requiring prior information on the type of changes between mean and covariance structures as an input for the implementation, the proposed algorithm provides the output indicating the type of change and the estimated location of its occurrence. The performance of the proposed method is demonstrated in simulations and the analysis of two real finance datasets.

• Journal of the Korean Statistical Society
• /
• 제27권1호
• /
• pp.57-66
• /
• 1998

In the analysis of time series it is an important issue to determine whether a time series under study is stationary. For the test of the stationary of the time series the Dickey-Fuller (DF) type tests have been mainly used. In this paper, we consider the regular unit root tests and seasonal unit root tests based on the generalized Durbin-Watson (DW) statistics when the errors are independent. The limiting distributions of the proposed DW-type test statistics are the functionals of standard Brownian motions. We also obtain the finite distributions and powers of the DW-type test statistics and compare the performances with the DF-type tests. It is observed that the DW-type test statistics have good behaviors against the DF-type test statistics especially in the nonzero (seasonal) mean model.

• 응용통계연구
• /
• 제25권4호
• /
• pp.641-650
• /
• 2012

Spatial time series data can be viewed as a set of time series simultaneously collected at a number of spatial locations. This paper studies Bayesian inferences in a spatial time bilinear model with a Gibbs sampling algorithm to overcome problems in the numerical analysis techniques of a spatial time series model. For illustration, the data set of mumps cases reported from the Korea Center for Disease Control and Prevention monthly over the years 2001~2009 are selected for analysis.

• 한국경영과학회:학술대회논문집
• /
• 한국경영과학회 2007년도 추계학술대회 및 정기총회
• /
• pp.477-481
• /
• 2007

The purpose of this study is to provide the ideal forecasting model of cadastral survey work load through the Economeatric Analysis of Time Series, Granger Causality and VAR Model Analysis, it suggested the forecasting reference materials for the total amount of cadastral survey general work load. The main result is that the derive of the environment variables which affect cadastral survey general work load and the outcome of VAR(vector auto regression) analysis materials(impulse response function and forecast error variance decomposition analysis materials), which explain the change of general work load depending on altering the environment variables. And also, For confirming the stability of time series data, we took a unit root test, ADF(Augmented Dickey-Fuller) analysis and the time series model analysis derives the best cadastral forecasting model regarding on general cadastral survey work load. And also, it showed up the various standards that are applied the statistical method of econometric analysis so it enhanced the prior aggregate system of cadastral survey work load forecasting.

• Communications for Statistical Applications and Methods
• /
• 제7권2호
• /
• pp.513-523
• /
• 2000

The X-12-ARIMA program was utilized on the analysis of the time series trend on 76 Korean industrial activities data in order to ensure that the trading day effect adjustment as well as the seasonal effect adjustment is needed to extract the fundamental trend-cycle factors from various economic time series data. The trading day effect is strongly correlated with the activity of production and shipping but not with the activity of inventory. Furthermore, the industrial activities were classified with respect to the sensitivity on the tranding day effect.

• Journal of applied mathematics & informatics
• /
• 제26권5_6호
• /
• pp.933-943
• /
• 2008

Spectral analysis of a strictly stationary r-vector valued time series is considered under the assumption that some of the observations are missed due to some random failure. Statistical properties and asymptotic moments are derived. Asymptotic normality is discussed.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2010년도 학술발표회
• /
• pp.581-585
• /
• 2010

This study introduced a Bayesian based frequency analysis in which the statistical trend seasonal analysis for hydrologic extreme series is incorporated. The proposed model employed Gumbel and GEV extreme distribution to characterize extreme events and a fully coupled bayesian frequency model was finally utilized to estimate design rainfalls in Seoul. Posterior distributions of the model parameters in both trend and seasonal analysis were updated through Markov Chain Monte Carlo Simulation mainly utilizing Gibbs sampler. This study proposed a way to make use of nonstationary frequency model for dynamic risk analysis, and showed an increase of hydrologic risk with time varying probability density functions. In addition, full annual cycle of the design rainfall through seasonal model could be applied to annual control such as dam operation, flood control, irrigation water management, and so on. The proposed study showed advantage in assessing statistical significance of parameters associated with trend analysis through statistical inference utilizing derived posterior distributions.

• Communications for Statistical Applications and Methods
• /
• 제19권6호
• /
• pp.885-898
• /
• 2012

In this paper, we consider Bayesian approaches to partially linear models, in which a regression function is represented by a semiparametric additive form of a parametric linear regression function and a nonparametric regression function. We make a comparative study on the performance of widely used Bayesian partially linear models in terms of empirical analysis. Specifically, we deal with three Bayesian methods to estimate the nonparametric regression function, one method using Fourier series representation, the other method based on Gaussian process regression approach, and the third method based on the smoothness of the function and differencing. We compare the numerical performance of three methods by the root mean squared error(RMSE). For empirical analysis, we consider synthetic data with simulation studies and real data application by fitting each of them with three Bayesian methods and comparing the RMSEs.