• The KIPS Transactions:PartC
• /
• v.14C no.3 s.113
• /
• pp.305-312
• /
• 2007

In this paper, we present a received signal strength (RSS) prediction model to timely Initiate link layer triggers for fast handoff in a wireless LAN system. Noting that the distance between a mobile terminal and an access point is not changed abruptly in a short time interval, an adaptive RSS predictor based on a stationary time series model is proposed. RSS data obtained from ns-2 simulations are used to identity the time series model and verify the predictability of the RSS data. The results suggest that an autoregressive process of order 1 (AR(1)) can be used to represent the measured RSSs in a short time interval and predict at least 1-step ahead RSS with a high confidence level.

• Bulletin of the Korean Mathematical Society
• /
• v.38 no.3
• /
• pp.495-504
• /
• 2001

In this paper we consider the (generalized) autoregressive model with conditional heteroscedasticity (ARCH/GARCH models). We willing give conditions under which strict stationarity, ergodicity and the functional central limit theorem hold for the corresponding models.

• Communications of the Korean Mathematical Society
• /
• v.17 no.2
• /
• pp.309-319
• /
• 2002

We consider the nonlinear autoregressive model with nonlinear ARCH errors, and find sufficient conditions for the existence of a strictly stationary process. New results are obtained, and known results are shown to emerge as special oases.

• Journal of the Korean Statistical Society
• /
• v.26 no.3
• /
• pp.397-405
• /
• 1997

Recently maximum likelihood estimators using unconditional likelihood function are used for testing unit roots. When one wants to use this method the determinant term of initial values in the multivariate unconditional likelihood function produces a complicated function of the elements in the coefficient matrix and variance matrix. In this paper an approximation of the determinant term is calculated and based on this aproximation an approximated unconditional likelihood function is calculated. The approximated unconditional maximum likelihood estimators can be used to test for unit roots. When multivariate process has one unit root the limiting distribution obtained by this method and the limiting distribution using exact unconditional likelihood function are the same.

• Journal of the Korean Data and Information Science Society
• /
• v.15 no.4
• /
• pp.783-791
• /
• 2004

In this paper we review recent developments in nonlinear time series modeling on both conditional mean and conditional variance. Traditional linear model in conditional mean is referred to as ARMA(autoregressive moving average) process investigated by Box and Jenkins(1976). Nonlinear mean models such as threshold, exponential and random coefficient models are reviewed and their characteristics are explained. In terms of conditional variances, ARCH(autoregressive conditional heteroscedasticity) class is considered as typical linear models. As nonlinear variants of ARCH, diverse nonlinear models appearing in recent literature including threshold ARCH, beta-ARCH and Box-Cox ARCH models are remarked. Also, a class of unified nonlinear models are considered and parameter estimation for that class is briefly discussed.

• Magazine of the Korean Society of Agricultural Engineers
• /
• v.34 no.1
• /
• pp.100-106
• /
• 1992

The objective of this study is to develop a real-time runoff forecasting model considering stochastic component. The model is composed of deterministic and stochastic components. Simplified tank model was selected as a deterministic runoff forecasting model. The time series of estimation residual resulting from the tank model simulation was analyzed and was best suited to the second-order autoregressive model. ARTANK model which combined the tank model with the autoregressive process was developed. And it was applied to a BANWEOL basin for validation. The simulation results showed a good agreement with the observed field data.

• Wind and Structures
• /
• v.7 no.5
• /
• pp.333-344
• /
• 2004

This paper illustrates application of the proper orthogonal decomposition (POD) and the autoregressive (AR) model to simulate large wind pressures due to gusts on a low-rise building. In the POD analysis, the covariance of the ensemble of large wind pressures is employed to calculate the principal modes and coordinates. The POD principal coordinates are modeled using the AR process, and the fitted AR models are employed to generate the principal coordinates. The generated principal coordinates are then used to simulate large wind pressures. The results show that the structure characterizing large wind pressures is well represented by the dominant eigenmodes (up to the first fifteen eigenmodes). Also, wind pressures with large peak values are simulated very well using the dominant eigenmodes along with the principal coordinates generated by the AR models.

• Proceedings of the Korean Society for Quality Management Conference
• /
• 1998.11a
• /
• pp.174-179
• /
• 1998

This research explores the application of the bootstrap methods to the construction of control limits for the x charts and the EWMA charts based on single observations with stationary autoregressive processes. The subsample means-based control chars in the presence autocorrelation are also considered. We use a technique for inferring confidence intervals using bootstrap, the percentile method. Simulation studies are conducted to compare the performance of the bootstrap method and that of standard method for constructing control charts under several conditions.

• Journal of the Korean Statistical Society
• /
• v.26 no.1
• /
• pp.47-56
• /
• 1997

The asymptotic distribution of the extended Yule-Walker estimates of a mixed ARMA process is derived. Also, a recursive algorithm is derived to calculate the extended Yule-Walker estimates recursively, which is a generalization of the Levinson-Durbin algorithm.

• Communications of the Korean Mathematical Society
• /
• v.10 no.2
• /
• pp.409-417
• /
• 1995

We consider the $R^k$-valued $(k \geq 1)$ process ${X_n}$ generated by $X_n + 1 = f(X_n)+e_{n+1}$, where $f(x) = (h(x),x^{(1)},x^{(1)},\cdots,x{(k-1)})'$. We assume that h is a real-valued measuable function on $R^k$ and that $e_n = (e'_n,0,\cdot,0)'$ where ${e'_n}$ are independent and identically distributed random variables. We obtained a practical criteria guaranteeing a given process to be geometrically ergodic. Sufficient condition for transience is also given.