• The Korean Journal of Applied Statistics
• /
• v.37 no.3
• /
• pp.297-309
• /
• 2024

This paper evaluates the performance of the neural network autoregressive model combined with an exponential smoothing model, called the NNARX+ETS model. The combined model utilizes the components of ETS as exogenous variables for NNARX, to forecast time series data using artificial neural networks. The main idea is to enhance the performance of NNAR using only lags of the original time series data, by combining traditional time series analysis methods with the neural networks through NNARX. We employ two real data for performance evaluation and compare the NNARX+ETS with NNAR and traditional time series analysis methods such as ETS and ARIMA (autoregressive integrated moving average) models.

• Journal of Korea Water Resources Association
• /
• v.35 no.3
• /
• pp.275-284
• /
• 2002

In this study, a method of random resampling of residuals from stochastic models such as the Monte-Carlo model, the lag-one autoregressive model(AR(1)) and the periodic lag-one autoregressive model(PAR(1)), has been adopted to generate a large number of long traces of annual and monthly steamflows. Main advantage of this resampling scheme called the Bootstrap method is that it does not rely on the assumption of population distribution. The Bootstrap is a method for estimating the statistical distribution by resampling the data. When the data are a random sample from a distribution, the Bootstrap method can be implemented (among other ways) by sampling the data randomly with replacement. This procedure has been applied to the Yongdam site to check the performance of Bootstrap method for the streamflow generation. and then the statistics between the historical and generated streamflows have been computed and compared. It has been shown that both the conventional and Bootstrap methods for the generation reproduce fairly well the mean, standard deviation, and serial correlation, but the Bootstrap technique reproduces the skewness better than the conventional ones. Thus, it has been noted that the Bootstrap method might be more appropriate for the preservation of skewness.

• Journal of Korean Institute of Industrial Engineers
• /
• v.25 no.3
• /
• pp.330-335
• /
• 1999

The goal of the study is to determine the most sensitive parameter to represent the degree of muscle force and fatigue. Various numerical parameters such as the first coefficient of Autoregressive (AR) Model, Root Mean Square (RMS), Zero Crossing Rate (ZCR), Mean Power Frequency (MPF), Median Frequency (MF) were tested in this study. Ten healthy male subjects participated in the experiment. They were asked to extend their trunk by using the right and left erector spinae muscles during a sustained isometric contraction for twenty seconds. The force levels were 15%, 30%, 45%, 60%, and 75% of Maximal Voluntary Contraction (MVC), and the order of trials was randomized. The results showed that RMS was the best parameter to measure the force level of the muscle, and that the first coefficient of AR model was relatively sensitive parameter for the fatigue measurement at less than 60% MVC condition. At the 75% MVC, however, both MPF and the first coefficient of AR Model showed the best performance in quantification of muscle fatigue. Therefore, the sensitivity of measurement can be improved by properly selecting the parameter based upon the level of force during a sustained isometric condition.

• The Korean Journal of Applied Statistics
• /
• v.29 no.1
• /
• pp.123-132
• /
• 2016

We can achieve the principle of parsimony and efficiency if homogeneity for panel time series model is satisfied. We suggest a Rao test statistic and a Wald test statistic for the test of homogeneity for panel AR(1) and derived the limit distribution. We performed a simulation to examine statistics with the same chisquare distribution when number of the individual is small and in common with large. We also simulated to compare the empirical power of the statistics in a small panel. In application, we fit panel AR(1) model using regional monthly economical active population data and test homogeneity for panel AR(1). It is satisfied homogeneity, so it could be fitted AR(1) using the sample mean at the time point. We also compare the power of prediction between each individual and pooled model.

• Communications for Statistical Applications and Methods
• /
• v.21 no.2
• /
• pp.169-181
• /
• 2014

Marginalized random effects models (MREM) are commonly used to analyze longitudinal categorical data when the population-averaged effects is of interest. In these models, random effects are used to explain both subject and time variations. The estimation of the random effects covariance matrix is not simple in MREM because of the high dimension and the positive definiteness. A relatively simple structure for the correlation is assumed such as a homogeneous AR(1) structure; however, it is too strong of an assumption. In consequence, the estimates of the fixed effects can be biased. To avoid this problem, we introduce one approach to explain a heterogenous random effects covariance matrix using a modified Cholesky decomposition. The approach results in parameters that can be easily modeled without concern that the resulting estimator will not be positive definite. The interpretation of the parameters is sensible. We analyze metabolic syndrome data from a Korean Genomic Epidemiology Study using this method.

• Proceedings of the KIEE Conference
• /
• 1993.07a
• /
• pp.131-133
• /
• 1993

In the power system state estimation, the J(x)-index test and normalized residuals $r_N$ have been used to detect the presence of bad measurements and identify their location. But, these methods require the complete re-estimation of system states whenever bad data is identified. This paper presents back-propagation neural network model using autoregressive filter for identification of bad measurements. The performances of neural network method are compared with those of conventional methods and simulation results show the good performance in the bad data identification based on the neural network under sample power system.

• The Journal of the Acoustical Society of Korea
• /
• v.15 no.4
• /
• pp.50-57
• /
• 1996

In this paper, we proposed the method of optimal wavelet selection and wavelet expansion of AR(autoregressive) parameters by selected wavelet using F-test. A cost function is introduced as a wavelet selection method. Using this cost function, wavelets (D4 to D20) are tested to the synthesized signal. With this selected wavelet, we get the wavelet coefficients of AR parameters to both synthesized signal and real speech signal. To evaluate the proposed method, this wavelet based algorithm is compared with the Kalman filering algorithm. As a results, the proposed method shows a better performance by about 5-10dB than the Kalman filter.

• Proceedings of the Korea Electromagnetic Engineering Society Conference
• /
• 2001.11a
• /
• pp.324-327
• /
• 2001

In this paper, a 24GHz FMCW radar system which measures the range and the relative velocity of a vehicle in close range is described. The intended ranging accuracy is 15cm and a possible system concept to achieve this objective is presented. The VCO nonlinearity correction method using a reference delay-line and the data extrapolation algorithms based on AR(autoregressive) model are applied. The implemented system shows relatively satisfactory results in ranging accuracy.

• Transactions of the Korean Society of Mechanical Engineers
• /
• v.16 no.9
• /
• pp.1788-1795
• /
• 1992

Numerical simulations have been performed to investigate various spectral estimators used in LDV signal processing. In order to simulate a particle arrival time statistics known as the doubly stochastic poisson process, an autoregressive vector model was adopted to construct a primary velocity field. The conditional Poisson process with a random rate parameter was generated through the rescaling time process using the mean value function. The direct transform based on random sampling sequences and the standard periodogram using periodically resampled data by the sample and hold interpolation were applied to obtain power spectral density functions. For low turbulent intensity flows, the direct transform with a constant Poisson intensity is in good agreement with the theoretical spectrum. The periodogram using the sample and hold sequences is better than the direct transform in the view of the stability and the weighting of the velocity bias for high data density flows. The high Reynolds stress and high fluctuation of the transverse velocity component affects the velocity bias which increases the distortion of spectral components in the direct transform.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2020.06a
• /
• pp.101-101
• /
• 2020

Traditional stochastic simulation of hydroclimatological variables often underestimates the variability and correlation structure of larger timescale due to the difficulty in preserving long-term memory. However, the Long Short-Term Memory (LSTM) model illustrates a remarkable long-term memory from the recursive hidden and cell states. The current study, therefore, employed the LSTM model in stochastic generation of hydrologic and climate variables to examine how much the LSTM model can preserve the long-term memory and overcome the drawbacks of conventional time series models such as autoregressive (AR). A trigonometric function and the Rössler system as well as real case studies for hydrological and climatological variables were tested. Results presented that the LSTM model reproduced the variability and correlation structure of the larger timescale as well as the key statistics of the original time domain better than the AR and other traditional models. The hidden and cell states of the LSTM containing the long-memory and oscillation structure following the observations allows better performance compared to the other tested conventional models. This good representation of the long-term variability can be important in water manager since future water resources planning and management is highly related with this long-term variability.