• Communications for Statistical Applications and Methods
• /
• v.10 no.1
• /
• pp.19-30
• /
• 2003

Spatiotemporal statistical models are used for analyzing space-time data in many fields, such as environmental sciences, meteorology, geology, epidemiology, forestry, hydrology, fishery, and so on. It is well known that classical spatiotemporal process modeling requires the estimation of space-time variogram or covariance functions. In practice, the estimation of such variogram or covariance functions are computationally difficult and highly sensitive to data structures. We investigate a Bayesian hierarchical model which allows the specification of a more realistic series of conditional distributions instead of computationally difficult and less realistic joint covariance functions. The spatiotemporal model investigated in this study allows both spatial component and autoregressive temporal component. These two features overcome the inability of pure time series models to adequately predict changes in trends in individual sites.

• Journal of Positioning, Navigation, and Timing
• /
• v.11 no.4
• /
• pp.287-295
• /
• 2022

The GNSS coordinate time series is used as important data for geophysical analysis such as terrestrial reference frame establishment, crustal deformation, Earth orientation parameter estimation, etc. However, various factors may cause discontinuity in the coordinate time series, which may lead to errors in the interpretation. In this paper, we describe the discontinuity in the coordinate time series due to the equipment replacement for domestic GNSS stations and discuss the change in movement magnitude and velocity vector difference in each direction before and after discontinuity correction. To do this, we used three years (2017-2019) of data from 40 GNSS stations. The average magnitude of the velocity vector in the north-south, east-west, and vertical directions before correction is -12.9±1.5, 28.0±1.9, and 4.2±7.6 mm/yr, respectively. After correction, the average moving speed in each direction was -13.0±1.0, 28.2±0.8, and 0.7±2.1 mm/yr, respectively. The average magnitudes of the horizontal GNSS velocity vectors before and after discontinuous correction was similar, but the deviation in movement size of stations decreased after correction. After equipment replacement, the change in the vertical movement occurred more than the horizontal movement variation. Moreover, the change in the magnitude of movement in each direction may also cause a change in the velocity vector, which may lead to errors in geophysical analysis.

• Communications for Statistical Applications and Methods
• /
• v.29 no.3
• /
• pp.353-371
• /
• 2022

This paper analyzes death counts after World War II of several countries to identify and to compare their stochastic structures. The stochastic structures that this paper entertains are three structural time series models, a local level with a random walk model, a fixed local linear trend model and a local linear trend model. The structural time series models assume that a time series can be formulated directly with the unobserved components such as trend, slope, seasonal, cycle and daily effect. Random effect of each unobserved component is characterized by its own stochastic structure and a distribution of its irregular component. The structural time series models use the Kalman filter to estimate unknown parameters of a stochastic model, to predict future data, and to do filtering data. This paper identifies the best-fitted stochastic model for three types of death counts (Female, Male and Total) of each country. Two diagnostic procedures are used to check the validity of fitted models. Three criteria, AIC, BIC and SSPE are used to select the best-fitted valid stochastic model for each type of death counts of each country.

• 제어로봇시스템학회:학술대회논문집
• /
• 2004.08a
• /
• pp.631-634
• /
• 2004

In this paper, the Bayesian recurrent neural network (BRNN) is proposed to predict time series data. Among the various traditional prediction methodologies, a neural network method is considered to be more effective in case of non-linear and non-stationary time series data. A neural network predictor requests proper learning strategy to adjust the network weights, and one need to prepare for non-linear and non-stationary evolution of network weights. The Bayesian neural network in this paper estimates not the single set of weights but the probability distributions of weights. In other words, we sets the weight vector as a state vector of state space method, and estimates its probability distributions in accordance with the Bayesian inference. This approach makes it possible to obtain more exact estimation of the weights. Moreover, in the aspect of network architecture, it is known that the recurrent feedback structure is superior to the feedforward structure for the problem of time series prediction. Therefore, the recurrent network with Bayesian inference, what we call BRNN, is expected to show higher performance than the normal neural network. To verify the performance of the proposed method, the time series data are numerically generated and a neural network predictor is applied on it. As a result, BRNN is proved to show better prediction result than common feedforward Bayesian neural network.

• Communications for Statistical Applications and Methods
• /
• v.29 no.6
• /
• pp.695-708
• /
• 2022

Recently, several studies have been conducted using state space model. In this study, a dynamic linear model with state space model form is applied to stock data. The monthly returns for 135 Korean stocks are fitted to a dynamic linear model, to obtain an estimate of the time-varying 𝛽-coefficient time-series. The model formula used for the return is a capital asset pricing model formula explained in economics. In particular, the transition equation of the state space model form is appropriately modified to satisfy the assumptions of the error term. k-shape clustering is performed to classify the 135 estimated 𝛽 time-series into several groups. As a result of the clustering, four clusters are obtained, each consisting of approximately 30 stocks. It is found that the distribution is different for each group, so that it is well grouped to have its own characteristics. In addition, a common pattern is observed for each group, which could be interpreted appropriately.

• Journal of the Korea Society of Computer and Information
• /
• v.11 no.5 s.43
• /
• pp.69-74
• /
• 2006

The recent development of multimedia content-based retrieval technologies brings great attention of musician retrieval using features of a digital audio data among music information retrieval technologies. But the indexing techniques for music databases have not been studied completely. In this paper, we present a musician retrieval technique for audio features using the space split methods in the time-series pattern index file. We use features of audio to retrieve the musician and a time-series pattern index file to search the candidate musicians. Experimental results show that the time-series pattern index file using the rotational split method is efficient for musician retrievals in the time-series pattern files.

• Journal of Astronomy and Space Sciences
• /
• v.30 no.4
• /
• pp.241-246
• /
• 2013

We have investigated drought periodicities occurred in Seoul to find out any indication of relationship between drought in Korea and solar activities. It is motivated, in view of solar-terrestrial connection, to search for an example of extreme weather condition controlled by solar activity. The periodicity of drought in Seoul has been re-examined using the wavelet transform technique as the consensus is not achieved yet. The reason we have chosen Seoul is because daily precipitation was recorded for longer than 200 years, which meets our requirement that analyses of drought frequency demand long-term historical data to ensure reliable estimates. We have examined three types of time series of the Effective Drought Index (EDI). We have directly analyzed EDI time series in the first place. And we have constructed and analyzed time series of histogram in which the number of days whose EDI is less than -1.5 for a given month of the year is given as a function of time, and one in which the number of occasions where EDI values of three consecutive days are all less than -1.5 is given as a function of time. All the time series data sets we analyzed are periodic. Apart from the annual cycle due to seasonal variations, periodicities shorter than the 11 year sunspot cycle, ~ 3, ~ 4, ~ 6 years, have been confirmed. Periodicities to which theses short periodicities (shorter than Hale period) may be corresponding are not yet known. Longer periodicities possibly related to Gleissberg cycles, ~ 55, ~ 120 years, can be also seen. However, periodicity comparable to the 11 year solar cycle seems absent in both EDI and the constructed data sets.

• 한국데이터정보과학회:학술대회논문집
• /
• 2004.04a
• /
• pp.91-101
• /
• 2004

The turbulent flow is of fundamental interest because the conservation equations for thermodynamics, mass and momentum are linked together. This turbulent flow consists of some coherent time- and space-organized vortical structures. Research has already shown that some dynamic systems and experimental models still cannot provide a good nonlinear analysis of turbulent time series. In the real turbulent flow, very complicated nonlinear behaviors, which are affected by many vague factors are present. In this paper, a kernel-based machine for fuzzy nonlinear regression analysis is proposed to predict the nonlinear time series of turbulent flows. In order to show the practicality and usefulness of this model, we present an example of predicting the near-wall turbulence time series as a verifiable model and compare with fuzzy piecewise regression. The results of practical applications show that the proposed method is appropriate and appears to be useful in nonlinear analysis and in fuzzy environments to predict the turbulence time series.

• The Bulletin of The Korean Astronomical Society
• /
• v.41 no.1
• /
• pp.56.2-56.2
• /
• 2016

We present a multi-aperture photometry pipeline for DEEP-South (Deep Ecliptic Patrol of the Southern Sky) time-series data, written in C. The pipeline is designed to do robust high-precision photometry and calibration of non-crowded fields with a varying point-spread function, allowing for the wholesale search and characterization of both temporal and spatial variabilities. Our time-series photometry method consists of three parts: (i) extracting all point sources with several pixel/blind parameters, (ii) determining the optimized aperture for each source where we consider whether the measured flux within the aperture is contaminated by unwanted artifacts, and (iii) correcting position-dependent variations in the PSF shape across the mosaic CCD. In order to provide faster access to the resultant catalogs, we also utilize an efficient indexing technique using compressed bitmap indices (FastBit). Lastly, we focus on the development and application of catalog-based searches that aid the identification of high-probable single events from the indexed database. This catalog-based approach is still useful to identify new point-sources or moving objects in non-crowded fields. The performance of the pipeline is being tested on various sets of time-series data available in several archives: DEEP-South asteroid survey and HAT-South/MMT exoplanet survey data sets.

• Communications for Statistical Applications and Methods
• /
• v.16 no.1
• /
• pp.31-40
• /
• 2009

Spatial time series data can be viewed either as a set of time series collected simultaneously at a number of spatial locations. In this paper, We estimate the parameters of spatial time autoregressive moving average (SIARMA) process by method of Gibbs sampling. Finally, We apply this method to a set of U.S. Mumps data over a 12 states region.