• Communications for Statistical Applications and Methods
• /
• 제12권1호
• /
• pp.139-147
• /
• 2005

It is interesting to locate homogeneous segments within a DNA sequence. Suppose that the DNA sequence has segments within which the observations follow the same residue frequency distribution, and between which observations have different distributions. In this setting, change points correspond to the end points of these segments. This article explores the use of a binary segmentation procedure in detecting the change points in the DNA sequence. The change points are determined using a sequence of nested hypothesis tests of whether a change point exists. At each test, we compare no change-point model with a single change-point model by using the Bayesian information criterion. Thus, the method circumvents the computational complexity one would normally face in problems with an unknown number of change points. We illustrate the procedure by analyzing the genome of the bacteriophage lambda.

• Journal of the Korean Data and Information Science Society
• /
• 제28권4호
• /
• pp.889-898
• /
• 2017

In this research multiple change-points estimation for South Korean electricity generation data is considered. We analyze the South Korean electricity data via deterministically trending dynamic time series model with multiple structural changes in trends in a Bayesian approach. The number of change-points and the timing are unknown. The goal is to find the best model with the appropriate number of change-points and the length of the segments. A genetic algorithm is implemented to solve this optimization problem with a variable dimension of parameters. We estimate the structural change-points for South Korean electricity generation data and Nile River flow data additionally.

• 응용통계연구
• /
• 제36권6호
• /
• pp.573-589
• /
• 2023

조각별 선형 추세 모형에서의 변화점은 1차 차분한 시계열의 평균 변화점과 일치한다. 그러므로 1차 차분한 시계열의 평균 변화점을 탐색하면 조각별 선형 추세 모형의 변화점을 추정할 수 있다. 본 논문에서는 이와 같은 사실에 근거하여 원 시계열이 아닌 1차 차분한 시계열의 단순이동평균을 이용하여 원 시계열의 기울기가 변하는 변화점을 탐색하는 방법을 제안하고, 이에 대한 모의실험을 수행하였다. 모의실험 결과 본 논문에서 제안한 방법은 오차항들이 서로 독립인 경우뿐만 아니라 오차항들 사이에 강한 양의 자기상관이 존재하는 경우에도 변화점의 개수를 잘 추정하는 것으로 나타났다.

• Geosystem Engineering
• /
• 제21권6호
• /
• pp.309-317
• /
• 2018

We employ a three-dimensional indirect boundary element method (BEM) to simulate temperature change around an underground liquefied natural gas storage cavern. The indirect BEM (IBEM) uses fictitious heat source strength on boundary elements as basic variables which are solved from equations of boundary conditions and then used to compute the temperature change at other points in the considered problem domain. The IBEM requires evaluation of singular integration for temperature change due to heat conduction from a constant heat source on a planar (triangular) region. The singularity can be eliminated by a semi-analytical integration scheme. However, it is found that the semi-analytical integration scheme yields sharp temperature gradient for points close to vertices of triangle. This affects the accuracy of heat flux, if they are evaluated by finite difference method at these points. This difficulty can be overcome by a combination of using a direct numerical integration for these points and the semi-analytical scheme for other points distance away from the vertices. The IBEM and the hybrid integration scheme have been verified with an analytic solution and then used to the application of the underground storage.

• Communications for Statistical Applications and Methods
• /
• 제20권6호
• /
• pp.439-454
• /
• 2013

This study presents a Bayesian multiple change-point detection approach to segment and classify the observations that no longer come from an initial population after a certain time. Inferences are based on the multiple change-points in a sequence of random variables where the probability distribution changes. Bayesian multiple change-point estimation is classifies each observation into a segment. We use a truncated Poisson distribution for the number of change-points and conjugate prior for the exponential family distributions. The Bayesian method can lead the unsupervised classification of discrete, continuous variables and multivariate vectors based on latent class models; therefore, the solution for change-points corresponds to the stochastic partitions of observed data. We demonstrate segmentation with real data.

• Journal of the Korean Data and Information Science Society
• /
• 제13권2호
• /
• pp.251-260
• /
• 2002

The aim of this paper is to consider of detecting the location, the jump size and the number of change-points in regression functions by using the local linear fit which is one of nonparametric regression techniques. It is obtained the asymptotic properties of the change points and the jump sizes. and the correspondin grates of convergence for change-point estimators.

• Journal of the Korean Data and Information Science Society
• /
• 제13권2호
• /
• pp.185-193
• /
• 2002

The purpose of this paper is to suggest a method for detecting the linear regression change-points or variance change-points in regression model by the combination of Schwarz information criteria. The advantage of the suggested method is to detect change-points more detailed when one compares the suggest method with Chen (1998)'s method.

• 응용통계연구
• /
• 제32권4호
• /
• pp.561-572
• /
• 2019

본 연구는 다층적 다중변화점 추정법으로 FDRSeg 기법과 SMUCE 기법의 이론적 특성을 파악하고 모의실험을 통해 경험적 특성을 비교하고자한다. FDRSeg (False discovery rate segmentation)기법은 FDR 기반 조절을 하여 변화점을 추정하고 SMUCE (simultaneous multiscale change-point estimator) 기법은 국소우도함수 기반 다중 검정으로 변화점을 추정한다. 변화점의 개수가 작을경우에는 두 기법에 의한 추정능력이 비슷하다. 변화점 개수가 많을수록 FDRSeg 의 추정이 변화점 개수와 추정측도 면에서 더 좋은 편이다. 실제 데이터 분석으로 검층 주상도 데이터에 대해 각 기법으로 다중변화점 추정을 하고 비교한다.

• Asia pacific journal of information systems
• /
• 제11권4호
• /
• pp.99-111
• /
• 2001

The prediction of stock price index is a very difficult problem because of the complexity of stock market data. It has been studied by a number of researchers since they strongly affect other economic and financial parameters. The movement of stock price index has a series of change points due to the strategies of institutional investors. This study presents a two-stage forecasting model of stock price index using change-point detection and artificial neural networks. The basic concept of this proposed model is to obtain intervals divided by change points, to identify them as change-point groups, and to use them in stock price index forecasting. First, the proposed model tries to detect successive change points in stock price index. Then, the model forecasts the change-point group with the backpropagation neural network(BPN). Finally, the model forecasts the output with BPN. This study then examines the predictability of the integrated neural network model for stock price index forecasting using change-point detection.

• Communications for Statistical Applications and Methods
• /
• 제29권1호
• /
• pp.127-150
• /
• 2022

We discuss multiple change-point estimation as edge detection in piecewise smooth functions with finitely many jump discontinuities. In this paper we propose change-point estimators using concentration kernels with Fourier coefficients. The change-points can be located via the signal based on Fourier transformation system. This method yields location and amplitude of the change-points with refinement via concentration kernels. We prove that, in an appropriate asymptotic framework, this method provides consistent estimators of change-points with an almost optimal rate. In a simulation study the proposed change-point estimators are compared and discussed. Applications of the proposed methods are provided with Nile flow data and daily won-dollar exchange rate data.