• Communications for Statistical Applications and Methods
• /
• 제18권3호
• /
• pp.319-331
• /
• 2011

In this paper, we propose automatic procedures for the model selection of various univariate time series data. Automatic model selection is important, especially in data mining with large number of time series, for example, the number (in thousands) of signals accessing a web server during a specific time period. Several methods have been proposed for automatic model selection of time series. However, most existing methods focus on linear time series models such as exponential smoothing and autoregressive integrated moving average(ARIMA) models. The key feature that distinguishes the proposed procedures from previous approaches is that the former can be used for both linear time series models and nonlinear time series models such as threshold autoregressive(TAR) models and autoregressive moving average-generalized autoregressive conditional heteroscedasticity(ARMA-GARCH) models. The proposed methods select a model from among the various models in the prediction error sense. We also provide an R package autots that implements the proposed automatic model selection procedures. In this paper, we illustrate these algorithms with the artificial and real data, and describe the implementation of the autots package for R.

• 상하수도학회지
• /
• 제29권4호
• /
• pp.519-531
• /
• 2015

It has been widely accepted that the pressure management of water distribution systems using pressure reducing valves(PRVs) would be an effective method for controlling leakages. A pressure reducing valve (PRV) regulates outlet pressure regardless of fluctuating flow and varying inlet pressure, thereby reducing leakage and mitigating the stress on the water distribution system. However, the operation of a PRV is vulnerable to its mechanical condition and hydraulic operability. In this research, the effect of PRVs installed in water distribution system are evaluated in terms of hydraulic pressure reduction and mechanical performance by analyzing measured pressure data with statistical approach. A statistical approach using the moving average filter and frequency analysis based on fourier transform is presented to detect abnormally operated PRVs that have been densely installed in water distribution system. The result shows that the proposed approach can be a good performance evaluation method by simply measuring pressures for the PRVs.

• Smart Structures and Systems
• /
• 제3권3호
• /
• pp.245-261
• /
• 2007

Nonlinear time-domain system identification (SI) algorithm is proposed to assess damage in a shear building by synchronously estimating time-varying stiffness and damping parameters using measured acceleration data. Mass properties have been assumed as the a priori known information. Viscous damping was utilized for the current research. To chase possible nonlinear dynamic behavior under severe vibration, an incremental governing equation of vibrational motion has been utilized. Stiffness and damping parameters are estimated at each time step by minimizing the response error between measured and computed acceleration increments at the measured degrees-of-freedom. To solve a nonlinear constrained optimization problem for optimal structural parameters, sensitivities of acceleration increment were formulated with respect to stiffness and damping parameters, respectively. Incremental state vectors of vibrational motion were computed numerically by Newmark-${\beta}$ method. No model is pre-defined in the proposed algorithm for recovering the nonlinear response. A time-window scheme together with Monte Carlo iterations was utilized to estimate parameters with noise polluted sparse measured acceleration. A moving average scheme was applied to estimate the time-varying trend of structural parameters in all the examples. To examine the proposed SI algorithm, simulation studies were carried out intensively with sample shear buildings under earthquake excitations. In addition, the algorithm was applied to assess damage with laboratory test data obtained from free vibration on a three-story shear building model.

• 대한전기학회논문지:전력기술부문A
• /
• 제55권2호
• /
• pp.85-93
• /
• 2006

Since the SMP(System Marginal Price) is a vital factor to the market participants who intend to maximize the their profit and to the ISO(Independent System Operator) who wish to operate the electricity market in a stable sense, the short-term marginal price forecasting should be performed correctly. In an electricity market the short-term market price affects considerably the short-term trading between the market entities. Therefore, the exact forecasting of SMP can influence on the profit of market participants. This paper presents a new methodology for a day-ahead SMP forecasting using ARIMA(Autoregressive Integrated Moving Average) model based on the time-series method. And also the correction algorithm is proposed to minimize the forecasting error in order to improve the efficiency and accuracy of the SMP forecasting. To show the efficiency and effectiveness of the proposed method, the case studies are performed using historical data of SMP in 2004 published by KPX(Korea Power Exchange).

• 대한전기학회논문지:전력기술부문A
• /
• 제53권7호
• /
• pp.405-413
• /
• 2004

Traditionally, electrical power systems had the vertically-integrated industry structures based on the economics of scale. However power systems have been recently reformed to increase the energy efficiency of the power system. According to these trends, Korean power industry has been partially restructured, and the competitive generation market was opened in 2001. In competitive electric markets, correct demand data are one of the most important issue to maintain the flexible electric markets as well as the reliable power systems. However, the measuring load data can have the uncertainty because of mechanical trouble, communication jamming, and other things. To obtain the reliable load data, an efficient evaluation technique to adust the missing load data is needed. This paper analyzes the load pattern of historical real data and then the turned ARIMA (Autoregressive Integrated Moving Average) model, PCHIP(Piecewise Cubic Interporation) and Branch & Bound method are applied to seek the missing parameters. The proposed method is tested under a variety of conditions and tested with historical measured data from the Korea Energy Management Corporation (KEMCO).

• Journal of the Korean Data and Information Science Society
• /
• 제20권5호
• /
• pp.857-867
• /
• 2009

본 연구는 학년 (연령) 진급에 따른 인구증감률에 대하여 전국 학생수를 예측하는 다양한 방법들을 제시하고, 제시된 예측 모형들을 이용하여 출생아들이 고3학생이 되는 18년 후인 2026까지의 학생수를 예측하는 것이다. 이동평균과 시계열모형, 회귀분석 등 다양한 예측모형들이 사용되었고, 적합 척도들을 이용하여 이들의 오차들을 측정하였다. 예측오차를 측정하는 도구들을 기준으로 제시된 예측방법들 중 이동평균에 의한 방법은 쉽고 단순한 장점을 지니면서도 기존에 예측되어진 한국교육개발원의 예측결과 뿐 아니라 회귀분석 및 시계열예측의 고등기법들의 결과들 보다 예측 능력이 우수한 것으로 나타났다.

• Journal of the Korean Data and Information Science Society
• /
• 제20권1호
• /
• pp.117-124
• /
• 2009

시계열자료에 계절효과가 존재할 때 성공적인 수요예측을 위해 Winters 방법과 같은 다양한 통계적 방법이 존재지만 신상품과 같이 과거 매출자료가 충분하지 않을 경우 통계적 방법 적용에 한계가 존재한다. 본 연구논문은 신제품과 같이 과거 매출자료가 충분하지 않아 계절효과 등을 추정하기 어려울 때 누적자료를 활용한 통계적 예측방법을 제안한다. 제안된 통계적 방법은 회귀모형이론에 기초하고 있으며 이 방법의 유효성을 최근 화장품 매출자료를 이용하여 검증하였다.

• Journal of the Korean Data and Information Science Society
• /
• 제21권3호
• /
• pp.523-534
• /
• 2010

본 연구의 목적은 이중 이동평균법에 의한 초, 중, 고등학교 학생 수 예측 기법을 이용하여 2027년까지의 수도권의 고3학생 수를 예측하고, 수도권 전문대학, 대학교 입학정원과 대학과 전문대학, 교육대학을 합한 총 입학정원과의 관계를 향후 2027년까지 분석하는 것이다. 이 분석 결과 수도권의 집중화 현상으로 심각한 저 출산의 영향에도 불구하고, 수도권의 대학들의 신입생 유치에는 문제가 없다. 그러나 향후 대학들의 입학정책에 영향을 끼칠 것이다.

• Smart Structures and Systems
• /
• 제26권1호
• /
• pp.23-33
• /
• 2020

Majority of the damage in engineering structures is nonlinear. Damage sensitive features (DSFs) extracted by traditional methods from linear time series models cannot effectively handle nonlinearity induced by structural damage. A new DSF is proposed based on vector space cosine similarity (VSCS), which combines K-means cluster analysis and Bayesian discrimination to detect nonlinear structural damage. A reference autoregressive moving average (ARMA) model is built based on measured acceleration data. This study first considers an existing DSF, residual standard deviation (RSD). The DSF is further advanced using the VSCS, and then the advanced VSCS is classified using K-means cluster analysis and Bayes discriminant analysis, respectively. The performance of the proposed approach is then verified using experimental data from a three-story shear building structure, and compared with the results of existing RSD. It is demonstrated that combining the linear ARMA model and the advanced VSCS, with cluster analysis and Bayes discriminant analysis, respectively, is an effective approach for detection of nonlinear damage. This approach improves the reliability and accuracy of the nonlinear damage detection using the linear model and significantly reduces the computational cost. The results indicate that the proposed approach is potential to be a promising damage detection technique.

• Journal of Positioning, Navigation, and Timing
• /
• 제9권2호
• /
• pp.89-98
• /
• 2020

Prediction of clock behaviors is necessary to generate very high stable system time which is essential for a satellite navigation system. For the purpose, we applied the Auto-Regressive Integrated Moving Average (ARIMA) model to the prediction of two hydrogen masers' behaviors with respect to the rapid Coordinated Universal Time (UTCr). Using the packaged programming language R, we made an analysis and prediction of time series data of [UTCr - clocks]. The maximum variation width of the residuals which were obtained by the difference between the predicted and measured values, was 6.2 ns for 106 days. This variation width was just one-sixth of [UTCr-UTC (KRIS)] published by the BIPM for the same period. Since the two hydrogen masers were found to be strongly correlated, we applied the Vector Auto-Regressive Moving Average (VARMA) model for more accurate prediction. The result showed that the prediction accuarcy was improved by two times for one hydrogen maser.