• 산업경영시스템학회지
• /
• 제37권4호
• /
• pp.35-41
• /
• 2014

Real-life time series characteristic data has significant amount of non-stationary components, especially periodic components in nature. Extracting such components has required many ad-hoc techniques with external parameters set by users in a case-by-case manner. In this study, we used Empirical Mode Decomposition Method from Hilbert-Huang Transform to extract them in a systematic manner with least number of ad-hoc parameters set by users. After the periodic components are removed, the remaining time-series data can be analyzed with traditional methods such as ARIMA model. Then we suggest a different way of setting control chart limits for characteristic data with periodic components in addition to ARIMA components.

• 산업경영시스템학회지
• /
• 제35권2호
• /
• pp.106-112
• /
• 2012

Real-life time series characteristic data has significant amount of non-stationary components, especially periodic components in nature. Extracting such components has required many ad-hoc techniques with external parameters set by users in case-by-case manner. In our study, we evaluate whether Hilbert-Huang Transform, a new tool of time-series analysis can be used for effective analysis of such data. It is divided into two points : 1) how effective it is in finding periodic components, 2) whether we can use its results directly in detecting values outside control limits, for which a traditional method such as ARIMA had been used. We use glass furnace temperature data to illustrate the method.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2003년도 ISIS 2003
• /
• pp.338-341
• /
• 2003

Recently, the chaotic method is employed to forecast a near future of uncertain phenomena. This method makes it possible by restructuring an attractor of given time-series data in multi-dimensional space through Takens' embedding theory. However, many economical time-series data are not sufficiently chaotic. In other words, it is hard to forecast the future trend of such economical data on the basis of chaotic theory. In this paper, time-series data are divided into wave components using wavelet transform. It is shown that some divided components of time-series data show much more chaotic in the sense of correlation dimension than the original time-series data. The highly chaotic nature of the divided component enables us to precisely forecast the value or the movement of the time-series data in near future. The up and down movement of TOPICS value is shown so highly predicted by this method as 70％.

• 응용통계연구
• /
• 제32권6호
• /
• pp.851-865
• /
• 2019

하나의 시계열 자료에서 다양한 특징을 발견하는 일은 간단한 문제가 아니다. 본 논문에서는 하나의 시계열 자료에서 복수의 패턴을 찾아내어 예측 정확도를 높이는 방식인 다중 결합 예측 알고리즘을 소개한다. 이 알고리즘은 시간적 결합과 예측값 조합의 개념을 사용한다. 시간적 결합 방식을 통해, 하나의 시계열 자료에서 여러 개의 시계열 자료를 생성할 수 있으며, 각각의 자료는 별도의 특성을 가지게 된다. 여러 개의 시계열 자료에서 다양한 특성을 추출하기 위하여 지수평활법을 사용하고 시계열 요소들 및 이들의 예측값을 계산한다. 마지막 단계에서 시계열 요소 별로 예측값을 혼합 한 후, 각 시계열 요소들의 조합값을 더하여 최종 예측값을 만든다. 실증 분석으로 국내 교통사고 발생 건수를 예측한다. 분석 결과, 기존의 다른 예측 방식보다 예측 성능이 우수함을 확인할 수 있다.

• 전력전자학회:학술대회논문집
• /
• 전력전자학회 2000년도 전력전자학술대회 논문집
• /
• pp.651-656
• /
• 2000

This paper describes the optimal sizing of each component using computer simulation and presents the efficient operating scheme of series HEV using hardware simulator the equivalent system. As the sizing method of components have been experimental and empirical it is needed to spend much time and development cost. however the results of computer simulation will set the optimal sizing of components in short time. There are two type of driving control power-tracking mode and load-levelling mode in series HEV. This paper presents that series HEV be operated in the load-levelling mode which is more efficient that power-tracking mode.

• 한국우주과학회:학술대회논문집(한국우주과학회보)
• /
• 한국우주과학회 2011년도 한국우주과학회보 제20권1호
• /
• pp.22.1-22.1
• /
• 2011

Two dominant components of polar motion are the Chandler and the annual components. Recently, the existence of 500-day period component in the Earth's polar motion has been manifested. But its existence is not clear on Fourier spectrum. One cause of difficulty involved here is that the amplitudes of the two main components are slightly variable in time by certain amounts (Chandler: 0.15~0.28 arcsec, annual: 0.09~0.15 arcsec). A residual polar motion time series excluding the two main components for a time span between 1962 Jan and 2010 Nov from IERS C04 time series dataset was constructed by least square fitting. For faithful fitting, 43 time segments of 6.8 year length (each starts on January 1st of successive years) were separately acquired and later combined together. The period of dominant peak in the spectrum of this residual polar motion time series is 490 days. Next peaks have their periods as semi-annual, 300~330 days, ~560 days, 670 days, and 1360 days.

• 대한기계학회논문집A
• /
• 제33권10호
• /
• pp.1144-1150
• /
• 2009

This paper investigates the feasibility of the Bayesian discrete time approximation method to estimate the parameters of Weibull distributions of failures for two non-identical components connected in series system. A Bayesian model based on the discrete time approximation method is formulated to infer the Weibull parameters of two non-identical components with the failure data of the virtual tests. The study of this paper comes to a conclusion that the method is feasible only for some special cases under the given constraints on the concerned parameters.

• 응용통계연구
• /
• 제24권6호
• /
• pp.995-1006
• /
• 2011

A time series can be decomposed into simple components with a multiscale method. Empirical mode decomposition(EMD) is a recently invented multiscale method in Huang et al. (1998). It is natural to apply a classical prediction method such a vector autoregressive(AR) model to the obtained simple components instead of the original time series; in addition, a prediction procedure combining a classical prediction model to EMD and Hilbert spectrum is proposed in Kim et al. (2008). In this paper, we suggest to adopt principal component analysis(PCA) to the prediction procedure that enables the efficient selection of input variables among obtained components by EMD. We discuss the utility of adopting PCA in the prediction procedure based on EMD and Hilbert spectrum and analyze the daily worm account data by the proposed PCA adopted prediction method.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2007년도 학술발표회 논문집
• /
• pp.1437-1440
• /
• 2007

Many hydroclimatic time series are marked by interannual and longer quasi-period features that are associated with narrow band oscillatory climate modes. A time series modeling approach that directly considers such structures is developed and presented. The essence of the approach is to first develop a wavelet decomposition of the time series that retains only the statistically significant wavelet components, and to then model each such component and the residual time series as univariate autoregressive processes. The efficacy of this approach is demonstrated through the simulation of observed and paleo reconstructions of climate indices related to ENSO and AMO, tree ring and rainfall time series. Long ensemble simulations that preserve the spectral attributes of the time series in each ensemble member can be generated. The usual low order statistics are preserved by the proposed model, and its long memory performance is superior to the direction application of an autoregressive model.

• 산업경영시스템학회지
• /
• 제43권2호
• /
• pp.33-38
• /
• 2020

Anomaly detection of Machine Learning such as PCA anomaly detection and CNN image classification has been focused on cross-sectional data. In this paper, two approaches has been suggested to apply ML techniques for identifying the failure time of big time series data. PCA anomaly detection to identify time rows as normal or abnormal was suggested by converting subjects identification problem to time domain. CNN image classification was suggested to identify the failure time by re-structuring of time series data, which computed the correlation matrix of one minute data and converted to tiff image format. Also, LASSO, one of feature selection methods, was applied to select the most affecting variables which could identify the failure status. For the empirical study, time series data was collected in seconds from a power generator of 214 components for 25 minutes including 20 minutes before the failure time. The failure time was predicted and detected 9 minutes 17 seconds before the failure time by PCA anomaly detection, but was not detected by the combination of LASSO and PCA because the target variable was binary variable which was assigned on the base of the failure time. CNN image classification with the train data of 10 normal status image and 5 failure status images detected just one minute before.