• 응용통계연구
• /
• 제32권1호
• /
• pp.69-81
• /
• 2019

본 논문에서는 딥러닝을 이용한 이변량 장기종속시계열(long-range dependent time series) 예측을 고려하였다. 시계열 데이터 예측에 적합한 LSTM(long short-term memory) 네트워크를 이용하여 이변량 장기종속시계열을 예측하고 이를 이변량 FARIMA(fractional ARIMA) 모형인 FIVARMA 모형과 VARFIMA 모형과의 예측 성능을 실증 자료 분석을 통해 비교하였다. 실증 자료로는 기능적 자기공명 영상(fMRI) 및 일일 실현 변동성(daily realized volatility) 자료를 이용하였으며 표본외 예측(out-of sample forecasting) 오차 비교를 통해 예측 성능을 측정하였다. 그 결과, FIVARMA 모형과 VARFIMA 모형의 예측값에는 미묘한 차이가 존재하며, LSTM 네트워크의 경우 초매개변수 선택으로 복잡해 보이지만 계산적으로 더 안정되면서 예측 성능도 모수적 장기종속시계열과 뒤지지 않은 좋은 예측 성능을 보였다.

• 한국공간구조학회논문집
• /
• 제14권3호
• /
• pp.93-100
• /
• 2014

Ethylene Tetrafluoroethylene (ETFE) has been widely used in long-span buildings because of its light weight and high transparency. This paper studies the short and long term creep behaviour of ETFE foil. A series of short-term creep and recovery tests were performed, in which the residual strain was observed. A long-term creep test of the ETFE foil was also performed over 110 days. A viscoelastic-plastic model was then established to describe the short-term creep and recovery behaviour. The model contains a traditional multi-Kelvin part and an added steady-flow component to represent the viscoelastic and viscoplastic behaviour, respectively. The model successfully fit the data for three stresses and six temperatures. Additionally, time-temperature equivalency was adopted to predict the long-term creep behaviour of ETFE foil. Horizontal shifting factors were determined from the process of shifting creep-curves at six temperatures. The long-term creep behaviours at three temperatures were predicted. Finally, the long-term creep test showed that the short-term creep test at identical temperatures insufficiently predicted additional creep behaviour, and the long-term test verified the horizontal shifting factors derived from the time-temperature equivalency.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2020년도 학술발표회
• /
• 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.

• 한국지반신소재학회논문집
• /
• 제17권4호
• /
• pp.239-249
• /
• 2018

연약점토 지반 개량을 위해 연직배수재 타설 후 선행재하공법이 일반적으로 적용되는데, 현장에서의 시공계획 변경 등으로 인해 연직배수재 타설 후 장기간 방치되는 경우가 종종 발생된다. 따라서 장기간 방치된 조건에서의 연직배수재 열화 현상을 고려하기 위해 구속압으로 적용되는 수온을 각각 30, 35, $40^{\circ}C$를 적용하였다. 그 결과, 시간경과에 따라 배수성능이 급격히 저하되는 경향을 나타냈다. 그리고 현장 원위치 조건, 즉, 점토 구속조건하에서 장기간 통수능 저하 정도를 평가하기 위하여 Miura와 Chai(2000)식을 적용하였다. 그 결과, 온도 변화 조건에서 수행된 통수능 시험결과를 이용한 신뢰성 해석 방법과 Miura와 chai(2000)식을 적용하여 장기 통수능을 평가할 수 있는 것으로 평가되었다.

• Journal of Information Processing Systems
• /
• 제15권3호
• /
• pp.694-706
• /
• 2019

In this study, we applied the long short-term memory (LSTM) model to classify the cryptocurrency price time series. We collected historic cryptocurrency price time series data and preprocessed them in order to make them clean for use as train and target data. After such preprocessing, the price time series data were systematically encoded into the three-dimensional price tensor representing the past price changes of cryptocurrencies. We also presented our LSTM model structure as well as how to use such price tensor as input data of the LSTM model. In particular, a grid search-based k-fold cross-validation technique was applied to find the most suitable LSTM model parameters. Lastly, through the comparison of the f1-score values, our study showed that the LSTM model outperforms the gradient boosting model, a general machine learning model known to have relatively good prediction performance, for the time series classification of the cryptocurrency price trend. With the LSTM model, we got a performance improvement of about 7% compared to using the GB model.

• 응용통계연구
• /
• 제23권2호
• /
• pp.249-261
• /
• 2010

Long-term forecasting of seasonal time series is critical in many applications such as planning business strategies and resolving possible problems of a business company. Unlike the traditional approach that depends solely on dynamic models, Li and Hinich (2002) introduced a combination of stochastic dynamic modeling with filter bank approach for forecasting seasonal patterns using highly coherent(High-C) waveforms. We modify the filter selection and forecasting procedure on wavelet domain to be more feasible and compare the resulting predictor with one that obtained from the wavelet variance estimation method. An improvement over other seasonal pattern extraction and forecasting methods based on such as wavelet scalogram, Holt-Winters, and seasonal autoregressive integrated moving average(SARIMA) is shown in terms of the prediction error. The performance of the proposed method is illustrated by a simulation study and an application to the real stock price data.

• Communications for Statistical Applications and Methods
• /
• 제22권6호
• /
• pp.675-683
• /
• 2015

In the 21st century, we now face the serious problems of the enormous consumption of the energy resources. Depending on the power consumption increases, both China and South Korea face a reduction in available resources. This paper considers the regression models and time-series models to compare the performance of the forecasting accuracy based on Mean Absolute Percentage Error (MAPE) in order to forecast the electricity demand accurately on the short-term period (68 months) data in Northeast China and find the relationship with Korea. Among the models the support vector regression (SVR) model shows superior performance than time-series models for the short-term period data and the time-series models show similar results with the SVR model when we use long-term period data.

• 한국환경과학회지
• /
• 제9권1호
• /
• pp.19-25
• /
• 2000

As the tideland reclamation is done on a large scale these days, construction work is active in the coastal areas. Facilities in the coastal areas must be built with the tide characteristics taken into consideration. Thus the tide characteristics affect the overall reclamation plan. The analysis of the tide data boils down to a harmonic analysis of the hourly changes of long-term tide data and extraction of unharmonic coefficients from the results. Since considerable amount of tide data of the West Coast are available, the existing data can be collected and can be used to obtain the temporal changes of the tide by being fitted into the tide prediction model. The goal of this thesis lies in assessing whether the mean sea level used in the field agrees with the analysis results from the long-term observation data obtained with their homogeneity guaranteed. To achieve this goal, the research was conducted as follows. First the present conditions of the observation stations, the land level standard, and the sea level standard were analyzed to set up a time series model formula for representing them. To secure the homogeneity of the time series, each component was separated. Lastly the mean sea level used in the field was assessed based on the results obtained form the analysis of the time series.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권4호
• /
• pp.1232-1245
• /
• 2021

In this study, prediction of product sales as they relate to changes in temperature is proposed. This model uses long short-term memory (LSTM), which has shown excellent performance for time series predictions. For verification of the proposed sales prediction model, the sales of short pants, flip-flop sandals, and winter outerwear are predicted based on changes in temperature and time series sales data for clothing products collected from 2015 to 2019 (a total of 1,865 days). The sales predictions using the proposed model show increases in the sale of shorts and flip-flops as the temperature rises (a pattern similar to actual sales), while the sale of winter outerwear increases as the temperature decreases.

• 한국수자원학회논문집
• /
• 제42권10호
• /
• pp.809-824
• /
• 2009

한정된 기간의 짧은 유출량 기록을 갖는 댐 유역에서의 수자원 시스템 거동예측은 수문학적 지속성여부에 대한 판단이 선행 되어야 하며 가용한 시계열자료에 대한 추계학적 분석을 통하여 실시하여야 한다. 본 연구에서는 계절형 ARIMA모형을 통하여 안동댐 유역의 강우량, 증발량 및 유출량 시계열자료로 월별 수문시스템 거동을 예측하였으며, 예측된 결과를 토대로 TANK모형과 ARIMA+TANK결합모형에 의한 장기유출모의를 실시하였다. 분석결과 관측자료의 특성을 비교적 잘 반영 하였으며, 댐 유입량 예측을 위한 추계학적 결합모형의 적용가능성을 검토하였다. 이는 상대적으로 유출량자료의 보유년한이 짧은 대상유역의 시계열 수문인자 예측을 통한 유출모의의 적용으로 수자원의 중 장기 전략수립에 도움이 되리라 사료된다.