• 한국전자통신학회논문지
• /
• 제9권1호
• /
• pp.131-136
• /
• 2014

본 논문에서는 패션 상품 수요 예측을 위하여 ARIMA 모형과 웨이블렛 신경회로망 모형을 결합한 상품 수요 예측 알고리즘을 개발하였다. 제시된 방법을 검증하기 위하여 2008년에서 2012년까지의 H사의 패션 상품 데이터를 바탕으로 다양한 알고리즘을 축하고 제안한 방법의 정확도를 분석하였다. 실험 결과 ARIMA 모형은 MAPE가 5.179%, 웨이블렛 신경회로망은 4.553%, 제안한 ARIMA + 웨이블렛 신경회로망 모형은 4.448%로 나타나 성능이 우수한 것으로 나타났다. 따라서 제안된 방법을 사용할 경우 패션 상품 수요 예측을 위해 유용하게 활용할 수 있음을 보였다.

• Journal of the Korean Data and Information Science Society
• /
• 제27권2호
• /
• pp.275-284
• /
• 2016

정확한 전력수요 예측은 에너지 소비를 줄이고 전력수급의 불균형을 방지한다. 본 연구는 외부요인의 영향을 가장 적게 받는 특정 시간대의 일 단위 전력 수요량을 참조선 (reference line)으로 한 시계열모형을 세우고자 한다. 고려된 시계열모형은 슬라이딩 창을 이용한 이중 계절성 Holt-Winters 모형과 TBATS 모형이다. 시계열모형의 모수는 2009년 1월 4일부터 2011년 12월 31일까지 자료를 이용하여 추정되었으며, 2012년 1월 1일부터 2012년 12월 29일까지의 각 모형의 전력수요량을 예측하여 성능을 비교하였다. RMSE와 MAPE를 통해 예측 성능을 비교한 결과 TBATS 모형의 성능이 우수하였다.

• 조명전기설비학회논문지
• /
• 제18권5호
• /
• pp.105-111
• /
• 2004

본 논문에서는 실제 전력 수요 데이터를 이용하여 유효전력에 단기 부하 예측함에 있어 무효전력이 중요한 역할을 하는 것을 회귀 분석 검정 통계량으로 증명한다. 무효전력의 공급과 수요는 계통의 전압과 아주 밀접한 관계를 가지고 있으므로 계통전압을 관리하고 계통의 신뢰도를 높이기 위해서는 예측된 무효전력 수요에 따라 무효전력 공급계획을 별도로 수립하여 운영해야 한다. 따라서 본 논문에서는 다중 시계열 모델을 이용한 시전 예측방법을 이용하여 설명변수로 유효전력을 사용하여 부하의 무효전력을 예측 하였다.

• Journal of the Korean Wood Science and Technology
• /
• 제34권5호
• /
• pp.59-66
• /
• 2006

The thermal properties of wood flour, Hwangto, and maleated polyethylene (MAPE) reinforced HDPE composites were investigated in this study. The thermal behavior of reinforced wood polymer composites was characterized by means of thermogravimetric (TGA) and differential scanning calorimetric (DSC) analyses. Hwangto and MAPE were used as an inorganic filler and a coupling agent, respectively. According to TGA analysis, the increase of wood flour level increased the thermal degradation of composites in the early stage, but decreased in the late stage. On the other hand, Hwangto reinforced composites showed the higher thermal stability than virgin HDPE, from the determination of differential peak temperature ($DT_p$). Decomposition temperature of wood flour and/or Hwangto reinforced composites increased with increase of heating rate. From DSC analysis, melting temperature of reinforced composites little bit increased with the addition of wood flour or Hwangto. As the loading of wood flour or Hwangto to HDPE increased, overall enthalpy decreased. It showed that wood flour and Hwangto absorbed more heat energy for melting the reinforced composites. Hwangto reinforced composites required more heat energy than wood flour reinforced composites and virgin HDPE. Coupling agent gave no significant effect on the thermal properties of composites. Thermal analyses indicate that composites with Hwangto are more thermally stable than those without Hwangto.

• Journal of the Korean Data and Information Science Society
• /
• 제23권6호
• /
• pp.1093-1102
• /
• 2012

본 연구에서는 다변량시계열모형인 VAR (vector autoregressive regression)모형에 의하여 금리 스프레드의 시계열예측을 수행하였다. 국내외 거시경제변수들 중에서 교차상관분석 및 그랜져인과 검정을 통하여 상호간에 설명력이 있는 변수들을 추출하여 VAR모형의 시계열변수로 사용하였다. 마지막 12개월의 예측치에 대한 MAPE (mean absolute percentage error)와 RMSE (root mean square error)에 근거하여 모형의 예측력을 단일변량 시계열모형인 AR (autoregressive regression) 모형과 비교하였다.

• Computers and Concrete
• /
• 제19권5호
• /
• pp.467-475
• /
• 2017

The purpose of this study is to establish a prediction model for the electrical resistivity ($E_r$) of self-consolidating concrete by using waste LCD (liquid crystal display) glass as part of the fine aggregate and then, to analyze the results obtained from a series of laboratory tests. A hyperbolic function is used to perform nonlinear multivariate regression analysis of the electrical resistivity prediction model, with parameters such as water-binder ratio (w/b), curing age (t) and waste glass content (G). Furthermore, the relationship of compressive strength and electrical resistivity of waste LCD glass concrete is also found by a logarithm function, while compressive strength is evaluated by the electrical resistivity of non-destructive testing (NDT). According to relative regression analysis, the electrical resistivity and compressive strength prediction models are developed, and the results show that a good agreement is obtained using the proposed prediction models. From the comparison between the predicted analysis values and test results, the MAPE value of electrical resistivity is 17.0-18.2% and less than 20%, the MAPE value of compressive strength evaluated by $E_r$ is 5.9-10.6% and nearly less than 10%. Therefore, the prediction models established in this study have good predictive ability for electrical resistivity and compressive strength of waste LCD glass concrete. However, further study is needed in regard to applying the proposed prediction models to other ranges of mixture parameters.

• 한국멀티미디어학회논문지
• /
• 제24권9호
• /
• pp.1251-1260
• /
• 2021

This paper discusses missing data processing using simple moving average (SMA) and kalman filter. Also SMA and kalman predictive value are made a comparative study. Time series analysis is a generally method to deals with time series data in photovoltaic field. Photovoltaic system records data irregularly whenever the power value changes. Irregularly recorded data must be transferred into a consistent format to get accurate results. Missing data results from the process having same intervals. For the reason, it was imputed using SMA and kalman filter. The kalman filter has better performance to observed data than SMA. SMA graph is stepped line graph and kalman filter graph is a smoothing line graph. MAPE of SMA prediction is 0.00737%, MAPE of kalman prediction is 0.00078%. But time complexity of SMA is O(N) and time complexity of kalman filter is O(D²) about D-dimensional object. Accordingly we suggest that you pick the best way considering computational power.

• 한국공간구조학회논문집
• /
• 제21권2호
• /
• pp.99-110
• /
• 2021

This study presents the estimation of crack depth by analyzing temperatures extracted from thermal images and environmental parameters such as air temperature, air humidity, illumination. The statistics of all acquired features and the correlation coefficient among thermal images and environmental parameters are presented. The concrete crack depths were predicted by four different machine learning models: Multi-Layer Perceptron (MLP), Random Forest (RF), Gradient Boosting (GB), and AdaBoost (AB). The machine learning algorithms are validated by the coefficient of determination, accuracy, and Mean Absolute Percentage Error (MAPE). The AB model had a great performance among the four models due to the non-linearity of features and weak learner aggregation with weights on misclassified data. The maximum depth 11 of the base estimator in the AB model is efficient with high performance with 97.6% of accuracy and 0.07% of MAPE. Feature importances, permutation importance, and partial dependence are analyzed in the AB model. The results show that the marginal effect of air humidity, crack depth, and crack temperature in order is higher than that of the others.

• 한국멀티미디어학회논문지
• /
• 제25권1호
• /
• pp.82-91
• /
• 2022

In this paper, time series prediction method of photovoltaic power is introduced using seasonal autoregressive integrated moving average (SARIMA). In order to obtain the best fitting model by a time series method in the absence of an environmental sensor, this research was used data below 50% of cloud cover. Three samples were extracted by time intervals from the raw data. After that, the best fitting models were derived from mean absolute percentage error (MAPE) with the minimum akaike information criterion (AIC) or beysian information criterion (BIC). They are SARIMA (1,0,0)(0,2,2)14, SARIMA (1,0,0)(0,2,2)28, SARIMA (2,0,3)(1,2,2)55. Generally parameter of model derived from BIC was lower than AIC. SARIMA (2,0,3)(1,2,2)55, unlike other models, was drawn by AIC. And the performance of models obtained by SARIMA was compared. MAPE value was affected by the seasonal period of the sample. It is estimated that long seasonal period samples include atmosphere irregularity. Consequently using 1 hour or 30 minutes interval sample is able to be helpful for prediction accuracy improvement.

• 한국정보전자통신기술학회논문지
• /
• 제17권4호
• /
• pp.183-189
• /
• 2024

본 연구는 시계열 데이터를 효과적으로 예측하기 위해 데이터를 Seasonal-Trend Decomposition on Loess 을 통해 추세, 계절성, 잔차 성분으로 분해한 후 추세 성분에는 ARIMA, 계절성 성분에는 Fourier Series Regression, 잔차 성분에는 XGBoost를 적용하는 하이브리드 예측 모델을 제안하였다. 또한, ARIMA, XGBoost, LSTM, EMD-ARIMA, CEEMDAN-LSTM 모델을 포함한 성능 비교 실험을 수행하여 각 모델의 예측 성능을 평가하였다. 실험 결과, 제안된 하이브리드 모델은 MAPE, MAAPE, RMSE 지표에서 각각 3.8%, 3.5%, 0.35로 가장 좋은 평가 지표 값을 보이며 기존의 단일 모델보다 우수한 성능을 보였다.