• 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.

• Journal of Communications and Networks
• /
• 제13권6호
• /
• pp.621-624
• /
• 2011

With the rapid growth of internet traffic, accurate and reliable prediction of internet traffic has been a key issue in network management and planning. This paper proposes an autoregressive-generalized autoregressive conditional heteroscedasticity (AR-GARCH) error model for forecasting internet traffic and evaluates its performance by comparing it with seasonal autoregressive integrated moving average (ARIMA) models in terms of root mean square error (RMSE) criterion. The results indicated that the seasonal AR-GARCH models outperformed the seasonal ARIMA models in terms of forecasting accuracy with respect to the RMSE criterion.

• International Journal of Advanced Culture Technology
• /
• 제11권3호
• /
• pp.310-314
• /
• 2023

The purpose of this study is to predict the remaining capacity of lithium-ion batteries and evaluate their performance using five artificial intelligence models, including linear regression analysis, decision tree, random forest, neural network, and ensemble model. We is in the study, measured Excel data from the CS2 lithium-ion battery was used, and the prediction accuracy of the model was measured using evaluation indicators such as mean square error, mean absolute error, coefficient of determination, and root mean square error. As a result of this study, the Root Mean Square Error(RMSE) of the linear regression model was 0.045, the decision tree model was 0.038, the random forest model was 0.034, the neural network model was 0.032, and the ensemble model was 0.030. The ensemble model had the best prediction performance, with the neural network model taking second place. The decision tree model and random forest model also performed quite well, and the linear regression model showed poor prediction performance compared to other models. Therefore, through this study, ensemble models and neural network models are most suitable for predicting the remaining capacity of lithium-ion batteries, and decision tree and random forest models also showed good performance. Linear regression models showed relatively poor predictive performance. Therefore, it was concluded that it is appropriate to prioritize ensemble models and neural network models in order to improve the efficiency of battery management and energy systems.

• 시스템엔지니어링학술지
• /
• 제16권1호
• /
• pp.58-67
• /
• 2020

A big data processing method to predict solar power generation using systems engineering approach is developed in this work. For developing analytical method, linear model (LM), support vector machine (SVN), and artificial neural network (ANN) technique are chosen. As evaluation indices, the cross-correlation and the mean square root of prediction error (RMSEP) are used. From multi-variable comparison test, it was found that ANN methodology provides the highest correlation and the lowest RMSEP.

• Computers and Concrete
• /
• 제5권5호
• /
• pp.461-473
• /
• 2008

The paper explores the potential of Support Vector Machines (SVM) approach in predicting 28-day compressive strength and slump flow of self-compacting concrete. Total of 80 data collected from the exiting literature were used in present work. To compare the performance of the technique, prediction was also done using a back propagation neural network model. For this data-set, RBF kernel worked well in comparison to polynomial kernel based support vector machines and provide a root mean square error of 4.688 (MPa) (correlation coefficient=0.942) for 28-day compressive strength prediction and a root mean square error of 7.825 cm (correlation coefficient=0.931) for slump flow. Results obtained for RMSE and correlation coefficient suggested a comparable performance by Support Vector Machine approach to neural network approach for both 28-day compressive strength and slump flow prediction.

• 산업식품공학
• /
• 제14권1호
• /
• pp.75-79
• /
• 2010

시중 즉석 면류의 관능적 성질과 back extrusion test 데이터에 대하여 partial least square regression(PLSR)을 실시하였다. 즉석유탕면 8종과 즉석비유탕면 2종에 대한 관능적 속성으로서 경도(A), 탄성(B), 껄끄러운 정도(C), 이에 박히는 정도(D), 굵기감(E)를 검사하였고, 실험 데이터로 힘-변형 곡선 전체를 사용하였다. PLSR의 회귀계수는 힘-변형곡선의 압착단계, 항복단계, 압출단계로 크게 구분되어 각관능속성에 대한 특유의 양 또는 음의 효과를 나타냈다. PLSR의 상관계수는 E>D>A>B>C, 오차(root mean square error of prediction expressed in sensory units)는 D>C>E>B>A, 예측능(relative ability of prediction)는 D>C>E>B>A 로 나타나 종합적으로 '이에 박히는 정도'가 PLSR의 적용에 가장 우수하게 나타났다. '경도'는 예측능은 낮았지만 상관성은 높아서 시료간 순위의 결정에 합당하게 평가되었다.

• Geomechanics and Engineering
• /
• 제30권5호
• /
• pp.437-448
• /
• 2022

Alluvial soil is challenging to work with due to its high compressibility. Thus, consolidation settlement of this type of soil should be accurately estimated. Accurate estimation of the consolidation settlement of alluvial soil requires accurate prediction of compressibility parameters. Geotechnical engineers usually use empirical correlations to estimate these compressibility parameters. However, no attempts have been made to develop correlations to estimate compressibility parameters of alluvial soil. Thus, this paper aims to develop new models to predict the compression and recompression indices (Cc and Cr) of alluvial soils. As part of the study, geotechnical laboratory tests have been conducted on large number of undisturbed samples of local alluvial soil. The obtained results from these tests in addition to available results from the literature from different parts in the world have been compiled to form the database of this study. This database is then employed to examine the accuracy of the available empirical correlations of the compressibility parameters and to develop the new models to estimate the compressibility parameters using the nonlinear regression analysis. The accuracy of the new models has been accessed using mean absolute error, root mean square error, mean, percentage of predictions with error range of ±20%, percentage of predictions with error range of ±30%, and coefficient of determination. It was found that the new models outperform the available correlations. Thus, these models can be used by geotechnical engineers with more confidence to predict Cc and Cr.

• 전기전자학회논문지
• /
• 제23권1호
• /
• pp.120-126
• /
• 2019

최근 에너지 인터넷에서 지능형 원격검침 인프라를 이용하여 확보된 대량의 전력사용데이터를 기반으로 효과적인 전력수요 예측을 위해 다양한 기계학습기법에 관한 연구가 활발히 진행되고 있다. 본 연구에서는 전력량 데이터와 같은 시계열 데이터에 대해 효율적으로 패턴인식을 수행하는 인공지능 네트워크인 Gated Recurrent Unit(GRU)을 기반으로 딥 러닝 모델을 제안하고, 실제 가정의 전력사용량 데이터를 토대로 예측 성능을 분석한다. 제안한 학습 모델의 예측 성능과 기존의 Long Short Term Memory (LSTM) 인공지능 네트워크 기반의 전력량 예측 성능을 비교하며, 성능평가 지표로써 Mean Squared Error (MSE), Mean Absolute Error (MAE), Forecast Skill Score, Normalized Root Mean Squared Error (RMSE), Normalized Mean Bias Error (NMBE)를 이용한다. 실험 결과에서 GRU기반의 제안한 시계열 데이터 예측 모델의 전력량 수요 예측 성능이 개선되는 것을 확인한다.

• 한국공간구조학회논문집
• /
• 제24권2호
• /
• pp.83-90
• /
• 2024

Machine learning is widely applied to various engineering fields. In structural engineering area, machine learning is generally used to predict structural responses of building structures. The aging deterioration of reinforced concrete structure affects its structural behavior. Therefore, the aging deterioration of R.C. structure should be consider to exactly predict seismic responses of the structure. In this study, the machine learning based seismic response prediction model was developed. To this end, four machine learning algorithms were employed and prediction performance of each algorithm was compared. A 3-story coupled shear wall structure was selected as an example structure for numerical simulation. Artificial ground motions were generated based on domestic site characteristics. Elastic modulus, damping ratio and density were changed to considering concrete degradation due to chloride penetration and carbonation, etc. Various intensity measures were used input parameters of the training database. Performance evaluation was performed using metrics like root mean square error, mean square error, mean absolute error, and coefficient of determination. The optimization of hyperparameters was achieved through k-fold cross-validation and grid search techniques. The analysis results show that neural networks and extreme gradient boosting algorithms present good prediction performance.

• 한국가금학회지
• /
• 제47권2호
• /
• pp.107-114
• /
• 2020

This study was conducted to investigate the variation in nutrient composition of oilseed meals and to develop prediction equations for amino acid concentrations. Energy and nutrient contents were determined in a total of 1,380 feed ingredient samples including copra byproducts, corn distillers, dried grains with solubles, palm kernel byproducts, and soybean meal. The ingredient samples were imported to the Republic of Korea between 2006 and 2015. Data were analyzed using the MIXED procedure of SAS. The regression procedure of SAS was used to generate the prediction equation for the lysine concentration using the crude protein (CP) concentration as an independent variable. The concentrations of moisture, gross energy, CP, ether extract, crude fiber, ash, calcium, phosphorus, lysine, methionine, cysteine, and threonine in tested oilseed meals differed (P<0.05) depending on producing countries. The prediction equations for amino acid concentrations (% as-is basis) in the oilseed meals are: lysine = -1.08 + 0.080 × CP (root mean square error = 0.244, R² = 0.924, and P<0.001); threonine = -0.297 + 0.044 × CP (root mean square error = 0.099, R² = 0.958, and P<0.001). In conclusion, energy and nutrient compositions vary in the oilseed meals depending on the producing countries. Moreover, the crude protein concentration can be used as a suitable independent variable for estimating lysine and threonine concentrations in the oilseed meals.