• Proceedings of the KSME Conference
• /
• 2001.11b
• /
• pp.288-293
• /
• 2001

A critical heat flux (CHF) prediction method using an artificial neural network (ANN) was evaluated for application to the high-heat-flux (HHF) subcooled flow boiling. The developed ANN predictions were compared with the experimental database consisting of a total of 3069 CHF data points. Also, the prediction performance by the ANN was compared with those by mechanistic models and a look up table technique. The parameter ranges of the experimental data are: $0.33{\leq}D{\leq}37.5mm$, $0.002{\leq}L{\leq}4m$, $0.37{\leq}G{\leq}134Mg/m^2s$, $0.1{\leq}P{\leq}20MPa$, $50\leq{\Delta}h_{sub,in}\leq1660kJ/kg$, and $1.1{\leq}q_{CHF}\leq276MW/m^2$. $276MW/m^2$. It was found that 91.5% of the total data points were predicted within $a{\pm}20%$ error band, which showed the best prediction performance among the existing CHF prediction methods considered.

• Journal of the Korean Data and Information Science Society
• /
• v.21 no.1
• /
• pp.185-194
• /
• 2010

In recommender systems which are used widely at e-commerce, collaborative filtering needs the information of user-ratings and neighbor user-ratings. These are an important value for recommendation in recommender systems. We investigate the in-formation of rating in NBCFA (neighbor Based Collaborative Filtering Algorithm), we suggest new algorithm that improve prediction accuracy of recommender system. After we analyze relations between two variable and Error Value (EV), we suggest new algorithm and apply it to fitted line. This fitted line uses Least Squares Method (LSM) in Exploratory Data Analysis (EDA). To compute the prediction value of new algorithm, the fitted line is applied to experimental data with fitted function. In order to confirm prediction accuracy of new algorithm, we applied new algorithm to increased sparsity data and total data. As a result of study, the prediction accuracy of recommender system in the new algorithm was more improved than current algorithm.

• Journal of Communications and Networks
• /
• v.12 no.1
• /
• pp.5-10
• /
• 2010

This paper introduces a new fast motion estimation based on estimating a block matching error (i.e., sum of absolute difference (SAD)) between blocks which can eliminate an impossible candidate block much earlier than a conventional partial distortion elimination (PDE) scheme. The basic idea of the proposed scheme is based on predicting the total SAD of a candidate block using its partial SAD. In particular, in order to improve prediction accuracy and computational efficiency, a sub-sample based block matching and a selective pixel-based approaches are employed. In order to evaluate the proposed scheme, several baseline approaches are described and compared. The experimental results show that the proposed algorithm can reduce the computations by about 44% for motion estimation at the cost of 0.0005 dB quality degradation versus the general PDE algorithm.

• Food Science and Preservation
• /
• v.12 no.6
• /
• pp.608-612
• /
• 2005

Fourier transform-near infrared (FT-NIR) spectroscopy is a simple, rapid, non-destructive technique which can be used to make quantitative analysis of chemical composition in grain. An interest in total dietary fiber (TDF) of grain such as rice has been increased due to its beneficial effects for health. Since measuring methods for TDF content were highly depending on experimental technique and time consumptions, the application of FT-NIR spectroscopy to determine TDF content in milled rice. Results of enzymatic-gravimetric method were $1.17-1.92\%$ Partial least square (PLS) regression on raw NIR spectra to predict TDF content was developed Accuracy of prediction model for TDF content was certified for regression coefficient (r), standard error of estimation (SEE) and standard error of prediction (SEP). The r, SEE and SEP were 0.9705, 0.0464, and 0.0604, respectively. The results indicated that FT-NIR techniques could be very useful in the food industry and rice processing complex for determination of TDF in milled rice on real time analysis.

• Computers and Concrete
• /
• v.29 no.6
• /
• pp.433-444
• /
• 2022

Concrete's compressive strength is widely studied in order to understand many qualities and the grade of the concrete mixture. Conventional civil engineering tests involve time and resources consuming laboratory operations which results in the deterioration of concrete samples. Proposing efficient non-destructive models for the prediction of concrete compressive strength will certainly yield advancements in concrete studies. In this study, the efficiency of using radial basis function neural network (RBFNN) which is not common in this field, is studied for the concrete compressive strength prediction. Complementary studies with back propagation neural network (BPNN), which is commonly used in this field, have also been carried out in order to verify the efficiency of RBFNN for compressive strength prediction. A total of 13 input parameters, including novel ones such as cement's and fly ash's compositional information, have been employed in the prediction models with RBFNN and BPNN since all these parameters are known to influence concrete strength. Three different train: test ratios were tested with both models, while different hidden neurons, epochs, and spread values were introduced to determine the optimum parameters for yielding the best prediction results. Prediction results obtained by RBFNN are observed to yield satisfactory high correlation coefficients and satisfactory low mean square error values when compared to the results in the previous studies, indicating the efficiency of the proposed model.

• Journal of Electrical Engineering and Technology
• /
• v.13 no.3
• /
• pp.1089-1098
• /
• 2018

This study aims at developing and applying a hybrid model to the wind power prediction (WPP). The hybrid model for a very-short-term WPP (VSTWPP) is achieved through analytical data, multiple linear regressions and least square methods (MLR&LS). The data used in our hybrid model are based on the historical records of wind power from an offshore region. In this model, the WPP is achieved in four steps: 1) transforming historical data into ratios; 2) predicting the wind power using the ratios; 3) predicting rectification ratios by the total wind power; 4) predicting the wind power using the proposed rectification method. The proposed method includes one-step and multi-step predictions. The WPP is tested by applying different models, such as the autoregressive moving average (ARMA), support vector machine (SVM), and artificial neural network (ANN). The results of all these models confirmed the validity of the proposed hybrid model in terms of error as well as its effectiveness. Furthermore, forecasting errors are compared to depict a highly variable WPP, and the correlations between the actual and predicted wind powers are shown. Simulations are carried out to definitely prove the feasibility and excellent performance of the proposed method for the VSTWPP versus that of the SVM, ANN and ARMA models.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2021.11a
• /
• pp.30-31
• /
• 2021

This study aims to build a deep learning model that can predict the value of concrete mixing properties according to a given concrete strength value. A model was created for a total of 1,291 concrete data, including 8 characteristics related to concrete mixing elements and environment, and the compressive strength of concrete. As the deep learning model, DNN-3L-256N, which showed the best performance on the prior study, was used. The average value for each characteristic of the data set was used as the initial input value. In results, in the case of 'curing temperature', which had a narrow range of values in the existing data set, showed the lowest error rate with less than 1% error based on MAE. The highest error rate with an error of 12 to 14% for fly and bfs.

• Journal of Energy Engineering
• /
• v.28 no.4
• /
• pp.82-93
• /
• 2019

In this study, a new model is proposed to improve the problem of the decline of predict rate of heat demand on a particular date, such as a public holiday for the conventional heat demand forecasting system. The proposed model was the Four Season Mixed Heat Demand Prediction Neural Network Model, which showed an increase in the forecast rate of heat demand, especially for each type of forecast date (weekday/weekend/holiday). The proposed model was selected through the following process. A model with an even error for each type of forecast date in a particular season is selected to form the entire forecast model. To avoid shortening learning time and excessive learning, after each of the four different models that were structurally simplified were learning and a model that showed optimal prediction error was selected through various combinations. The output of the model is the hourly 24-hour heat demand at the forecast date and the total is the daily total heat demand. These forecasts enable efficient heat supply planning and allow the selection and utilization of output values according to their purpose. For daily heat demand forecasts for the proposed model, the overall MAPE improved from 5.3~6.1% for individual models to 5.2% and the forecast for holiday heat demand greatly improved from 4.9~7.9% to 2.9%. The data in this study utilized 34 months of heat demand data from a specific apartment complex provided by the Korea District Heating Corp. (January 2015 to October 2017).

• The Transactions of the Korea Information Processing Society
• /
• v.3 no.6
• /
• pp.1468-1472
• /
• 1996

In this study, the performance of the CART(Classification and Regression Tree) is compared with that of discriminant analysis method. In most experiments using bank data, discriminant analysis shows better performance in terms of the total cost. In contrast, most experiments using insurance data show that the CART is better than discriminant analysis in terms of the total cost. The contradictory result are analysed by using the characteristics of the data sets. The performances of both the Classification and Regression Tree and discriminant analysis depend on the parameters:failure prior probability, data used, type I error, type II error cost, and validation method.

• Journal of Korea Water Resources Association
• /
• v.55 no.spc1
• /
• pp.1295-1303
• /
• 2022

As the role of water distribution networks (WDNs) becomes more important, identifying abnormal events (e.g., pipe burst) rapidly and accurately is required. Since existing approaches such as field equipment-based detection methods have several limitations, model-based methods (e.g., machine learning based detection model) that identify abnormal events using hydraulic simulation models have been developed. However, no previous work has examined the impact of data uncertainties on the results. Thus, this study compares the effects of measurement error-induced pressure data uncertainty in WDNs. An artificial neural network (ANN) is used to predict nodal pressures and measurement errors are generated by using cumulative density function inverse sampling method that follows Gaussian distribution. Total of nine conditions (3 input datasets × 3 output datasets) are considered in the ANN model to investigate the impact of measurement error size on the prediction results. The results have shown that higher data uncertainty decreased ANN model's prediction accuracy. Also, the measurement error of output data had more impact on the model performance than input data that for a same measurement error size on the input and output data, the prediction accuracy was 72.25% and 38.61%, respectively. Thus, to increase ANN models prediction performance, reducing the magnitude of measurement errors of the output pressure node is considered to be more important than input node.