• The Journal of the Korea Contents Association
• /
• v.20 no.12
• /
• pp.49-57
• /
• 2020

This study predicts the ratio of added value, which represents the competitiveness of export industries in South Korea, using various machine learning techniques. To enhance the accuracy and stability of prediction, forecast combination technique was applied to predicted values of machine learning techniques. In particular, this study improved the efficiency of the prediction process by selecting key variables out of many variables using recursive feature elimination method and applying them to machine learning techniques. As a result, it was found that the predicted value by the forecast combination method was closer to the actual value than the predicted values of the machine learning techniques. In addition, the forecast combination method showed stable prediction results unlike volatile predicted values by machine learning techniques.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.373-373
• /
• 2021

Rainfall forecasting is an important issue that is applied in many areas, such as agriculture, flood warning, and water resources management. In this context, this study proposed a statistical and machine learning-based forecasting model for monthly rainfall. The Bayesian Gaussian process was chosen to optimize the hyperparameters of the Stacked Long Short-term memory (SLSTM) model. The proposed SLSTM model was applied for predicting monthly precipitation of Seoul station, South Korea. Data were retrieved from the Korea Meteorological Administration (KMA) in the period between 1960 and 2019. Four schemes were examined in this study: (i) prediction with only rainfall; (ii) with deseasonalized rainfall; (iii) with rainfall and minimum temperature; (iv) with deseasonalized rainfall and minimum temperature. The error of predicted rainfall based on the root mean squared error (RMSE), 16-17 mm, is relatively small compared with the average monthly rainfall at Seoul station is 117mm. The results showed scheme (iv) gives the best prediction result. Therefore, this approach is more straightforward than the hydrological and hydraulic models, which request much more input data. The result indicated that a deep learning network could be applied successfully in the hydrology field. Overall, the proposed method is promising, given a good solution for rainfall prediction.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2022.05a
• /
• pp.150-150
• /
• 2022

This study investigates the roles of decomposition methods on high accuracy in daily rainfall prediction from light gradient boosting machine (LightGBM) algorithm. Here, empirical mode decomposition (EMD) and singular spectrum analysis (SSA) methods were considered to decompose and reconstruct input time series into trend terms, fluctuating terms, and noise components. The decomposed time series from EMD and SSA methods were used as input data for LightGBM algorithm in two hybrid models, including empirical mode-based light gradient boosting machine (EMDGBM) and singular spectrum analysis-based light gradient boosting machine (SSAGBM), respectively. A total of four parameters (i.e., temperature, humidity, wind speed, and rainfall) at a daily scale from 2003 to 2017 is used as input data for daily rainfall prediction. As results from statistical performance indicators, it indicates that the SSAGBM model shows a better performance than the EMDGBM model and the original LightGBM algorithm with no decomposition methods. It represents that the accuracy of LightGBM algorithm in rainfall prediction was improved with the SSA method when using multivariate dataset.

• Journal of Korean Association for Spatial Structures
• /
• v.24 no.2
• /
• 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.

• Journal of the Korean Professional Engineers Association
• /
• v.32 no.5
• /
• pp.56-62
• /
• 1999

• Journal of Environmental Science International
• /
• v.24 no.9
• /
• pp.1131-1138
• /
• 2015

Radon exhalation rates have been determined for samples of concrete, gypsum board, marble, and tile among building materials that are used in domestic construction environment. Radon emanation was measured using the closed chamber method based on CR-39 nuclear track detectors. The radon concentrations in apartments of 100 households in Seoul, Busan and Gyeonggi Provinces were measured to verify the prediction model of indoor radon concentration. The results obtained by the four samples showed the largest radon exhalation rate of $0.34314Bq/m^2{\cdot}h$ for sample concrete. The radon concentration contribution to indoor radon in the house due to exhalation from the concrete was $31.006{\pm}7.529Bq/m^3$. The difference between the prediction concentration and actual measured concentration was believed to be due to the uncertainty resulting from the model implementation.

• Asian-Australasian Journal of Animal Sciences
• /
• v.11 no.5
• /
• pp.580-585
• /
• 1998

The study was conducted to determine if variation in protein yield can be explained by expressions of early lactation somatic cell score (SCS) and if prediction can be improved by including SCS among the predictors. A data set was prepared (n = 663,438) from Wisconsin Dairy Improvement Association (USA) records for protein yield with sample days near 20. Stepwise regression was used requiring F statistic (p < .01) for any variable to stay in the model. Separate analyses were run for 12 combinations of four seasons and first three parities. Selection of SCS variables was not consistent across seasons or lactations. Coefficients of detennination ($R^2$) ranged from 51 to 61% with higher values for earlier lactations. Including any expression of SCS in the prediction equations improved $R^2$ by < 1 %. SCS was associated with milk yield on the sample day, but the association was not strong enough to improve the prediction of future yield when other expressions of milk yield were in the model.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.14 no.4
• /
• pp.116-127
• /
• 2011

This study conducted landslide susceptibility analysis using logistic regression. The performance of prediction model needs to be evaluated considering two aspects such as a goodness of fit and a prediction accuracy. Thus to gain more objective prediction results in this study, the prediction performance of the applied model was evaluated considering two such evaluation aspects. The selected study area is located between Inje-eup and Buk-myeon in the middle of Kwangwon. Landslides in the study area were caused by heavy rain in 2006. Landslide causal factors were extracted from topographic map, forest map and soil map. The evaluation of prediction model was assessed based on the area under the curve of the cumulative gain chart. From the results of experiments, 87.9% in the goodness of fit and 84.8% in the cross validation were evaluated, showing good prediction accuracies and not big difference between the results of the two evaluation methods. The results can be interpreted in terms of the use of environmental factors which are highly related to landslide occurrences and the accuracy of the prediction model.

• The Journal of the Korea Contents Association
• /
• v.9 no.5
• /
• pp.332-336
• /
• 2009

Functional prediction of unannotated proteins is one of the most important tasks in yeast genomics. Analysis of a protein-protein interaction network leads to a better understanding of the functions of unannotated proteins. A number of researches have been performed for the functional prediction of unannotated proteins from a protein-protein interaction network. A chi-square method is one of the existing methods for the functional prediction of unannotated proteins from a protein-protein interaction network. But, the method does not consider the topology of network. In this paper, we propose a novel method that is able to predict specific molecular functions for unannotated proteins from a protein-protein interaction network. To do this, we investigated all protein interaction DBs of yeast in the public sites such as MIPS, DIP, and SGD. For the prediction of unannotated proteins, we employed a modified chi-square measure based on neighborhood counting and we assess the prediction accuracy of protein function from a protein-protein interaction network.

• The Journal of the Korea Contents Association
• /
• v.18 no.9
• /
• pp.623-632
• /
• 2018

Both investors and researchers are attentive to the prediction of stock price movement directions since the accurate prediction plays an important role in strategic decision making on stock trading. According to previous studies, taken together, one can see that different factors are considered depending on stock markets and prediction periods. This paper aims to analyze what data mining techniques show better performance with some representative index and stock price datasets in the Korea stock market. In particular, extreme gradient boosting technique, proving itself to be the fore-runner through recent open competitions, is applied to the prediction problem. Its performance has been analyzed in comparison with other data mining techniques reported good in the prediction of stock price movement directions such as random forests, support vector machines, and artificial neural networks. Through experiments with the index/price datasets of 12 years, it is identified that the gradient boosting technique is the best in predicting the movement directions after 1 to 4 days with a few partial equivalence to the other techniques.