• Transactions of Materials Processing
• /
• v.29 no.5
• /
• pp.282-289
• /
• 2020

Flexible roll forming is an advanced sheet-metal-forming process that allows the production of parts with various cross-sections. During the flexible process, material is subjected to three-dimensional deformation such as transverse bending, inhomogeneous elongations, or contraction. Because of the effects of process variables on the quality of the roll-formed products, the approaches used to investigate the roll-forming process have been largely dependent on experience and trial- and-error methods. Web-warping is one of the major shape defects encountered in flexible roll forming. In this study, an SVR model was developed to predict the web-warping during the flexible roll forming process. In the development of the SVR model, three process parameters, namely the forming-roll speed condition, leveling-roll height, and bend angle were considered as the model inputs, and the web-warping height was used as the response variable for three blank shapes; rectangular, concave, and convex shape. MATLAB software was used to train the SVR model and optimize three hyperparameters (λ, ε, and γ). To evaluate the SVR model performance, the statistical analysis was carried out based on the three indicators: the root-mean-square error, mean absolute error, and relative root-mean-square error.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.34 no.4
• /
• pp.383-390
• /
• 2016

Remote sensing data has been widely used in the estimation of crop yields by employing statistical methods such as regression model. Machine learning, which is an efficient empirical method for classification and prediction, is another approach to crop yield estimation. This paper described the corn yield estimation in Iowa State using four machine learning approaches such as SVM (Support Vector Machine), RF (Random Forest), ERT (Extremely Randomized Trees) and DL (Deep Learning). Also, comparisons of the validation statistics among them were presented. To examine the seasonal sensitivities of the corn yields, three period groups were set up: (1) MJJAS (May to September), (2) JA (July and August) and (3) OC (optimal combination of month). In overall, the DL method showed the highest accuracies in terms of the correlation coefficient for the three period groups. The accuracies were relatively favorable in the OC group, which indicates the optimal combination of month can be significant in statistical modeling of crop yields. The differences between our predictions and USDA (United States Department of Agriculture) statistics were about 6-8 %, which shows the machine learning approaches can be a viable option for crop yield modeling. In particular, the DL showed more stable results by overcoming the overfitting problem of generic machine learning methods.

• Journal of Sasang Constitutional Medicine
• /
• v.32 no.2
• /
• pp.10-21
• /
• 2020

Objectives Genome-wide association studies(GWAS) is a useful method to identify genetic associations for various phenotypes. The purpose of this study was to develop predictive models for Sasang constitution types using genetic factors. Methods The genotypes of the 1,999 subjects was performed using Axiom Precision Medicine Research Array (PMRA) by Life Technologies. All participants were prescribed Sasang Constitution-specific herbal remedies for the treatment, and showed improvement of original symptoms as confirmed by Korean medicine doctor. The genotypes were imputed by using the IMPUTE program. Association analysis was conducted using a logistic regression model to discover Single Nucleotide Polymorphism (SNP), adjusting for age, sex, and BMI. Results & Conclusions We developed models to predict Korean medicine constitution types using identified genectic factors and sex, age, BMI using Random Forest (RF), Support Vector Machine (SVM), and Neural Network (NN). Each maximum Area Under the Curve (AUC) of Teaeum, Soeum, Soyang is 0.894, 0.868, 0.767, respectively. Each AUC of the models increased by 6~17% more than that of models except for genetic factors. By developing the predictive models, we confirmed usefulness of genetic factors related with types. It demonstrates a mechanism for more accurate prediction through genetic factors related with type.

• The Bulletin of The Korean Astronomical Society
• /
• v.38 no.1
• /
• pp.61.1-61.1
• /
• 2013

In this study we apply Support Vector Machine (SVM) to the prediction of geo-effective halo coronal mass ejections (CMEs). The SVM, which is one of machine learning algorithms, is used for the purpose of classification and regression analysis. We use halo and partial halo CMEs from January 1996 to April 2010 in the SOHO/LASCO CME Catalog for training and prediction. And we also use their associated X-ray flare classes to identify front-side halo CMEs (stronger than B1 class), and the Dst index to determine geo-effective halo CMEs (stronger than -50 nT). The combinations of the speed and the angular width of CMEs, and their associated X-ray classes are used for input features of the SVM. We make an attempt to find the best model by using cross-validation which is processed by changing kernel functions of the SVM and their parameters. As a result we obtain statistical parameters for the best model by using the speed of CME and its associated X-ray flare class as input features of the SVM: Accuracy=0.66, PODy=0.76, PODn=0.49, FAR=0.72, Bias=1.06, CSI=0.59, TSS=0.25. The performance of the statistical parameters by applying the SVM is much better than those from the simple classifications based on constant classifiers.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2002.12a
• /
• pp.162-165
• /
• 2002

Q-learning은 강화학습의 한 방법으로서, 여러 분야에 널리 응용되고 있는 기법이다. 최근에는 Linear Quadratic Regulation(이하 LQR) 문제에 성공적으로 적용된 바 있는데, 특히, 시스템모델의 파라미터에 대한 구체적인 정보가 없는 상태에서 적절한 입력과 출력만을 가지고 학습을 통해 문제를 해결할 수 있어서 상황에 따라서 매우 실용적인 대안이 될 수 있다. Neural Q-learning은 이러한 Q-learning의 Q-value를 MLP(multilayer perceptron) 신경망의 출력으로 대치시킴으로써, 비선형 시스템의 최적제어 문제를 다룰 수 있게 한 방법이다. 그러나, Neural Q방식은 신경망의 구조를 먼저 결정한 후 역전파 알고리즘을 이용하여 학습하는 절차를 취하기 때문에, 시행착오를 통하여 신경망 구조를 결정해야 한다는 점, 역전파 알고리즘의 적용으로 인해 신경망의 연결강도 값들이 지역적 최적해로 수렴한다는 점등의 문제점을 상속받는 한계가 있다. 따라서, 본 논문에서는 Neural-0 학습의 도구로, 역전파 알고리즘으로 학습되는 MLP 신경망을 사용하는 대신 최근 들어 여러 분야에서 그 성능을 인정받고 있는 서포트 벡터 학습법을 사용하는 방법을 택하여, $\varepsilon$-SVR(Epsilon Support Vector Regression)을 이용한 Q-value 근사 기법을 제안하고 관련 수식을 유도하였다. 그리고, 모의 실험을 통하여, 제안된 서포트 벡터학습 기반 Neural-Q 방법의 적용 가능성을 알아보았다.

• Journal of Information Processing Systems
• /
• v.10 no.2
• /
• pp.314-333
• /
• 2014

When analyzing default predictions in real estate companies, the number of non-defaulted cases always greatly exceeds the defaulted ones, which creates the two-class imbalance problem. This lowers the ability of prediction models to distinguish the default sample. In order to avoid this sample selection bias and to improve the prediction model, this paper applies a minority sample generation approach to create new minority samples. The logistic regression, support vector machine (SVM) classification, and neural network (NN) classification use an imbalanced dataset. They were used as benchmarks with a single prediction model that used a balanced dataset corrected by the minority samples generation approach. Instead of using prediction-oriented tests and the overall accuracy, the true positive rate (TPR), the true negative rate (TNR), G-mean, and F-score are used to measure the performance of default prediction models for imbalanced dataset. In this paper, we describe an empirical experiment that used a sampling of 14 default and 315 non-default listed real estate companies in China and report that most results using single prediction models with a balanced dataset generated better results than an imbalanced dataset.

• Journal of The Geomorphological Association of Korea
• /
• v.23 no.3
• /
• pp.67-78
• /
• 2016

Soil carbon(C) is an essential property for characterizing soil quality. Understanding spatial patterns of soil C is particularly limited for mountain areas. This study aims to predict the spatial pattern of soil C using terrain analysis in a steep mountainous area. Specifically, model performances and prediction uncertainties were investigated based on the number of resampling repetitions. Further, important predictors for soil C were also identified. Finally, the spatial distribution of uncertainty was analyzed. A total of 91 soil samples were collected via conditioned latin hypercube sampling and a digital soil C map was developed using support vector regression which is one of the powerful machine learning methods. Results showed that there were no distinct differences of model performances depending on the number of repetitions except for 10-fold cross validation. For soil C, elevation and surface curvature were selected as important predictors by recursive feature elimination. Soil C showed higher values in higher elevation and concave slopes. The spatial pattern of soil C might possibly reflect lateral movement of water and materials along the surface configuration of the study area. The higher values of uncertainty in higher elevation and concave slopes might be related to geomorphological characteristics of the research area and the sampling design. This study is believed to provide a better understanding of the relationship between geomorphology and soil C in the mountainous ecosystem.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2019.05a
• /
• pp.115-115
• /
• 2019

하천수 흐름예측에 대한 연구는 대부분 WRF-Hydro와 같은 과정기반 모델링 시스템을 이용한다. 과정기반 모델링 시스템은 물리적 현상을 일반화한 수식으로 구성되어있다. 일반화된 수식은 불확실성을 내포하고 있으며 지역적 특성도 반영하지 못한다. 특히 수식에 사용되는 입력자료는 측정값으로 오차가 존재한다. 따라서 과정기반 모델링 시스템 예측결과는 계통오차와 우연오차가 존재한다. 현재 매개변수 보정을 통해 예측결과를 개선하는 방법을 사용하고 있으나 한계가 있다. 본 연구는 이러한 한계를 극복하기 위해 상호보완적인 Data-driven 모델을 구축하여 과정기반 모델링 시스템 결과를 개선하고자 하였다. Data-driven 모델 구축을 위해 머신러닝 기법인 instance-based weighting(IBW)과 support vector regression(SVR)을 사용하였다. 구축된 Data-driven 모델은 한반도 지역 주요 저수지 및 호수의 하천수 흐름예측을 통해 검증하였다. 검증을 위해 과정기반 모델링 시스템으로 WRF-Hydro를 구동하였다. 입력자료는 기상청의 국지수치예측모델자료(LDAPS), HydroSHEDS의 수치표고모델자료(DEM), 국가지리정보원의 저수지 및 호수 연속수치지형도를 사용하였다. 본 연구를 통해 구축된 Data-driven모델은 기존 과정기반 모델링 시스템의 오류수정 한계를 머신러닝을 이용하여 개선할 수 있는 가능성을 제시하였다.

• Journal of Korean Society of Water and Wastewater
• /
• v.35 no.4
• /
• pp.259-275
• /
• 2021

This study explored the usefulness and implications of the Bayesian hyperparameter optimization in developing species distribution models (SDMs). A variety of machine learning (ML) algorithms, namely, support vector machine (SVM), random forest (RF), boosted regression tree (BRT), XGBoost (XGB), and Multilayer perceptron (MLP) were used for predicting the occurrence of four benthic macroinvertebrate species. The Bayesian optimization method successfully tuned model hyperparameters, with all ML models resulting an area under the curve (AUC) > 0.7. Also, hyperparameter search ranges that generally clustered around the optimal values suggest the efficiency of the Bayesian optimization in finding optimal sets of hyperparameters. Tree based ensemble algorithms (BRT, RF, and XGB) tended to show higher performances than SVM and MLP. Important hyperparameters and optimal values differed by species and ML model, indicating the necessity of hyperparameter tuning for improving individual model performances. The optimization results demonstrate that for all macroinvertebrate species SVM and RF required fewer numbers of trials until obtaining optimal hyperparameter sets, leading to reduced computational cost compared to other ML algorithms. The results of this study suggest that the Bayesian optimization is an efficient method for hyperparameter optimization of machine learning algorithms.

• Korean Journal of Remote Sensing
• /
• v.35 no.1
• /
• pp.137-149
• /
• 2019

Traffic emissions are the main cause of environmental pollution in cities and respiratory problems amongst people. This study developed a model based on an integration of support vector regression (SVR) algorithm and geographic information system (GIS) to map traffic carbon monoxide (CO) concentrations and produce prediction maps from micro level to macro level at a particular time gap in a day in a very densely populated area (Utara-Selatan Expressway-NKVE, Kuala Lumpur, Malaysia). The proposed model comprised two models: the first model was implemented to estimate traffic CO concentrations using the SVR model, and the second model was applied to create prediction maps at different times a day using the GIS approach. The parameters for analysis were collected from field survey and remote sensing data sources such as very-high-resolution aerial photos and light detection and ranging point clouds. The correlation coefficient was 0.97, the mean absolute error was 1.401 ppm and the root mean square error was 2.45 ppm. The proposed models can be effectively implemented as decision-making tools to find a suitable solution for mitigating traffic jams near tollgates, highways and road networks.