• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.10
• /
• pp.1296-1301
• /
• 2021

With the recent increase in diabetes incidence worldwide, research has been conducted to predict diabetes through various machine learning and deep learning technologies. In this work, we present a model for predicting diabetes using machine learning techniques with German Frankfurt Hospital data. We apply outlier handling using Interquartile Range (IQR) techniques and Pearson correlation and compare model-specific diabetes prediction performance with Decision Tree, Random Forest, Knn (k-nearest neighbor), SVM (support vector machine), Bayesian Network, ensemble techniques XGBoost, Voting, and Stacking. As a result of the study, the XGBoost technique showed the best performance with 97% accuracy on top of the various scenarios. Therefore, this study is meaningful in that the model can be used to accurately predict and prevent diabetes prevalent in modern society.

• The Korean Journal of Applied Statistics
• /
• v.34 no.2
• /
• pp.153-166
• /
• 2021

A main goal of pharmacogenomics studies is to predict individual's drug responsiveness based on high dimensional genetic variables. Due to a large number of variables, feature selection is required in order to reduce the number of variables. The selected features are used to construct a predictive model using machine learning algorithms. In the present study, we applied several hybrid feature selection methods such as combinations of logistic regression, ReliefF, TurF, random forest, and LASSO to a next generation sequencing data set of 400 epilepsy patients. We then applied the selected features to machine learning methods including random forest, gradient boosting, and support vector machine as well as a stacking ensemble method. Our results showed that the stacking model with a hybrid feature selection of random forest and ReliefF performs better than with other combinations of approaches. Based on a 5-fold cross validation partition, the mean test accuracy value of the best model was 0.727 and the mean test AUC value of the best model was 0.761. It also appeared that the stacking models outperform than single machine learning predictive models when using the same selected features.

• Biomedical Science Letters
• /
• v.1 no.1
• /
• pp.89-94
• /
• 1995

Considering the planar structure and nonpolar properity of benzo(a)pyrene(B(a)p) and the planar heme part of cytochrome P-450, stacking interaction is probable. MO calculation on B(a)P and heme part of cytochrome P-450 were carried out to dertermine probable stacking interaction models. In this case, orbital interaction is most important. Accordingly, the stacking positions have high eigen vector in frontier orbital and boning type between two molecules. In this way, five probate models were selected and examined by MN2 and MO method. The most probable .stacking interaction model which is the 4, 5, 6 positions of B(a)P overlap carbon atom and pyrrole ring of ring of heme group was determined.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.30 no.4 s.247
• /
• pp.409-419
• /
• 2006

The actuating performance of plate-type unimorph piezoelectric composite actuators having various stacking sequences was evaluated by three dimensional finite element analysis on the basis of thermal analogy model. Thermal residual stress distribution at each layer in an asymmetrically laminated plate with PZT ceramic layer and thermally induced dome height were predicted using classical laminated plate theory. Thermal analogy model was applied to a bimorph cantilever beam and LIPCA-C2 actuator in order to confirm its validity. Finite element analysis considering thermal residual deformation showed that the bending behavior of piezoelectric composite actuator subjected to electric loads was significantly different according to the stacking sequence, thickness of constituent PZT ceramic and boundary conditions. In particular, the increase of thickness of PZT ceramic led to the increase of the bending stiffness of piezoelectric composite actuator but it did not always lead to the decrease of actuation distance according to the stacking sequences of piezoelectric composite actuator. Therefore, it is noted that the actuating performance of unimorph piezoelectric composite actuator is rather affected by bending stiffness than actuation distance.

• Proceedings of the Korean Society For Composite Materials Conference
• /
• 2002.05a
• /
• pp.181-183
• /
• 2002

The accurate permeability for preform is critical to model and design the impregnation of fluid resin in the composite manufacturing process. In this study, the in-plane and transverse permeability for a woven fabric are predicted numerically through the coupled flow model which combines microscopic with macroscopic flow. The microscopic and macroscopic flow which are flows within the micro-unit and macro-unit cell, respectively, are calculated by using 3-D CVFEM(control volume finite element method). To avoid checker-board pressure field and improve the efficiency on numerical computation, A new interpolation function for velocity is proposed on the basis of analytic solutions. The permeability of plain woven fabric is measured through unidirectional flow experiment and compared with the permeability calculated numerically. Based on the good agreement of the results, the relationships between the permeability and the structures of preform such as the fiber volume fraction and stacking effect can be understood. The reverse and the simple stacking are taken in account. Unlike past literatures, this study is based on more realistic unit cell and the improved prediction of permeability can be achieved. It is observed that in-plane flow is more dominant than transverse flow in the real flow through preform and the stacking effect of multi-layered preform is negligible. Consequently, the proposed coupled flow model can be applied to modeling of real composite materials processing.

• Journal of Intelligence and Information Systems
• /
• v.26 no.2
• /
• pp.105-129
• /
• 2020

This study uses corporate data from 2012 to 2018 when K-IFRS was applied in earnest to predict default risks. The data used in the analysis totaled 10,545 rows, consisting of 160 columns including 38 in the statement of financial position, 26 in the statement of comprehensive income, 11 in the statement of cash flows, and 76 in the index of financial ratios. Unlike most previous prior studies used the default event as the basis for learning about default risk, this study calculated default risk using the market capitalization and stock price volatility of each company based on the Merton model. Through this, it was able to solve the problem of data imbalance due to the scarcity of default events, which had been pointed out as the limitation of the existing methodology, and the problem of reflecting the difference in default risk that exists within ordinary companies. Because learning was conducted only by using corporate information available to unlisted companies, default risks of unlisted companies without stock price information can be appropriately derived. Through this, it can provide stable default risk assessment services to unlisted companies that are difficult to determine proper default risk with traditional credit rating models such as small and medium-sized companies and startups. Although there has been an active study of predicting corporate default risks using machine learning recently, model bias issues exist because most studies are making predictions based on a single model. Stable and reliable valuation methodology is required for the calculation of default risk, given that the entity's default risk information is very widely utilized in the market and the sensitivity to the difference in default risk is high. Also, Strict standards are also required for methods of calculation. The credit rating method stipulated by the Financial Services Commission in the Financial Investment Regulations calls for the preparation of evaluation methods, including verification of the adequacy of evaluation methods, in consideration of past statistical data and experiences on credit ratings and changes in future market conditions. This study allowed the reduction of individual models' bias by utilizing stacking ensemble techniques that synthesize various machine learning models. This allows us to capture complex nonlinear relationships between default risk and various corporate information and maximize the advantages of machine learning-based default risk prediction models that take less time to calculate. To calculate forecasts by sub model to be used as input data for the Stacking Ensemble model, training data were divided into seven pieces, and sub-models were trained in a divided set to produce forecasts. To compare the predictive power of the Stacking Ensemble model, Random Forest, MLP, and CNN models were trained with full training data, then the predictive power of each model was verified on the test set. The analysis showed that the Stacking Ensemble model exceeded the predictive power of the Random Forest model, which had the best performance on a single model. Next, to check for statistically significant differences between the Stacking Ensemble model and the forecasts for each individual model, the Pair between the Stacking Ensemble model and each individual model was constructed. Because the results of the Shapiro-wilk normality test also showed that all Pair did not follow normality, Using the nonparametric method wilcoxon rank sum test, we checked whether the two model forecasts that make up the Pair showed statistically significant differences. The analysis showed that the forecasts of the Staging Ensemble model showed statistically significant differences from those of the MLP model and CNN model. In addition, this study can provide a methodology that allows existing credit rating agencies to apply machine learning-based bankruptcy risk prediction methodologies, given that traditional credit rating models can also be reflected as sub-models to calculate the final default probability. Also, the Stacking Ensemble techniques proposed in this study can help design to meet the requirements of the Financial Investment Business Regulations through the combination of various sub-models. We hope that this research will be used as a resource to increase practical use by overcoming and improving the limitations of existing machine learning-based models.

• Journal of the Korean Society for information Management
• /
• v.19 no.4
• /
• pp.35-51
• /
• 2002

Inductive learning and classification techniques have been employed in various research and applications that organize textual data to solve the problem of information access. In this study, we develop hybrid model combination methods which incorporate the concepts and techniques for multiple modeling algorithms to improve the accuracy of text classification, and conduct experiments to evaluate the performances of proposed schemes. Boosted stacking, one of the extended stacking schemes proposed in this study yields higher accuracy relative to the conventional model combination methods and single classifiers.

• Composites Research
• /
• v.31 no.1
• /
• pp.37-41
• /
• 2018

The aim of the current work is to characterise a piecewisely-integrated composite bumper beam based on the IIHS bumper crash protocol. IIHS bumper crash FE analysis for an aluminium type bumper beam was carried out to get the information about the dominant loading types at several regions in the bumper beam during crash. In the meantime, robust stacking sequences against tension and compression have been searched for using FE analysis of a coupon type model. After determining most effective stacking sequences for tension and compression, three-point bending simulation was preliminarily carried out to investigate the combination performance of them. Finally, IIHS bumper crash FE analysis for the piecewisely-integrated composite bumper beam, which consisted of the combination of tension effective stacking sequence and compression efficacious stacking sequence, was conducted and the result was compared with other types of composite bumper beams. It was found that the newly suggested piecewisely-integrated composite bumper beam showed superior crashworthy behaviour to those of uni-modal stacking sequence composite bumper beams.

• Composites Research
• /
• v.36 no.1
• /
• pp.48-52
• /
• 2023

Fiber-reinforced composites have anisotropic material properties, so the mechanical properties of composite structures can vary depending on the stacking sequence. Therefore, it is essential to design the proper stacking sequence of composite structures according to the functional requirements. However, depending on the manufacturing condition or the shape of the structure, there are many cases where the designed stacking angle is out of range, which can affect structural performance. Accordingly, it is important to analyze the stacking angle in order to confirm that the composite structure is correctly fabricated as designed. In this study, the stacking angle was predicted from real cross-sectional images of fiber-reinforced composites using convolutional neural network (CNN)-based deep learning. Carbon fiber-reinforced composite specimens with several stacking angles were fabricated and their cross-sections were photographed on a micro-scale using an optical microscope. The training was performed for a CNN-based deep learning model using the cross-sectional image data of the composite specimens. As a result, the stacking angle can be predicted from the actual cross-sectional image of the fiber-reinforced composite with high accuracy.

• Composites Research
• /
• v.29 no.6
• /
• pp.342-346
• /
• 2016

Carbon fiber reinforced plastic (CFRP), one of lightweight materials, is the fiber structure using carbon fiber. It is the composite material that has the characteristics of carbon and plastic. As for the fiber structure, it has the great strength due to fiber direction. CFRP for woven type is used mostly as such a CFRP with lightweight. Woven type is more stable when compared with unidirectional type. On the other hand, woven type is highly priced. Therefore, this study aims to analyze the fiber structure of unidirectional CFRP. In this study, as the stacking angle [0/X/-X/0], X is the variable. This is unidirectional CFRP in which the angle phase of X has been reversed and stacked. By using such a unidirectional CFRP, the analysis model which had a crack at the center as the form of panel with the thickness of 2 mm was used. On analysis, the load is applied on the upper and lower parts being connected with a pin. The damage in the area near center crack was investigated. As for the analysis model, 3D surface model was designed by using CATIA. For CFRP stacking, the stacking direction was determined by using ACP in ANSYS program and the analysis model with two stacks was made. Afterwards, the structural analysis was carried out.