• Tuberculosis and Respiratory Diseases
• /
• v.86 no.3
• /
• pp.203-215
• /
• 2023

Background: Surgical resection is the standard treatment for early-stage lung cancer. Since postoperative lung function is related to mortality, predicted postoperative lung function is used to determine the treatment modality. The aim of this study was to evaluate the predictive performance of linear regression and machine learning models. Methods: We extracted data from the Clinical Data Warehouse and developed three sets: set I, the linear regression model; set II, machine learning models omitting the missing data: and set III, machine learning models imputing the missing data. Six machine learning models, the least absolute shrinkage and selection operator (LASSO), Ridge regression, ElasticNet, Random Forest, eXtreme gradient boosting (XGBoost), and the light gradient boosting machine (LightGBM) were implemented. The forced expiratory volume in 1 second measured 6 months after surgery was defined as the outcome. Five-fold cross-validation was performed for hyperparameter tuning of the machine learning models. The dataset was split into training and test datasets at a 70:30 ratio. Implementation was done after dataset splitting in set III. Predictive performance was evaluated by R² and mean squared error (MSE) in the three sets. Results: A total of 1,487 patients were included in sets I and III and 896 patients were included in set II. In set I, the R² value was 0.27 and in set II, LightGBM was the best model with the highest R² value of 0.5 and the lowest MSE of 154.95. In set III, LightGBM was the best model with the highest R² value of 0.56 and the lowest MSE of 174.07. Conclusion: The LightGBM model showed the best performance in predicting postoperative lung function.

• Genomics & Informatics
• /
• v.14 no.4
• /
• pp.138-148
• /
• 2016

The success of genome-wide association studies (GWASs) has enabled us to improve risk assessment and provide novel genetic variants for diagnosis, prevention, and treatment. However, most variants discovered by GWASs have been reported to have very small effect sizes on complex human diseases, which has been a big hurdle in building risk prediction models. Recently, many statistical approaches based on penalized regression have been developed to solve the "large p and small n" problem. In this report, we evaluated the performance of several statistical methods for predicting a binary trait: stepwise logistic regression (SLR), least absolute shrinkage and selection operator (LASSO), and Elastic-Net (EN). We first built a prediction model by combining variable selection and prediction methods for type 2 diabetes using Affymetrix Genome-Wide Human SNP Array 5.0 from the Korean Association Resource project. We assessed the risk prediction performance using area under the receiver operating characteristic curve (AUC) for the internal and external validation datasets. In the internal validation, SLR-LASSO and SLR-EN tended to yield more accurate predictions than other combinations. During the external validation, the SLR-SLR and SLR-EN combinations achieved the highest AUC of 0.726. We propose these combinations as a potentially powerful risk prediction model for type 2 diabetes.

• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• pp.580-585
• /
• 2005

A QRT(Quad-Rotor Type) hovering robot system is developed for quick detection and observation of the circumstances under calamity environment such as indoor fire spots. The UAV(Unmanned Aerial Vehicle) is equipped with four propellers driven by each electric motor, an embedded controller using a DSP, INS(Inertial Navigation System) using 3-axis rate gyros, a CCD camera with wireless communication transmitter for observation, and an ultrasonic range sensor for height control. The developed hovering robot shows stable flying performances under the adoption of RIC(Robust Internal-loop Compensator) based disturbance compensation and the vision based localization method. The UAV can also avoid obstacles using eight IR and four ultrasonic range sensors. The VTOL(Vertical Take-Off and Landing) flying object flies into indoor fire spots and sends the images captured by the CCD camera to the operator. This kind of small-sized UAV can be widely used in various calamity observation fields without danger of human beings under harmful environment.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 1997.10a
• /
• pp.207-210
• /
• 1997

The drastic structural changes in telecommunications industry are imposing new strains on operators, regulators and customers. Many researchers have offered diverse frameworks for the changes from the perspectives of sociology, technology, and/or economics. However, there have been few attempts to document the competitive phenomena from management perspectives because of the technological complexities and dynamism in the fundamental transition of competition. In this study, we examine competitive environment in telecommunications industry, and identified five structural elements; telecom operator, competitors, regulation, suppliers, and customer demand. The suggested framework is used to provide a basis for explaining the changes in the characteristics of individual elements and the interactions among them. The dynamic industry-specific changes will be explained through an evolutionary model. We specify the characteristics of progressive stages and the determinants of the evolution. Changes are reviewed in terms of five criteria; regulations and competitions, value chain, technology, customers demand, and internal operations. The result of this study will be useful in analyzing and predicting industry structure and major participants' strategic behaviors and decision patterns. This study can alse be extended to other industries facing dynamic structural changes.

• Culinary science and hospitality research
• /
• v.7 no.3
• /
• pp.1-12
• /
• 2001

Regarding to foodservice industry, menu analysis of foodservice has two significant meanings. One is to elevate a satisfaction to customer's desires, the other is to find a menu which can maximize profits to restaurant operator. In these reasons, Menu organization methods were developed and has been constantly developing by many researchers. Specially, Since computerization has been introduced in the foodservice business, menu organization methods has been made a growth. On the other hand, menu organization methods has not been developed by lack of recognition of foodservice-worker. methods for menu analysis focused on profits and preference out of foodservice operation have a lot of limits. That reason is why factors of internal and external influence are more than other industries. In the future, foodservice industry should improve sales-performance through the menu analysis after due consideration and need to develop methods for menu analysis. In the conclusion, development of foodservice indusrty can be expected if menu development and menu control should be go on through the menu analysis.

• Journal of Institute of Control, Robotics and Systems
• /
• v.3 no.1
• /
• pp.89-93
• /
• 1997

This paper describes the automatic testing system developed for powder metallurgy process using the visual inspection, and its some internal algorithms. The system consists of one unit from each of the five types of units; feeding, slot, vision inspection, volumn counter, and inferior good extractor units. Some applications of the system to powder metallurgy process has shown the possibility of reducing the rework and increasing the efficiency of operation.

• Proceedings of the KSR Conference
• /
• 2002.05a
• /
• pp.516-521
• /
• 2002

According as railway signalling equipments are computerized recently, necessity of communication protocol for interface between these equipments is increasing, Therefore the research about communication protocol structure that is need according to computerization trend of these signalling goes, especially communication protocol structure for interface between LDTS(Local Data Transmission System) and EIS(Electronic Interlocking System). Analyzed existent protocols that is applied currently for interfaces between above two signalling for this research and also technology analysis of internal/external similar protocols and operator and maker's requirement. With these study finding plain in this paper, explained summary of communication protocol structure for interface between LDTS and EIS.

• Journal of Electrical Engineering and Technology
• /
• v.7 no.2
• /
• pp.171-177
• /
• 2012

The autonomous microgrid is a system that is autonomously operated depending on the grid and internal load condition, without the operator's intervention. In this study, a control algorithm for the microsource and an operation algorithm for the microgrid are proposed to realize the autonomous microgrid system. In addition, a microgrid operation system based on the operation algorithm is proposed. The electromagnetic transient program is used by the proposed microsource control algorithm for simulation, and the validity of the algorithm is verified. The proposed operation system is verified based on a case study using a simulator and test devices.

• Proceedings of the KSR Conference
• /
• 2008.11b
• /
• pp.1570-1594
• /
• 2008

Nowadays there are lots of changes in the domestic railroad industries because of the reorganization in the industries, operation of KTX and expansion of city train in local areas. To cope with these changes effectively, domestic & abroad safety guideline and regulation were investigated and reviewed by railroad safety technical development project. Based on this project, domestic rolling stock safety regulation was established in the July and December on 2005. It's been a 3 years after 2005 and to confirm whether there are some problems to applicate the regulation in the field like korail, the necessity of reviewing the regulation gains force. In this study, to improve the field application in rolling stock safety regulation, we investigated the results of integrated railroad audit system and internal safety regulation system in a train operator and also collected the opinions from train manufacturer. Then through the result of investigation and collection of the opinions, we proposed the amendment to the rolling stock safety regulation.

• Biomedical Science Letters
• /
• v.22 no.4
• /
• pp.140-149
• /
• 2016

All pesticides must be assessed strictly whether safe or not when agricultural operators are exposed to the pesticides in farmland. A pesticide is commonly regarded as safe when estimated dermal absorption amount is lower than the acceptable operator's exposure level (AOEL). In this study, dermal absorption rate of chlorpyrifos, a widely used organophosphate insecticide, was investigated using rat dermal tissue model. Chlorpyrifos wettable powder solved in water (250, 500 and 2,500 ppm) was applied to freshly excised rat dermal slices ($341{\sim}413{\mu}m$ thickness) on static Franz diffusion cells at $32^{\circ}C$ for 6 hours. After exposure period of 6 hours, and then washing-at residual amount of chlorpyrifos was analyzed in dermal tissues, tape strips, washing solution, washing swabs of receptor bottles and receptor fluids at 1, 2, 4, 8 and 24 hours. Chlorpyrifos was only detected in dermal tissue but not found in receptor fluid at each concentration and time point, and the absorption rate of 250, 500 and 2,500 ppm was 2.36%, 1.96% and 1.69%, respectively. The estimated exposure level of chlorpyrifos was calculated as 0.012 mg/kg bw/day. The health risk for farmers in this condition is a level of concern because the estimated exposure level is 12 times higher than AOEL 0.001 mg/kg bw/day. However, actual health risk will be alleviated than estimated because absorbed chlorpyrifos is not permeated into internal body system and only retained in skin layer.