• IE interfaces
• /
• v.20 no.1
• /
• pp.41-48
• /
• 2007

The main purpose of this paper is cost reduction in absurd pilot positive expense and human accident prevention which is caused by in the pilot selection process. We use classification models such as logistic regression, decision tree, and neural network based on aptitude test results of 505 ROK Air Force applicants in 2001~2004. First, we determine the reliability and propriety against the aptitude test system which has been improved. Based on this conference flight simulator test item was compared to the new aptitude test item in order to make additional yes or no decision from different models in terms of classification accuracy, ROC and Response Threshold side. Decision tree was selected as the most efficient for each sequential flight training result and the last flight training results predict excellent. Therefore, we propose that the standard of pilot selection be adopted by the decision tree and it presents in the aptitude test item which is new a conference flight simulator test.

• Proceedings of the SAREK Conference
• /
• 2006.06a
• /
• pp.454-459
• /
• 2006

There are two main streams for pattern classification technology One is the method using PCA (Principal Component Analysis) and the other is the method using Neural network. Both of them have merits and demerits. In general, using PCA is so simple while using neural network can improve algorithm continually. Algorithm using neural network needs so many calculations rendering very slow response. In this work, an attempt is made to develop algorithms adopting both PCA and neural network merits for simpler, but faster and smarter.

• Communications for Statistical Applications and Methods
• /
• v.29 no.3
• /
• pp.319-331
• /
• 2022

In this paper, we develop a new statistical model to forecast the PM_2.5 level in Seoul, South Korea. The proposed model is based on the extreme quantile regression model with lasso penalty. Various meteorological variables and air pollution variables are considered as predictors in the regression model, and the lasso quantile regression performs variable selection and solves the multicollinearity problem. The final prediction model is obtained by combining various extreme lasso quantile regression estimators and we construct a binary classifier based on the model. Prediction performance is evaluated through the statistical measures of the performance of a binary classification test. We observe that the proposed method works better compared to the other classification methods, and predicts 'very bad' cases of the PM_2.5 level well.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2005.11a
• /
• pp.323-326
• /
• 2005

This paper introduces design method for air pump system using bond graph and genetic programming to maximize outflow subject to a constraint specifying maximum power consumption. The air pump system is a mixed domain system which includes electromagnetic, mechanical and pneumaticelements. Therefore an appropriate approach for a better system for synthesis is required. Bond graphs are domain independent, allow free composition, and are efficient for classification and analysis of models, Genetic programming is well recognized as a powerful tool for open-ended search. The combination of these two powerful methods for evolution of multi-domain system, BG/GP, was tested for redesign of air pump system.

• Proceedings of the IEEK Conference
• /
• 2001.10a
• /
• pp.759-764
• /
• 2001

The separation performance of zigzag air classifier with angle of 90 degrees was studied using narrow size fractions of thin square samples and granular samples. The simulation results of air velocity inside the classifier indicated that the zigzag geometry induces a new pattern consisting of an upward flow and a circulation flow, Experimental results showed that overflow product recovery was described as an integral calculus of normal distribution as a function of dimensionless air velocity ( $V_{A}$ $V_{A50}$), where $V_{A}$ is superficial air velocity and $V_{A50}$ is the $V_{A}$ at the fifty percent recovery. The $V_{A}$ values were predicted using the equations derived from dynamics for a particle dropping in air. A monitoring system that utilizes changes in acoustic signals emitted during the process of air classification was developed to separate PET with desired recovery or grade. The technical feasibility of the on-line monitoring of the PET recovery and grade was demonstrated by measuring relative energy of the signals.signals.als.

• Journal of Climate Change Research
• /
• v.7 no.4
• /
• pp.507-512
• /
• 2016

This study was conducted to classify agroclimatic zones in South Korea. To classify the agroclimatic zones, such climatic factors as amount of rainfall from April to May, amount of rainfall in October, monthly average air temperature in January, monthly average air temperature from April to May, monthly average air temperature from April to September, monthly average air temperature from December to March, monthly minimum air temperature in January, monthly minimum air temperature from April to May, Warmth Index were considered as major influencing factors on the crop growth. Climatic factors were computed from monthly air temperature and precipitation of climatological normal year (1981~2010) at 1 km grid cell estimated from a geospatial climate interpolation method. The agroclimatic zones using k-means cluster analysis method were classified into 6 zones.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.26 no.4
• /
• pp.404-413
• /
• 2015

The target classification for ballistic target(BT) is one of the most critical issues of ballistic defence mode(BDM) in multi-function radar(MFR). Radar responds to the target according to the result of classifying BT and air breathing target(ABT) on BDM. Since the efficiency and accuracy of the classification is closely related to the capacity of the response to the ballistic missile offense, effective and accurate classification scheme is necessary. Generally, JEM(Jet Engine Modulation), HRR(High Range Resolution) and ISAR(Inverse Synthetic Array Radar) image are used for a target classification, which require specific radar waveform, data base and algorithms. In this paper, the classification method that is applicable to a MFR system in a real environment without specific waveform is proposed. The proposed classifier adopts kinematic data as a feature vector to save radar resources at the radar time and hardware point of view and is implemented by fuzzy logic of which simple implementation makes it possible to apply to the real environment. The performance of the proposed method is verified through measured data of the aircraft and simulated data of the ballistic missile.

• Proceedings of the Korea Air Pollution Research Association Conference
• /
• 2004.05a
• /
• pp.222-223
• /
• 2004

• Proceedings of the Korea Air Pollution Research Association Conference
• /
• 2006.04a
• /
• pp.569-570
• /
• 2006

• Particle and aerosol research
• /
• v.17 no.4
• /
• pp.133-148
• /
• 2021

This study aims to estimate the amount of air pollutants emitted from heavy industry facilities in North Korea. To compare the emission in 2017 from the heavy industry sector in North Korea with South Korea, the heavy industry sector was classified with the South Korean classification (Matching Heavy Industry sector) and air pollutant emissions by Matching Heavy Industry sector in North Korea were estimated. The CO, NO_x and SO_x emissions of Matching Heavy Industry sector in North Korea are 22%, 73%, and 31% of the emission in South Korea, respectively. The air pollutant emissions in the Matching Heavy Industry sector in North Korea for CO, NO_x and SO_x were 0.6%, 124%, and 24% of the total air pollutant emission in North Korea estimated from EDGAR, respectively. As for the distribution of emissions by administrative district of the Matching Heavy Industry sector in North Korea, NO_x was concentrated in the western part of North Korea, and CO and SO_x emissions were concentrated in Hamgyong-bukto.