• Journal of Korea Society of Industrial Information Systems
• /
• v.20 no.5
• /
• pp.1-11
• /
• 2015

This paper is focused on how the trajectory of launch vehicle could be optimally estimated by the quadratic regression of trajectory data mining for the operation of telemetry ground system in NARO space center during real-time. To receive the telemetry data, the telemetry ground system has to track the space launch vehicle without tracking loss, and it is possible by the well-designed algorithm to estimate a flight position in real-time. For this reason, the quadratic regression model instead of interpolation was considered to estimate the exact position data of launch vehicle and the improvement of antenna performance. For analysis, the real trajectory data which had been logged during NARO 1st launch mission were used, the estimation result of launcher current position was analyzed by the mathematical modeling. In conclusion, the algorithm using quadratic regression based on trajectory data mining showed the better performance than previous interpolation algorithm to estimate the next flight position and the antenna driving performance.

• Journal of the Korean Data and Information Science Society
• /
• v.24 no.1
• /
• pp.135-150
• /
• 2013

This study proposes a novel option strategy by using characteristic of volatility reversion and rough set algorithm in options market. Until now, various research has been conducted on stock and future markets, but minimal research has been done in options market. Particularly, research on the option trading strategy using high frequency data is limited. This study consists of two purposes. The first is to enjoy a profit using volatility reversion model when volatility gap is occurred. The second is to pursue a more stable profit by filtering inaccurate entry point through rough set algorithm. Since options market is affected by various elements like underlying assets, volatility and interest rate, the point of this study is to hedge elements except volatility and enjoy the profit following the volatility gap.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.35 no.11
• /
• pp.1111-1117
• /
• 2011

This paper proposed a fault detection and diagnosis (FDD) algorithm using nonlinear regression models, focusing especially on heat exchanger faults. This research concerned four working modes: those with no fault, evaporator fault, condenser fault, and evaporator and condenser faults. This research used no fault mode data to create an FDD algorithm. Using the no fault mode data, correlation functions for predicting the degree of superheat or subcool of heat exchangers (an evaporator and a condenser) were derived. Each correlation function has five inputs and one output. Based on these correlation functions, it is possible to predict the degree of superheat or subcool of each heat exchanger under various working conditions. The FDD algorithm was developed by comparing the predicted value and the simulation value. The FDD algorithm works well in all four working modes.

• Proceedings of the Korean Society of Near Infrared Spectroscopy Conference
• /
• 2002.11a
• /
• pp.25-58
• /
• 2002

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.26 no.1B
• /
• pp.39-50
• /
• 2006

The flood control offices of main rivers have used a storage function model to forecast flood stage in Korea and studies of flood forecasting actively have been done even now. On this account, the storage function model, which is used in flood control office, regression models and artificial neural network model are applied into flood forecasting of study watershed in this paper. The result obtained by each method are analyzed for the comparative study. In case of storage function model, this paper uses the representative parameters of the flood control offices and the optimized parameters. Regression coefficients are obtained by regression analysis and neural network is trained by backpropagation algorithm after selecting four events between 1995 to 2001. As a result of this study, it is shown that the optimized parameters are superior to the representative parameters for flood forecasting. The results obtained by multiple, robust, stepwise regression analysis, one of the regression methods, show very good forecasts. Although the artificial neural network model shows less exact results than the regression model, it can be efficient way to produce a good forecasts.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.7
• /
• pp.963-971
• /
• 2022

Water pipeline network in local and metropolitan area is buried underground, by which it is hard to know the degree of pipe aging and leakage. In this study, assuming various sensor combinations installed in the water pipeline network, the optimal algorithm was derived by predicting the water flow rate and pressure through artificial intelligence algorithms such as linear regression and neuro fuzzy analysis to examine the possibility of detecting pipe leakage according to the data combination. In the case of leakage detection through water supply pressure prediction, Neuro fuzzy algorithm was superior to linear regression analysis. In case of leakage detection through water supply flow prediction, flow rate prediction using neuro fuzzy algorithm should be considered first. If flow meter for prediction don't exists, linear regression algorithm should be considered instead for pressure estimation.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2017.05a
• /
• pp.219-219
• /
• 2017

상대적으로 유역의 관측 자료가 충분하지 못하거나 검증되지 않았을 경우 미계측 유역으로 정의되며 수문모형의 매개변수 검정을 할 수 없으므로 다른 방법을 고안해야 한다. 이를 위해 기존 연구에서는 지역적 특성을 고려한 지역회기분석을 통해 미계측 유역의 유량을 산정하였는데, 대부분 유역의 특성과 연 평균 유출량 자료의 관계를 이용한 회귀식으로 실시간 유량의 변화를 고려하기 어려웠다. 본 연구에서는 개념적 강우-유출모형으로 많이 사용되고 있는 개념적 수문모형인 GR4J의 매개변수에 대해 미계측 유역의 특성을 고려한 변수들을 이용하여 회귀식을 구하고 그 적용성을 평가하였다. 이를 통해 미계측 유역의 유량 시계열 자료를 생성할 수 있었다. 또한 IPCC에서 발간한 AR5의 RCP 4.5 시나리오를 적용하여 미래 유출량을 산정하였다. 우선 지역회귀분석을 적용하기 위해 수문모형을 이용한 계측 유역의 유출량을 구하였으며 22개의 전국 댐 상류 지점을 기준으로 SCE 알고리즘을 이용하여 GR4J의 최적 매개변수를 구하고 각 유역별로 물리적, 지형적, 기상학적 특성을 고려하여 11개의 변수를 선택하였다. 각 변수간 다중공선성(Multicollinearity)를 고려하기 위해 VIF(Variation Inflation Factor) test를 적용하여 최종 7개의 변수를 선정하고 단계별 회귀방법(Stepwise regression)을 이용하여 GR4J의 매개변수별 회귀식을 생성하였다.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.21 no.1
• /
• pp.21-34
• /
• 2008

An improved optimum design method for reinforced concrete frames using integrated genetic algorithm(GA) with direct search method is presented. First, various sets of initially assumed sections are generated using GA, and then, for each resultant design member force condition optimum solutions are selected by regression analysis and direct search within pre-determined design section database. In advance, global optimum solutions are selected from accumulated results through several generations. Proposed algorithm makes up for the weak point in standard genetic algorithm(GA), that is, low efficiency in convergence causing the deterioration of quality of final solutions and shows fast convergence together with improved results. Moreover, for the purpose of elevating economic efficiency, optimum design based on the nonlinear structural analysis is performed and therefore makes all members resist against given loading condition with the nearest resisting capacity. The investigation for the effectiveness of the introduced design procedure is conducted through correlation study for example structures.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.33 no.4
• /
• pp.1693-1705
• /
• 2013

To restore old aqueduct in Korea which is a irrigation bridge to supply water in paddy field area, it is needed to estimate approximate costs of restoration because the basic design for estimation of construction costs is often ruled out in current system. In this paper, estimating models of construction costs were developed on the basis of performance data for restoration of RC aqueduct bridges since 2003. The regression analysis (RA) model and case-based reasoning (CBR) model for the estimation of construction costs were developed respectively. Error rate of simple RA model was lower than that of multiple RA model. CBR model using genetic algorithm (GA) has been applied in the estimation of construction costs. In the model three factors like attribute weight, attribute deviation and rank of case similarity were optimized. Especially, error rate of estimated construction costs decreased since limit ranges of the attribute weights were applied. The results showed that error rates between RA model and CBR models were inconsiderable statistically. It is expected that the proposed estimating method of approximate costs of aqueduct restoration will be utilized to support quick decision making in phased rehabilitation project.

• Journal of Industrial Convergence
• /
• v.16 no.4
• /
• pp.33-46
• /
• 2018

Personal credit scoring is an effective tool for banks to properly guide decision profitably on granting loans. Recently, many classification algorithms and models are used in personal credit scoring. Personal credit scoring technology is usually divided into statistical method and non-statistical method. Statistical method includes linear regression, discriminate analysis, logistic regression, and decision tree, etc. Non-statistical method includes linear programming, neural network, genetic algorithm and support vector machine, etc. But for the development of the credit scoring model, there is no consistent conclusion to be drawn regarding which method is the best. In this paper, we will compare the performance of the most common scoring techniques such as logistic regression, neural network, and support vector machines using personal credit data of the financial institution in China. Specifically, we build three models respectively, classify the customers and compare analysis results. According to the results, support vector machine has better performance than logistic regression and neural networks.