• 한국지능시스템학회논문지
• /
• 제11권4호
• /
• pp.293-301
• /
• 2001

본 논문은 신경회로망과 같은 경험적 모델에서 출력별로 신뢰 구간을 추정하는 세 가지 대표적인 방법을 검토하고, 검토한 방법을 뉴로-퍼지 모델에 적용하여 장단점을 비교 분석한다. 본 논문에서 고려한 출력별 신뢰 구간 계산 방법은 cross-validation을 이용한 stacked generalization, 회귀 모델에서 유도된 predictive error bar, 지역 표현하는 신경회로망의 특성에 기반한 local reliability measure이다. 간단한 함수 근사화 문제와 혼돈 시계열 예측 문제를 이용하여 모의 실험을 수행하고, 세 가지 신뢰도 추정 방법의 성능을 정량적, 정성적으로 비교 분석한다. 분석 결과를 기초로 각 방법의 장단점 및 특성을 고찰하고, 모델링 문제에서 모델의 출력별 신뢰 구간 계산 방법의 실제 적용 가능성을 탐색한다.

• 신재생에너지
• /
• 제20권2호
• /
• pp.17-25
• /
• 2024

In this study, the effect of the time step specified in a computational fluid dynamics (CFD) simulation on load response is analyzed and the drag coefficients of the floating body of floating offshore wind turbines (FOWTs) are estimated. By evaluating the error in the FOWT load response and the change in the drag-coefficient values based on the density of the time intervals, this study aims to establish a time-interval setting that minimizes the time and cost of CFD simulations for selecting drag-coefficient values. Practical CFD utilization strategies necessary for the calibration of medium-to high-fidelity analysis tools are presented. Based on a comparative analysis of CFD simulations conducted at various time intervals, the results confirmed that under a certain time interval that sufficiently considers various factors, the accuracy of the FOWT response with respect to density shows minimal differences, thereby providing an efficient utilization method for CFD simulations in FOWT design and analysis.

• 대한전기학회논문지
• /
• 제41권9호
• /
• pp.1051-1059
• /
• 1992

In this paper, two general methods using time-series analysis in the functional separation of the myoelectric signal of human arm movements are developed. Autocorrelation, covariance method and sequential least squares algorithm were used to determine the model parameters and the order of signal model to describe six arm movement patterns` the forearm flexion and extension, the wrist pronation and supination, rotation-in and rotation-out. The confidence interval to classify the functions of arm movement was defined by the mean and standard deviation of total squared error. With the error signals of autoregressive(AR) model, the result showed that the highest success rate was obtained in the case of 4th order, and success rate was decreased with increase of order. Autocorrelation was the method of choice for better success rate. This technique might be applied to biomedical and rehabilitation engineering.

• 한국ITS학회 논문지
• /
• 제3권2호
• /
• pp.129-140
• /
• 2004

본 논문에서는 지방부 간선도로 단속류 구간(국도 42호선 양지$\~$용인구간 6km)의 통행시간정보에 관한 체계적인 수집 $\cdot$ 분석을 위해 현재 국도교통관리시스템(RTMS : Rural Trafc Management System)상에서 운영중인 차량 번호판 매칭방식 AVI 수집자료에 대한 신뢰성 검증 및 단속류 구간 통행시간 자료의 적정집락간격에 관한 연구가 수행되었다. 우선 AVI수집자료 신뢰성 검증을 위하여 번호판 매칭방식 AVI표본수집자료와 전수조사자료를 Kolmogorov-Smirnov 검증기법을 이용하여 분석한 결과 AVI 자료는 통과위주의 대표차로상에서 수집되는 관계로 전차로에 대한 수집자료와 교통특성에 차이가 있어 현재의 번호판 매칭방식 AW 표본수집자료를 통해 산출된 구간통행시간을 구간의 대표값으로 적용하는 문제는 추가 검토가 필요하다. 그리고 적정집락간격을 산출하기 위하여 통계적 추정 개념인 점추정과 구간추정을 적용하여 모형을 개발하여 적용한 결과 점추정기법이 구간추정기법보다 집락간격결정에 민감하고, 보다 정확한 적정집락간격 선정이 가능한 것으로 밝혀졌으며, 적정집락간격은 5분으로 산정되어 현재 적용되고 있는 5분 집락간격은 적정한 것으로 판단된다.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2004년도 학술대회 논문집 정보 및 제어부문
• /
• pp.135-137
• /
• 2004

In this study we'll deal with the small-sized metalized film capacitors with large capacity which head have $5mm{\times}5mm{\times}2.5mm$ dimension. The lead wire is used to weld at both sides of capacitors. At that time the position gap between the welding machine and lead wire supplier would cause the welding error. Also, during the tapping processing of metalized film capacitors, the interval error among the capacitors, the length error of lead frame attached at the capacitors, and the straightness distortion of the lead frame could happen. As mentioned, four kinds of error parameters will be measured and analyzed by using the automatic visual inspection system that is implemented with CCD camera, optical parts, background lighting, and image processing algorithms. Finally we are able to achieve success rate above 99% to detect the welding faults of capacitors in the field test.

• 한국군사과학기술학회지
• /
• 제18권1호
• /
• pp.84-92
• /
• 2015

This paper proposes a new approach to reduce the target estimation error of the measurement angle, especially applied to the medium and long range surveillance radar. If the target has no maneuver and no change in heading direction for a certain time interval, the predicted angle of interacting multiple model(IMM) from the previous track information can be used to reduce the angle estimation error. The proposed method is simulated in 2 scenarios, a scenario with a non-maneuvering target and a scenario with a maneuvering target. The result shows that the new fusion solution(weighted IMM) with the predicted azimuth and the measured azimuth is worked properly in the two scenarios.

• 한국공작기계학회논문집
• /
• 제10권6호
• /
• pp.1-7
• /
• 2001

It is very important to test circular motion accuracy of NC machine tools as it affects all other machines machined by them in industries. In this paper, it has become possible to detect errors of linear displacement of radial directions for circle tar motion accuracy test using newly assembled magnetic type of linear scale so called Magnescale ball-bar system. It has also organized computer program systems using tick pulses come out from computer for getting error motion data at colt start time interval in circular motion test on NC lathe. Error data gotten from test is expressed to plots and analysed to numerics by various statistical treatments.

• International Journal of Quality Innovation
• /
• 제4권1호
• /
• pp.191-204
• /
• 2003

The target costing technique, mathematically discussed by Sauers, only uses the $C_p index along with Taguchi loss function and $\bar{X}$-P control charts to setup goal control limits. The new specification limits derived from Taguchi loss function is linked through the $C_p value to $\bar{X}$-P control charts to obtain goal control limits. Studies have shown that the point estimator of the $C_p index, $C_p, could vary from time to time due to the sampling error. The suggested approach is to use confidence intervals, especially the lower confidence intervals, to replace the point estimator. Therefore, an improvement on target costing technique is presented by applying the lower confidence interval of the $C_p index and using both Taguchi and Spiring's loss functions together with $\bar{X}$-P charts to make this technique more robust in practice. An example is also provided to illustrate how the improved target costing technique works.

• 응용통계연구
• /
• 제24권5호
• /
• pp.871-881
• /
• 2011

In this paper we propose a logistic regression method to estimate the survival function and the median survival time in interval-censored data. The proposed method is motivated by the data augmentation technique with no sacrifice in augmenting data. In addition, we develop a cross validation criterion to determine the size of data augmentation. We compare the proposed estimator with other existing methods such as the parametric method, the single point imputation method, and the nonparametric maximum likelihood estimator through extensive numerical studies to show that the proposed estimator performs better than others in the sense of the mean squared error. An illustrative example based on a real data set is given.

• Journal of Biosystems Engineering
• /
• 제21권2호
• /
• pp.155-166
• /
• 1996

A direct injection sprayer was designed using the concepts of injection mixing and total flow control, flowrate-based system compensating for the variation of forwarding speed. A metered rate, proportionally to the actual diluent flow rate, of a tracer chemical was injected directly into the diluent stream. The injection of chemical may improve the precision and safety of chemical application process. The control system was evaluated for the variables of the control interval, tolerances and sensitivities of flow regulation valve and injection pump. Performance of the system was assessed as that the response time of flow rate, response time of injection rate, absolute steady state error, and the coefficient of variance(C.V.) of concentration were 8.5 and -0.53 seconds, 0.067 lpm(0.8%) and 3.15%, respectively, at optimal parameters of control interval of 1.0 sec, fast sensitivity of flow regulation valve, medium sensitivity of injection pump and medium tolerance of flow rate. Performance of the system can be improved by increasing the sensitivity of flow regulating valve and employing a high resolution velocimeter, such as Doppler radar.