• Proceedings of the KIEE Conference
• /
• 1999.11c
• /
• pp.564-566
• /
• 1999

계측 시스템이나 시스템 식별을 수행할 때 정확히 모델링 되는 플랜트를 가정할 경우, 입출력 신호간 혹은 상태 변수들 사이의 비선형 함수 관계를 유도해 낼 수 있다. 그런데 특히 비선형 함수가 매우 복잡하여 해를 닫힌 형태로 구할 수 없을 경우 고려하는 변수들 양자간의 수학적 모델링을 기반으로 루프내 변수가 방정식의 해로 수렴하는 대수 루프를 구성할 수 있다. 이는 모델을 정확히 아는 시스템에 대하여 출력으로부터 입력을 추정하는 역시스템(inverse system)을 구성하는 것과 유사하다. 이러한 개념을 응용한 간단한 예로 용량형 센서의 입출력 비선형성을 제거해주는 역시스템을 대수 루프를 통하여 구현하였다. 또한 구현한 루프가 항상 유일한 해로 수렴할 수 있도록 하는 조건을 구하였다. 해석된 결과를 바탕으로 구현된 루프가 컴퓨터 시뮬레이션 및 아날로그 회로 실험에서도 잘 동작함을 검증하였다. 시뮬레이션 결과로 보인 잡음에 대한 강인성과 실제 회로 실험 결과는 대수 루프의 구현이 실제 용량형 센서 등에 용이하게 적용될 수 있음을 보여준다.

• Proceedings of the Acoustical Society of Korea Conference
• /
• 1998.06e
• /
• pp.327-330
• /
• 1998

독립성분분석(ICA: Independent Component Analysis)이란 특징이 상이한 둘 이상의 신호들이 선형적으로 결합되어 있을 때 이를 효과적으로 분리하는 방법들을 통칭하며 잡음제거, 음질개선 및 신호처리 분야에서 많이 활용되고 있다. 본 논문에서는 전화음성 화자인식 시스템의 성능향상을 위해 독립성분분석을 이용하는 방법을 제안한다. 먼저 화자가 발성한 음성신호의 켑스트럼 계수를 여러 채널 함수들의 선형적인 합으로 가정하고, 독립성분분석을 이용하여 얻은 새로운 켑스트럼 벡터를 학습과 인식에 사용하였다. 실험자료는 잔화음성 화자식별기의 성능평가에 널리 쓰이고 있는 SPIDRE를 사용하였고 regodic 은닉 마코프 모델을 이용하여 문장 독립 화자식별 시스템을 구성하였다. 학습음성의 특징과 실험음성의 특징이 다른 조건에서 기존의 채널 정규화 방법들에 비해 10~15%이상 인식률이 향상되었다.

• Journal of Navigation and Port Research
• /
• v.28 no.3
• /
• pp.221-225
• /
• 2004

This paper deals with a nonlinear system modelling using neural network and genetic algorithm Application q{ neural network to control and identification is actively studied because of their approximating ability of nonlinear function. It is important to design the neural network with optimal structure for minimum error and fast response time. Genetic algorithm is getting more popular nowadays because of their simplicity and robustness. in this paper, we optimize a neural network structure using genetic algorithm The genetic algorithm uses binary coding for neural network structure and searches for an optimal neural network structure of minimum error and fast response time. Through an extensive simulation, the optimal neural network structure is shown to be effective for identification of nonlinear system.

• Annual Conference of KIPS
• /
• 2011.04a
• /
• pp.376-377
• /
• 2011

일반적으로 저조도 환경에서 촬영된 영상에서 컬러의 정보를 식별하는 것은 어렵다. 기존의 대표적인 영상 개선의 방법인 레티넥스(Retinex)는 연산량이 많고 원본 영상의 컬러 정보를 정확히 반영하지 못하는 문제점이 있다. 따라서, 본 논문에서는 저조도 환경에서 촬영된 영상에 대해 컬러의 왜곡 문제를 개선하기 위하여 비선형 함수와 RGB 컬러 공간에서의 벡터 상수곱을 이용한 실시간 영상 개선 방법을 제안한다.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.9 no.1
• /
• pp.17-24
• /
• 1972

A method utilizing vector representation is investigated for determining a faulty elenlent in passive and active networks by simple external measurements. A large system may be considered as an interconnection of a number of subnetlvorks. By utilizing the relationships between the magintudes of a transfer function at various frequencies and the deviations of a circuit element, the fault simulation curves can be drawn. The fault identification regions are defined from the fault simulation curves. A fault identlfication matrix is constructed corresponding the defined fault identification regions. The fault identification matrix, when premultiplied by a vector whose components are measured from a network, yieldg another vector whose components identify a network element which is faulty. A test procedure for the fault identification method is presented and verified by experiments.

• Journal of KIISE:Software and Applications
• /
• v.27 no.5
• /
• pp.583-592
• /
• 2000

This paper proposes feature parameter transformation method using independent component analysis (ICA) for speaker identification. The proposed method assumes that the cepstral vectors from various channel-conditioned speech are constructed by a linear combination of some characteristic functions with random channel noise added, and transforms them into new vectors using ICA. The resultant vector space can give emphasis to the repetitive speaker information and suppress the random channel distortions. Experimental results show that the transformation method is effective for the improvement of speaker identification system.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.20 no.5
• /
• pp.526-534
• /
• 2014

In this study, single-input transfer function model is applied to forecast monthly mean sea surface temperature(SST) in 2010 at Yeosu in Korean coastal waters. As input series, monthly mean air temperature series for ten years(2000-2009) at Yeosu in Korea is used, and Monthly mean SST at Yeosu station in Korean coastal waters is used as output series(the same period of input). To build transfer function model, first, input time series is prewhitened, and then cross-correlation functions between prewhitened input and output series are determined. The cross-correlation functions have just two significant values at time lag at 0 and 1. The lag between input and output series, the order of denominator and the order of numerator of transfer function, (b, r, s) are identified as (0, 1, 0). The selected transfer function model shows that there does not exist the lag between monthly mean air temperature and monthly mean SST, and that transfer function has a first-order autoregressive component for monthly mean SST, and that noise model was identified as $ARIMA(1,0,1)(2,0,0)_{12}$. The forecasted values by the selected transfer function model are generally $0.3-1.3^{\circ}C$ higher than actual SST in 2010 and have 6.4 % mean absolute percentage error(MAPE). The error is 2 % lower than MAPE by ARIMA model. This implies that transfer function model could be more available than ARIMA model in terms of forecasting performance of SST.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.43 no.6 s.312
• /
• pp.105-112
• /
• 2006

To improve the performance of identification for radars in an ES(Electronic warfare Support) system, it is necessary to estimate scan characteristics as well as the basic identification parameters such as frequency, pulse repetition interval and pulse width of radars. This paper presents the method of estimating the scan period and the scan beam width of circular scanning radars. The proposed method estimates the scan period using the quality of the autocorrelation of a periodic signal. And, it estimates the scan beam width using the linear interpolation and the proposed method of estimating the scan period. Simulation results are presented to show the performance of the proposed method.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.15 no.2
• /
• pp.204-210
• /
• 2005

This paper presents online identification algorithm for TSK fuzzy model. The proposed algorithm identify structure of premise part by using distance, and obtain the parameters of the piecewise linear function consisting consequent part by using recursive least square. Only input space was considered in Most researches on structure identification, but input and output space is considered in the proposed algorithm. By doing so, outliers are excluded in clustering effectively. The existing other algorithm has disadvantage that it is sensitive to noise by using data itself as cluster centers. The proposed algorithm is non-sensitive to noise not by using data itself as cluster centers. Model can be obtained through one pass and it is not needed to memorize many data in the proposed algorithm.

• Journal of the Korean Society for Precision Engineering
• /
• v.14 no.10
• /
• pp.135-140
• /
• 1997

The detection of cutting tool states in machining is important for the automation. The information of cutting tool states in metal cutting process is uncertain. Hence a industry needs the system which can detect the cutting tool states in real time and control the feed motion. Cutting signal features must be sifted before the classification. In this paper the Fisher's linear discriminant function was applied to the pattern recognition of the cutting tool states successfully. Cutting conditions and cutting force para- meters have shown to be sensitive to tool states, so these cutting conditions and cutting force paramenters can be used as features for tool state detection.