• Journal of the Korean Data and Information Science Society
• /
• 제14권2호
• /
• pp.345-354
• /
• 2003

An incremental kernel principal component analysis(IKPCA) is proposed for the nonlinear feature extraction from the data. The problem of batch kernel principal component analysis(KPCA) is that the computation becomes prohibitive when the data set is large. Another problem is that, in order to update the eigenvectors with another data, the whole eigenvectors should be recomputed. IKPCA overcomes this problem by incrementally updating the eigenspace model. IKPCA is more efficient in memory requirement than a batch KPCA and can be easily improved by re-learning the data. In our experiments we show that IKPCA is comparable in performance to a batch KPCA for the classification problem on nonlinear data set.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2003년도 ISIS 2003
• /
• pp.86-89
• /
• 2003

To model a numerical problem space under the limitation of available data, we need to extract sparse but key points from the space and to efficiently approximate the space with them. This study proposes a sampling method based on the search process of genetic algorithm and a space modeling method based on least-squares approximation using the summation of Gaussian functions. We conducted simulations to evaluate them for several kinds of problem spaces: DeJong's, Schaffer's, and our original one. We then compared the performance between our sampling method and sampling at regular intervals and that between our modeling method and modeling using a polynomial. The results showed that the error between a problem space and its model was the smallest for the combination of our sampling and modeling methods for many problem spaces when the number of samples was considerably small.

• 한국음향학회지
• /
• 제14권3호
• /
• pp.37-48
• /
• 1995

일반화된 완전최소자승법 (generalized total least squares method, GTLS)의 ARMA 시스템 식별에의 적용과 GTLS의 적응알고리듬에 대하여 논한다. 일반화된 완전최소자승법은 일별과 출력을 알고 있는 시스템식별 (system identification)문제에서, 출력이 잡음에 의하여 오염된 경우, 편이되지 않은 해를 구하기 위하여 사용되는 방법이다. 본 논문에서는 먼저 GTLS를 ARMA 시스템 식별에 적용하기 위한 formulation을 하고, 일반화된 완전최소자승법의 일반 해의 성질과 역행렬 정리 (matrix inverse lemma)를 이용하여 적응 GTLS 방법을 제안한다. 다음 제안된 방법을 통하여 시스템식별에 적용하여 그 성능을 평가한다. 또한 GTLS 알고리듬과 제안한 적응 GTLS 알고리듬의 성능을 수학적으로 해석하고 컴퓨터 시뮬레이션을 통하여 이를 검증한다.

• 방송공학회논문지
• /
• 제14권2호
• /
• pp.107-113
• /
• 2009

지상파 DMB 동일 채널 중계기에서는 송신 안테나로부터 수신 안테나로 재입력되는 궤환 신호가 존재한다. 동일 채널 중계기에서 궤환 신호가 제대로 제거되지 않았을 경우, 수신 신호에 간섭으로 작용하게 되어 중계기 시스템의 안정성이 크게 떨어지게 된다. 이러한 궤환 신호를 제거하기 위하여 궤환 채널을 적응적으로 추정하여 간섭을 제거시키는 궤환 신호 제거기를 사용하였다. 하지만 기존의 채널 추정 알고리듬은 간단한 구현에 비해 수렴 성능과 속도 면에서 만족할만한 성능을 얻을 수 없었으며, 신호간 상관도 제거를 위해 충분한 시간 지연을 해야 하는 단점이 있다. 따라서 본 논문은 궤환 채널 추정에 적합한 PNLMS (Proportionate Normalized Least Mean Squares) 적응형 알고리듬을 적용한 새로운 궤환 신호 제거 기법을 제안하였으며, 전산 모의 실험을 통해 이와 같은 문제를 효과적으로 해결할 수 있음을 확인하였다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2003년도 ICCAS
• /
• pp.2627-2631
• /
• 2003

With the development of RAIM techniques for single failure, there has been increasing interest in the multiple failure problem. There have been many approaches to tackle the problem from various points of view. This paper approaches to two failure problem with total least squares (TLS) technique, which has rarely been addressed because TLS requires a great number of computations. In this paper, the special form of the observation matrix H, that is, one column is exactly known, is exploited so as to develop an algorithm in a sequential form, which reduces computational burden. The algorithm makes us enjoy the advantages of TLS without much computational burden. The proposed algorithm is verified through a numerical simulation.

• Communications for Statistical Applications and Methods
• /
• 제8권2호
• /
• pp.337-346
• /
• 2001

In this paper we consider the problem of identifying and testing the outliers in linear regression. first we consider the problem for testing the null hypothesis of no outliers. The test based on the ratio of two scale estimates is proposed. We show the asymptotic distribution of the test statistic by Monte Carlo simulation and investigate its properties. Next we consider the problem of identifying the outliers. A forward sequential procedure based on the suggested test is proposed and shown to perform fairly well. The forward sequential procedure is unaffected by masking and swamping effects because the test statistic is based on robust estimate.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2001년도 하계종합학술대회 논문집(1)
• /
• pp.317-320
• /
• 2001

Blind adaptive channel identification of communication channels is a problem of important current theoretical and practical concerns. Recently proposed solutions for this problem exploit the diversity induced by antenna array or time oversampling leading to the so-called, second order statistics techniques. And adaptive blind channel identification techniques based on a off-line least-squares approach have been proposed. In this paper, a new approach is proposed that is based on eigenvalue decomposition. And the eigenvector corresponding to the minimum eigenvalue of the covariance matrix of the received signals contains the channel impulse response. And we present a adaptive algorithm to solve this problem. The performance of the proposed technique is evaluated over real measured channel and is compared to existing algorithms.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2000년도 제13회 신호처리 합동 학술대회 논문집
• /
• pp.399-402
• /
• 2000

In this paper, we present a regularized mixed norm multichannel image restoration algorithm. The problem of multichannel restoration using both within- and between- channel deterministic information is considered. For each channel a functional which combines the least mean squares (LMS), the least mean fourth(LMF), and a smoothing functional is proposed, We introduce a mixed norm parameter that controls the relative contribution between the LMS and the LMF, and a regularization parameter that defines the degree of smoothness of the solution, both updated at each iteration according to the noise characteristics of each channel. The novelty of the proposed algorithm is that no knowledge of the noise distribution for each channel is required, and the parameters mentioned above are adjusted based on the partially restored image.

• 한국컴퓨터정보학회논문지
• /
• 제21권12호
• /
• pp.125-130
• /
• 2016

Automatic quality inspection by computer vision can be applied and give a solution to the pharmaceutical industry field. Pharmaceutical capsule can be easily affected by flaws like dents, cracks, holes, etc. In order to solve the quality inspection problem, it is required computationally efficient image processing technique like thresholding, boundary edge detection and segmentation and some automated systems are available but they are very expensive to use. In this paper, we have developed a dented capsule image processing technique using edge-based image segmentation, TLS(Total Least Squares) curve fitting technique and adopted low cost camera module for capsule image capturing. We have tested and evaluated the accuracy, training and testing time of the classification recognition algorithms like PCA(Principal Component Analysis), ICA(Independent Component Analysis) and SVM(Support Vector Machine) to show the performance. With the result, PCA, ICA has low accuracy, but SVM has good accuracy to use for classifying the dented capsule.

• 산업공학
• /
• 제14권2호
• /
• pp.190-197
• /
• 2001

Growth curves including Logistic and Gompertz functions are widely used in forecasting the market demand. To estimated the parameters of those functions, we use the non-linear least square method. However, it is difficult to set up the starting points for each parameter. If a wrong starting point is selected, the result reveals the local optimum or does not converge to a certain value. The purpose of this paper is to resolve the problem of selecting a starting point. Especially, rescaling the market data using the national economic index make it possible to figure out the range of parameters and to utilize the grid search method. Applications to some real data are also included.