• Journal of the Korea Society of Computer and Information
• /
• v.16 no.4
• /
• pp.15-22
• /
• 2011

Principal component analysis (PCA) is a well-known method for dimensionality reduction and feature extraction while maintaining most of the variation in data. Although PCA has been applied in many areas successfully, it is sensitive to outliers and only valid for Gaussian distributions. Several variants of PCA have been proposed to resolve noise sensitivity and, among the variants, improved robust fuzzy PCA (RF-PCA2) demonstrated promising results. RF-PCA, however, is still a linear algorithm that cannot accommodate non-Gaussian distributions. In this paper, a non-linear algorithm that combines RF-PCA2 and kernel PCA (K-PCA), called improved robust kernel fuzzy PCA (RKF-PCA2), is introduced. The kernel methods make it to accommodate non-Gaussian distributions. RKF-PCA2 inherits noise robustness from RF-PCA2 and non-linearity from K-PCA. RKF-PCA2 outperforms previous methods in handling non-Gaussian distributions in a noise robust way. Experimental results also support this.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.14 no.5
• /
• pp.1093-1102
• /
• 2010

Principal component analysis (PCA) is a well-known method for dimension reduction while maintaining most of the variation in data. Although PCA has been applied to many areas successfully, it is sensitive to outliers. Several variants of PCA have been proposed to resolve the problem and, among the variants, robust fuzzy PCA (RF-PCA) demonstrated promising results. RF-PCA uses fuzzy memberships to reduce the noise sensitivity. However, there are also problems in RF-PCA and the convergence property is one of them. RF-PCA uses two different objective functions to update memberships and principal components, which is the main reason of the lack of convergence property. The difference between two functions also slows the convergence and deteriorates the solutions of RF-PCA. In this paper, a variant of RF-PCA, called RF-PCA2, is proposed. RF-PCA2 uses an integrated objective function both for memberships and principal components. By using alternating optimization, RF-PCA2 is guaranteed to converge on a local optimum. Furthermore, RF-PCA2 converges faster than RF-PCA and the solutions found are more similar to the desired solutions than those of RF-PCA. Experimental results also support this.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2007.10a
• /
• pp.383-386
• /
• 2007

허프 변환(Hough transform)은 영상에서 몇 개의 파라미터로 표현되는 기하학적 요소 추출을 위해 널리 사용되고 있는 방법 중 하나이다. 하지만 허프 변환은 영상의 한 픽셀이 허프 공간(Hough space)의 한 방정식에 대응되는 일대다 특성으로 인해 잡음에 민감한 특성을 갖는다. 이러한 잡음 민감성은 검출되는 직선의 개수뿐만이 아니라 검출된 직선의 품질에도 영향을 미칠 수 있다. 즉, 실제 직선에서 벗어난 직선이 검출되거나 하나의 실제 직선에 대해 여러 개의 직선이 검출되는 등의 직선 왜곡이 발생할 수 있다. 이러한 직선 왜곡은 잡음 이외에도 허프 공간의 설정, 특히 각 해상도의 설정에 영향을 받는다. 이 논문에서는 기존의 허프 변환에서 발생하는 이러한 직선 왜곡을 분석하고, 잡음 민감성을 줄이기 위해 제안된 경계선 강도 허프 변환(Edge Strength Hough Transform, ESHT)에서 이러한 왜곡이 적게 발생함을 보인다. 또한 ESHT에서만 발생할 수 있는 왜곡을 분석하고 해결방안을 제시한다. 제시한 방법에 의해 직선의 왜곡이 감소하는 것은 실험 결과를 통해 확인할 수 있다.

• Journal of the Korea Society of Computer and Information
• /
• v.15 no.1
• /
• pp.43-50
• /
• 2010

Fuzzy c-means (FCM) and possibilistic c-means (PCM) are the two most well-known clustering algorithms in fuzzy clustering area, and have been applied in many applications in their original or modified forms. However, FCM's noise sensitivity problem and PCM's overlapping cluster problem are also well known. Recently there have been several attempts to combine both of them to mitigate the problems and possibilistic fuzzy c-means (PFCM) showed promising results. In this paper, we proposed a modified PFCM using regularization to reduce noise sensitivity in PFCM further. Regularization is a well-known technique to make a solution space smooth and an algorithm noise insensitive. The proposed algorithm, PFCM with regularization (PFCM-R), can take advantage of regularization and further reduce the effect of noise. Experimental results are given and show that the proposed method is better than the existing methods in noisy conditions.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 1994.10a
• /
• pp.312-316
• /
• 1994

본 연구를 통해 공간 푸리에변환을 이용한 반사계수측정에 있어서 L.S.B.M 및 유한크기 모델의 사용가능성과 유용성을 살펴보았다. 1) L.S.B.M은 P.D.M의 측정음압내에 포함되는 잡음에 대한 민감성을 줄일 수 있어 잡음에 대해 안정한 측정을 할 수 있는 장점이 있음을 알 수 있었다. 2) 유한크기모델은 무한크기모델의 경우 측정면적보다 큰 측정할 반사물질이 요구되는데 반해 측정할 물질의 크기에는 무관하게 반사계수를 얻을 수 있었고 이는 공간 푸리에 변환을 이용한 반사계수 측정방법의 유용성을 증가시킬 수 있다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.12 no.2
• /
• pp.369-377
• /
• 2008

Though the Hough transform(HT) is a well-known method for detecting analytical shape represented by a number of free parameters, the basic property of the HT, the one-to-many mapping from an image spare to a Hough space, causes the innate problem, the sensitivity to noise. This basic problem also deteriorates the quality of detected lines and makes the detected line deviated from the real one or generates some bogus, multiple lines where only one real line exists. The size of Hough space also affects the quality of detected lines. In this paper, we analyzed the line distortions in the traditional Hough transform and showed that the distortions are relieved in the edge strength Hough transform(ESHT), which is a modified HT. However the usage of expanded edge and edge strength in ESHT can cause some new line distortions which do not exist in the HT. These new ones can be solved by a proper setting of decreasing and broadening parameter values and the optimal values can be determined only by some pre-determined values. We also illustrated several examples to show the distortion-decreasing property of ESHT.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2007.06a
• /
• pp.728-731
• /
• 2007

Though the Hough transform is a well-known method for detecting analytical shape represented by a number of free parameters, the basic property of the Hough transform, the one-to-many mapping from an image space to a Hough space, causes the innate problem, the sensitivity to noise. To remedy this problem, Edge Strength Hough Transform (ESHT) was proposed and proved to reduce the noise sensitivity. However the performance of ESHT depends on the size of a Hough space and image and some other parameters, which play an important role in ESHT and should be decided experimentally. In this paper, we derived a formula to decide decreasing parameter. Using the derived formulae, the decreasing parameter value can be decided only with the pre-determined values, the size of a Hough space and an image, which make it possible to decide them automatically.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.10 no.11
• /
• pp.2055-2061
• /
• 2006

The detection of geometric primitives from a digital image is one of the basic tasks in computer vision area and the Hough transform is a well-known method for detecting analytical shape represented by a number of free parameters. However the basic property of the Hough transform, the one-to-many mapping from an image space to a Hough space, causes the innate problem, the sensitivity to noise. In this paper, we proposed Edge Strength Hough Transform which uses edge strength to reduce the sensitivity to noise and proved the insensitivity using the ratio of peaks in a Mough space. We also experimented the proposed method on lines and got small number of peaks in a Hough space compared to traditional Hough transform, which supports the noise insensitivity of the proposed method.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.17 no.5
• /
• pp.575-581
• /
• 2007

Though the Hough transform is a well-known method for detecting analytical shape represented by a number of free parameters, the basic property of the Hough transform, the one-to-many mapping from an image space to a Hough space, causes the innate problem, the sensitivity to noise. To remedy this problem, Edge Strength Hough Transform (ESHT) was proposed and proved to reduce the noise sensitivity. However the performance of ESHT depends on the size of a Hough space and image and some other parameters which should be decided experimentally. In this paper, we derived formulae to decide 2 parameter values; decreasing parameter and broadening parameter, which play an important role in ESHT. Using the derived formulae, 2 parameter values can be decided only with the pre-determined values, the size of a Hough space and an image, which make it possible to decide them automatically. The experiments with different parameter values also support the result.

• Journal of IKEEE
• /
• v.19 no.3
• /
• pp.440-446
• /
• 2015

This study has examined susceptibility of LNA(Low Noise Amplifier) due to Front-Door Coupling under Narrow-Band high power electromagnetic wave. M/DFR(Malfunction/Destruction Failure Rate) was measured to investigate the diagnostic of IC test. In addition, decapsulation analysis was used to understand the inside of the chip state in LNA devices. The experiments is employed as an open-ended waveguide to study the destruction effects of LNA using a 2.45 GHz Magnetron as a high power electromagnetic wave. The susceptibility level of LNA was assessed by electric field strength, and its failure modes were observed. The malfunction of LNA device has showed as the type of self-reset and power-reset. The electric field strength of malfunction threshold is 524 V/m and 1150 V/m respectively. Also, he electric field of destruction threshold is 1530 V/m. Three types of damaged LNA were observed by decapsulation analysis: component, onchipwire, and bondwire destruction. Based on these results, the susceptibility of the LNA can be applied to a database to help elucidate the effects of microwaves on electronic equipment.