• The Journal of the Korea Contents Association
• /
• v.3 no.3
• /
• pp.98-102
• /
• 2003

For elucidating the key role of hidden neurons in information processing of Multilayer perceptrons(MLPs), we prove that the correlation coefficient between weighted sums to hidden neurons decreases under element-wise nonlinear transformations. This is verified through training of MLPs for an isolated word recognition problem. From this result, we can say that the element-wise nonlinear functions reduces redundancy in the information contents of hidden neurons.

• Journal of the Korean Society of Radiology
• /
• v.13 no.4
• /
• pp.509-516
• /
• 2019

In the linear transformation method, the original image is divided into a plurality of range blocks, and a partial transform system for finding an optimal domain block existing in the image for each range block is used to adjust the performance of the compression ratio and the picture quality, The nonlinear transformation method uses only the rotation transformation among eight shuffle transforms. Since the search is performed only in the limited domain block, the coding time is faster than the linear transformation method of searching the domain block for any block in the image, Since the optimal domain block for the range block can not be selected in the image, the performance may be lower than other methods. Therefore, the nonlinear transformation method improves the performance by increasing the approximation degree of the brightness coefficient conversion instead of selecting the optimal domain block, The smaller the size of the block, the higher the PSNR value, The higher the compression ratio is increased groups were quadtree block divided to encode the image at best.

• Proceedings of the Optical Society of Korea Conference
• /
• 2001.02a
• /
• pp.224-225
• /
• 2001

3차 비선형 광학 현상을 이용한 파장변환에 대한 연구는 1960년대 초 비선형 광학 연구가 시작된 이래 최근까지 연구자들로부터 큰 관심을 끌지 못하였다. 1963년 Terhune 등이 방해석을 이용한 3차 조화파 발생의 첫 연구결과를 보고하였으나, 일반적으로 직접적인 3차 파장변환 효율은 2차의 경우에 비해 현저히 낮기 때문에, 2차 파장변환 과정을 두 번 이용하여 3차에 해당하는 파장변환을 얻는 방법이 널리 활용되어 왔다. (중략)

• Journal of Broadcast Engineering
• /
• v.17 no.4
• /
• pp.634-639
• /
• 2012

In this paper, we propose nonlinear optimization method for feature matching from multiple view image. Typical solution of feature matching is by solving linear equation. However this solution has large error due to nonlinearity of image formation model. If typical nonlinear optimization method is used, complexity grows exponentially over the number of features. To make complexity lower, we use sparse Levenberg-Marquardt nonlinear optimization for matching of features over multiple view image.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2012.05a
• /
• pp.336-339
• /
• 2012

본 논문에서는 비선형 MLCA(Maximum Length Cellular Automata)와 1D CAT(One-Dimensional Cellular Automata Transform)를 이용하여 의료 영상 암호화 방법을 제안한다. 암호화 방법은 먼저, Wolfram Rule 행렬에 의해 전이행렬 T를 생성한다. 그 후, 암호화하려는 원 영상에 생성된 전이 행렬 T를 곱하여 원 영상의 픽셀 값을 변환한다. 또한 변환된 원 영상을 여원 벡터 F와 XOR 연산하여 비선형 MLCA가 적용된 영상으로 변환한다. 다음, 게이트웨이 값을 설정하여 1D CAT 기저함수를 생성한다. 그리고, 비선형 MLCA가 적용된 영상에 생성된 1D CAT 기저함수를 곱하여 암호화를 한다. 마지막으로 키 공간 분석을 통하여 제안한 방법이 높은 암호화 수준의 성질을 가졌음을 검증한다.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.26 no.5B
• /
• pp.439-446
• /
• 2006

In the present study, we applied wavelet transform to decompose the hydro-meteorological data such as precipitation and temperature into the components with different return periods with a primary objective for extraction of nonlinear dynamical component. For the transform, we used the Daubechies wavelet of order 9 ('db9') as a basis function. Also, we applied the correlation dimension analysis to determine whether or not the detail and approximation components at the respective decomposition stage with the increasing of scale in the wavelet transform reveal the nonlinear dynamical characteristics. In other words, we proposed the combined use of the wavelet transform and the correlation dimension analysis as methodology to extract the nonlinear dynamical component from the hydro-meteorological data. The derived result has shown the method proposed in the present study is suitable for the segregation and extraction of the nonlinear dynamical component which is, in general, difficult to reveal by using the raw data.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.19 no.6
• /
• pp.865-871
• /
• 2009

In this paper, a novel feedback linearization is proposed for discrete-time nonlinear systems described by discrete-time T-S fuzzy models. The local linear models of a T-S fuzzy model are transformed to a controllable canonical form respectively, and their T-S fuzzy combination results in a feedback linearizable Tagaki-Sugeno fuzzy model. Based on this model, a nonlinear state feedback linearizing input is determined. Nonlinear state transformation is inferred from the linear state transformations for the controllable canonical forms. The proposed method of this paper is more intuitive and easier to understand mathematically compared to the well-known feedback linearization technique which requires a profound mathematical background. The feedback linearizable condition of this paper is also weakened compared to the conventional feedback linearization. This means that larger class of nonlinear systems is linearizable compared to the case of classical linearization.

• Proceedings of the Acoustical Society of Korea Conference
• /
• 1998.06c
• /
• pp.115-118
• /
• 1998

본 연구에서는 입력 음성 특징 파라메터를 선형 및 비선형 변환함으로써 음성 특징의 1 차, 2 차 및 고차 통계치를 정규화하였다. 이러한 정규화 기법을 통해서 부가잡음 환경에서의 음성인식 성능향상을 얻을 수 있었다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2000.10b
• /
• pp.1321-1324
• /
• 2000

본 논문에서는 한국전자통신연구원 VR 연구센터에서 개발한 비선형 MPEG-2 편질 시스템인 "솔거(Solger2001)" 에 사용되는 스트림 형식 변환기를 소개한다. 기존 솔거의 단점으로 여겨져 왔던 다양한 입력 스트림을 지원하지 않는 문제점을 해결하고자 기존의 많은 비선형 편집기에서 입력 포맷으로 사용되고 있는 AVI를 지원하도록 하여 솔거의 활용 범위를 넓혔다.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.36 no.1
• /
• pp.57-65
• /
• 2023

A vibration response-based detection system was used to investigate the adhesive areas of single-lap joints using a nonlinear transformation approach for deep learning. In industry or engineering fields, it is difficult to know the condition of an invisible part within a structure that cannot easily be disassembled and the conditions of adhesive areas of adhesively bonded structures. To address these issues, a detection method was devised that uses nonlinear transformation to determine the adhesive areas of various single-lap-jointed specimens from the vibration response of the reference specimen. In this study, a frequency response function with nonlinear transformation was employed to identify the vibration characteristics, and a virtual spectrogram was used for classification in convolutional neural network based deep learning. Moreover, a vibration experiment, an analytical solution, and a finite-element analysis were performed to verify the developed method with aluminum, carbon fiber composite, and ultra-high-molecular-weight polyethylene specimens.