• Proceedings of the Korea Multimedia Society Conference
• /
• 2002.05c
• /
• pp.320-324
• /
• 2002

본 연구에서는 모멘트와 뉴우턴법 및 모멘트와 할선법에 각각 기초한 고정점 알고리즘의 신경망 기반 독립성분분석 기법을 제안하였다. 여기서 뉴우턴법과 할선법은 각각 엔트로피에 기초한 목적함수의 근을 구하는 근사화 방법으로 빠른 경신을 위함이고, 모멘트는 근사화에 의한 역혼합행렬의 경신과정에서 발생하는 발진을 줄여 좀 더 빠른 학습을 위함이다. 제안된 기법을 256×256 픽셀(pixel)의 8개 지문영상으로부터 임의의 혼합행렬에 따라 발생되는 영상들을 각각 대상으로 시뮬레이션 한 결과, 모멘트와 할선법에 기초한 알고리즘이 모멘트와 뉴우턴에 기초한 알고리즘보다 우수한 분리성능과 빠른 학습속도가 있음을 확인하였다.

• The KIPS Transactions:PartB
• /
• v.11B no.4
• /
• pp.429-436
• /
• 2004

This paper proposes an independent component analyses(ICAs) of the fixed-point (FP) algorithm based on Newton and secant method by adding the kurtosis, respectively. The kurtosis is applied to cluster the analyzed components, and the FP algorithm is applied to get the fast analysis and superior performance irrelevant to learning parameters. The proposed ICAs have been applied to the problems for separating the 6-mixed signals of 500 samples and 10-mixed images of $512\times512$ pixels, respectively. The experimental results show that the proposed ICAs have always a fixed analysis sequence. The results can be solved the limit of conventional ICA without a kurtosis which has a variable sequence depending on the running of algorithm. Especially. the proposed ICA can be used for classifying and identifying the signals or the images. The results also show that the secant method has better the separation speed and performance than Newton method. And, the secant method gives relatively larger improvement degree as the problem size increases.

• The KIPS Transactions:PartB
• /
• v.9B no.5
• /
• pp.643-652
• /
• 2002

This paper proposes an efficient hybrid fixed-point (FP) algorithm for improving performances of the independent component analysis (ICA) based on neural networks. The proposed algorithm is the FP algorithm based on secant method and momentum for ICA. Secant method is applied to improve the separation performance by simplifying the computation process for estimating the root of objective function, which is to minimize the mutual informations of the independent components. The momentum is applied for high-speed convergence by restraining the oscillation if the process of converging to the optimal solution. It can simultaneously achieve a superior properties of the secant method and the momentum. The proposed algorithm has been applied to the composite fingerprints and the images generated by random mixing matrix in the 8 fingerprints of $256\times{256}$-pixel and the 10 images of $512\times{512}$-pixel, respectively. The simulation results show that the proposed algorithm has better performances of the separation speed and rate than those using the FP algorithm based on Newton and secant method. Especially, the secant FP algorithm can be solved the separating performances depending on initial points settings and the nonrealistic learning time for separating the large size images by using the Newton FP algorithm.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.12 no.3
• /
• pp.210-218
• /
• 2002

This paper proposes an efficient separation method of the composite images by using independent component analysis(ICA) based on neural networks of the approximate learning algorithm. The Proposed learning algorithm is the fixed point(FP) algorithm based on Secant method which can be approximately computed by only the values of function for estimating the root of objective function for optimizing entropy. The secant method is an alternative of the Newton method which is essential to differentiate the function for estimating the root. It can achieve a superior property of the FP algorithm for ICA due to simplify the composite computation of differential process. The proposed algorithm has been applied to the composite signals and image generated by random mixing matrix in the 4 signal of 500-sample and the 10 images of $512{\times}512-pixel$, respectively The simulation results show that the proposed algorithm has better performance of the learning speed and the separation than those using the conventional algorithm based method. It also solved the training performances depending on initial points setting and the nonrealistic learning time for separating the large size image by using the conventional algorithm.