• The Journal of the Acoustical Society of Korea
• /
• v.27 no.1
• /
• pp.26-32
• /
• 2008

UBSS (unde-determined blind source separation) is composed of the stages of BMMR (blind mixing matrix recovery) and BSR (blind source recovery). Generally, these two stages are executed using the sparseness of the observed data, and their performance is influenced by the accuracy of the measure of the sparseness. In this paper, as introducing the measure of the sparseness using the Gini coefficient to BSR stage, we obtained more accurate measure of the sparseness and better performance of BSR than methods using the $l_1$-norm, $l_q$-norm, and hyperbolic tangent, which was confirmed via computer simulations.

• Journal of Digital Contents Society
• /
• v.18 no.2
• /
• pp.347-356
• /
• 2017

It is well-known that the face recognition method via sparse representation has been proved very robust and showed good performance. Its weakness is, however, that its time complexity is very high because it should solve $L_1$-minimization problem to find the sparse solution. In this paper, we propose to use the ROMP(Regularized Orthogonal Matching Pursuit) method for the sparse solution, which solves the $L_2$-minimization problem with regularization condition using the greed strategy. In experiments, we shows that the proposed method is comparable to the existing best $L_1$-minimization solver, Homotopy, but is 60 times faster than Homotopy. Also, we proposed C-SCI method for classification. The C-SCI method is very effective since it considers the sparse solution only without reconstructing the test data. It is shown that the C-SCI method is comparable to, but is 5 times faster than the existing best classification method.

• The Journal of the Korea Contents Association
• /
• v.2 no.2
• /
• pp.91-97
• /
• 2002

Let (X, F, g) be a fuzzy measure space. Then for any h$\in$ $L^{0}$ (X) , a$\in$[0 , 1] , and $A\in$F ∫$_{A}$aㆍh($\chi$)┬g＝aㆍ∫$_{A}$h($\chi$)┬g with the t-seminorm ┬(x, y)= xy. And we prove that the Seminormed fuzzy integral has some linearity properties only for ｛0,1｝-classes of fuzzy measure as follow, For any f, h$\in$ $L^{0}$ ($\chi$), any a, b$\in$R+: af＋bh$\in$ $L^{0}$ ($\chi$)⇒ ∫$_{A}$(af＋bh)┬g＝a∫$_{A}$f┬g＋b∫$_{A}$h┬g; if and only if g is a probability measure fulfilling g(A) $\in$｛0, 1｝ for all $A\in$F.n$F.

• Korean Journal of Remote Sensing
• /
• v.36 no.5_2
• /
• pp.961-973
• /
• 2020

In this manuscript, a new pansharpening model based on Convolutional Neural Network (CNN) was developed. Dilated convolution, which is one of the representative convolution technologies in CNN, was applied to the model by making it deep and complex to improve the performance of the deep learning architecture. Based on the dilated convolution, the residual network is used to enhance the efficiency of training process. In addition, we consider the spatial correlation coefficient in the loss function with traditional L1 norm. We experimented with Dilated Residual Networks (DRNet), which is applied to the structure using only a panchromatic (PAN) image and using both a PAN and multispectral (MS) image. In the experiments using KOMPSAT-3A, DRNet using both a PAN and MS image tended to overfit the spectral characteristics, and DRNet using only a PAN image showed a spatial resolution improvement over existing CNN-based models.