• Journal of applied mathematics & informatics
• /
• v.19 no.1_2
• /
• pp.151-164
• /
• 2005

The regularized structured total least norm (RSTLN) method finds an approximate solution x and error matrix E to the overdetermined linear system (H + E)x $\approx$ b, preserving structure of H. A new separation scheme by parts of variables for the regularized structured total least norm on blind deconvolution problem is suggested. A method combining the regularized structured total least norm method with a separation by parts of variables can be obtain a better approximated solution and a smaller residual. Computational results for the practical problem with Block Toeplitz with Toeplitz Block structure show the new method ensures more efficiency on image restoration.

• Journal of Institute of Control, Robotics and Systems
• /
• v.4 no.2
• /
• pp.170-177
• /
• 1998

In this paper, a unified solution of Hankel norm approximation problem is proposed by $\delta$-operator. To derive the main result, all-pass property is derived from the inner and co-inner property in the $\delta$-domain. The solution of all-pass becomes an optimal Hankel norm approximation problem in .delta.-domain through LLFT(Low Linear Fractional Transformation) inserting feedback term $\phi(\gamma)$, which is a free design parameter, to hold the error bound desired against the variance between the original model and the solution of Hankel norm approximation problem. The proposed solution does not only cover continuous and discrete ones depending on sampling interval but also plays a key role in robust control and model reduction problem. The verification of the proposed solution is exemplified via simulation for the zero-order Hankel norm approximation problem and the model reduction problem applied to a 16th order MIMO system.

• Journal of Communications and Networks
• /
• v.9 no.2
• /
• pp.185-191
• /
• 2007

Alpha stable distribution is better for modeling impulsive noises than Gaussian distribution in signal processing. This class of process has no closed form of probability density function and finite second order moments. In general, Wiener filter theory is not meaningful in S$\alpha$SG environments because the expectations may be unbounded. We proposed a new adaptive recursive least p-norm Kalman filtering algorithm based on least p-norm of innovation process with infinite variances, and a new robust multiuser detection method based on least p-norm Kalman filtering. The simulation experiments show that the proposed new algorithm is more robust than the conventional Kalman filtering multiuser detection algorithm.

• Proceedings of the KSRS Conference
• /
• 2000.04a
• /
• pp.96-101
• /
• 2000

SAR(Synthetic Aperture Radar) interferometry 기술은 co-registration, 정밀궤도 계산, phase unwrapping, 지형보정과 같은 기술로 구성되어있다. 구속화된 위상값을 절대 위상값으로 변환하는 과정인 phase unwrapping 기술은 정밀지형고도를 얻는데 있어서 핵심기술이다. 본 연구에서는 JERS-1 SAR 영상으로부터 interferogram을 구하고, 이로부터 추출된 위상정보를 이용하여 branch cut(Goldstein et. al, 1988), minimum discontinuity(Flynn, 1997) 그리고 minimum $L^p$-norm(Ghiglia and Romero, 1996)방법 적용결과에 대한 비교 분석을 실시하였다. Goldstein 알고리즘은 수행속동가 매우 빠르지만 residue를 연결한 branch cut에 의해 분활된 영역 내에서, 서로 다른 적분 경로로 인해 위상이 단절되었다. 영상내의 모든 화소에서 절대 위상을 구한 minimum discontinuity와 minimum $L^p$-norm 알고리즘 수행 결과는 상관관계가 0.995로 매우 유사하였는데, 가중된 불연속선의 합을 최소화하는 minimum discontinuity 알고리즘이 minimum $L^p$-norm에 비해 영상 일부 지역에서 발생하는 위상 오차를 전파시키지 않는다는 장점이 있다. Minimum $L^p$-norm 방법은 다른 두 방법과 달리 위상정보 내에 많은 잡음이 있더라도 적절한 해를 구할 수 있다는 장점이 있다. 각 방법은 대상 자료의 특성에 따라 효율성이 있으나 Flynn의 알고리즘이 지역적 특성과 무관하게 가장 효과적임을 알 수 있었다.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.12 no.5
• /
• pp.521-528
• /
• 2019

Epilepsy is one of the most prevalent neurological diseases. Electroencephalogram (EEG) signals are widely used for monitoring and diagnosis tool for epileptic seizure. Typically, a huge amount of EEG signals is needed, where they are visually examined by experienced clinicians. In this study, we propose a simple automatic seizure detection framework using intracranial EEG signals. We suggest a sparse approximation based classification (SAC) scheme by solving overdetermined system. L1-norm minimization algorithms are utilized for efficient sparse signal recovery. For evaluation of the proposed scheme, the public EEG dataset obtained by five healthy subjects and five epileptic patients is utilized. The results show that the proposed fast L1-norm minimization based SAC methods achieve the 99.5% classification accuracy which is 1% improved result than the conventional L2 norm based method with negligibly increased execution time (42msec).

• Korean Journal of Human Ecology
• /
• v.17 no.1
• /
• pp.141-150
• /
• 2008

The purpose of this study was to assess the causal relationships among hedonic belief, ambivalence, subjective norm, attitude and meat consumption behavior. A total of 318 questionnaires were completed. Structural equation model was used to measure the causal effects of constructs. Results of the study demonstrated that fit of the restricted baseline model is significantly worse than that of the unrestricted proposed model, in which more parameters are estimated. The effects of hedonic belief, ambivalence and subjective norm on attitude were statistically significant. The effects of hedonic belief, subjective norm and attitude on meat consumption were statistically significant. The effect of attitude on intention was statistically significant. Moreover, attitude played a mediating role in the relationships between hedonic belief and meat consumption, between ambivalence and meat consumption, and between subjective norm and intention. This study suggested that the consumer decision-making process for eating meat products is best modeled as a complex system that incorporates both direct and indirect effects on meat consumption. This study believed the evidence presented supports this position. Moreover, this study appeared to be a worthy area of pursuit.

• Journal of the Korean Mathematical Society
• /
• v.57 no.3
• /
• pp.721-745
• /
• 2020

In this paper we study fractional Sobolev spaces characterized by a norm based on eigenfunction expansions. The goal of this paper is twofold. The first one is to define fractional Sobolev spaces of order -1 ≤ s ≤ 2 equipped with a norm defined in terms of Neumann eigenfunction expansions. Due to the zero Neumann trace of Neumann eigenfunctions on a boundary, fractional Sobolev spaces of order 3/2 ≤ s ≤ 2 characterized by the norm are the spaces of functions with zero Neumann trace on a boundary. The spaces equipped with the norm are useful for studying cross-sectional traces of solutions to the Helmholtz equation in waveguides with a homogeneous Neumann boundary condition. The second one is to define fractional Sobolev spaces of order -1 ≤ s ≤ 1 for vector-valued functions in a simply-connected, bounded and smooth domain in ℝ². These spaces are defined by a norm based on series expansions in terms of eigenfunctions of the vector Laplacian with boundary conditions of zero tangential component or zero normal component. The spaces defined by the norm are important for analyzing cross-sectional traces of time-harmonic electromagnetic fields in perfectly conducting waveguides.

• Journal of IKEEE
• /
• v.20 no.3
• /
• pp.226-234
• /
• 2016

Electrical resistance tomography (ERT) is an imaging technique where the internal resistivity distribution inside an object is reconstructed. The ERT image reconstruction is a highly nonlinear ill-posed problem, so regularization methods are used to achieve desired image. The reconstruction outcome is dependent on the type of regularization method employed such as l2-norm, l1-norm, and total variation regularization method. That is, use of an appropriate regularization method considering the flow characteristics is necessary to attain good reconstruction performance. Therefore, in this paper, regularization methods are tested through numerical simulations with different flow conditions and the performance is compared.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.11
• /
• pp.3507-3522
• /
• 2022

Model pruning methods have attracted huge attention owing to the increasing demand of deploying models on low-resource devices recently. Most existing methods use the weight norm of filters to represent their importance, and discard the ones with small value directly to achieve the pruning target, which ignores the contribution of the small norm filters. This is not only results in filter contribution waste, but also gives comparable performance to training with the random initialized weights [1]. In this paper, we point out that the small norm filters can harm the performance of the pruned model greatly, if they are discarded directly. Therefore, we propose a novel filter contribution recycle (FCR) method for structured model pruning to resolve the fore-mentioned problem. FCR collects and reassembles contribution from the small norm filters to obtain a mixed contribution collector, and then assigns the reassembled contribution to other filters with higher probability to be preserved. To achieve the target FLOPs, FCR also adopts a weight decay strategy for the small norm filters. To explore the effectiveness of our approach, extensive experiments are conducted on ImageNet2012 and CIFAR-10 datasets, and superior results are reported when comparing with other methods under the same or even more FLOPs reduction. In addition, our method is flexible to be combined with other different pruning criterions.

• Journal of the Korean Society of Food Culture
• /
• v.23 no.3
• /
• pp.328-335
• /
• 2008

The objective of this study was to evaluate the causal relationships among environmental belief, ambivalence, subjective norm, attitude and meat consumption behavior. A total of 318 questionnaires were completed. A structural equation model was employed to assess the causal effects of constructs. The results of the study demonstrated that the structural analysis results for the data also indicated excellent model fit. The effects of environmental belief, ambivalence, and subjective norm on attitude were statistically significant. The effects of environmental belief, subjective norm and attitude on meat consumption were statistically significant. The effects of attitude on intention were statistically significant. As had been expected, intention exerted a significant effect on meat consumption. Moreover, environmental belief and ambivalence exerted significant indirect effects on meat consumption through attitude. Subjective norm exerted a significant indirect effect on meat consumption through attitude and intention. Subjective norm also exerted a significant indirect effect on intention through attitude. In developing and testing conceptual models which integrate the relationship among behavioral belief, attitude variable, behavioral intention and meat consumption, this study may approach a deeper understanding of the complex relationship among meat consumption behavior-related variables. Greater understanding of the complex relationship among meat consumption behavior-related variables can improve the practical or managerial diagnosis of the problem and opportunities for different marketing strategies including meat production and meat product development and marketing communication.