• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.8 no.4
• /
• pp.75-88
• /
• 2008

This paper presents a spatial-level nonparametric multi-focus image fusion technique based on kernel estimates of input image blocks' underlying class-conditional probability density functions. Image fusion is approached as a classification task whose posterior class probabilities, P($wi{\mid}Bikl$), are calculated with likelihood density functions that are estimated from the training patterns. For each of the C input images Ii, the proposed method defines i classes wi and forms the fused image Z(k,l) from a decision map represented by a set of $P{\times}Q$ blocks Bikl whose features maximize the discriminant function based on the Bayesian decision principle. Performance of the proposed technique is evaluated in terms of RMSE and Mutual Information (MI) as the output quality measures. The width of the kernel functions, ${\sigma}$, were made to vary, and different kernels and block sizes were applied in performance evaluation. The proposed scheme is tested with C=2 and C=3 input images and results exhibited good performance.

• Bulletin of the Korean Mathematical Society
• /
• v.59 no.5
• /
• pp.1255-1268
• /
• 2022

We consider the Schrödinger type operator 𝓛 = (-𝚫_ℍⁿ)² + V² on the Heisenberg group ℍⁿ, where 𝚫_ℍⁿ is the sub-Laplacian and the non-negative potential V belongs to the reverse Hölder class RH_s for s ≥ Q/2 and Q ≥ 6. We shall establish the (L^p, L^q) estimates for the Riesz transforms T_𝛼,𝛽,j = V^2𝛼𝛁^j_ℍⁿ𝓛^-𝛽, j = 0, 1, 2, 3, where 𝛁_ℍⁿ is the gradient operator on ℍⁿ, 0 < α ≤ 1-j/4, j/4 < 𝛽 ≤ 1, and 𝛽 - 𝛼 ≥ j/4.

• Bulletin of the Korean Mathematical Society
• /
• v.61 no.2
• /
• pp.489-509
• /
• 2024

In this paper, let q ∈ (0, 1]. We establish the boundedness of intrinsic g-functions from the Hardy-Lorentz spaces with variable exponent H^p(·),q(ℝⁿ) into Lorentz spaces with variable exponent L^p(·),q(ℝⁿ). Then, for any q ∈ (0, 1], via some estimates on a discrete Littlewood-Paley g-function and a Peetre-type maximal function, we obtain several equivalent characterizations of H^p(·),q(ℝⁿ) in terms of wavelets.

• Bulletin of the Korean Mathematical Society
• /
• v.51 no.4
• /
• pp.965-978
• /
• 2014

In this paper we establish sharp $L^p$-regularity estimates for averaging operators with convolution kernel associated to hypersurfaces in $\mathbb{R}^d(d{\geq}2)$ of the form $y{\mapsto}(y,{\gamma}(y))$ where $y{\in}\mathbb{R}^{d-1}$ and ${\gamma}(y)={\sum}^{d-1}_{i=1}{\pm}{\mid}y_i{\mid}^{m_i}$ with $2{\leq}m_1{\leq}{\cdots}{\leq}m_{d-1}$.

• Environmental and Resource Economics Review
• /
• v.15 no.1
• /
• pp.51-69
• /
• 2006

This paper analyze the degree of competitiveness of the refining industry after price liberalization. We use two well-known methods: the first is Bresnahan (1982) and Lau (1982) method that estimates a structural model consisting of a demand relation and supply relation and the second is Panzar and Rosse (1987) method that estimates non structural model of the sum of elasticities of gross revenue with respect to input prices. Results from two models show mixed sign, however, our results indicate that price liberalization improved the degree of competitiveness.

• Journal of applied mathematics & informatics
• /
• v.30 no.3_4
• /
• pp.677-683
• /
• 2012

W.Choi([1]) obtains a complete description of ergodic property and several property by making use of the semigroup method. In this note, we shall consider separately the martingale problems for two operators A and B as a detail decomposition of operator L. A key point is that the (K, L, $p$)-martingale problem in population genetics model is related to diffusion processes, so we begin with some a priori estimates and we shall show existence of contraction semigroup {$T_t$} associated with decomposition operator A.

• Bulletin of the Korean Mathematical Society
• /
• v.58 no.1
• /
• pp.235-251
• /
• 2021

We consider the Schrödinger type operator ��k = (-∆)k+Vk on ℝn(n ≥ 2k + 1), where k = 1, 2 and the nonnegative potential V belongs to the reverse Hölder class RHs with n/2 < s < n. In this paper, we establish the (Lp, Lq)-boundedness of the higher order Riesz transform T��,�� = V2��∇2��-��2 (0 ≤ �� ≤ 1/2 < �� ≤ 1, �� - �� ≥ 1/2) and its adjoint operator T∗��,�� respectively. We show that T��,�� is bounded from Hardy type space $H^1_{\mathcal{L}_2}({\mathbb{R}}_n)$ into Lp2 (ℝn) and T∗��,�� is bounded from ��p1 (ℝn) into BMO type space $BMO_{\mathcal{L}_1}$ (ℝn) when �� - �� > 1/2, where $p_1={\frac{n}{4({\beta}-{\alpha})-2}}$, $p_2={\frac{n}{n-4({\beta}-{\alpha})+2}}$. Moreover, we prove that T��,�� is bounded from $BMO_{\mathcal{L}_1}({\mathbb{R}}_n)$ to itself when �� - �� = 1/2.

• Smart Structures and Systems
• /
• v.34 no.2
• /
• pp.97-116
• /
• 2024

The standard l₁-norm regularization is recently introduced for impact force identification, but generally underestimates the peak force. Compared to l₁-norm regularization, l_p-norm (0 ≤ p < 1) regularization, with a nonconvex penalty function, has some promising properties such as enforcing sparsity. In the framework of sparse regularization, if the desired solution is sparse in the time domain or other domains, the under-determined problem with fewer measurements than candidate excitations may obtain the unique solution, i.e., the sparsest solution. Considering the joint sparse structure of impact force in temporal and spatial domains, we propose a general l_p-norm (0 ≤ p < 1) regularization methodology for simultaneous identification of the impact location and force time-history from highly incomplete measurements. Firstly, a nonconvex optimization model based on l_p-norm penalty is developed for regularizing the highly under-determined problem of impact force identification. Secondly, an iteratively reweighed l₁-norm algorithm is introduced to solve such an under-determined and unconditioned regularization model through transforming it into a series of l₁-norm regularization problems. Finally, numerical simulation and experimental validation including single-source and two-source cases of impact force identification are conducted on plate structures to evaluate the performance of l_p-norm (0 ≤ p < 1) regularization. Both numerical and experimental results demonstrate that the proposed l_p-norm regularization method, merely using a single accelerometer, can locate the actual impacts from nine fixed candidate sources and simultaneously reconstruct the impact force time-history; compared to the state-of-the-art l₁-norm regularization, l_p-norm (0 ≤ p < 1) regularization procures sufficiently sparse and more accurate estimates; although the peak relative error of the identified impact force using l_p-norm regularization has a decreasing tendency as p is approaching 0, the results of l_p-norm regularization with 0 ≤ p ≤ 1/2 have no significant differences.

• Asian-Australasian Journal of Animal Sciences
• /
• v.14 no.12
• /
• pp.1665-1669
• /
• 2001

A QTL was localized near S0120 on porcine chromosome 18. The QTL was significant (p<0.05) for average daily gain (ADG) of body weight and backfat thickness (BFT). The estimates of additive and dominance effects for the QTL were 0.0135 kg/day (p<0.001) and 0.0138 kg/day (p>0.5) for ADG and 1.6115 mm (p<0.001) and 0.9281 mm (p>0.05) for BFT. The location of this QTL coincided with a few growth hormone pathway genes. This study suggested that a QTL allele probably resulted from a mutation responsible for physiological lipase deficiency favoring obesity. This QTL might be important to obesity as well as growth in pigs.

• Journal of the Korean Data and Information Science Society
• /
• v.26 no.4
• /
• pp.915-921
• /
• 2015

This experiment was conducted to estimate the heritability and coheritablity of daily milk yield, acetone and ${\beta}$-hydroxybutyrate (BHBA) concentrations in raw milk. The average concentrations of acetone and BHBA were $135.54{\pm}96.29{\mu}mol$ and $61.08{\pm}66.76{\mu}mol$, respectively, and the differences between high group and low group cows were highly significant (p <0.01). The estimates of heritability of daily milk yield, acetone and BHBA concentrations were in the range of 0.18~0.21, 0.11~0.13 and 0.01~0.02, respectively. The estimate of heritability of $Log_e$acetone did not change much, while that of $Log_eBHBA$ increased to 0.03~0.04. The estimates of phenotypic and genetic correlation coefficients between acetone and BHBA were 0.44 and 0.48, respectively. In low milk yield group, the coheritability estimates of BHBA and $Log_eBHBA$ when selection was for daily milk yield were 0.26 and 0.32, respectively. These were higher than the coheritability estimate of acetone when selection was for daily milk yield. The same trend was noted in the coherihability estimates from the whole records using both high and low milk yield groups together. BHBA concentration seemed to be more effectively responding than acetone concentration when selection was for daily milk yield.