• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.11
• /
• pp.3493-3506
• /
• 2022

In the field of scene segmentation, the precise segmentation of object boundaries in sports movement scene images is a great challenge. The geometric information and spatial information of the image are very important, but in many models, they are usually easy to be lost, which has a big influence on the performance of the model. To alleviate this problem, a parallel dense dilated convolution merging Network (termed PDDCM-Net) was proposed. The proposed PDDCMNet consists of a feature extractor, parallel dilated convolutions, and dense dilated convolutions merged with different dilation rates. We utilize different combinations of dilated convolutions that expand the receptive field of the model with fewer parameters than other advanced methods. Importantly, PDDCM-Net fuses both low-level and high-level information, in effect alleviating the problem of accurately segmenting the edge of the object and positioning the object position accurately. Experimental results validate that the proposed PDDCM-Net achieves a great improvement compared to several representative models on the COCO-Stuff data set.

• Bulletin of the Korean Mathematical Society
• /
• v.48 no.2
• /
• pp.291-302
• /
• 2011

We first study the generalized Fourier-Gauss transforms of functionals defined on the complexification $\cal{B}_C$ of an abstract Wiener space ($\cal{H}$, $\cal{B}$, ${\nu}$). Secondly, we introduce a new class of convolution products of functionals defined on $\cal{B}_C$ and study several properties of the convolutions. Then we study various relations among the first variation the convolutions, and the generalized Fourier-Gauss transforms.

• Communications of the Korean Mathematical Society
• /
• v.31 no.4
• /
• pp.791-809
• /
• 2016

By introducing two fractional convolutions, we obtain the convolution theorems for fractional Fourier cosine and sine transforms. Applying these convolutions, we construct two Boehmian spaces and then we extend the fractional Fourier cosine and sine transforms from these Boehmian spaces into another Boehmian space with desired properties.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2006.05a
• /
• pp.441-442
• /
• 2006

It is attempted to find out the optimal shape of U-type bellows using the finite element analysis. The design factors, mountain height, length, thickness, and the number of convolutions are considered and the proper values are chosen fur the simulation. The results show that as the number of convolutions reduces, the volume decreases while the stress increases. However, as the number of convolutions increases, the volume increases above the standard volume and the stress obviously increases. In addition, the effect of the thickness of bellows on the stress is very large. Both of the mass and stress are decreasing at a certain lower value region. Also, we investigated shape optimization with considering maximum stress distribution tendency.

• Journal of the Korean Mathematical Society
• /
• v.22 no.2
• /
• pp.191-197
• /
• 1985

• Korean Journal of Mathematics
• /
• v.24 no.3
• /
• pp.573-586
• /
• 2016

We study the conditional integral transforms and conditional convolutions of functionals defined on K[0, T]. We consider a general vector-valued conditioning functions $X_k(x)=({\gamma}_1(x),{\ldots},{\gamma}_k(x))$ where ${\gamma}_j(x)$ are Gaussian random variables on the Wiener space which need not depend upon the values of x at only finitely many points in (0, T]. We then obtain several relationships and formulas for the conditioning functions that exist among conditional integral transform, conditional convolution and first variation of functionals in $E_{\sigma}$.

• The Korean Journal of Applied Statistics
• /
• v.22 no.6
• /
• pp.1345-1353
• /
• 2009

We introduce a simple methodology, so-called generalized gamma-polynomial approximation, based on moment-matching technique to approximate survival and hazard functions in the context of parametric survival analysis. We use the generalized gamma-polynomial approximation to approximate the density and distribution functions of convolutions and finite mixtures of random variables, from which the approximated survival and hazard functions are obtained. This technique provides very accurate approximation to the target functions, in addition to their being computationally efficient and easy to implement. In addition, the generalized gamma-polynomial approximations are very stable in middle range of the target distributions, whereas saddlepoint approximations are often unstable in a neighborhood of the mean.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2020.11a
• /
• pp.25-28
• /
• 2020

Automatic segmentation of brain tissues such as WM, GM, and CSF from brain MRI scans is helpful for the diagnosis of many neurological disorders. Accurate segmentation of these brain structures is a very challenging task due to low tissue contrast, bias filed, and partial volume effects. With the aim to improve brain MRI segmentation accuracy, we propose an end-to-end convolutional based U-SegNet architecture designed with multi-scale kernels, which includes cascaded dilated convolutions for the task of brain MRI segmentation. The multi-scale convolution kernels are designed to extract abundant semantic features and capture context information at different scales. Further, the cascaded dilated convolution scheme helps to alleviate the vanishing gradient problem in the proposed model. Experimental outcomes indicate that the proposed architecture is superior to the traditional deep-learning methods such as Segnet, U-net, and U-Segnet and achieves high performance with an average DSC of 93% and 86% of JI value for brain MRI segmentation.

• Journal of Ocean Engineering and Technology
• /
• v.20 no.6 s.73
• /
• pp.123-129
• /
• 2006

The mechanical properties of bellows, such as the extensibility and the strength can be changed depending on the shape. For the shipbuilding material, it is desirable that the fatigue life is long due to the elastic property and the reduction of thermal stress in piping system. Nowadays, the domestic production and design of bellows are based on the E.J.M.A. Code. Therefore, the design standard is in need because of much errors and lack of detailed analysis. In this study, it is attempted to find out the optimal shape of U-type bellows using the finite element analysis. The design factors, mountain height, length, thickness, and the number of convolutions are considered and the proper values are chosen for the simulation. The results shaw that as the number of convolutions reduces, the volume decreases while the stress increases. However, as the number of convolutions increases, the volume increases above the standard volume and the stress obviously increases. In addition, the effect of the thickness of bellows on the stress is very large. Both of the mass and stress are decreasing at a certain lower value region. Also, we investigated shape optimization with considering maximum stress distribution tendency.

• Communications of the Korean Mathematical Society
• /
• v.36 no.3
• /
• pp.485-494
• /
• 2021

In this article, we prove the existence of a solution to some classes of integral equations of generalized convolution type generated by the Kontorovich-Lebedev (K) transform, the Laplace (𝓛) transform and the Fourier (F) transform in some appropriate function spaces and represent it in a closed form.