• International journal of advanced smart convergence
• /
• v.12 no.4
• /
• pp.134-141
• /
• 2023

We present a novel method aimed at refining ground truth data through regularization and modification, particularly applicable when working with the original ground truth set. Enhancing the performance of deep neural networks is achieved by applying regularization techniques to the existing ground truth data. In many machine learning tasks requiring pixel-level segmentation sets, accurately delineating objects is vital. However, it proves challenging for thin and elongated objects such as blood vessels in X-ray coronary angiography, often resulting in inconsistent generation of ground truth data. This method involves an analysis of the quality of training set pairs - comprising images and ground truth data - to automatically regulate and modify the boundaries of ground truth segmentation. Employing the active contour model and a recursive ground truth generation approach results in stable and precisely defined boundary contours. Following the regularization and adjustment of the ground truth set, there is a substantial improvement in the performance of deep neural networks.

• Journal of the Chungcheong Mathematical Society
• /
• v.26 no.4
• /
• pp.853-867
• /
• 2013

In this paper we study the cardinality of the dot product set generated by two subsets of vector spaces over finite fields. We notice that the results on the dot product problems for one set can be simply extended to two sets. Let E and F be subsets of the d-dimensional vector space $\mathbb{F}^d_q$ over a finite field $\mathbb{F}_q$ with q elements. As a new result, we prove that if E and F are subsets of the paraboloid and ${\mid}E{\parallel}F{\mid}{\geq}Cq^d$ for some large C > 1, then ${\mid}{\Pi}(E,F){\mid}{\geq}cq$ for some 0 < c < 1. In particular, we find a connection between the size of the dot product set and the number of lines through both the origin and a nonzero point in the given set E. As an application of this observation, we obtain more sharpened results on the generalized dot product set problems. The discrete Fourier analysis and geometrical observation play a crucial role in proving our results.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2001.01a
• /
• pp.410-420
• /
• 2001

A primitive conceptualization is defined as the set of all intended situations. A non-primitive conceptualization is defined as the set of all the pairs every of which consists of an intended knowledge system and the set of all the situations admitted by the knowledge system. The reality of a domain is considered as the set of all the situation which have ever taken place in the past, are taking place now and will take place in the future. A conceptualization is defined as precise if the set of intended situations is equal to the domain reality. The representation of various elements of a domain ontology in a model of the ontology is considered. These elements are terms for situation description and situations themselves, terms for knowledge description and knowledge systems themselves, mathematical terms and constructions, auxiliary terms and ontological agreements. It has been shown that any ontology representing a conceptualization has to be non-primitive if either (1) a conceptualization contains intended situations of different structures, or (2) a conceptualization contains concepts designated by terms for knowledge description, or (3) a conceptualization contains concept classes and determines properties of the concepts belonging to these classes, but the concepts themselves are introduced by domain knowledge, or (4) some restrictions on meanings of terms for situation description in a conceptualization depend on the meaning of terms for knowledge description.

• 한국생물공학회:학술대회논문집
• /
• 2001.11a
• /
• pp.886-889
• /
• 2001

C-terminus specific immobilization often results in a increased structural stability resistant to various denaturation factors. In order to elucidate the immobilization effect on the c-terminus in molecular level, we made over 200 protein data set from Protein Data Bank(PDB), analyzed c-terminus structure of each protein, and investigated the structural relationship with the stabilizing factors such as hydrogen bond, ion pairs, cation pi, disulfide bond, solvation free energy, surface area, flexibility and so on.

• Journal of the Korean Mathematical Society
• /
• v.45 no.3
• /
• pp.711-725
• /
• 2008

We give an explicit construction of Grobner-Shirshov pairs and monomial bases for finite-dimensional irreducible representations of the simple Lie algebra $sp_4$. We also identify the monomial basis consisting of the reduced monomials with a set of semistandard tableaux of a given shape, on which we give a colored oriented graph structure.

• 제어로봇시스템학회:학술대회논문집
• /
• 1988.10a
• /
• pp.471-475
• /
• 1988

Pressure and flowrate control systems for a supercritical extraction process are designed and analyzed. To do this, the dynamic model was first set up using the performance equations of control valves, CO2 compressor and the state equation of the supercritical fluid. Using this model, optimum pairs of manipulated and controlled variable which give least steady stat interaction are determined though the relative gain analysis.

• Education of Primary School Mathematics
• /
• v.5 no.2
• /
• pp.95-110
• /
• 2001

What characteristics of computer games encourage persistence, engagement, and learning for both girls and boys\ulcorner The purpose in conducting this research was to identify characteristics of computer games that engage all children-girls and boys- in significant mathematical learning. A set of criteria for evaluating gender fair computer games was developed. Much of this research had involved observing children playing computer games in pairs and small groups. Two game softwares were analyzed by way of dialogues that occurred with the games.

• Proceedings of the IEEK Conference
• /
• 2002.06d
• /
• pp.347-350
• /
• 2002

This paper describes eye detection algorithm using edge information and Support Vector Machine (SVM). We adopt an edge detection and labelling algorithm to detect isolated components. Detected candidate eye pairs finally verified by SVM using Radial Basis Function (RBF) kernel. A detection rate over the test set has been achieved more than 90%, and compared with template matching method. this proposed method significantly reduced FAR.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.38 no.2
• /
• pp.145-153
• /
• 2001

As combinational ATPG algorithms achieve effectively 100% fault coverage, reducing the length of test set without loosing its fault coverage becomes a challenging work. The new approach is based on the independent and the compatible relationships between faults. For more compact test set, the size of compatible fault set must be maximized, thus this algorithm generates fault-pattern pairs, and a fault-pattern pair tree structure using the independent and the compatible relationships between faults. With the fault-pattern pair tree structure, a compact test set effectively generated. The experimental results for ISCAS 85 and 89 benchmark circuits demonstrate the effectiveness of the proposed method.

• KIPS Transactions on Software and Data Engineering
• /
• v.6 no.11
• /
• pp.507-520
• /
• 2017

The set-based similar sequence matching method measures similarity not for an individual data item but for a set grouping multiple data items. In the method, the similarity of two sets is represented as the size of intersection between them. However, there is a critical performances issue for the method in twofold: 1) calculating intersection size is a time consuming process, and 2) the number of set pairs that should be calculated the intersection size is quite large. In this paper, we propose an index-based search method for improving performance of set-based similar sequence matching in order to solve these performance issues. Our method consists of two parts. In the first part, we convert the set similarity problem into the intersection size comparison problem, and then, provide an index structure that accelerates the intersection size calculation. Second, we propose an efficient set-based similar sequence matching method which exploits the proposed index structure. Through experiments, we show that the proposed method reduces the execution time by 30 to 50 times then the existing methods. We also show that the proposed method has scalability since the performance gap becomes larger as the number of data sequences increases.