• 대한원격탐사학회지
• /
• 제20권4호
• /
• pp.275-288
• /
• 2004

이 논문은 다중 센서 원격탐사 화상의 분류를 위해 퍼지 논리 융합과 결합된 relaxation labeling 방법을 제안하였다. 다중 센서 원격탐사 화상의 융합에는 퍼지 논리를, 분광정보와 공간정보의 융합에는 반복적인 relaxation labeling 방법을 적용하였다. 특히 반복적 relaxation labeling 방법은 공간정보의 이용에 따른 분류 화소의 변화양상을 얻을 수 있는 장점이 있다. 토지 피복의 감독 분류를 목적으로 광학 화상과 다중 주파수/편광 SAR 화상에 제안 기법을 적용한 결과, 다중 센서 자료를 이용하고 공간정보를 함께 결합하였을 때 향상된 분류 정확도를 얻을 수 있었다.

• 한국방재학회 논문집
• /
• 제11권3호
• /
• pp.49-56
• /
• 2011

본 연구는 위험물 수송의 최적경로를 결정하는 방법론을 제안하였다. 위험물 차량의 최적경로를 결정할 때에는 위험도 최소화를 목적으로 하는 공공의 입장과 통행시간 최소화를 목적으로 하는 민간기업의 입장이 서로 상충한다. 본 연구에서는 이러한 다기준 의사결정(Multi-criteria decision making)문제 중 하나인 위험물 수송용 최적경로를 탐색하는 방법론으로 Efficient Vector Labeling(이하 EVL) 알고리즘을 제시하였다. EVL 알고리즘은 위험도와 통행시간을 동시에 고려하여 복수의 Pareto optimal 경로(또는 비지배경로)를 탐색하게 한다. 본 연구는 또한 탐색된 비지배경로간의 중복도를 제어할 수 있도록 설계하였다. 개발된 Efficient Vector Labeling 알고리즘을 Test bed network에 적용하여 기존의 경로탐색 방법론과 비교하였다. 적용 결과 새로운 알고리즘이 기존의 알고리즘보다 합리적인 대안경로를 탐색할 수 있는 것으로 분석되었다.

• Journal of applied mathematics & informatics
• /
• 제41권3호
• /
• pp.511-524
• /
• 2023

An L(p₁, p₂, p₃, . . . , p_m)-labeling of a graph G is an assignment of non-negative integers, called as labels, to the vertices such that the vertices at distance i should have at least pi as their label difference. If p₁ = 4, p₂ = 3, p₃ = 2, p₄ = 1, then it is called a L(4, 3, 2, 1)-labeling which is widely studied in the literature. A L(4, 3, 2, 1)-path coloring of graphs, is a labeling g : V (G) → Z⁺ such that there exists at least one path P between every pair of vertices in which the labeling restricted to this path is a L(4, 3, 2, 1)-labeling. This concept was defined and results for some simple graphs were obtained by the same authors in an earlier article. In this article, we study the concept of L(4, 3, 2, 1)-path coloring for complete bipartite graphs, 2-edge connected split graph, Cartesian product and join of two graphs and prove an existence theorem for the same.

• 산업기술연구
• /
• 제30권A호
• /
• pp.25-29
• /
• 2010

In this paper, we implement a multi-touch system using FIDR. The implementation consists of hardware manufacture and development of image processing system. In the hardware system, touch screen, infrared LED placements and infrared camera are made. The image processing procedure is to extract each pointer's coordinates from image data and includes binary-coding, noise-elimination, labeling and calculation of mass center. From the implementation, we are able to make a multi-touch system with considerably lower cost than the existing ones.

• 대한임베디드공학회논문지
• /
• 제10권5호
• /
• pp.325-333
• /
• 2015

Vision based night-time vehicle detection has been an emerging research field in various advanced driver assistance systems(ADAS) and automotive vehicle as well as automatic head-lamp control. In this paper, we propose night-time vehicle detection method based on multi-class support vector machine(SVM) that consists of thresholding, labeling, feature extraction, and multi-class SVM. Vehicle light candidate blobs are extracted by local mean based thresholding following by labeling process. Seven geometric and stochastic features are extracted from each candidate through the feature extraction step. Each candidate blob is classified into vehicle light or not by multi-class SVM. Four different multi-class SVM including one-against-all(OAA), one-against-one(OAO), top-down tree structured and bottom-up tree structured SVM classifiers are implemented and evaluated in terms of vehicle detection performances. Through the simulations tested on road video sequences, we prove that top-down tree structured and bottom-up tree structured SVM have relatively better performances than the others.

• Reproductive and Developmental Biology
• /
• 제35권4호
• /
• pp.503-510
• /
• 2011

Cellular uptake of nanoparticles for stem cell labeling and tracking is a critical technique for biomedical therapeutic applications. However, current techniques suffer from low intracellular labeling efficiency and cytotoxic effects, which has led to great interest in the development of a new labeling strategy. Using silica-coated nanoparticles conjugated with rhodamine B isothiocyanate (RITC) (SR), we tested the cellular uptake efficiency, biocompatibility, proliferation or differentiation ability with murine bone marrow derived hematopoietic stem/progenitor cells. The bone marrow hematopoietic cells showed efficient uptake with SR with dose or time dependent manner and also provided a higher uptake on hematopoietic stem/progenitor cells. Biocompatibility tests revealed that the SR had no deleterious effects on cell cytotoxicity, proliferation, or multi-differentiation capacities in vitro and in vivo. SR nanoparticles are advantageous over traditional labeling techniques as they possess a high level of cellular internalization without limiting the biofunctionality of the cells. Therefore, SR provides a useful alternative for gene or drug delivery into hematopoietic stem/progenitor cells for basic research and clinical applications.

• 한국콘텐츠학회:학술대회논문집
• /
• 한국콘텐츠학회 2009년도 춘계 종합학술대회 논문집
• /
• pp.23-29
• /
• 2009

Blob detection is an essential ingredient process in some computer applications such as intelligent visual surveillance. However, previous blob detection algorithms are still computationally heavy so that supporting real-time multi-channel intelligent visual surveillance in a workstation or even one-channel real-time visual surveillance in a embedded system using them turns out prohibitively difficult. In this paper, we propose a fast and precise blob detection algorithm for visual surveillance. Blob detection in visual surveillance goes through several processing steps: foreground mask extraction, foreground mask correction, and connected component labeling. Foreground mask correction necessary for a precise detection is usually accomplished using morphological operations like opening and closing. Morphological operations are computationally expensive and moreover, they are difficult to run in parallel with connected component labeling routine since they need much different processing from what connected component labeling does. In this paper, we first develop a fast and precise foreground mask correction method utilizing on neighbor pixel checking which is also employed in connected component labeling so that the developed foreground mask correction method can be incorporated into connected component labeling routine. Through experiments, it is verified that our proposed blob detection algorithm based on the foreground mask correction method developed in this paper shows better processing speed and more precise blob detection.

• 한국전기전자재료학회논문지
• /
• 제19권10호
• /
• pp.960-965
• /
• 2006

This research aims to develop the multiple channel electrochemical DNA chip using microfabrication technology. At first, we fabricated a high integration type DNA chip array by lithography technology. Several probe DNAs consisting of thiol group at their 5-end were immobilized on the gold electrodes. Then target DNAs were hybridized and reacted. Cyclic voltammetry showed a difference between target DNA and control DNA in the anodic peak current values. Therefore, it is able to detect a plural genes electrochemically after immobilization of a plural probe DNA and hybridization of non-labeling target DNA on the electrodes simultaneously. It suggested that this DNA chip could recognize the sequence specific genes.

• 한국어정보학회:학술대회논문집
• /
• 한국어정보학회 2017년도 제29회 한글및한국어정보처리학술대회
• /
• pp.56-59
• /
• 2017

CNN(Convolutional Neural Network)을 이용하여 발화 주제 다중 분류 task를 multi-labeling 방법과, cluster 방법을 이용하여 수행하고, 각 방법론에 MSE(Mean Square Error), softmax cross-entropy, sigmoid cross-entropy를 적용하여 성능을 평가하였다. Network는 음절 단위로 tokenize하고, 품사정보를 각 token의 추가한 sequence와, Naver DB를 통하여 얻은 named entity 정보를 입력으로 사용한다. 실험결과 cluster 방법으로 문제를 변형하고, sigmoid를 output layer의 activation function으로 사용하고 cross entropy cost function을 이용하여 network를 학습시켰을 때 F1 0.9873으로 가장 좋은 성능을 보였다.

• 한국정보통신학회논문지
• /
• 제19권8호
• /
• pp.1780-1784
• /
• 2015

현재의 IP 라우팅은 Layer 3 라우팅 정보를 이용하여 Forwarding시 Destination Address만을 참조하며 Destination-Based Routing Lookup은 모든 Hop에서 필요하다. 따라서 모든 라우터는 Full Internet 라우팅 정보, 약 12만 여개의 라우트 정보를 필요로 할 수 있으며 라우터는 이러한 폭주에 따라 트래픽 부하를 분산 할 수 있는 환경 구성이 필요하다. 본 연구에서는 인터넷 기존망의 고유 특징인 Best Effect 환경에서 대용량 멀티미디어 데이터 전송의 QoS 보장과 하드웨어적 고속 스위칭을 위해 Labeling을 이용하여 packet을 forwarding하는 환경 구성이 필요하다. 데이터 전송을 고성능화하기 위해서 라벨링망의 여러 단계의 정책보다는 프로세스 등 자원 효율화와 단순화 정책이 효과적인지 연구를 통해 알아보며 그 방안으로 일명 lock-up 라벨링망 Header Format으로 고정시켜 단순화된 정책으로 보다 QoS에 효과적인 정책을 적용하는 방법을 고찰한다.