• Journal of KIISE:Software and Applications
• /
• v.36 no.4
• /
• pp.335-345
• /
• 2009

In this paper, we propose a new web image caption extraction method considering the positional relation between a caption and an image and the lexical similarity between a caption and the main text containing the caption. The positional relation between a caption and an image represents how the caption is located with respect to the distance and the direction of the corresponding image. The lexical similarity between a caption and the main text indicates how likely the main text generates the caption of the image. Compared with previous image caption extraction approaches which only utilize the independent features of image and captions, the proposed approach can improve caption extraction recall rate, precision rate and 28% F-measure by including additional features of positional relation and lexical similarity.

• Journal of the Economic Geographical Society of Korea
• /
• v.11 no.4
• /
• pp.564-579
• /
• 2008

It is often challenging to evaluate local spatial association among onedimensional vectors generally representing paired-location events where two points are physically or functionally connected. This is largely because of complex process of such geographic phenomena itself and partially representational complexity. This paper addresses an alternative way to identify spatially autocorrelated paired-location events (or vectors) at a local scale. In doing so, we propose a statistical algorithm combining univariate point pattern analysis for evaluating local clustering of origin-points and similarity measure of corresponding vectors. For practical use of the suggested method, we present an empirical application using transactions data in a local housing market, particularly recorded from 2004 to 2006 in Franklin County, Ohio in the United States. As a result, several locally characterized similar transactions are identified among a set of vectors showing various local moves associated with communities defined.

• Journal of KIISE:Databases
• /
• v.31 no.2
• /
• pp.163-173
• /
• 2004

Recently, location-based services are becoming very Popular in mobile environments. In this paper, we propose a new association based prefetch algorithm (called by STAP) that efficiently supports information service based on the large quantity of spatial database in mobile environments. We apply the spatial-temporal relations that are meaningful for location-based queries in mobile environments. Moreover, STAP considers user's mobility and the weight of spatial data. The relation of services is a new aspect not considered in previous cache politics. So STAP is the first prefetch algorithm considering the spatial-temporal relations and thus the cache policy begins to gain a new dimension. We evaluate the performance of STAP and prove the efficiency of STAP.

• Proceedings of the Korean Statistical Society Conference
• /
• 2003.10a
• /
• pp.295-300
• /
• 2003

공간적으로 영향을 받는 위치에서의 상호 연관성을 고려한 예측모형 중에서 크리깅 (kriging) 방법은 관측된 데이터를 보간(interpolation)하고, 부드럽게 연결(smoothing)하며, 새로운 데이터를 예측(prediction)하는 통계적 모형으로서 많이 활용되고 있다. 크리깅 모형을 적용하기 위해서는 먼저 주어진 두 위치에서의 비연관성을 나타내는 세미베리오그램 (semivariogram)의 3가지 모수(nugget, sill, range)를 추정해야 한다. 본 연구에서는 전역 적 최적화 방법인 유전자 알고리즘(genetic algorithm)을 도입하여 세미베리오그램 모수들을 추정하였고, 이를 통해 강우량(rainfall)에 대한 크리깅 추정량을 산출하고 효과성을 판단하였다.

• The KIPS Transactions:PartD
• /
• v.18D no.2
• /
• pp.89-100
• /
• 2011

The CNV (Copy Number Variation) which is one of the genetic structural variations in human genome is closely related with the function of gene. In particular, the genome-wide association studies for genetic diseased persons have been researched. However, there have been few studies which infer the genetic function of CNV with normal human. In this paper, we propose the analysis method to reveal the functional relationship between common CNV and genes without considering their genomic loci. To achieve that, we propose the data integration method for heterogeneity biological data and novel measurement which can calculate the correlation between common CNV and genes. To verify the significance of proposed method, we has experimented several verification tests with GO database. The result showed that the novel measurement had enough significance compared with random test and the proposed method could systematically produce the candidates of genetic function which have strong correlation with common CNV.

• Journal of KIISE:Software and Applications
• /
• v.37 no.1
• /
• pp.74-79
• /
• 2010

The amino acid composition of a protein provides basic information for solving many problems in bioinformatics. We propose a new method that uses biologically relevant similarity between amino acids to determine the amino acid composition, where the BOLOSUM matrix is exploited to define a similarity measure between amino acids. Futhermore, to extract more information from a protein sequence than conventional methods for determining amino acid composition, we exploit the concepts of spectral analysis of signals such as radar and speech signals-the concepts of time-dependent analysis, time resolution, and frequency resolution. The proposed method was applied to predict subcellular localization of proteins, and showed significantly improved performance over previous methods for amino acid composition estimation.

• The korean journal of orthodontics
• /
• v.28 no.4 s.69
• /
• pp.499-515
• /
• 1998

The purpose of this study was to examine the associations of head posture the position of the tongue or the hyoid bone to craniofacial structure. Cephalograms taken in Natural head position(NHP) of 90 dental students (50 in male, 40 in female, 20 to 30 years in age) were traced and measured using the extracranial true horizontal and vertical lines. The obtained results were as follows; 1. There was no sex difference in head posture, but the hyoid bone was placed anteroinferiorly in male more than in female and anteroinferior inclination of the hyoid bone showed greatly in male. 2. The more inclined was the cervical column, the less prognathic was the face in natural head posture, and the larger cervical curvature, the more vertical pattern of the face. 3. The less small showed craniocervical angulation, the more anteriorly placed was the hyoid bone to the cranial base, and there was no significantly association between craniocervical angulation and the vertical position of the hyoid bone. 4. The more prognathic was the mandible, the more anteriorly placed was the hyoid bone, and there was slightly association between the craniofacial morphology and the vertical position of the hyoid bone.

• Proceedings of the Korean Information Science Society Conference
• /
• 2012.06b
• /
• pp.420-422
• /
• 2012

DNA 메틸화는 후성유전학의 한 유형으로 유전자 발현을 조절하여 질병을 비롯한 다양한 생물학적 프로세스에 영향을 준다고 알려져 있다. 따라서 DNA 메틸화 정도와 인간 질병과의 연관성에 관한 연구는 질병의 원인 및 기전을 밝히고 메틸화 프로세스 조절을 통한 질병 치료 방법 개발을 위한 기반이 될 수 있다. 유전자 발현 조절 및 질병 발생은 많은 인자들의 복합적인 상호작용에 영향을 받으므로, 여러 위치에서의 메틸화 정도들의 고차원 조합을 이용한 질병과의 연관 관계 분석이 필수적이다. 본 연구에서는 진화 연산과 가중치 학습에 기반하여 유방암 발생과 연관되어 있는 메틸화 위치의 고차 상호작용을 탐색할 수 있는 방법을 제안한다.

• Annual Conference on Human and Language Technology
• /
• 2002.10e
• /
• pp.300-305
• /
• 2002

자동 문서 요약 분야에서 대상 문서를 컴퓨터가 이해할 수 있는 형태로 어떻게 파악하고 구조화할 것인가는 중요한 이슈가 되어 왔다. 문서에 출현한 단어들은 Bag of Words 가정처럼 서로 독립적으로 존재하는 것이 아니라 문서가 쓰여진 의도에 따라 서로 간의 의미적, 혹은 지시적으로 연관되어 있다. 이러한 단어간의 연관성은 결속성(cohesion)이라고 표현하며, 이를 이용한 자동 방법으로 Barzilay의 어휘 체인(lexical chain)을 사용한 자동 방법이 대표적이다. 본 연구에서는 단어간의 연관성과 영문 시소러스인 워드넷(wordnet)에서 단어의 위치 정보를 사용하여 어휘 체인의 성능을 개선하였고, 대상 문서의 개념을 어휘 체인에 기반해 표현하여 자동의 성능을 개선하는 방안을 제시한다.

• The Journal of Information Technology and Database
• /
• v.3 no.1
• /
• pp.85-95
• /
• 1996

본 논문은 특정문서에서 문서가 갖고 있는 일반적인 지식을 이용하여 논리적 항목을 추출하는 방법에 관한 연구이다. 먼저 입력된 문서의 영역 분할, 분리자 추출, 그리고 문자와 비문자를 구별하였다. 논리구조 추출단계에서는 구별된 요소의 상대적 크기, 위치 및 전후 블록들의 연관성에 관한 지식을 이용하여 각 블록들을 레이블링 하였고, 레이블된 항목들의 위치정보값을 이용하여 각 항목들을 자료화하였다. 마지막으로, 오분류된 항목에 대해서는 배치기술자를 이용한 검증을 통해 정정하였다. 본 논문에서 구현한 방법으로 실험한 결과 96.5%의 논리항목 추출율을 획득함으로써 그 유효성을 입증하였다.