• The KIPS Transactions:PartD
• /
• v.10D no.4
• /
• pp.577-590
• /
• 2003

The shape-based retrieval is defined as the operation that searches for the (sub) sequences whose shapes are similar to that of a query sequence regardless of their actual element values. In this paper, we propose a similarity model suitable for shape-based retrieval and present an indexing method for supporting the similarity model. The proposed similarity model enables to retrieve similar shapes accurately by providing the combination of various shape-preserving transformations such as normalization, moving average, and time warping. Our indexing method stores every distinct subsequence concisely into the disk-based suffix tree for efficient and adaptive query processing. We allow the user to dynamically choose a similarity model suitable for a given application. More specifically, we allow the user to determine the parameter p of the distance function $L_p$ when submitting a query. The result of extensive experiments revealed that our approach not only successfully finds the subsequences whose shapes are similar to a query shape but also significantly outperforms the sequence search.

• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.5 no.2
• /
• pp.107-120
• /
• 1993

This paper presents a new modal solution of linear three-dimensional hydrodynamic equations using similarity transform technique. The governing equations are first separated into external and internal mode equations. The solution of the internal mode equation then proceeds as in previous modal models using the Galerkin method but with expansion of arbitrary basis functions. Application of similarity transform to resulting full matrix equations gives rise to a set of uncoupled partial differential equations of which the unknowns are coefficients of mode vector. Using the transform technique a computationally efficient time integration is possible. In present from the model use Chebyshev polynomials for Galerkin solution of internal mode equations. To examine model performance the model is applied to a homogeneous, rectangular basin of constant depth under steady, uniform wind field.

• Journal of the Korea Society of Computer and Information
• /
• v.19 no.8
• /
• pp.27-34
• /
• 2014

In this paper, we propose a pupil detection method using hybrid projection function and rank order filter. To reduce error to detect eyebrows as pupil, eyebrows are detected using hybrid projection function in face region and eye region is set to not include the eyebrows. In the eye region, potential pupil candidates are detected using rank order filter and then the positions of pupil candidates are corrected. The pupil candidates are grouped into pairs based on geometric constraints. A similarity measure is obtained for two eye of each pair using template matching, we select a pair with the smallest similarity measure as final two pupils. The experiments have been performed for 700 images of the BioID face database. The pupil detection rate is 92.4% and the proposed method improves about 21.5% over the existing method..

• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.6 no.2
• /
• pp.174-185
• /
• 1994

This paper presents a modal solution of linear three-dimensional hydrodynamic equations using similarity transform technique. The solution over the vertical space domain is obtained using the Galerkin method with linear shape funtions (Galerkin-FEM model). Application of similarity transform to resulting tri-diagonal matrix equations gives rise 掠 a set of uncoupled partial differential equations of which the unknowns are coefficients of mode shape vectors. The proposed method.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2001.11a
• /
• pp.477-482
• /
• 2001

이미지 데이터베이스에서 특성 객체를 가지고 있는 이미지를 효율적으로 검색하는 각 객체의 모양 특징을 질의 이미지의 질의 객체의 특징과 비교해야 한다. 올바른 모양 비교 기준은 사람이 보기에 같거나 유사하다고 판단하는 방법을 기준으로 삼는다. 본 논문에서는 질의 객체를 가진 이미지의 유사 검색에서 모양 비교의 정확도를 높이기 위한 매칭 기법을 제안한다. 이를 위해 질의 객체와 대상 객체에 비교를 시작할 근사한 우세점을 찾고 올바른 모양 비교를 위한 매칭 알고리즘을 제안한다. 또한 질의 중심의 유사도를 비교하기 위해 유사함수를 설정한다. 유사성 검색을 위해 사용되는 객체의 모양 특징은 객체의 윤곽선상의 점들 중 결정된 지역 특징을 지닌 (거리 ${\gamma}$, 각도$\theta$)의 우세점 집합으로 표현한다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2003.04a
• /
• pp.707-709
• /
• 2003

본 논문에서는 유사도(similarity) 기반 이미지 클러스터링 기법에 대하여 논하고자 한다. 비트맵 이미지의 특징을 추출하고 이러한 특징에 기반한 유사도 측정 함수들을 소개하고 이미지 클러스터링 알고리즘과 구현을 통한 실험 예제들에 대해서 설명한다. 이 실험에서 우리는 유사도에 따라 이미지들이 계층적(Hierarchical)으로 집단화 되는 계층적 클러스터링 알고리즘을 사용하였다. 이미지의 특징 표현을 위해서는 HSV 기반의 히스토그램을 이용하였다. 본 논문에서 제안한 기법의 실험 결과는 이미지 데이터베이스에서 유사한 이미지를 검색하는데 높은 효율성이 있는 것을 보여준다.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.38 no.9
• /
• pp.773-779
• /
• 2014

A qualitative and quantitative analysis on flame dynamics is required to model combustion instability characteristics in gas turbine lean premixed combustors. The current paper shows the flame transfer function modeling results using CFD(Computational Fluid Dynamics) techniques for the flame dynamics study. It is generally known that flame shapes determine the basic characteristics of the flame transfer function. The comparisons of the modeled flame shapes with the measured ones were made using the optimized heat transfer conditions. Modeling results of the flame transfer function show the close behaviors to the measured data with a reasonable accuracy if the flame geometry can be exactly captured.

• Proceedings of the Korean Information Science Society Conference
• /
• 1998.10c
• /
• pp.69-71
• /
• 1998

본 논문에서는 웹을 기반으로 한 인터넷에서 유전자 알고리즘을 이용한 정보검색 방법을 제시한다. 특정 문제에 대한 가설 공간을 탐색하여 최적의 해를 찾을 때 지역성과 전역성을 함께 고려하는 유전자 알고리즘의 특성을 웹에서의 정보검색에 이용한다. 여기에서 고려할 점은 탐색속도와 탐색방향인데 본 논문에서는 탐색속도를 고려하지 않았다. 탐색방향은 사용자의 정보 요구와 검색된 문서와 유사도 평가함수로 조절하였다. 본 논문에서 제안한 유사도 평가함수로 실험을 한 결과, 사용자의 초기 정보요구에 대한 검색결과의 적합성 여부에 대한 사용자의평가가 기존의 검색엔진을 사용했을 때보다 개선된 결과를 얻을 수 있었다. 그리고 HTML 문서의 특성을 고려해서 검색하는 경우에는 검색어에 대해 보다 특정적인 결과를 제시했으며, 문서 내에서 검색어의 지역 중요도만을 고려하는 경우는 보다 일반적인 결과를 제시하는 것을 확인할 수 있었다.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1995.10a
• /
• pp.740-743
• /
• 1995

The analysis model is the power law creep material containing an elliptical rigid inclusion subjected to the arbitrarily directional stress on infinite boundary. The stress analysis is performed using the conformal mapping function and complex pseudo-stress function. The stress distributions near an elliptical rigid inclusion are obtained with various ellipse shapes, strain hardening exponents and directions of applied stress.

• Journal of KIISE:Databases
• /
• v.33 no.7
• /
• pp.682-692
• /
• 2006

Searching for gene products which have similar biological functions are crucial for bioinformatics. Modern day biological databases provide the functional description of gene products using Gene Ontology(GO). In this paper, we propose a technique for semantic similarity search for gene products using the GO annotation information. For this purpose, an information-theoretic measure for semantic similarity between gene products is defined. And an algorithm for semantic similarity search using this measure is proposed. We adapt Fagin's Threshold Algorithm to process the semantic similarity query as follows. First, we redefine the threshold for our measure. This is because our similarity function is not monotonic. Then cluster-skipping and the access ordering of the inverted index lists are proposed to reduce the number of disk accesses. Experiments with real GO and annotation data show that GORank is efficient and scalable.