• Journal of Korea Multimedia Society
• /
• v.11 no.9
• /
• pp.1302-1309
• /
• 2008

Traditional clustering methods, like k-means or fuzzy clustering, are prototype-based methods which are applicable only to convex clusters. On the other hand, spectral clustering tries to find clusters only using local similarity information. Its ability to handle concave clusters has gained the popularity recent years together with support vector machine (SVM) which is a kernel-based classification method. However, as is in SVM, the kernel width plays an important role and has a great impact on the result. Several methods are proposed to decide it automatically, it is still determined based on heuristics. In this paper, we proposed an adaptive method deciding the kernel width based on distance histogram. The proposed method is motivated by the fact that the affinity matrix should be formed into a block diagonal matrix to generate the best result. We use the tradition Euclidean distance together with the random walk distance, which make it possible to form a more apparent block diagonal affinity matrix. Experimental results show that the proposed method generates more clear block structured affinity matrix than the existing one does.

• Proceedings of the Korean Information Science Society Conference
• /
• 2003.04a
• /
• pp.695-697
• /
• 2003

다중데이터베이스 마이닝에서 하나의 데이터 집합을 형성하는 작업은 많은 부하가 따른다. 그러므로, 본 논문에서는, 가중치 거리를 이용한 클러스터링을 통해 관련성이 높은 데이터베이스를 식별하는 기법을 제안한다. 제안한 기법은 빈발한 항목으로 구성된 데이터 집합을 생성하여 데이터베이스 사이의 유사성과 거리를 측정하고 데이터베이스간의 거리에 대한 식별성을 향상시키기 위하여 최다 빈발항목에 대한 비교 연산을 통해 가중치를 산출한다. 그리고 성능평가를 통하여 제안한 기법이 Ideal&Goodness 기법보다 다중데이터베이스의 트랜잭션 데이터베이스에 대한 식별 능력이 우수함을 알 수 있었다.

• Journal of KIISE:Computer Systems and Theory
• /
• v.37 no.6
• /
• pp.323-329
• /
• 2010

The edit distance problem is finding the minimum number of edit operations to transform a string into another one. It is one of the important problems in algorithm research and there are some algorithms that compute an optimal edit distance for the one-dimensional languages such as the English alphabet. However, there are a few researches to find the edit distance for the more complicated language such as the Korean or Chinese alphabet. In this paper, we define the measure of the edit distance for the Korean alphabet with the phoneme classification system to improve the previous edit distance algorithm and present an algorithm for the edit distance problem for the Korean alphabet.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.43 no.6 s.312
• /
• pp.43-51
• /
• 2006

This paper proposes a metrics for example matching under the example-based machine translation for English-Korean machine translation. Our metrics served as similarity measure is based on edit-distance algorithm, and it is employed to retrieve the most similar example sentences to a given query. Basically it makes use of simple information such as lemma and part-of-speech information of typographically mismatched words. Edit-distance algorithm cannot fully reflect the context of matched word units. In other words, only if matched word units are ordered, it is considered that the contribution of full matching context to similarity is identical to that of partial matching context for the sequence of words in which mismatching word units are intervened. To overcome this drawback, we propose the context-weighting scheme that uses the contiguity information of matched word units to catch the full context. To change the edit-distance metrics representing dissimilarity to similarity metrics, to apply this context-weighted metrics to the example matching problem and also to rank by similarity, we normalize it. In addition, we generalize previous methods using some linguistic information to one representative system. In order to verify the correctness of the proposed context-weighted metrics, we carry out the experiment to compare it with generalized previous methods.

• Proceedings of the Korean Information Science Society Conference
• /
• 2011.06c
• /
• pp.67-69
• /
• 2011

데이터의 군집 분석에서 두 개의 서로 다른 데이터에 대한 유사도(거리)를 어떻게 정의하는가는 매우 중요한 문제이다. 수치속성에 대한 거리 측정 방법에는 다양한 기법이 존재하지만 각 속성의 크기와 범위가 서로 크게 다를 경우 이들을 동일한 인자로 여기고 거리 측정을 하게 되면 논리적인 오류를 범할 수 있다. 기존의 군집 분석 연구에서 사용된 거리 측정 기법은 데이터의 정규화 과정을 통해 이 문제를 해결하려고 노력하지만 일반적인 정규화는 이상치의 존재나 데이터의 편중된 분포 등의 이유로 속성별 거리가 왜곡될 수 있다. 본 논문은 이러한 문제점을 해결하기 위해 정규화된 데이터에서 각 속성의 비중을 고려한 적응적 유클리드 거리 측정 기법(AEDM: Adaptive Euclidean Distance Measure)을 제안한다. AEDM은 유클리드 거리를 기반으로 정규화 된 데이터의 형태에 따라 가중치를 부여하여 데이터의 분포에 관계없이 각 속성간의 거리를 충분히 반영하기 때문에 더욱 정확한 군집 분석을 가능하게 한다.

• The Journal of the Korea Contents Association
• /
• v.6 no.10
• /
• pp.134-142
• /
• 2006

In this paper, we investigate a Hausdorff distance, which is used for the measurement of image similarity, to see whether it is also effective for document retrieval. The proposed method uses a local crowdedness and a Hausdorff distance to locate text images by determining whether a pair of images scanned at different time comes from the same text or not. To reduce the processing time, which is one of the disadvantages of a Hausdorff distance algorithm, we adopt a local crowdedness for feature point extraction. We apply the proposed method to 190 pairs of the same class and 190 pairs of the different class collected from postal envelop images. The results show that the modified Hausdorff distance proposed in this paper performed well in locating the tort region and calculating the degree of similarity between two images. An improvement of accuracy by 2.7% and 9.0% has been obtained, compared to a binary correlation method and the original Hausdorff distance method, respectively.

• Journal of Information Management
• /
• v.40 no.2
• /
• pp.95-115
• /
• 2009

Author resolution is to disambiguate same-name author occurrences into real individuals. For this, pair-wise author similarities are computed for author name entities, and then clustering is performed. So far, many studies have employed hierarchical clustering techniques for author disambiguation. However, various hierarchical clustering methods have not been sufficiently investigated. This study covers an empirical evaluation and analysis of hierarchical clustering applied to Korean author resolution, using multiple distance functions such as Dice coefficient, Cosine similarity, Euclidean distance, Jaccard coefficient, Pearson correlation coefficient.

• KIPS Transactions on Software and Data Engineering
• /
• v.8 no.9
• /
• pp.363-372
• /
• 2019

A sequence refers to data in which the order exists on the two items, and purchase transaction data in which the products purchased by one customer are listed is one of the representative sequence data. In general, all goods have a product taxonomy, such as category/ sub-category/ sub-sub category, and if they are similar to each other, they are classified into the same category according to their characteristics. Therefore, in this paper, we not only consider the purchase order of products to compare two purchase transaction sequences, but also calculate their similarity by giving a higher score if they are in the same category in spite of their difference. Especially, in order to choose the best similarity measure that directly affects the calculation performance of the purchase transaction sequences, we have compared the performance of three representative similarity measures, the Levenshtein distance, dynamic time warping distance, and the Needleman-Wunsch similarity. We have extended the existing methods to take into account the product taxonomy. For conventional similarity measures, the comparison of goods in two sequences is calculated by simply assigning a value of 0 or 1 according to whether or not the product is matched. However, the proposed method is subdivided to have a value between 0 and 1 using the product taxonomy tree to give a different degree of relevance between the two products, even if they are different products. Through experiments, we have confirmed that the proposed method was measured the similarity more accurately than the previous method. Furthermore, we have confirmed that dynamic time warping distance was the most suitable measure because it considered the degree of association of the product in the sequence and showed good performance for two sequences with different lengths.

• Proceedings of the Korean Information Science Society Conference
• /
• 2011.06b
• /
• pp.282-285
• /
• 2011

효과적인 수술 훈련 시뮬레이터를 구축하기 위해서는 사실적인 훈련 환경을 제공하는 것뿐만 아니라 훈련 결과를 바탕으로 사용자의 숙련도를 객관적으로 측정하고 평가하는 과정 또한 중요하다. 이를 위해 본 연구는 수술 훈련 중 큰 비중을 차지하는 절개 동작에 대한 정량적 평가 척도를 제공하는 것을 목표로 한다. 사용자가 가상 장기 모델에 대해 절개를 수행하는 동안 평가 시스템은 절개 경로와 깊이를 일정 간격으로 샘플링하여 저장하고, 이를 두 곡선 간의 유사성 측정 알고리즘을 통해 훈련 시나리오 상에 정의된 표준 절개 경로와 깊이, 속도를 각각 비교한다. 이렇게 계산된 두 경로 사이의 거리가 가까울수록 유사성이 높은 것으로 간주하며, 사전에 설정된 기준치 이상의 유사성을 기록할 경우 훈련 목표를 충족한 것으로 판단할 수 있다. 본 연구에서는 단순 거리 측정에 의존한 일반적인 경로의 유사성 판단 알고리즘의 문제점을 제시하고, 전체 절개 경로의 길이 대비 현재까지 진행된 정도를 매개변수로 하는 방법을 이용하여 절개 경로의 방향을 고려한 유사성 측정 알고리즘을 제안하였다. 이와 같이 정량적이며 자동화된 절개 숙련도 평가 기법을 제안함으로써 사용자의 훈련 결과에 대해 보다 객관적인 피드백을 제공 할 수 있다.

• Journal of Korea Multimedia Society
• /
• v.7 no.5
• /
• pp.617-632
• /
• 2004

Video Data includes moving objects which change spatial positions as time goes by. In this paper, we propose a new modeling method for a moving object contained in the video data. In order to effectively retrieve moving objects, the proposed modeling method represents the spatial position and the size of a moving object. It also represents the visual features and the trajectory by considering direction, distance and speed or moving objects as time goes by. Therefore, It allows various types of retrieval such as visual feature based similarity retrieval, distance based similarity retrieval and trajectory based similarity retrieval and their mixed type of weighted retrieval.