• The Journal of the Korea Contents Association
• /
• v.7 no.1
• /
• pp.58-64
• /
• 2007

In pattern recognition field, there are many optimization problems having exponential search spaces. To solve of sequential search algorithms seeking sub-optimal solutions have been used. The algorithms have limitations of stopping at local optimums. Recently lots of researches attempt to solve the problems using genetic algorithms. This paper explains the huge search spaces of typical problems such as feature selection, classifier ensemble selection, neural network pruning, and clustering, and it reviews the genetic algorithms for solving them. Additionally we present several subjects worthy of noting as future researches.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.6 no.2
• /
• pp.138-143
• /
• 2006

In this paper, we have presented a Sequential Agglomerative Hierarchical Nested (SAHN) algorithm-based data clustering method in fuzzy inference system to achieve optimal performance of fuzzy model. SAHN-based algorithm is used to give possible range of number of clusters with cluster centers for the system identification. The axes of membership functions of this fuzzy model are optimized by using cluster centers obtained from clustering method and the consequence parameters of the fuzzy model are identified by standard least square method. Finally, in this paper, we have observed our model's output performance using the Box and Jenkins's gas furnace data and Sugeno's non-linear process data.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 1999.10a
• /
• pp.345-350
• /
• 1999

The effectiveness of software error compensation for thermally induced machine tool errors relies on the prediction accuracy of the pre-established thermal error models. The selection of optimal sensor locations is the most important in establishing these empirical models. In this paper, a methodology for the selection of optimal sensor locations is proposed to establish a robust linear model which is not subjected to collinearity. Correlation coefficient and time delay are used as thermal parameters for optimal sensor location. Firstly, thermal deformation and temperatures are measured with machine tools being excited by sinusoidal heat input. And then, after correlation coefficient and time delays are calculated from the measured data, the optimal sensor location is selected through hard c-means clustering and sequential selection method. The validity of the proposed methodology is verified through the estimation of thermal expansion along Z-axis by spindle rotation.

• Annual Conference of KIPS
• /
• 2011.11a
• /
• pp.123-125
• /
• 2011

A SATA hard disk has been widely used in recent years and NCQ is one of its crucial features. Despite the development from IDE to SATA disk, there is still much room for improvement for a SATA disk. In addition, until now a hard disk is a black box to us and it is very hard to make research at the level of a disk controller. To enhance the performance of NCQ, we try to do I/O clustering over the requests, which combines multiple sequential requests into a single large one. To evaluate the effect of an I/O clustering mechanism, we created a simple but practical SATA hard disk simulator. Experimental results show that the proposed approach is effective in enhancing the I/O performance of a SATA disk.

• The KIPS Transactions:PartD
• /
• v.13D no.2 s.105
• /
• pp.199-206
• /
• 2006

Sequential pattern mining is an important data mining task with broad applications. However, conventional methods may meet inherent difficulties in mining databases with long sequences and noise. They may generate a huge number of short and trivial patterns but fail to find interesting patterns shared by many sequences. In this paper, to overcome these problems, we propose the theme of approximate sequential pattern mining roughly defined as identifying patterns approximately shared by many sequences. The proposed method works in two steps: one is to cluster target sequences by their similarities and the other is to find consensus patterns that ire similar to the sequences in each cluster directly through multiple alignment. For this purpose, a novel structure called weighted sequence is presented to compress the alignment result, and the longest consensus pattern that represents each cluster is generated from its weighted sequence. Finally, the effectiveness of the proposed method is verified by a set of experiments.

• Journal of the Korean Society for information Management
• /
• v.21 no.3
• /
• pp.289-303
• /
• 2004

This experimental study proposes a multi-document summarization method that produces optimal summaries in which users can find answers to their queries. In order to identify the most effective method for this purpose, the performance of the three summarization methods were compared. The investigated methods are sentence clustering, passage extraction through spreading activation, and clustering-passage extraction hybrid methods. The effectiveness of each summarizing method was evaluated by two criteria used to measure the accuracy and the redundancy of a summary. The passage extraction method using the sequential bnb search algorithm proved to be most effective in summarizing multiple documents with regard to summarization precision. This study proposes the passage extraction method as the optimal multi-document summarization method.

• Journal of the Korea Computer Graphics Society
• /
• v.16 no.4
• /
• pp.35-40
• /
• 2010

Due to the distribution of digital camera, many work for photo management has been studied. However, most work use a sequential grid layout which arranges photos considering one criterion of digital photo. This interface makes users have lots of scrolling and concentrate ability when they manage their photos. In this paper, we propose a clustering method based on a temporal sequence considering their color similarity in detail. First we cluster photos using Cooper's event clustering method. Second, we makes more detailed clusters from each clustered photo set, which are clustered temporal clustering before, using maximal clique finding algorithm of interval graph. Finally, we arrange each detailed dusters on a user screen with their overlap keeping their temporal sequence. In order to evaluate our proposed system, we conducted on user studies based on a simple questionnaire.

• Proceedings of the IEEK Conference
• /
• 2001.09a
• /
• pp.11-14
• /
• 2001

본 논문은 컬러를 이용한 영상 검색 방법에 관한 것으로 영상 데이터의 효율적인 관리를 위해 먼저 전처리 단계로 웨이블릿 변환을 수행한 후 가장 낮은 저주파 부밴드 영상을 획득한다. 그리고, 변환 후 획득된 영상을 클러스터로 구분한 후, 고유치 및 고유 벡터를 이용하여 특징을 추출하여 색인 정보로 이용하였다. 클러스터링은 영상 화소의 컬러공간 상의 3차원 거리를 클러스터링의 기준으로 삼아 순차 영역 분할(Sequential Clustering) 방법을 적용하였다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2002.04b
• /
• pp.106-108
• /
• 2002

본 연구에서는 멀티미디어 데이터 검색에 클러스터링과 인덱싱 기법을 같이 적용하여 유사할 이미지끼리는 인접 디스크에 클러스터하고 이 클러스터에 접근하는 인덱스를 구축하여 검색이 빠르게 이루어지는 유사 검색방법을 제시한다. 이 연구에서는 트리 유사 구조의 인덱스 대신 해싱 방법을 이용하며 검색시 I/O시간을 줄이기 위해 오브젝트를 가진 클러스터 위치를 찾는데 한번의 I/O를 사용하고 이 클러스터를 읽기 위해 연속주인 파일 I/O를 사용하여 클러스터를 찾는 데용을 최소화한다 클러스터인덱싱 접근은 트리 유사 구조와 임의 I/O를 사용한 내용기반의 이미지 검색보다 효율적인 검색 적합성을 보이며 연속적 I/O를 통해 검색 미용을 낮춘다.

• Proceedings of the IEEK Conference
• /
• 2000.07b
• /
• pp.793-798
• /
• 2000

As we review the mechanism regarding digital font generation and birth of TrueType font, we realizes that the process is composed of sequential steps such as contour fonts from glyph table. This fact implies that we propose classification of TrueType font in terms of segment width and the number of occurrence from the glyph data.