• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2004년도 추계학술발표논문집(상)
• /
• pp.459-462
• /
• 2004

This paper proposes a genetically inspired adaptive clustering algorithm. The algorithm automatically discovers the actual number of clusters and efficiently performs clustering without unduly compromising cluster purity. Chromosome encoding that ensures the correct number of clusters and cluster purity is discussed. The required fitness function is desisted on the basis of modified similarity criteria and genetic operators. These are incorporated into the proposed adaptive clustering algorithm. Experimental results show the efficiency of the clustering algorithm on synthetic data sets and real world data sets.

• 전자공학회논문지CI
• /
• 제45권4호
• /
• pp.27-33
• /
• 2008

유전자 발현 데이터의 분석 기법 중 무감독 학습 기반의 클러스터링 기법은 생물학적 변화와 진의 발현 정도를 이해하는데 자주 사용되는 방법이다. 생명공학 연구에 있어서 그래프 기반의 MCL 알고리즘은 그래프 내의 노드들을 클러스터링 하는 알고리즘으로 빠르고 효과적이다. 우리는 기존의 MCL 알고리즘을 개선하여 마이크로어레이 데이터에 적용시켰다. MCL 알고리즘 수행 시 inflation과 대각선 항의 두 요인을 조정하는 시뮬레이션을 실행하였으며, 마코브 행렬을 이용하여 변환하였다. 또한 개선된 MCL 알고리즘에서는 더 명확한 클래스를 구분하기 위하여 각 열의 평균을 구한 후 그 값을 임계치로 사용하였다. 따라서 수정된 알고리즘은 기존의 알고리즘들보다 정확도를 높일 수 있었다. 즉, 실제 실험 결과 기존에 알려진 클래스와 비교했을 때 평균 70%의 정확도를 보였다. 또한, 다른 클러스터링 기법, K-means 알고리즘, 계층적 클러스터링 그리고 SOM 알고리즘을 비교 분석하였으며, 그 결과 MCL 알고리즘이 다른 클러스터링 기법보다 더 좋은 결과를 보임을 알 수 있다.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2008년도 하계종합학술대회
• /
• pp.671-672
• /
• 2008

K-means is a popular one in clustering algorithms, and it minimizes the mutual euclidean distance among the sample points. But K-means has some demerits, such as depending on initial condition, unsupervised learning and local optimum. However mahalanobis distancecan deal this case well. In this paper, the author proposed a new clustering algorithm, named exponential probability clustering, which applied Mahalanobis distance into K-means clustering. This new clustering does possess not only the probability interpretation, but also clustering merits. Finally, the simulation results also demonstrate its good performance compared to K-means algorithm.

• 지식경영연구
• /
• 제10권4호
• /
• pp.17-30
• /
• 2009

This study is concerned with suggesting a new clustering algorithm to evaluate the value of papers which were supported by research grants by Korea Research Fund (KRF). The algorithm is based on an extended version of a conventional PSO (Particle Swarm Optimization) mechanism. In other words, the proposed algorithm is based on integration of k-means algorithm and simulated annealing mechanism, named KASA-PSO. To evaluate the robustness of KASA-PSO, its clustering results are evaluated by research grants experts working at KRF. Empirical results revealed that the proposed KASA-PSO clustering method shows improved results than conventional clustering method.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권7호
• /
• pp.2957-2980
• /
• 2020

Ensemble clustering commonly integrates multiple basic partitions to obtain a more accurate clustering result than a single partition. Specifically, it exists an inevitable problem that the incomplete transformation from the original space to the integrated space. In this paper, a novel ensemble clustering algorithm using a newly reconstructed mapping coefficient (ECRMC) is proposed. In the algorithm, a newly reconstructed mapping coefficient between objects and micro-clusters is designed based on the principle of increasing information entropy to enhance effective information. This can reduce the information loss in the transformation from micro-clusters to the original space. Then the correlation of the micro-clusters is creatively calculated by the Spearman coefficient. Therefore, the revised co-association graph between objects can be built more accurately because the supplementary information can well ensure the completeness of the whole conversion process. Experiment results demonstrate that the ECRMC clustering algorithm has high performance, effectiveness, and feasibility.

• 한국컴퓨터정보학회논문지
• /
• 제19권3호
• /
• pp.37-43
• /
• 2014

본 논문에서는 색상 군집화를 이용한 입술탐지 알고리즘을 제안한다. RGB 색상 모델로 주어진 입력영상에서 AdaBoost 알고리즘을 이용하여 얼굴영역을 추출한 후, 얼굴영역을 Lab 컬러 모델로 변환한다. Lab 컬러 모델에서 a 성분은 입술과 유사한 색상을 잘 표현할 수 있는 반면 b 성분은 입술의 보색을 표현할 수 있기 때문에 Lab 컬러로 표현된 얼굴영역에서 a와 b 성분을 기준으로 최단 이웃(nearest neighbour) 군집화 알고리즘을 이용하여 피부 영역을 분리한 후, K-means 색상 군집화를 통해 입술 후보 영역을 추출하고, 마지막으로 기하학적 특징을 이용하여 최종적인 입술영역을 탐지하였다. 실험 결과는 제안된 방법이 강건하게 입술을 탐지함을 보인다.

• Journal of Information Processing Systems
• /
• 제12권4호
• /
• pp.555-576
• /
• 2016

In the conventional clustering algorithms, an object could be assigned to only one group. However, this is sometimes not the case in reality, there are cases where the data do not belong to one group. As against, the fuzzy clustering takes into consideration the degree of fuzzy membership of each pixel relative to different classes. In order to overcome some shortcoming with traditional clustering methods, such as slow convergence and their sensitivity to initialization values, we have used the Harmony Search algorithm. It is based on the population metaheuristic algorithm, imitating the musical improvisation process. The major thrust of this algorithm lies in its ability to integrate the key components of population-based methods and local search-based methods in a simple optimization model. We propose in this paper a new unsupervised clustering method called the Fuzzy Harmony Search-Fourier Transform (FHS-FT). It is based on hybridization fuzzy clustering and the harmony search algorithm to increase its exploitation process and to further improve the generated solution, while the Fourier transform to increase the size of the image's data. The results show that the proposed method is able to provide viable solutions as compared to previous work.

• International journal of advanced smart convergence
• /
• 제8권3호
• /
• pp.46-53
• /
• 2019

When a partitioned structure is derived from a data set using a clustering algorithm, it is not unusual to have a different set of outcomes when it runs with a different order of data. This problem is known as the order bias problem. Many algorithms in machine learning fields try to achieve optimized result from available training and test data. Optimization is determined by an evaluation function which has also a tendency toward a certain goal. It is inevitable to have a tendency in the evaluation function both for efficiency and for consistency in the result. But its preference for a specific goal in the evaluation function may sometimes lead to unfavorable consequences in the final result of the clustering. To overcome this bias problems, the first clustering process proceeds to construct an initial partition. The initial partition is expected to imply the possible range in the number of final clusters. We apply the data centric sorting to the data objects in the clusters of the partition to rearrange them in a new order. The same clustering procedure is reapplied to the newly arranged data set to build a new partition. We have developed an algorithm that reduces bias effect resulting from how data is fed into the algorithm. Experiment results have been presented to show that the algorithm helps minimize the order bias effects. We have also shown that the current evaluation measure used for the clustering algorithm is biased toward favoring a smaller number of clusters and a larger size of clusters as a result.

• Journal of Information Processing Systems
• /
• 제4권2호
• /
• pp.67-76
• /
• 2008

This research proposes a new strategy where documents are encoded into string vectors and modified version of k means algorithm to be adaptable to string vectors for text clustering. Traditionally, when k means algorithm is used for pattern classification, raw data should be encoded into numerical vectors. This encoding may be difficult, depending on a given application area of pattern classification. For example, in text clustering, encoding full texts given as raw data into numerical vectors leads to two main problems: huge dimensionality and sparse distribution. In this research, we encode full texts into string vectors, and modify the k means algorithm adaptable to string vectors for text clustering.

• 한국인터넷방송통신학회논문지
• /
• 제13권1호
• /
• pp.83-88
• /
• 2013

본 연구의 목적은 유사 블로그 추천 시스템을 통해서 특정 주제의 유사도에 따라 주제를 찾아 주는 것이다. 유사 추천 시스템을 실현하기 위해서는 대규모 데이터 집합에서 유사항목을 가진 그룹을 찾을 수 있도록 군집해야 한다. 군집화(clustering) 기법은 군집하고자 하는 목적에 따라 적합한 기법과 군집수가 결정되어야 한다. 군집기법으로는 가장 많이 사용되는 K-means 알고리즘을 사용 하였고 추천 알고리즘은 흰개미 군집 알고리즘을 사용하였다. 흰개미 습성 모델을 이용한 군집화 기법은 K-means 알고리즘이 갖고 있는 적절한 군집 갯수 문제점을 해결하고, 군집화 시간을 단축하며, 군집을 위한 군집 평균 이동횟수를 개선한다.