• The KIPS Transactions:PartB
• /
• v.13B no.5 s.108
• /
• pp.541-546
• /
• 2006

Data Mining is the process of finding hidden patterns inside a large data set. Cluster analysis has been used as a popular technique for data mining. It is a fundamental process of data analysis and it has been Playing an important role in solving many problems in pattern recognition and image processing. If fuzzy cluster analysis is to make a significant contribution to engineering applications, much more attention must be paid to fundamental decision on the number of clusters in data. It is related to cluster validity problem which is how well it has identified the structure that Is present in the data. In this paper, we design an adaptive data mining model using fuzzy performance measures. It discovers clusters through an unsupervised neural network model based on a fuzzy objective function and evaluates clustering results by a fuzzy performance measure. We also present the experimental results on newsgroup data. They show that the proposed model can be used as a document classifier.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.6 no.3
• /
• pp.81-88
• /
• 1996

Cluster analysis is based on partitioning a collection of data points into a number of clusters, where the data points in side a cluster have a certain degree of similarity and it is a fundamental process of data analysis. So, it has been playing an important role in solving many problems in pattern recognition and image processing. For these many clustering algorithms depending on distance criteria have been developed and fuzzy set theory has been introduced to reflect the description of real data, where boundaries might be fuzzy. If fuzzy cluster analysis is tomake a significant contribution to engineering applications, much more attention must be paid to fundamental questions of cluster validity problem which is how well it has identified the structure that is present in the data. Several validity functionals such as partition coefficient, claasification entropy and proportion exponent, have been used for measuring validity mathematically. But the issue of cluster validity involves complex aspects, it is difficult to measure it with one measuring function as the conventional study. In this paper, we propose four performance indices and the way to measure the quality of clustering formed by given learning strategy.

• Proceedings of the Korean Information Science Society Conference
• /
• 2001.10b
• /
• pp.25-27
• /
• 2001

진화 알고리즘에서 고려할 사항 중 하나는 문제와 관련 있는 진화연산 즉, 교배 연산과 돌연변이 연산을 정의하는 것이다. 일반적으로 교배 연산은 두 개체의 정보를 교환하는 재조합 연산으로써 진화의 속도를 촉진시키는 역할을 하고 돌연변이 인산은 개체집단의 다양성 을 유지시키는 역할을 한다. 그러나 이러한 진화연산자는 확률에 근거하여 모든 개체에 적용되는 맹목적인 연산이 가질 수 있는 진화시간 지연의 문제점을 갖는다. 본 논문에서는 맹목적 진화연산에 의한 진화 시간 지연을 해결하기 위해 휴리스틱 연산을 제안한다. 휴리스픽 연산은 문제의 특성에 맞지 않는 개체에만 적용되는 연산으로 진화 시간을 단축시킬 수 있다. 따라서 이러한 휴리스틱 연산의 타당성을 확인하기 위해 본 논문에서는 진화 알고리즘을 이용하여 최적의 클러스터 위치와 개수를 자동으로 찾아주는 문제에 클러스터의 특성을 고려한 휴리스틱 연산인 합병연산과 분할연산 그리고 K-means연산을 정의하여 다차원 실험데이터로 실험한 결과를 보이고 있다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.23 no.4
• /
• pp.1045-1050
• /
• 1998

Classification techniques are often an importand component of intelligent systems and are use for both deta preprocessing and decision making. In the design of a classification system, the labled samples must be given to provide a priori information for the classification. Moreover, the number of classes to be categorized must be known a priori information, called OFCAM. In OFCAM, an unsupervised by OFCAM, the database of a classification system, called PCSDB, is constructed. Then, PCSDB can be effectively used in the decision process of the system.

• Journal of the Korea Society of Computer and Information
• /
• v.16 no.10
• /
• pp.197-203
• /
• 2011

In this paper, a new cluster configuration process is proposed. The energy consumption of sensor nodes is reduced by configuring the initial setup process only once with keeping the initial cluster. Selecting the highest power consumed node of the member nodes within the cluster to the header of next round can distribute power consumption of all nodes in the cluster evenly. With this proposed way, the lifetime of the USN is increased by the reduced energy consumption of all nodes in the cluster. Also, evenly distributed power consumptions of sensors are designed to improve the energy hole problem. The effectiveness of the proposed algorithms is confirmed through simulations.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2018.05a
• /
• pp.442-444
• /
• 2018

본 논문에서는 GA(Genetic Algorithm) 기반 점증적 입자모델(IGM: Incremental Granular Model)의 최적화 설계를 제안한다. IGM의 성능은 다양한 실세계 응용예제를 통해 성공적으로 연구되어져왔다. 그러나, IGM의 문제로 각 컨텍스트에서 동일한 클러스터 수가 사용되는 점과 전형적인 퍼지화 계수가 설정된다는 점이 있다. 이러한 문제를 해결하기 위해 IGM을 최적화하여 각 컨텍스트에서 클러스터 중심의 수와 퍼지화 계수를 최적화하는 설계 방법을 제시했다. 제안된 방법의 타당성을 확인하기 위해 Ecotect에서 시뮬레이션 한 12가지 건물 형태를 사용하여 에너지 효율 예측에 대한 실험을 수행하였고, 제안된 방법은 기존의 IGM보다 우수한 성능을 보이는 것을 확인했다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2006.06a
• /
• pp.55-57
• /
• 2006

k-medoid 클러스터링 알고리즘은 고정된 클러스터 수(k)를 가지고 실험하기 때문에 데이터에 대한 사전 지식이 없으면 올바른 분석이 어렵고, 클러스터 수를 변경하면서 여러 번 반복 실험하여 실험 결과에 대한 타당성을 조사해야 하기 때문에 데이터의 크기가 커질수록 시간 비용이 증가하는 단점이 생긴다. 본 논문에서는 k-medoid 클러스터링 알고리즘 분석에 있어서 가장 어려운 문제 중 하나인 적절한 클러스터 수 k를 사회 네트워크 분석 방법 중 매개중심 값을 이용하여 찾는 새로운 방법을 제안하고 이를 실제 마이크로 어레이 데이터에 적용하여 유전자 알고리즘에 기반한 k-medoid 클러스터링을 수행함으로써 좀 더 정확한 클러스터링 결과를 보인다.

• Journal of the Institute of Convergence Signal Processing
• /
• v.9 no.4
• /
• pp.313-320
• /
• 2008

The dynamic clustering technique has some problems regarding energy consumption. In the cluster configuration aspect the cluster structure must be modified every time the head nodes are re-selected resulting in high energy consumption. Also, there is excessive energy consumption when a cluster head node receives identical data from adjacent cluster sources nodes. This paper proposes a solution to the problems described above from the energy efficiency perspective. The round-robin cluster header(RRCH) technique, which fixes the initially structured cluster and sequentially selects duster head nodes, is suggested for solving the energy consumption problem regarding repetitive cluster construction. Furthermore, the issue of redundant data occurring at the cluster head node is dealt with by broadcasting metadata of the initially received data to prevent reception by a sensor node with identical data. A simulation experiment was performed to verify the validity of the proposed approach. The results of the simulation experiments were compared with the performances of two of the must widely used conventional techniques, the LEACH(Low Energy Adaptive Clustering Hierarchy) and HEED(Hybrid, Energy Efficient Distributed Clustering) algorithms, based on energy consumption, remaining energy for each node and uniform distribution. The evaluation confirmed that in terms of energy consumption, the technique proposed in this paper was 29.3% and 21.2% more efficient than LEACH and HEED, respectively.

• The KIPS Transactions:PartC
• /
• v.14C no.3 s.113
• /
• pp.277-284
• /
• 2007

The routing algorithm many used in the wireless sensor network features the clustering method to reduce the amount of data transmission from the energy efficiency perspective. However, the clustering method results in high energy consumption at the cluster head node. Dynamic clustering is a method used to resolve such a problem by distributing energy consumption through the re-selection of the cluster head node. Still, dynamic clustering modifies the cluster structure every time the cluster head node is re-selected, which causes energy consumption. In other words, the dynamic clustering approaches examined in previous studies involve the repetitive processes of cluster head node selection. This consumes a high amount of energy during the set-up process of cluster generation. In order to resolve the energy consumption problem associated with the repetitive set-up, this paper proposes the Round-Robin Cluster Header (RRCH) method that fixes the cluster and selects the head node in a round-robin method The RRCH approach is an energy-efficient method that realizes consistent and balanced energy consumption in each node of a generated cluster to prevent repetitious set-up processes as in the LEACH method. The propriety of the proposed method is substantiated with a simulation experiment.

• The Journal of the Korea Contents Association
• /
• v.10 no.9
• /
• pp.107-116
• /
• 2010

The facility location problem is one of the traditional optimization problems. In this paper, we deal with the single source capacitated facility location problem (SSCFLP) and it is known as an NP-hard problem. Thus, it seems to be natural to use a heuristic approach such as evolutionary algorithms for solving the SSCFLP. This paper introduces a new efficient evolutionary algorithm for the SSCFLP. The proposed algorithm is devised by incorporating a general adaptive link adjustment evolutionary algorithm and three heuristic local search methods. Finally we compare the proposed algorithm with the previous algorithms and show the proposed algorithm finds optimum solutions at almost all middle size test instances and very stable solutions at larger size test instances.