• Journal of Korean Institute of Industrial Engineers
• /
• v.27 no.3
• /
• pp.281-288
• /
• 2001

We consider in this article a multi-objective part-machine grouping problem in which parts have alternative process plans and expected annual demand of each part is known. This problem is characterized as optimally determining part sets and corresponding machine cells such that total sum of distance (or dissimilarity) between parts and total sum of load differences between machines are simultaneously minimized. Two heuristic algorithms are proposed, and examples are given to compare the performance of the algorithms.

• Korean Journal of Health Education and Promotion
• /
• v.29 no.2
• /
• pp.93-105
• /
• 2012

Objectives: The objective of the study was to examine the clustering patterns and correlates of multiple health behaviors (MHBs) in middle-aged Koreans with metabolic syndrome (MetS). Methods: Data on sociodemographics, clinical characteristics, health behaviors (vegetable intake, physical activity, cigarette smoking, and alcohol consumption), and psychological characteristics were collected by a self-reported survey and medical examination from 331 individuals with MetS. Clustering of MHBs was examined by measuring 1) the ratios of observed and expected prevalence of MHBs, and 2) the prevalence odds ratios. A binomial logistic regression were conducted. Results: Men were more likely than women to engage in multiple unhealthy behaviors. Clustering of smoking and heavy drinking was exhibited in the participants. Women with high vegetable intake were more likely to be physically inactive, and those with inadequate vegetable intake were more likely to be physically active. Those with lower self-regulation were more likely to engage in unhealthy behaviors. Conclusions: The findings support the multiple health behavior approach as opposed to the individual health behavior approach. Emphasis of self-regulation is necessary in developing multiple behavior intervention for individuals with MetS.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.11 no.5
• /
• pp.70-77
• /
• 2012

Dial-a-ride is the most widely available transit service for disabled persons or seniors in the United States and Europe. This paper studies a static dial-a-ride problem considering multiple depots, heterogeneous vehicles, and soft time windows. In this paper, we apply a heuristic based on clustering first-routing second(HCR) to a real-world large dial-a-ride problem from Maryland Transit Administration(MTA). MTA's real operation is compared with the results of developed heuristic for 24 cases. The objective function of the proposed model is to minimize the total cost composed of the service provider's cost and the customers' inconvenience cost. For the comparison, the objective function values of HCR do not include waiting cost, delay cost, and excess ride cost. The objective function values from HCR are better than those from MTA's operation for all cases. This result shows that our heuristic method can make the real operation better and more efficient.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.30B no.1
• /
• pp.72-78
• /
• 1993

While the rules for an expert system are obtained through the interviewing with domain experts or by designer's own experience, these are not adequate for fuzzy controllers dealing quantitative control values. In this paper, by considering a state of the controlled system as a pattern, we propose a method to obtain the control rules by a statistical method. Namely, we propose a method to obtain the control rules by a statistical method. Namely, we propose an rule acquisition method that is objective, mechanical, and inductive inference using a cluster-seeking algorithm, or K-means clustering algorithm. To validate this study, we show an example of an IRIS control in a CAMCODER and analyse the rules acquired from 98 sample patterns consisting of 45 features.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2003.09a
• /
• pp.330-333
• /
• 2003

Initial cluster size for clustering of partitioning methods is very important to the clustering result. In K-means algorithm, the result of cluster analysis becomes different with optimal cluster size K. Usually, the initial cluster size is determined by prior and subjective information. Sometimes this may not be optimal. Now, more objective method is needed to solve this problem. In our research, we propose a hybrid genetic algorithm, a tree induction based evolution algorithm, for determination of optimal cluster size. Initial population of this algorithm is determined by the number of terminal nodes of tree induction. From the initial population based on decision tree, our optimal cluster size is generated. The fitness function of ours is defined an inverse of dissimilarity measure. And the bagging approach is used for saying computational time cost.

• Proceedings of the KIEE Conference
• /
• 1999.07b
• /
• pp.960-962
• /
• 1999

The main idea of the proposed neuro-fuzzy system is conditional clustering whose main objective is to develop clusters preserving homogeneity of the clustered patterns with regard to their similarity in the input space as well as their respective values assumed in the output space. In the proposed neuro-fuzzy system, the structure identification is used with conditional fuzzy clustering, the parameter identification carried out by the hybrid learning scheme using back-propagation and total least squares.

• Korean Management Science Review
• /
• v.26 no.3
• /
• pp.55-65
• /
• 2009

The objective of this paper is to propose an ant colony optimization (ACO) for clustering design in wireless sensor network problem. This proposed ACO approach is designed to deal with the dynamics of the sensor nodes which can be adaptable to topological changes to any network graph in a time. Long communication distances between sensors and a sink in a sensor network can greatly consume the energy of sensors and reduce the lifetime of a network. We can greatly minimize the total communication distance while minimizing the number of cluster heads using proposed ACO. Simulation results show that our proposed method is very efficient to find the best solutions comparing to the optimal solution using CPLEX in 100, 200, and 400 node sensor networks.

• Proceedings of the Korean Society for Language and Information Conference
• /
• 2007.11a
• /
• pp.321-329
• /
• 2007

This paper reports on the application of network analysis approaches to investigate the characteristics of graph representations of Japanese word associations. Two semantic networks are constructed from two separate Japanese word association databases. The basic statistical features of the networks indicate that they have scale-free and small-world properties and that they exhibit hierarchical organization. A graph clustering method is also applied to the networks with the objective of generating hierarchical structures within the semantic networks. The method is shown to be an efficient tool for analyzing large-scale structures within corpora. As a utilization of the network clustering results, we briefly introduce two web-based applications: the first is a search system that highlights various possible relations between words according to association type, while the second is to present the hierarchical architecture of a semantic network. The systems realize dynamic representations of network structures based on the relationships between words and concepts.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.36 no.1
• /
• pp.24-35
• /
• 2013

A cell formation approach based on cluster analysis is developed for the configuration of manufacturing cells. Cell formation, which is to group machines and parts into machine cells and the associated part families, is implemented to add the flexibility and efficiency to manufacturing systems. In order to develop an efficient clustering procedure, this paper proposes a cluster analysis-based approach developed by incorporating and modifying two cluster analysis methods, a hierarchical clustering and a non-hierarchical clustering method. The objective of the proposed approach is to minimize intercellular movements and maximize the machine utilization within clusters. The proposed approach is tested on the cell formation problems and is compared with other well-known methodologies available in the literature. The result shows that the proposed approach is efficient enough to yield a good quality solution no matter what the difficulty of data sets is, ill or well-structured.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.40 no.4
• /
• pp.203-210
• /
• 2017

Data clustering is one of the most difficult and challenging problems and can be formally considered as a particular kind of NP-hard grouping problems. The K-means algorithm is one of the most popular and widely used clustering method because it is easy to implement and very efficient. However, it has high possibility to trap in local optimum and high variation of solutions with different initials for the large data set. Therefore, we need study efficient computational intelligence method to find the global optimal solution in data clustering problem within limited computational time. The objective of this paper is to propose a combined artificial bee colony (CABC) with K-means for initialization and finalization to find optimal solution that is effective on data clustering optimization problem. The artificial bee colony (ABC) is an algorithm motivated by the intelligent behavior exhibited by honeybees when searching for food. The performance of ABC is better than or similar to other population-based algorithms with the added advantage of employing fewer control parameters. Our proposed CABC method is able to provide near optimal solution within reasonable time to balance the converged and diversified searches. In this paper, the experiment and analysis of clustering problems demonstrate that CABC is a competitive approach comparing to previous partitioning approaches in satisfactory results with respect to solution quality. We validate the performance of CABC using Iris, Wine, Glass, Vowel, and Cloud UCI machine learning repository datasets comparing to previous studies by experiment and analysis. Our proposed KABCK (K-means+ABC+K-means) is better than ABCK (ABC+K-means), KABC (K-means+ABC), ABC, and K-means in our simulations.