• Title/Summary/Keyword: optimal number of clusters

Search Result 79, Processing Time 0.025 seconds

Optimal Fuzzy Models with the Aid of SAHN-based Algorithm

  • Lee Jong-Seok;Jang Kyung-Won;Ahn Tae-Chon
    • 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.

A Minimum Resources Allocation Algorithm for Optimal Design Automation (최적의 설계 자동화를 위한 최소자원 할당 알고리듬)

  • Kim, Young-Suk;Lin, Chi-Ho
    • The Journal of The Korea Institute of Intelligent Transport Systems
    • /
    • v.6 no.3
    • /
    • pp.165-173
    • /
    • 2007
  • In this paper, we propose a new minimum resources allocation algorithm for optimal design automation. In the proposed algorithm, the operation are allocated to functional units so that the number of interconnection wires between functional units can be minimized. The registers are allocated to the maximal clusters generated by the minimal cluster partitioning algorithm. Finally, the interconnection is minimized by removing the duplicated inputs of multiplexers and exchanging the inputs across multiplexers. The efficiency of the proposed allocation algorithm is shown by experiments using benchmark examples.

  • PDF

A Comparative Study on Statistical Clustering Methods and Kohonen Self-Organizing Maps for Highway Characteristic Classification of National Highway (일반국도 도로특성분류를 위한 통계적 군집분석과 Kohonen Self-Organizing Maps의 비교연구)

  • Cho, Jun Han;Kim, Seong Ho
    • KSCE Journal of Civil and Environmental Engineering Research
    • /
    • v.29 no.3D
    • /
    • pp.347-356
    • /
    • 2009
  • This paper is described clustering analysis of traffic characteristics-based highway classification in order to deviate from methodologies of existing highway functional classification. This research focuses on comparing the clustering techniques performance based on the total within-group errors and deriving the optimal number of cluster. This research analyzed statistical clustering method (Hierarchical Ward's minimum-variance method, Nonhierarchical K-means method) and Kohonen self-organizing maps clustering method for highway characteristic classification. The outcomes of cluster techniques compared for the number of samples and traffic characteristics from subsets derived by the optimal number of cluster. As a comprehensive result, the k-means method is superior result to other methods less than 12. For a cluster of more than 20, Kohonen self-organizing maps is the best result in the cluster method. The main contribution of this research is expected to use important the basic road attribution information that produced the highway characteristic classification.

A genetic algorithm for generating optimal fuzzy rules (퍼지 규칙 최적화를 위한 유전자 알고리즘)

  • 임창균;정영민;김응곤
    • Journal of the Korea Institute of Information and Communication Engineering
    • /
    • v.7 no.4
    • /
    • pp.767-778
    • /
    • 2003
  • This paper presents a method for generating optimal fuzzy rules using a genetic algorithm. Fuzzy rules are generated from the training data in the first stage. In this stage, fuzzy c-Means clustering method and cluster validity are used to determine the structure and initial parameters of the fuzzy inference system. A cluster validity is used to determine the number of clusters, which can be the number of fuzzy rules. Once the structure is figured out in the first stage, parameters relating the fuzzy rules are optimized in the second stage. Weights and variance parameters are tuned using genetic algorithms. Variance parameters are also managed with left and right for asymmetrical Gaussian membership function. The method ensures convergence toward a global minimum by using genetic algorithms in weight and variance spaces.

Optimal Number of Super-peers in Clustered P2P Networks (클러스터 P2P 네트워크에서의 최적 슈퍼피어 개수)

  • Kim Sung-Hee;Kim Ju-Gyun;Lee Sang-Kyu;Lee Jun-Soo
    • The KIPS Transactions:PartC
    • /
    • v.13C no.4 s.107
    • /
    • pp.481-490
    • /
    • 2006
  • In a super-peer based P2P network, The network is clustered and each cluster is managed by a special peer, called a super-peer which has information of all peers in its cluster. This clustered P2P model is known to have efficient information search and less traffic load. In this paper, we first estimate the message traffic cost caused by peer's query, join and update actions within a cluster as well as between the clusters and with these values, we present the optimal number of super-peers that minimizes the traffic cost for the various size of super-peer based P2P networks.rks.

Effects of Vine Induction Method on the Growth and Fruit Yield in Korean Schisandra (오미자 덩굴 유인방법이 생육 및 과실 수량에 미치는 영향)

  • Kim, Ju Ho;Lee, Beom Gyun;Choi, Eun Young
    • Korean Journal of Medicinal Crop Science
    • /
    • v.25 no.2
    • /
    • pp.83-88
    • /
    • 2017
  • Background: This study was aimed to determine the optimal vine induction method for growing of Korean schisandra (Schisandra chinensis), by comparing plant growth and fruit yields between plants grown with either fence-type (U-type) or A-type induction. Methods and Results: Plants were transplanted on August 17, 2014, and the plant height, stem node number and weight were measured every two weeks, six times from June 17, 2016. The plant height, stem node number, and leaf length and width were higher with the A-type than with the U-type induction, by approximately 37.0%, 49.1%, 27.6%, and 12.7%, respectively. Although there was no significant difference between the photosynthesis rates of plants grown with the two vine induction method, the leaf area and leaf number per plant were higher in the plants grown with the A-type than the U-type, by approximately 23.7% and 46.0%, respectively. The number of green-color pixels, in a defined area of digital camera images of creeper leaves from the inducted vines, was significantly higher in the plants grown with the A-type than the U-type. The number of fruit clusters per plant was approximately 26 and 36, under the U-type and A-type, respectively. A two fold higher total fruit weight per plant was observed in the plants grown under the A-type (250 g/plant) than the U-type (120 g/plant). Conclusions: The A-type vine induction method is optimal for cultivation of Korean schisandra.

A Study on Road Characteristic Classification using Exploratory Factor Analysis (탐색적 요인분석을 이용한 도로특성분류에 관한 연구)

  • Cho, Jun-Han;Kim, Seong-Ho;Rho, Jeong-Hyun
    • Journal of Korean Society of Transportation
    • /
    • v.26 no.3
    • /
    • pp.53-66
    • /
    • 2008
  • This research is to the establishment of a conceptual framework that supports road characteristic classification from a new point of view in order to complement of the existing road functional classification and examine of traffic pattern. The road characteristic classification(RCC) is expected to use important performance criteria that produced a policy guidelines for transportation planning and operational management. For this study, the traffic data used the permanent traffic counters(PTCs) located within the national highway between 2002 and 2006. The research has described for a systematic review and assessment of how exploratory factor analysis should be applied from 12 explanatory variables. The optimal number of components and clusters are determined by interpretation of the factor analysis results. As a result, the scenario including all 12 explanatory variables is better than other scenarios. The four components is produced the optimal number of factors. This research made contributions to the understanding of the exploratory factor analysis for the road characteristic classification, further applying the objective input data for various analysis method, such as cluster analysis, regression analysis and discriminant analysis.

Improved TI-FCM Clustering Algorithm in Big Data (빅데이터에서 개선된 TI-FCM 클러스터링 알고리즘)

  • Lee, Kwang-Kyug
    • Journal of IKEEE
    • /
    • v.23 no.2
    • /
    • pp.419-424
    • /
    • 2019
  • The FCM algorithm finds the optimal solution through iterative optimization technique. In particular, there is a difference in execution time depending on the initial center of clustering, the location of noise, the location and number of crowded densities. However, this method gradually updates the center point, and the center of the initial cluster is shifted to one side. In this paper, we propose a TI-FCM(Triangular Inequality-Fuzzy C-Means) clustering algorithm that determines the cluster center density by maximizing the distance between clusters using triangular inequality. The proposed method is an effective method to converge to real clusters compared to FCM even in large data sets. Experiments show that execution time is reduced compared to existing FCM.

Fast Multi-Resolution Exhaustive Search Algorithm Based on Clustering for Efficient Image Retrieval (효율적인 영상 검색을 위한 클러스터링 기반 고속 다 해상도 전역 탐색 기법)

  • Song, Byeong-Cheol;Kim, Myeong-Jun;Ra, Jong-Beom
    • Journal of the Institute of Electronics Engineers of Korea SP
    • /
    • v.38 no.2
    • /
    • pp.117-128
    • /
    • 2001
  • In order to achieve optimal retrieval, i.e., to find the best match to a query according to a certain similarity measure, the exhaustive search should be performed literally for all the images in a database. However, the straightforward exhaustive search algorithm is computationally expensive in large image databases. To reduce its heavy computational cost, this paper presents a fast exhaustive multi-resolution search algorithm based on image database clustering. Firstly, the proposed algorithm partitions the whole image data set into a pre-defined number of clusters having similar feature contents. Next, for a given query, it checks the lower bound of distances in each cluster, eliminating disqualified clusters. Then, it only examines the candidates in the remaining clusters. To alleviate unnecessary feature matching operations in the search procedure, the distance inequality property is employed based on a multi-resolution data structure. The proposed algorithm realizes a fast exhaustive multi-resolution search for either the best match or multiple best matches to the query. Using luminance histograms as a feature, we prove that the proposed algorithm guarantees optimal retrieval with high searching speed.

  • PDF

DETECTOR SIMULATIONS FOR THE COREA PROJECT (COREA 프로젝트를 위한 검출기 모의실험)

  • Lee, Sung-Won;Kang, Hye-Sung
    • Publications of The Korean Astronomical Society
    • /
    • v.21 no.2
    • /
    • pp.87-94
    • /
    • 2006
  • The COREA (COsmic ray Research and Education Array in Korea) project aims to build a ground array of particle detectors distributed over Korean Peninsular, through collaborations of high school students, educators, and university researchers, in order to study the origin of ultra high energy cosmic rays. COREA array will consist of about 2000 detector stations covering several hundreds of $km^2$ area at its final configuration and detect electrons and muons in extensive air-showers triggered by high energy particles. During the intial phase COREA array will start with a small number of detector stations in Seoul area schools. In this paper, we have studied by Monte Carlo simulations how to select detector sites for optimal detection efficiency for proton triggered air-showers. We considered several model clusters with up to 30 detector stations and calculated the effective number of air-shower events that can be detected per year for each cluster. The greatest detection efficiency is achieved when the mean distance between detector stations of a cluster is comparable to the effective radius of the air-shower of a given proton energy. We find the detection efficiency of a cluster with randomly selected detector sites is comparable to that of clusters with uniform detector spacing. We also considered a hybrid cluster with 60 detector stations that combines a small cluster with ${\Delta}{\iota}{\approx}100m$ and a large cluster with ${Delta}{\iota}{\approx}1km$. We suggest that it can be an ideal configuration for the initial phase study of the COREA project, since it can measure the cosmic rays with a wide range energy, i.e., $10^{16}eV{\leq}E{\leq}10^{19}eV$, with a reasonable detection rate.