• The Korean Journal of Applied Statistics
• /
• v.8 no.1
• /
• pp.39-50
• /
• 1995

This article deals with the problem that all the statistical clustering methods do not supply the clustering rule after the analysis. We modify the Coulomb Energy Network model basically developed in physics and suggest one model appropriate for our purpose and show the implementation using an actual data. Finally the method suggested is compared with one of the well known methods, K-means algorithm using Rand C.

• The Korean Journal of Ecology
• /
• v.23 no.1
• /
• pp.25-32
• /
• 2000

To analyze the relationship between climatic factors (monthly temperatures and precipitations) and the radial growths or Pinus densiflora with different topographical settings in Worak National Park, Korea, 20 stands were chosen and 10 trees were selected from each stand. After crossdating, each ring-width series was double detrended (standardized) by fitting first a negative exponential or straight regression line and secondly a 60-year cubic spline. The growth patterns coud be categorized by four groups using cluster analysis. Cluster Ⅰ stand has north aspect, but others have south or southwest aspects. Cluster Ⅰ (one), cluster Ⅱ (ten), and cluster Ⅲ (two) stands are located in lower. elevation (305∼580 m), however, cluster Ⅳ (seven) stands are located in higher elevation, mostly in 560～870 m. Cluster Ⅱ and Ⅲ stands are located at similar elevation with the same aspect, however, cluster Ⅱ stands are located on more rocky and stiff slope with shallow soil depth. The response functions were used to examine the difference in the relationships between climatic factors and tree growths among the 4 cluster chronologies. The climatic factors are not limiting the growth in the cluster Ⅰ stand as highly as in other cluster plots because of rather mesic conditions in the north slope. The precipitation in the spring appears to be the main limiting factor in the cluster Ⅱ stands. The topographical characteristics of the sites of cluster Ⅱ, shallow soil depths on the rocky slope in the south aspect at lower elevation, may enhance the sensitivity of growth to moisture stress. In cluster Ⅲ and cluster Ⅳ, winter and spring temperature prior to the growth become more important than for cluster Ⅱ. This pattern is com-mon for Pinus densiflora trees growing in higher. elevation (equation omitted 800 m) in South Korea. It nay be re-lated with preconditioning effects of temperature as the temperature decreases with increasing elevation (cluster Ⅳ) or in the valley (cluster Ⅲ). The results obtained by tree-ring analysis were digitalized by GIS and spatio-temporal information on tree-ring data and topographic setting were analyzed and displayed simultaneously. The results of this study can be used to predict the future change of Pinus densiflora ecosystem to climate change expected in central Korea.

• The Korean Journal of Applied Statistics
• /
• v.5 no.2
• /
• pp.211-227
• /
• 1992

In this paper we consider the definition and mathematical properties of similarity or dissimilarity which have often used in clust analysis, and we apply a hierarchical agglomerative cluster algorithm to a dissimilarity metrx generated by these distance. Here we investigate the effect of relation between distance function and cluster algorithm on the retrieval ability of natural clusters. We present an empirical results for qualitative data as well as quantitative data.

• Journal of the Korea Convergence Society
• /
• v.8 no.11
• /
• pp.103-108
• /
• 2017

In the ubiquitous environment, there has been a problem of transmitting data from various sensors at a long distance. Especially, in the process of integrating data arriving at different locations, data having different property values of data or having some loss in data had to be processed. This paper present a method to analyze such data. The core of this method is to define an objective function suitable for the problem and to develop an algorithm that can optimize this objective function. The objective function is used by modifying the OCS function. MFA (Mean Field Annealing), which was able to process only binary data, is extended to be applicable to fields with continuous values. It is called CMFA and used as an optimization algorithm.

• Clinical and Experimental Pediatrics
• /
• v.45 no.2
• /
• pp.247-255
• /
• 2002

Purpose : This study was undertaken to obtain basic data about the megakaryocyte colony formation of fetal liver cells by using immunocytochemical staining and ex vivo culture with growth factors. Methods : The mononuclear cells were isolated from fetal liver and bone marrow with idiopathic thrombocytopenic purpura(ITP) and pancytopenia. These mononuclear cells were cultured in $MegaCult^{TM}-C$(Stem Cell Tech, Canada) media in the presence of growth factors and CFU-Megakaryocyte( CFU-Mk) colonies were counted on day 12. The expansion of CD34+ and CD41+ cell was analyzed by flow cytometry after 5 days incubation using flask culture. Results : The numbers of CFU-Mk colonies of mononuclear cells obtained from fetal liver in the 11th week gestational age were more than those in the 19th week specimens; growth factors could not enhance the colony expansion in all cases. Total numbers of CFU-Mk colony of fetal liver cells were higher than bone marrow from ITP or pancytopenia groups. The numbers of pure or large CFU-Mk colonies of fetal liver cells were also higher than bone marrow specimens. The rate of CD34+ cell expression of fetal liver was increased after flask culture and the enhancement effect of epression was seen only in cases which added thrombopoietin. The rate of CD41+ cell expression of fetal liver was increased after incubation, but the enhancement effect of growth factors was unclear. Conclusion : This study revealed good results about the megakaryocyte colony assay of fetal liver mononuclear cells using $MegaCult^{TM}-C$ media. This study suggests that the fetal liver could be a good source of megakaryocytic progenitor cells for clinical application in hematopoietic stem cell transplantation.

• Journal of Korean Society of Forest Science
• /
• v.95 no.3
• /
• pp.370-377
• /
• 2006

This study was conducted to develop an efficient method of sampling design appropriate for the sustainable forest management. For this, data were collected in Yangpyung-Gun, Gyunggi Province based on three different sampling designs such as systematic design, systematic cluster design, and stratified cluster design. Based on evaluation statistics, the sampling designs were compared to select a sampling method fitted to sustainable forest management. It was found that the systematical cluster sampling is the most efficient sampling method in terms of feasibility for sustainable forest management. It was also recommended that the sample plots should be made as a cluster of triangle-shape. The clusters should be consisted of a main plot and three sub-plots. And the sub-plots should be arranged with a distance of 50m from the main plot in the center of cluster.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 1995.04a
• /
• pp.682-693
• /
• 1995

• Korean Journal of Soil Science and Fertilizer
• /
• v.42 no.6
• /
• pp.447-453
• /
• 2009

Vegetation distribution and soil salinity were surveyed on the conservation plot in the Daeho reclaimed tidal land, in where the plants species distribution was more various than a periodically inundated tidal flat and the early stage of reclamation. According to the soil salinity where the vegetation patches were occurred, the mono patches of Salicornia europaea, Suaeda maritima, and Suaeda glauca were distributed in the average range of 31.05 dS/m in soil salinity, the mixed patches of them were distributed in the average range of 42.75 dS/m. Therefore, Salicornia europaea, Suaeda maritima, and Suaeda glauca showed strong salt tolerance. The mono patches of Aster tripolium, Sonchus brachyotus, and Scirpus planiculm were distributed in the range of 11.73 dS/m in soil salinity, and the mixed patches were distributed in the average range of 9.43 dS/m. Therefore Aster tripolium, Sonchus brachyotus, and Scirpus planiculmis showed moderate salt tolerance. The mono patches of Imperata cylindrica, Trifolium pratense, Miscanthus sinensis, Setaria viridis, and Trisetum bifidum were distributed in the range of 2.42 dS/m in soil salinity. These species showed characteristics of glycophytes with weak salt tolerance. The distribution of vegetation patches was influenced by the soil salinity as pioneer halophytes patches occurred at higher soil salinity zone than facultative halophytes patches, glycophytes patches occurred at lower soil salinity zone than facultative halophytes. These results suggested that occurrence of plant species and plant distribution type might be useful index to evaluate the soil salinity and desalinization in the reclaimed land of the midwest coastal area of Korea.

• Journal of Korean Society of Transportation
• /
• v.23 no.3 s.81
• /
• pp.109-123
• /
• 2005

The goals of this paper are two folds: i) to evaluate whether the data collected by a license plate matching AVI equipment being operated on some segment of a national highway are suitable or not for use in travel time estimation of interrupted traffic flows; ii) to study the statistical methodologies to be used for the determination of the optimal aggregation interval for travel time estimation. In this study it was found that the AVI data are not representative because the data are collected on some selected lanes of a roadway where main traffic is thru-traffic and, thus the AVI data are different from those collected from all lanes in traffic characteristics. For the determination of the optimal aggregation interval for travel time estimation. two statistical methods. namely point estimation and interval estimation. were tested. The test shows that the point estimation method is more sensitive and gives more desirable results in determing the optimal aggregation interval than the interval estimation method. And it turned out that the optimal aggregation interval on interrupted traffic flows has been calculated as 5 minute and thus the existing aggregation interval. 5 minute is proper.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.3 no.2 s.5
• /
• pp.129-140
• /
• 2004

In this paper, we conduct the research about optimal aggregation interval of travel time data on interrupted traffic flow and verify the reliability of AVI collected data by using car plate matching method in RTMS for systematic collection and analysis of link travel time data on interrupted traffic flow rural arterial. We perform Kolmosorov-Smirnov test on AVT collected sample data and on entire population data, and conclude that the sample data does not represent pure random sampling and hence includes sample collection error. We suggest that additional review is necessary to investigate the effectiveness of AVI collected sample data as link representative data. We also develop statistical model by applying two estimation techniques namely point estimation and interval estimation for calculating optimal aggregation interval. We have implemented our model and determine that point estimate is preferable over interval estimate for exactly selecting and deciding optimal aggregation interval. Our final conclusion is that 5-minute aggregation interval is optimal to estimate travel time in RTMS, as is currently being used our investigation is based on AVI data collected from Yang-ji to Yong-in $42^{nd}$ National road.