• Proceedings of the IEEK Conference
• /
• summer
• /
• pp.447-450
• /
• 2004

This paper proposes remotely sensed image classification method by fuzzy c-means clustering algorithm using average intra-cluster distance. The average intra-cluster distance acquires an average of the vector set belong to each cluster and proportionates to its size and density. We perform classification according to pixel's membership grade by cluster center of fuzzy c-means clustering using the mean-values of training data about each class. Fuzzy c-means algorithm considered membership degree for inter-cluster of each class. And then, we validate degree of overlap between clusters. A pixel which has a high degree of overlap applies to the maximum likelihood classification method. Finally, we decide category by comparing with fuzzy membership degree and likelihood rate. The proposed method is applied to IKONOS remote sensing satellite image for the verifying test.

• Journal of the Korean Vacuum Society
• /
• v.9 no.3
• /
• pp.273-278
• /
• 2000

We studied aluminum cluster deposition using molecular dynamics simulation. We investigated the variations of the substrate temperature and disordered atom number during cluster impact, and found that the correlated collisions between aluminum atoms in the cluster play a very important role in the impact on aluminum substrate surface. The correlated collisions effect is proportional to the cluster size.

• Smart Media Journal
• /
• v.8 no.4
• /
• pp.46-52
• /
• 2019

The size of data generated and collected at industrial sites or in public institutions is growing rapidly. The existing data processing server often handles the increasing data by increasing the performance by scaling up. However, in the big data era, when the speed of data generation is exploding, there is a limit to data processing with a conventional server. To overcome such limitations, a distributed cluster computing system has been introduced that distributes data in a scale-out manner. However, because distributed cluster computing systems distribute data, inefficient use of network bandwidth can degrade the performance of the cluster as a whole. In this paper, we propose a scheme that compresses data when transmitting data in a Hadoop cluster considering network bandwidth. The proposed scheme considers the network bandwidth and the characteristics of the compression algorithm and selects the optimal compression transmission scheme before transmission. Experimental results show that the proposed scheme reduces data transfer time and size.

• Asian Journal of Atmospheric Environment
• /
• v.4 no.1
• /
• pp.9-19
• /
• 2010

The size distribution of airborne particulate matter (PM) and the concentrations of associated metallic elements were investigated in a busy urban region of a typical Korean industrial city. The PM concentrations measured during the spring, except for those in the size range of 1.1 to 2.1 ${\mu}m$, were slightly higher than the PM concentrations in the summer. Coarse particles contributed greatly to the variation in PM concentrations in the spring, while fine and submicron particles contributed largely to the variation in PM concentrations in the summer. The difference in size modes of the PM concentrations between spring and summer may be explained by the Asian dust effect and its accompanying wind direction and speed. Extremely high enrichment factors (EFs) values (6,971 to 60,966) for all of the size distributions in PM were identified for cadmium (Cd). High EFs values (12 to 907) were also identified for other heavy metals including Cr, Cu, Ni, Pb, Zn and Mn. Low EF values (0.29 to 8.61) were identified for Ca, K, Mg and Na. These results support the common hypothesis that most heavy metals in ambient PM have anthropogenic sources and most light metals have crustal sources. The results of principal components analyses and cluster analyses for heavy metals indicate that the principal sources of PM and metals were emissions from non-ferrous metal smelters, oil combustion, incinerators, vehicular traffic and road dust.

• The Korean Journal of Applied Statistics
• /
• v.20 no.3
• /
• pp.605-618
• /
• 2007

Adaptive sampling design is the selection procedure which depends on observed values of the variable of interest. It is the method which could be applied to the rare and unapproachable population. Adaptive cluster sampling strategies are more efficient than simple random sampling on equivalent sample size. Adaptive sampling with new estimators through the Rao-blackwell method have lower variance than Horvitz-Thompson (HT) and Hansen-Hurwitz (HH). Also, to determine suitable sample size, it was used expected sample and the method finding appropriate sample size by changing initial sample size were studied.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.10 no.3
• /
• pp.37-48
• /
• 1986

The purpose of this study was to analyze 'the natural groupings' of subjects in order to classify highly similar somatotype for clothing construction. The sample for the study was drawn randomly out of senior high school boys in Seoul urban area. The sample size was 425 boys between age 16 and 18. Cluster analysis was more concerned with finding the hierarchical structure of subjects by three dimensional distance of stature. bust girth and sleeve length. The groups forming a partition can be subdivided into 5 and 6 sets by the hierarchical tree of the given subjects. Ward's Minimum Variance Method was applied after extraction of distance matrix by the Standardized Euclidean Distance. All of the above data was analyzed by the computer installed at Korea Advanced Institute of Science and Technology. The major findings, take for instance, of 16 age group can be summarized as follows. The results of cluster analysis of this study: 1. Cluster 1 (32 persons means $18.29\%$ of the total) is characterized with smaller bust girth than that of cluster 5, but stature and sleeve length of the cluster 1 are the largest group. 2. Cluster 2 (18 Persons means $10.29\%$ of the total) is characterized with the group of the smallest stature and sleeve length, but bust girth larger than that of cluster 3. 3. Cluster 3(35persons means $20\%$ of the total) is classified with the smallest group of all the stature, bust girth and sleeve length. 4. Cluster 4(60 persons means $34.29\%$ of the total) is grouped with the same value of sleeve length with the mean value of 16 age group, but the stature and bust girth is smaller than the mean value of this age group. 5. Cluster 5(30 persons means $17.14\%$ of the total) is characterized with smaller stature than that of cluster 1, and with larger bust girth than that of cluster 1, but with the same value of the sleeve length with the mean value of the 16 age group.

• Korean Journal of Human Ecology
• /
• v.12 no.4
• /
• pp.553-558
• /
• 2003

The purpose of this paper was to design the sizing system of the head gears which would be a guide of men for selecting their head gears of suitable size. This study was carried out on 214 men and was done by cluster analysis with two variables(head circumference and bitragus to vertex arc length). The results were as follows : First, most of measurements were larger in men than in women. Second, the suitable numbers of size were found that 5 sizes were proper by cluster analysis with two variables. After the design of sizing system, the cover ratio was investigated in order to decide whether it is proper or not. Third, in the cover ratio, the 5 sizes were the highest in all of them.

• The Korean Journal of Applied Statistics
• /
• v.25 no.5
• /
• pp.733-741
• /
• 2012

The successful launch of Arirang satellites allow the acquisition of high resolution satellite imagery of Korean territory and enables the transition from the conventional cultivation area survey method to new image based methods adopted in advanced nations. In this study, we suggested reasonable sizes of the primary sampling unit and the secondary sampling unit for the satellite imagery based sampling design in 8 provinces preselected for this research. The PSU size was determined mainly in consideration of intracorrelation that shows the degree of homogeneity within each cluster and the efficiency of the image process. For the SSU size, we considered the relative standard error and the differences between the land cover maps produced by the Ministry of Environment and the satellite imagery processed by the National Statistical Office.

• The Journal of Economics, Marketing and Management
• /
• v.10 no.6
• /
• pp.9-16
• /
• 2022

Purpose: This research investigates the differences in knowledge exchange activities and performances between startups and large companies in software industry clusters. Research design, data, and methodology: Six independent factors of human resource information, R&D and technology, marketing knowledge, government support information, strategic knowledge, and cooperation information were extracted to test the firm size effect in the relationships with two performance factors such as satisfaction with industry cluster location and satisfaction with financial performances. Data were collected through a survey of entrepreneurs, managers, and employees and tested by statistical analysis methodologies. Results: Three independent factors of human resource information, R&D and technology, and cooperation information were particularly significant in the relationship with both dependent factors. Strategic knowledge significantly affected financial performance. Knowledge exchange activities were more important in startups than in large companies for all eight factors. Conclusion: Policies for software industry clusters need a different approach for startups and large companies.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.41 no.12
• /
• pp.1801-1810
• /
• 2016

The OpenDaylight controller has been receiving significant attention as one of the enabling open source framework for SDN, and this paper analyzes the architecture and procedure of OpenDaylight based controller cluster. The OpenDaylight controller cluster uses shard based distributed datastore and Raft algorithm to maintain consistency among controllers inside a cluster. The performance evaluation analyzes the leader re-election time as well as latencies of CRUD and Routed RPC according to cluster size, shard role, and sharding strategy, and we discuss the optimal operation strategy for OpenDaylight controller cluster.