• Journal of the Korean Data and Information Science Society
• /
• v.26 no.1
• /
• pp.89-99
• /
• 2015

The World Economic Forum and the Korean Ministry of Knowledge Economy have selected big data as one of the top 10 in core information technology. The key of big data is to analyze effectively the properties that do have data. Clustering analysis method of big data techniques is a method of assigning a set of objects into the clusters so that the objects in the same cluster are more similar to each other clusters. Similarity measures being used in the cluster analysis may be classified into various types depending on the nature of the data. In this paper, we studied upper and lower bounds for binary similarity measures with negative matches such as Russel and Rao measure, simple matching measure by Sokal and Michener, Rogers and Tanimoto measure, Sokal and Sneath measure, Hamann measure, and Baroni-Urbani and Buser mesures I, II. And the comparative studies with these measures were shown by real data and simulated experiment.

• The Korean Journal of Mycology
• /
• v.27 no.5 s.92
• /
• pp.328-336
• /
• 1999

Isozyme comparisons of mycelial extracts from Pleurotus ostreatus were undertaken using isoelectric focusing. Enzyme isozyme patterns were Used to describe the extent of geographical diversity and degree of intraspecific variation in these extracts. A total of 77 bands were resolved from six different enzymes. Cluster analyses were performed using the zymograms for esterase (EST), glucose phosphate isomerase (GPI), leucine aminopeptidase (LAP), malate dehydrogenase(MDH), peroxidase (POX), and phosphoglucomutase (pGM). EST gave multiple banding patterns, while less variability was observed for GPI, MDH, and PGM. Cluster analyses demonstrated that strains of P. ostreatus from geographically different origins are genetically divergent, supporting the idea that there is little or no gene flow between these geographically distant population groups.

• Journal of Advanced Marine Engineering and Technology
• /
• v.37 no.2
• /
• pp.144-148
• /
• 2013

In this paper, the ultra water-repellent thin films were prepared by RF PECVD. On the basis of surface morphology, chemical bonding states and plasma diagnostics, a formation model of clusters for the ultra water-repellent films was discussed from considerations of formation process and laser scattering results. Moreover, using laser scattering method, the relative change of quantity of nano-clusters or size of agglomerates could be confirmed. From the results, the films were deposited with nano-clusters and those of agglomerates, which formed in organosilicon plasma, and formation of agglomerates were depended on the deposition time.

• The Korean Journal of Mycology
• /
• v.27 no.4 s.91
• /
• pp.274-279
• /
• 1999

The internal transcribed spacer regions(ITS) of the ribosomal DNA gene repeat from Coprinus and Psathyrella spp. were amplified using polymerase chain reaction (PCR) and sequenced. Sequences from 11 species including Coprinus comatus, C. atramentarius, C. micaceus, C. cinereus, C. rhizophorus, C. radians, C. echinosporus, C. disseminatus, Psathyrella candolleana, P. spadiceogrisea and Stropharia rugosoannulata were compared. The spacer region I and II were $258{\sim}301\;bp\;and\;253{\sim}275\;bp$ in length respectively and partially contained 17S, 5.8S and 25S. The reciprocal homologies of ITS sequences among these strains were in the range of $43.9{\sim}96.0%$. According to the analysis of ITS sequences, Coprinus and Psathyrella spp. were classified into three clusters. Cluster I consisted of Coprinus lagopus, C. cinereus, C. echinosporus, C. rhizophorus, and C. atramentarius. Cluster II comprised C. micaceus, C. radians, C. disseminatus, Psathyrella candolleana, and P. spadiceogrisea. On the other hand C. comatus is in Cluster III with Stropharia rugosoannulata even though this species is belonging to the section Coprinus in morphological aspect. These results suggest that taxonomic position of Psathyrella would better be inculded in genus Coprinus. Coprinus comatus, the type species of Coprinus, gives a doubt on monophyletic evolution and is assumed to be paraphyletic or polyphyletic.

• Journal of the Korean Institute of Educational Facilities
• /
• v.16 no.5
• /
• pp.19-26
• /
• 2009

This study attempts to find out the spatial characteristics of the converging technology laboratory. For this, the understanding of the nature of converging technology and its necessary system requirements are crucial. The foremost concern lies in the 'flexibility' of the laboratory space, i.e. 'open-lab system', because of the multi-disciplinary spatial arrangement which is supposed to be open to a number of different research fields in the same building cluster. From the case analysis, this study reveals that in order to maximize the adjustability, the module based space unit plan should be considered at the earliest stage. In addition, it is also found from the analysis that the linkage of the communication spaces such as seminar room, auditorium, lounge, rest room, dining room, and corridors should be dealt with a higher degree of sophistication, since these facilitate the interaction of information at the behavioral level.

• Journal of Sensor Science and Technology
• /
• v.32 no.6
• /
• pp.378-385
• /
• 2023

Human biosignals provide essential information for diagnosing diseases such as dementia and Parkinson's disease. Owing to the shortcomings of current clinical assessments, noninvasive solutions are required. Machine learning (ML) on wearable sensor data is a promising method for the real-time monitoring and early detection of abnormalities. ML facilitates disease identification, severity measurement, and remote rehabilitation by providing continuous feedback. In the context of wearable sensor technology, ML involves training on observed data for tasks such as classification and regression with applications in clinical metrics. Although supervised ML presents challenges in clinical settings, unsupervised learning, which focuses on tasks such as cluster identification and anomaly detection, has emerged as a useful alternative. This review examines and discusses a variety of ML algorithms such as Support Vector Machines (SVM), Random Forests (RF), Decision Trees (DT), Neural Networks (NN), and Deep Learning for the analysis of complex clinical data.

• International Journal of Oral Biology
• /
• v.43 no.2
• /
• pp.101-111
• /
• 2018

Understanding the classification of malocclusion is a crucial issue in Orthodontics. It can also help us to diagnose, treat, and understand malocclusion to establish a standard for definite class of patients. Principal component analysis (PCA) and k-means algorithms have been emerging as data analytic methods for cephalometric measurements, due to their intuitive concepts and application potentials. This study analyzed the macro- and meso-scale classification structure and feature basis vectors of 1020 (415 male, 605 female; mean age, 25 years) orthodontic patients using statistical preprocessing, PCA, random matrix theory (RMT) and k-means algorithms. RMT results show that 7 principal components (PCs) are significant standard in the extraction of features. Using k-means algorithms, 3 and 6 clusters were identified and the axes of PC1~3 were determined to be significant for patient classification. Macro-scale classification denotes skeletal Class I, II, III and PC1 means anteroposterior discrepancy of the maxilla and mandible and mandibular position. PC2 and PC3 means vertical pattern and maxillary position respectively; they played significant roles in the meso-scale classification. In conclusion, the typical patient profile (TPP) of each class showed that the data-based classification corresponds with the clinical classification of orthodontic patients. This data-based study can provide insight into the development of new diagnostic classifications.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.39 no.3
• /
• pp.156-169
• /
• 2016

The objective of this study is to investigate patent trends of Daegu city which tries to introduce environment friendly energy and to develop new technology or new industry sprung from technology convergence on smart decentralized energy technology and other technologies. After applying network analysis to corresponding groups of technology or industry convergence, strategy for future energy convergence industry is provided. Patent data applied in Daegu city area are used to obtain research goal. The technology which contains several IPC codes (IPC Co-occurrence) is considered as a convergence technology. Path finder network analysis is used for visualizing and grouping by using IPC codes. The analysis results categorized 13 groups in energy convergence industry and reclassified them into 3 cluster groups (Smart Energy Product Production Technology Group, Smart Energy Convergence Supply Technology Group, Smart Energy Indirect Application Technology Group) considering the technical characteristics and policy direction. Also, energy industry has evolved rapidly by technological convergence with other industries. Especially, it has been converged with IT industry, and there is a trend that energy industry will be converged with service industry and manufacturing industry such as textile, automobile parts, mechanics, and logistics by employing infrastructure as well as network. Based on the research results on core patent technology, convergence technology and inter-industry analysis, the direction of core technology research and development as well as evolution on decentralized energy industry is identified. By using research design and methodology in this study, the trend of convergence technology is investigated based on objective data (patent data). Above all, we can easily confirm the core technology in the local industry by analyzing the industrial competitiveness in the macro level. Based on this, we can identify convergence industry and technology by performing the technological convergence analysis in the micro level.

• Fisheries and Aquatic Sciences
• /
• v.8 no.3
• /
• pp.151-160
• /
• 2005

Genomic DNA samples isolated from Fenneropenaeus chinensis (fleshy prawn; FP) and Palaemon gravieri (Chinese ditch prawn; CDP) collected in the West Sea, off the Korean Peninsula, at Buan, were PCR-amplified repeatedly. The sizes of the DNA fragments generated by seven different primers varied from 50 bp to 1,600 bp. We identified 358 fragments for the FP species and 301 fragments for the CDP species. There were 18 polymorphic fragments (5.03$\%$) for the FP species and 12 (3.99$\%$) for the CDP species. In total, 66 common fragments (average of 9.4 fragments per primer) were observed for the FP species and 44 fragments (average of 6.3 fragments per primer) were observed for the CDP species. The numbers of specific fragments seen for the FP species and CDP species were 38 and 47, respectively. The complexity of the banding patterns varied dramatically between the primers and the two species. In the FP species, a specific fragment of approximately 1,200 bp generated by primer OPB-04 exhibited inter-individual-specific characteristics that were indicative of DNA polymorphisms. Moreover, in the CDP species, a major fragment of approximately 550 bp generated by primer OPB-20 was found to be specific for the CDP. The average bandsharing value between the two prawn species was 0.421$\pm$0.006, and ranged from 0.230 to 0.611. The dendrogram obtained using the data from the seven primers indicated seven genetic clusters: cluster 1, FLESHY 01, 02, 03, and 04; cluster 2, FLESHY 05, 06, and 07; cluster 3, FLESHY 08, 09, 10, and 11; cluster 4, DITCH 13, 14, 16, and 18; cluster 5, DITCH 12, 15, and 17; cluster 6, DITCH 19, 20, and 21; and cluster 7, DITCH 22. The genetic distance between the two prawn species ranged from 0.071 to 0.642. Thus, RAPD-PCR analysis revealed a significant genetic distance between the two prawn species. Using various arbitrary primers, RAPD-PCR may be applied to identify specific/polymorphic markers that are particular to a species and geographic population, and to define genetic diversity, polymorphisms, and similarities among shrimp species.

• 제어로봇시스템학회:학술대회논문집
• /
• 2003.10a
• /
• pp.1056-1059
• /
• 2003

Self-Oranizing Map(SOM) is an unsupervised neural network providing cluster analysis of high dimensional input data. The output from the SOM is represented in map that help us to explore data. The weak point of conventional SOM is when the map is large, it take a long time to train the data. The computing time is known to be O(MN) for trainning to find the winning node (M,N are the number of nodes in width and height of the map). This paper presents a new method to reduce the computing time by creating new map. Each node in a new map is the centroid of nodes' group that are in the original map. After create a new map, we find the winning node of this map, then find the winning node in original map only in nodes that are represented by the winning node from the new map. This new method is called "High Speed Self-Oranizing Map"(HS-SOM). Our experiment use HS-SOM to cluster documents and compare with SOM. The results from the experiment shows that HS-SOM can reduce computing time by 30%-50% over conventional SOM.