• Journal of the Korea Computer Graphics Society
• /
• v.24 no.4
• /
• pp.29-38
• /
• 2018

In this paper, we propose an automatic segmentation method of meniscus in knee MR images by automatic meniscus localization, multi-atlas-based locally-weighted voting, and patch-based edge feature classification. First, after segmenting the bone and knee articular cartilage, the volume of interest of the meniscus is automatically localized. Second, the meniscus is segmented by multi-atlas-based locally-weighted voting taking into account the weights of shape and intensity distribution in the volume of interest of the meniscus. Finally, to remove leakage to the collateral ligaments with similar intensity, meniscus is refined using patch-based edge feature classification considering shape and distance weights. Dice similarity coefficient between proposed method and manual segmentation were 80.13% of medial meniscus and 80.81 % for lateral meniscus, and showed better results of 7.25% for medial meniscus and 1.31% for lateral meniscus compared to the multi-atlas-based locally-weighted voting.

• Journal of the Korean earth science society
• /
• v.26 no.6
• /
• pp.511-523
• /
• 2005

The purpose of this study is to analyze the 1st and 2nd Korea Earth Science Olympiad (KESO) items, in order to find informations to enhance item quality. To do this, internal and external item classification frameworks are developed. Item difficulty (P), discrimination index (DI), correlation, and reliability are estimated by using classical test theory. Generalizability is also estimated by applying the generalizability theory. The results of item classification are as follows: (1) ‘Geology’, ‘astronomy’ and ‘data analysis and interpretation’ are dominant in content and inquiry process domain, respectively. Nearly every item has textbook context. (2) There is no difference between the preliminary and final tests in terms of their thinking skills sections. (3) As a whole, the ratio of items with pictures is high in item representation. However, multiple-choice and short answer items are more common in preliminary competition, and essay type items are found more often in final competition. The ratio of simple items is high in middle school section and preliminary competition, but composite items are dominant in high school section and final competition. The findings of item analysis are as follows: (1) In the middle school section, P is low and DI is moderate. But in the high school section, there is a considerable differences between science high schools and other high schools in general. (2) The highest correlation is reported between the scores of meteorology domain and total score in middle school, whereas in high school astronomy domain and total score show the highest correlation. (3) General high school section show the highest Cronbach $\alpha$ and generalizability. (4) General high school section show acceptable generalizability coefficient (> 0.80), but middle and science high school section should increase the number of items to reach acceptable generalizability level.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.24 no.2
• /
• pp.173-178
• /
• 2014

In this study, we introduce ASM-based face recognition classifier and its design methodology with the aid of 2-dimensional 2-directional hybird preprocessing algorithm. Since the image of face recognition is easily affected by external environments, ASM(active shape model) as image preprocessing algorithm is used to resolve such problem. In particular, ASM is used widely for the purpose of feature extraction for human face. After extracting face image area by using ASM, the dimensionality of the extracted face image data is reduced by using $(2D)^2$hybrid preprocessing algorithm based on LDA and PCA. Face image data through preprocessing algorithm is used as input data for the design of the proposed polynomials based radial basis function neural network. Unlike as the case in existing neural networks, the proposed pattern classifier has the characteristics of a robust neural network and it is also superior from the view point of predictive ability as well as ability to resolve the problem of multi-dimensionality. The essential design parameters (the number of row eigenvectors, column eigenvectors, and clusters, and fuzzification coefficient) of the classifier are optimized by means of ABC(artificial bee colony) algorithm. The performance of the proposed classifier is quantified through yale and AT&T dataset widely used in the face recognition.

• Korean Journal of Medicinal Crop Science
• /
• v.9 no.3
• /
• pp.225-231
• /
• 2001

This studies were conducted to provide the basic information on safflower collections and to identify the variations which could be utilized in safflower breeding programs, The RAPDs was used to clarify the genetic relationships among safflower collections and to classify them into distint genetic groups. Among 30 of 10 mer primers in RAPD analysis, twenty were selected as the appropriate primers for identification of the genetic characters in safflower collections. Amplified PCR showed the highly reproducible bands at $3.0{\sim}0.2kb$. The number of bands amplified with the each primer showed the variations ranged from 2 to 11, with the average of 5.6. Total of 111 bands were identified among 20 selected primers used in PCR reaction and 84 bands (75.7%) showed polymorphism. Based on the similarity value of 0.14 in dendrogram derived from the cluster analysis using RAPD-PCR, the 30 safflower collections were classified into 11 groups. The two main groups, VII and VIII included 7 collections (23%) and 8 collections (27%), respectively. Most of the collections in group VII were the Korean collections (85%).

• Korean Journal of Remote Sensing
• /
• v.27 no.4
• /
• pp.457-466
• /
• 2011

The objectives of this study are to produce level 3 type LULC map and analysis of phenological features of North Korea, ISODATA clustering of the 88scenes of MVC of MODIS NDVI in 2008 and 8scenes in 2009 was carried out. Analysis of phenological phases based mapping method was conducted, In level 2 type map, the confusion matrix was summarized and Kappa coefficient was calculated. Total of 27 typical habitat types that represent the dominant species or vegetation density that cover land surface of North Korea in 2008 were made. The total of 27 classes includes the 17 forest biotopes, 7 different croplands, 2 built up types and one water body. Dormancy phase of winter (${\sigma}^2$ = 0.348) and green up phase in spring (${\sigma}^2$ = 0.347) displays phenological dynamics when much vegetation growth changes take place. Overall accuracy is (851/955) 85.85% and Kappa coefficient is 0.84. Phenological phase based mapping method was possible to minimize classification error when analyzing the inaccessible land of North Korea.

• KOREAN JOURNAL OF CROP SCIENCE
• /
• v.42 no.3
• /
• pp.357-366
• /
• 1997

Rice quality is considered to have two general meanings; 1) milling, cooking, and processing quality, which refer to suitability of the grain for a particular end-use; and 2) physical quality, which means cleanliness, soundness, and freedom from foreign materials. Grain type is associated with specific milling, cooking, and processing characteristics. Thus, this experiment was conducted to classify the grain type categories and marketing grades for Korean leading rice varieties. Length: width ratio of brown rice kernel ranged from 1.57 to 2.25 and most of varieties belonged to short grain except Tongil type rice varieties. Mean of length: width ratio of brown rice kernel was 1.77 and coefficient of variance was 4.79％ in short grain type varieties. Grain shape could be further classified into 5 types by length:width ratio of brown rice kernel; 1 type(less than 1.75), 2 type(1.76∼1.80), 3 type(1.81∼1.90), 4 type(1.91∼2.00), and 5 type (greater than 2.00). For 1 and 2 type of varieties, woven wire sieve having 1.7mm openings showed better whole-kernel yields for special marketing grade, and sieve having 2.0mm openings for 3 and 4 type of varieties. Grain type which classified into 5 categories was not associated with physicochemical and cooking characteristics of rice grain, but sensory evaluation of cooked rice showed better score for 1 type varieties in terms of appearance, gloss, flavor, texture, stickiness, and taste.

• The Journal of Natural Sciences
• /
• v.8 no.2
• /
• pp.159-168
• /
• 1996

The major morphological characteristics of 97 lines selected from 1,510 local collection lines of Paeonia spp. were studied and classified into some groups according to their Q correlation. The Coefficient of Variation of 8 characteristics in 97 lines varied greatly with the range from 21.3% to 127.1%. The 22 lines with useful morphological characteristics selected from 97 lines had 2n=10 chromosomes, in which there were no difference among the number of chromosomes of 22 lines. The 97 lines were classified into 14 groups based upon the results of Q correlation analysis obtained from data with 16 quantitative factors; Group III and group VI were divided into two sub-groups. Group I was large flowered lines with a single flower, Group IIIa, doubled flowered lines, Group VII, late maturing lines and Group IX, early maturing lines flowering in 17th May. Group VIII were dwarf type lines which has the shortest stem length and leaf length among 14 groups, which are suitable for potted plants. Group XIII had a lot of stems per plant and a large type leaf with leaf length and width. A needle-type leaf was found in Group X, whereas a wide and oval-type leaf in group XII.

• The Korean Journal of Ecology
• /
• v.28 no.1
• /
• pp.15-23
• /
• 2005

The black locust (Robinia pseudoacacia L.) forests were studied by a phytosociological approach. Particular attention was given to characterize the vegetation classification, distribution pattern, and ecological flora of the syntaxa classified. A total of 38 releves were analyzed by using Correlation coefficient, UPGMA as the clustering method, and Principal Coordinates Analysis for ordination. Ecological flora analyzed by plant character sets such as scrambler, annual and biennial plants, forest elements, and actual urbanization index. The analyzed data are based on site-releve matrix with relative net contribution degree (r-NCD) of species. A total of 77 families, 193 genera and 323 species of vascular plants are recorded. Camellino-Robinietum pseudoacaciae ass. nov. and Phragmites-Robinia pseudoacacia community were described. Main cluster and ordination could be separated: 1) urban type, 2) rural type, 3) riparian type, and 4) combined type. It is defined that the Robinietum is a representative unit on the black locust afforestation, Phragmites-Robinia community on the lentic zone in the river ecosystem, and Cameliino-Robinietum ailanthetosum altissimae as an urban forest type. The Robinietum was considered as a perpetual community.

• Journal of Radiation Protection and Research
• /
• v.40 no.4
• /
• pp.211-215
• /
• 2015

In case of radiation emergencies, radioactive materials released into environments can cause internal exposure of members of the public. Even though whole body counters are widely used for direct measurement of internally deposited radionuclides, those are not likely to be used at the field to rapidly screen internal exposure. In this study, we estimated the counting efficiencies of portable NaI detector for different size BOMAB phantoms using Monte Carlo transport code to apply handheld gamma spectrometers for rapid screening of internal exposure following radiological accidents. As a result of comparison for two counting geometries, counting efficiencies for sitting model were about 1.1 times higher than those for standing model. We found, however, that differences of counting efficiencies according to different size are higher than those according to counting geometry. Therefore, we concluded that when we assess internal exposure of small size people compared to the reference male, the body size should be considered to estimate more accurate radioactivity in the human body because counting efficiencies of 4-year old BOMAB phantom were about 2.4~3.1 times higher than those of reference male BOMAB phantom.

• Asia-Pacific Journal of Business Venturing and Entrepreneurship
• /
• v.2 no.1
• /
• pp.37-64
• /
• 2007

The purpose of this study is verifying which financial property of a venture company listed in KOSDAQ is a primary factor to determine Highly Successful company or Less Successful one. For sampling, I classified 405 venture companies, whose averages for 2005 of 2 standards are In the 30% high/low rank, as Highly Successful/Less Successful companies subject to the higher Operating Income to Total Assets and Return on Invested Capital (ROIC), the Highly Successful company. And I verified which variable is most important one to distinguish between Highly Successful companies and Less Successful ones among 24 financial ratios selected through preceding studies. For the analysis, I firstly extracted analogous variables by Stepwise Method and secondly carried out Multi variate Discriminant Analysis. The result mainly shows variables related to returns and stability similar to preceding studies. Especially, Operating Income to Total Assets reveals most reliable variable distinguishing between Highly Successful company and Less Successful one, whereas Current Ratio does not. When reliability of function formula of variables were compared with Operating Income to Total Assets standard and ROIC standard, there was almost no difference.