• The Korean Journal of Mycology
• /
• v.16 no.4
• /
• pp.235-241
• /
• 1988

This study was carried out to investigate some morphological characters of fruit bodies of Ganoderma lucidum and to classify the fungus on the bases of the genetic character. Some of the isolates of the fungus which originally have the kidney-shaped fruit bodies produced the antler-shaped fruit bodies on artificial media and the latter characters were inherited. Pattern of the pileus surface and thickness of the pileus of the fruit bodies were also considered to be hereditary. Although morphology of the pileus margin and fruiting mode of the fungus were variable among the isolates, they were greatly influenced by environment conditions. Ganoderma lucidum could be classified into two groups and four strains according to the morphology of the fruit bodies on artificial cultivation media. Electrophoretic patterns of esterase, peroxidase, leucine aminopeptidase(LAP) and proteins of fruit bodies and mycelia of Ganoderma lucidum showed high genetic variation. Isozyme patterns of esterase of the mushroom mycelia were applicable for the classification of strains of the fungus. Patterns of proteins, leucine aminopeptidase and peroxidase did not indicate any genetic relation among the fungus strains.

• Asia pacific journal of information systems
• /
• v.29 no.4
• /
• pp.771-788
• /
• 2019

Deep learning techniques such as Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) show superior performance in text classification than traditional approaches such as Support Vector Machines (SVMs) and Naïve Bayesian approaches. When using CNNs for text classification tasks, word embedding or character embedding is a step to transform words or characters to fixed size vectors before feeding them into convolutional layers. In this paper, we propose a parallel word-level and character-level embedding approach in CNNs for text classification. The proposed approach can capture word-level and character-level patterns concurrently in CNNs. To show the usefulness of proposed approach, we perform experiments with two English and three Korean text datasets. The experimental results show that character-level embedding works better in Korean and word-level embedding performs well in English. Also the experimental results reveal that the proposed approach provides better performance than traditional CNNs with word-level embedding or character-level embedding in both Korean and English documents. From more detail investigation, we find that the proposed approach tends to perform better when there is relatively small amount of data comparing to the traditional embedding approaches.

• The Korean Journal of Malacology
• /
• v.17 no.2
• /
• pp.105-115
• /
• 2001

These studies were conducted to compare the external radulae of seven species (Semisulcospira gottschei, S. coreana, S. forticosta, S. tegulata, S. ibertina, Koreanomelania nodifila and Koreoleptoxis globus ovalis) of freshwater snails in three genera of the family Pleuroceridae in Korea. Under a microscope of 100 magnifications, observation of seven species can be distinguished sharply between three genera of Semisuicospira, Koreanomelania and Koreoleptoxis, and the morphological characters of radulae can be used as taxonomic tool in genus level of Pleuroceridae. Besides SEM photograph of the radulae based on the morphological characters in seven species can be verified a new criteria for classification of genus' unit grade in accord with firsthand drawing sketch under a microscope of 100 magnifications. But it is difficult that all of the species can be detected sharply the difference of interspecies by comparisons of radulae in the family Pleuroceridae in Korea. Therefore, the morphological characters of radulae can not be set a criteria for classification of species level.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.31B no.4
• /
• pp.1-8
• /
• 1994

In this paper, we propose an efficient two-step pattern matching method which promises shape distortion-tolerant recognition of handwritten of handwritten Hangul syllables. In the first step, nonlinear shape normalization is carried out to compensate for global shape distortions in handwritten characters, then a preliminary classification based on simple pattern matching is performed. In the next step, nonlinear pattern matching which achieves best matching between input and reference pattern is carried out to compensate for local shape distortions, then detailed classification which determines the final result of classification is performed. As the performance of recognition systems based on pattern matching methods is greatly effected by the quality of reference patterns. we construct reference patterns by combining the proposed nonlinear pattern matching method with a well-known averaging techniques. Experimental results reveal that recognition performance is greatly improved by the proposed two-step pattern matching method and the reference pattern construction scheme.

• Journal of the Korea Society of Computer and Information
• /
• v.18 no.9
• /
• pp.131-138
• /
• 2013

In this paper, I propose and evaluate the method that classifies emotional type of characters with their emotional words. Emotional types are classified as three types such as positive, negative and neutral. They are selected by classification of emotional words that characters speak. I propose the method to extract emotional words based on WordNet, and to represent as emotional vector. WordNet is thesaurus of network structure connected by hypernym, hyponym, synonym, antonym, and so on. Emotion word is extracted by calculating its emotional distance to each emotional category. The number of emotional category is 30. Therefore, emotional vector has 30 levels. When all emotional vectors of some character are accumulated, her/his emotion of a movie can be represented as a emotional vector. Also, thirty emotional categories can be classified as three elements of positive, negative, and neutral. As a result, emotion of some character can be represented by values of three elements. The proposed method was evaluated for 12 characters of four movies. Result of evaluation showed the accuracy of 75%.

• Journal of Broadcast Engineering
• /
• v.23 no.1
• /
• pp.53-62
• /
• 2018

It is necessary to analyze the character that are a key element of the story in order to analyze the story. Current character analysis methods such as Character-net and RoleNet are not sufficient to classify the roles of supporting characters by only analyzing the results of the final accumulated stories. It is necessary to study the time series analysis method according to the story progress in order to analyze the role of supporting characters rather than the accumulated story analysis method. In this paper, we propose a method to classify helpers as a mentor and a best friend through 3-D visualization of Character-net and evaluate the accuracy of the method. WebGL is used to configure the interface for 3D visualization so that anyone can see the results on the web browser. It is also proposed that rules to distinguish mentors and best friends and evaluated their performance. The results of the evaluation of 10 characters selected for 7 films confirms that they are 90% accurate.

• Journal of Acupuncture Research
• /
• v.26 no.6
• /
• pp.225-239
• /
• 2009

Objectives : To establish a well organized and systematic oriental medicine classification of headache, the western and oriental medicine diagnosis and treatment systems of headache were reviewed. Methods : The history and development process of western medicine classification of headache were studied. A literature review of oriental medicine classification of headache was done. The characters of each classification systems were assessed. Results : In western medicine, many international societies concerning headache have been established. Through these societies, a classification of headache which can be used by both researchers and practitioners has been suggested. And the suggested classification system is highly recommended to be used in studies in order to increase utilization. As data is accumulated, new versions of the classification system were updated. But in the case of oriental medicine, various classification systems of headache are presented in numerous literatures. But the effort to unify and systemize the oriental medicine headache classification has been in lack. Conclusions : Establishment and utilization of a standardized oriental medicine headache classification system, based on various classifications and detailed descriptions is needed.

• Korean Journal of Plant Taxonomy
• /
• v.34 no.4
• /
• pp.321-333
• /
• 2004

We researched fruit wall anatomical characters about the seven taxa of Krigia and the nearest one relative, Nothocalais cuspidata by making use of the fruit wall anatomy, and inferred systematical similarity. Among these characters, all species of the genus Krigia has identical characters in the shape of fruit and the number of rib, but showed specific differences in the shape of costa, the numbers of libriform fiber cell layers and fiber-sclereid cell layers in mesocarp, and development degree in these characters. Krigia biflora, K. cespitosa, K. occidentalis and K. wrightii have well developed libriform fiber cell, but K. dandelion, K. montana and K. virginica have undeveloped libriform fiber cell, and mostly consist of fiber-sclereid cell layers. According to the fruit wall anatomical characters, K. biflora which belonged to sect. Krigia in the previous classification system is more similar to sect. Cymbia than sect. Krigia.

• KOREAN JOURNAL OF CROP SCIENCE
• /
• v.28 no.3
• /
• pp.340-344
• /
• 1983

Taxonomic distances and Q correlations of all possible comparisons among thirty-two collected soybean varieties were calculated from the standardized mean of twenty-one characters. Ten varietal groups were classified by the single linkage clustering based on Q correlations. The means of Q correlations of intra-group were higher than those of inter-group. Each groups were characteristic in each mean of characters within varietal groups.

• Journal of fish pathology
• /
• v.16 no.1
• /
• pp.51-59
• /
• 2003

Streptococcal infection is one of the most serious disease of cultured olive flounder, Paralychthys olivaceus in Korea and caused by more than one species. However, there has been considerable confusions about the taxonomic position of the fish pathogenic streptococci. In this study, We performed the randomly amplified polymorphic DNA(RAPD) pattern analysis to evaluate the possible classification in 8 streptococci isolated from diseased olive flounder and reference strains based on their DNA structure. RAPD PCR with DNA solution prepared by simple boiling and 10-mer random primer was appeared to be a good tool for discrimination of different streptococcal strains. Phenotypical characters by simple biological test and API 20 Strep corresponded well to the specific profiles of RAPD in streptococcal isolates of this study. Therefore, the RAPD profile was considered as one of differential characters to discriminate the streptococcal isolates from diseased olive flounder.