• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2014.05a
• /
• pp.905-907
• /
• 2014

Twitter is the special place that people in the world can freely share their information and opinion. There are tries to utilize a vast amount of information made from twitter. The study on classification of tweets by subject is actively conducted. Twitter is a service for sharing information with short 140-characters text message. The short message including brief content makes extracting a variety of information hard. In the paper, we suggests the method to classify tweet by subject. The method uses both tweet and subject features. In order to conduct experiments to verify the proposed method, we collected 10,000 tweet messages with the Twitter API. Through the experimental results, we will show that the performance of our proposed method is better than those of previous methods.

• Korean Journal of Plant Resources
• /
• v.17 no.2
• /
• pp.202-212
• /
• 2004

The present study was conducted to compare of pollen morphological characteristics for five Haploxylon species in Korea using light microscopy(LM). The results are as follows; 1. Highly significant (P＜0.01) interspecific difference was observed in five Haploxylon species for their pollen morphological parameters. 2. The discreminant analysis based on the pollen morphological parameters demonstrated that the classification ratio of Haploxylon was 68.8 ％ ranging from 72.8 ％ of Pinus pumila to 62.2 ％ P. koraiensis. 3. The relationship among the species based on their pollen morphological parameters showed that P. koraiensis and P. pumila in Haploxylon were most closely related while P. pumila and P. bungeana were least related.

• Journal of Broadcast Engineering
• /
• v.13 no.6
• /
• pp.875-882
• /
• 2008

Ear detection in an image processing is the one of the important area in biometrics. In this paper we propose a human ear detection algorithm with side face images. First, we search a face candidate area in an input image by using skin-color model and try to find an ear area based on Haar-like feature. Then, to verity whether it is the ear area or not, we use the template which is excellent object classification compare to recognize the characters in the plate. In this experiment, the proposed method showed that the processing speed is improved by 60% than previous works and the detection success rate is 92%.

• Korean Journal of Plant Resources
• /
• v.17 no.2
• /
• pp.189-201
• /
• 2004

The present study has measured eight pollen morphological parameters of Diploxylon species in Korea by light microscopy (LM). The results are as follows; 1. Diploxylon species in Korea showed significant (P＜0.01) interspecific difference in their pollen morphological parameters. 2. The discriminant analysis based on the pollen morphological parameters demonstrated that the classification ratio of Diploxylon was 49.9％. The maximum was at Pinus banksiana (72.8％) and the minimum was at P. sylvestris (62.2％). 3. The relationship among the Diploxylon species based on their pollen morphological parameters showed that P. densiflora and P. sylvestris were had the closest relationship while P. rigida and banksiana had the least relationship.

• Smart Media Journal
• /
• v.7 no.4
• /
• pp.24-29
• /
• 2018

Text analysis technique for natural language processing in deep learning represents words in vector form through word embedding. In this paper, we propose a method of constructing a document vector and classifying it into spam and normal text message, using word embedding and deep learning method. Automatic spacing applied in the preprocessing process ensures that words with similar context are adjacently represented in vector space. Additionally, the intentional word formation errors with non-alphabetic or extraordinary characters are designed to avoid being blocked by spam message filter. Two embedding algorithms, CBOW and skip grams, are used to produce the sentence vector and the performance and the accuracy of deep learning based spam filter model are measured by comparing to those of SVM Light.

• Korean Journal of Ichthyology
• /
• v.6 no.2
• /
• pp.132-159
• /
• 1994

The taxonomic revision of the family Congridae was made based on the specimens collected from the south-western coasts of the Korea from June 1988 to Oct. 1993. The family Congridae was classified into 8 species belonging to 6 genera. based on the external and internal morphological characters : Anago anago, Ariosoma anagodies, Ariosoma shiroanago shiroanago, Conger myriaster, Conger japonicus, Gnathophis nystromi nystromi, Rhechias retrotincta and Uroconger lepturus. Among the species reported as the congrid eels from Korea until now, four species were transferred into different generic or specific name Conger flavirostris into Ariosoma anagoides ; Astroconger myriaster into Conger myriaster ; Congrina retrotincta into Rhechias retrotincta and Rhynchocymba nystromi into Gnathophis nystromi nystromi. A Korean congrid eel, Ariosoma shiroanago shiroanago, was reported for first time in Korea. Intergeneric characters of the family Congridae were the form of the lateralline scales, the state of the tip of tail, the segmented state of the dorsal and anal fin rays, the existance of the supraoccipital bone and of lateral ethmoid process of the skull, the origin of dorsal fin and the forms of upper labial flange. The interspecific classification was made according to the characters such as the numbers of sensory pores of head part and in front of vent, teeth rows and numbers of upper and lower jaw, the numbers of vertebrae, the body color, the shapes of the head part, the color of intestine, the size of eye, the structure of air bladder and the number of branchiostegal rays. A new key on the taxonomical characteristics to the genera and species of the family Congridae has been estabilished and their distribution in Korea is described.

• Cartoon and Animation Studies
• /
• s.16
• /
• pp.179-198
• /
• 2009

This study analyzed the chronology of children's cartoon through character while the children's cartoon section is planned at the Memorial Exhibition of 100th year of Korean Cartoon which will be held at the Contemporary Art Gallery in celebration of the 100th year after birth of Korean Cartoon. The approaching method based on character is regarded as the most proper and feasible in the identification of character and meaning of children's cartoon because the character in cartoon contains the bigger role and meaning than the descriptive structure of narration. The Committee of 100th Year of Korean Cartoon, Aicheorum which is a study association for children's cartoon and Cartoon My Love $Cafe^{42)}$ in Naver jointly selected the 70 cartoon characters. A brief history is established based on these characters through chronological classification in seven sectors of around 10 year session such as before 1950s of quickening period and liberation, 1950s, 1960s, 1970s, 1000s, 1900s and after 2000. It examined the historical meaning, its reflection and characteristics focused on the cartoon character and the cartoonist which were well-known to everybody not only the display according to chronological order. The study intented the stereoscopic illumination on the children's cartoon and character which were favored beyond the generations. In addition, the similarity and human relation among cartoonist to cartoonist and character to character were analyzed and traced to identity the fact that children cartoon character is not individualistic being but it lies on the extension of tradition and trend of eternal cartoon history Finally, hopefully it will make a contribution to activate the pure creative children's cartoon in Korea through reminding the importance of character in cartoon, affirming the industrial value and reflecting the direction and perspective of pure creative children's cartoon.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.17 no.2
• /
• pp.27-39
• /
• 1989

The purpose of this study is to prove the factors affecting the fluctuation of daily visitors in five mountainous national park(Kayasan, kyeryongsan, Naejangsan, Soraksan, Songnisan), and to analyze the relationship between these factors and daily visitors in Korea. "Three Factors and Nine Categories"(Aoki, K. & Aoki, Y. : 1974, 1979) has been applied to this study, and statistical analysis method was carried out by computer program SAS and SPSS. The number of daily visitors is calculated based on the data of "Daily entrance ticket sale report" by administration office in each national park. The scope of time period is during the last 5years(1982∼1986: 1825days) and the results were as follows: 1) There were significant differences in the number of daily visitors of each national park among months, days of a week and weather-the same as the previous study of urban park case. But it wold be better for their category classification to be adjusted according to the fluctuation pattern of each national park. 2) The peak of monthly visitors comes in May(Kayasan, Soraksan, Songnisan) or October(Kyeryongsan, Naejangsan). These months are specified as group tour season. On the basis of monthly fluctuation pattern, Each national park were classified into seasonal type, that is, kayasan, Soraksan were proved to be three-season type(Spring, Summer, Autumn), Songnisan to be two-season type(Spring, Autumn), and Naejangsan to be one-season type(Autumn). 3) The weekly pattern differs from three category (weekday, weekend, holiday: Eom, Choi 1986) in the case of urban park study. And there is no significant difference in daily fluctuation pattern by weather (fine, cloudy and rainy day), but significant difference between snowy and the others. This result is due to the characteristics of visitors, which is, the major visits of national park are planned in a advance of the tour, therefore it is difficult to change the plan by the weather. 4) the result of correlation analysis showed that the most influential factor on national park use in Kayasan, Naejangsan, Soraksan and Songnisan is ′Monthly characters (M)′, on the contrary ′Day of week(D)′ in Kyeryongsan only. From the result, The more parks are resource-based, the more ′Monthly characters′-factor is supposed to affect the number of daily visitors rather than ′Day of the week′-factor. This means that kayasan, naejangsan, Sorakson and Songnisan are classified into resource-based type, but on the other hand Kyeryongsan should be classified into intermediate type.

• Journal of the Korean Society for Library and Information Science
• /
• v.44 no.4
• /
• pp.203-230
• /
• 2010

This study analyzed the development and growth of folksonomy by examining tags associated with 40 bestsellers on LibraryThing.com in 6-month intervals. It was found that tag values do not decrease but grow in terms of quantity and quality. Accordingly, we examined the major significances of the tags and their potential utilization as an expression of subjects. Our findings were as follows. First, the motivations for tagging can be categorized into personal information for search purposes, self-fulfillment such as sense of achievement, display of emotion and sharing of one's experience with others, or an altruistic objective that emphasizes sociality with a desire that one's actions might provide social benefits. According to our analysis, 74.12% of tags had a social motivation. Second, the total number of tags and the frequency of usage increased with time. Third, the categories that showed a high increase in tag usage were dates of publication and reading, key words, main characters, and book reviews. Tags related to subjects had the highest ratio. Fourth, among Library of Congress Subject Headings (LCSH), multiple genres, key words and main characters were assigned to books, and specific key words and other properties were added as time progressed. There was also a slight increase in the number of tags consistent with LCSH. Fifth, we found that key tags could serve as a compilation of terms that reflects the knowledge base of the corresponding era. Thus, folksonomy should be continuously monitored for its quantitative and qualitative development of the tags to make improvements on its formative disadvantages, and identify internal semantic significance, be actively utilized in conjunction with taxonomy as a flexible compilation of terms that incorporate the history of a specific era.

• Science of Emotion and Sensibility
• /
• v.16 no.1
• /
• pp.107-116
• /
• 2013

In the implementation of a P300 speller, rows and columns paradigm (RCP) is most commonly used. However, the RCP remains subject to adjacency-distraction error and double-flash problems. This study suggests a novel P300 speller stimuli presentation-the sub-block paradigm (SBP) that is likely to solve the problems effectively. Fifteen subjects participated in this experiment where both SBP and RCP were used to implement the P300 speller. Electroencephalography (EEG) activity was recorded from Fz, Cz, Pz, Oz, P3, P4, PO7, and PO8. Each paradigm consisted of a training phase to train a classifier and a testing phase to evaluate the speller. Eighteen characters were used for the target stimuli in the training phase. Additionally, 5 subjects were required to spell 50 characters and the rest of the subjects were to spell 25 characters in the testing phase. Classification accuracy results show that average accuracy was significantly higher in SBP as of 83.73% than that of RCP as of 66.40%. Grand mean event-related potentials (ERPs) at Pz show that positive peak amplitude for the target stimuli was greater in SBP compared to that of RCP. It was found that subjects tended to attend more to the characters in SBP. According to the participants' ratings on how comfortable they were with using each type of paradigm on 7-point Likert scale, most subjects responded 'very difficult' in RCP while responding 'medium' and 'easy' in SBP. The result showed that SBP was felt more comfortable than RCP by the subjects. In sum, the SBP was more correct in P300 speller performance as well as more convenient for users than the RCP. The actual limitations in the study were discussed in the last part of this paper.