• Korean Journal of Plant Taxonomy
• /
• v.45 no.3
• /
• pp.227-238
• /
• 2015

Korean species within the genus Astragalus have been taxonomically revised based on herbarium specimens and field examinations. In this study, we recognized the following eight species and one variety: A. laxmannii subsp. laxmannii, A. dahuricus, A. sikokianus, A. uliginosus, A. schelichowii, A. setsureianus, A. mongholicus var. dahuricus, A. mongholicus var. nakaianus, and A. sinicus. Based on recent taxonomic progress with this genus, their scientific names are being reconsidered. A Korean plant, previously recorded as A. adsurgens, is included in the polymorphic taxa A. laxmannii subsp. laxmannii. Astragalus koraiensis was initially described from Gangwon Province as an endemic species, and it is now regarded as conspecific with A. sikokianus. Furthermore, the taxonomic entities and their morphological characteristics have been clarified for A. schelichowii and A. setsureianus, both of which are not well known in Korea. We provide a key to these species and enumerate their synonymies and taxonomic notes.

• Journal of Korean Society of Forest Science
• /
• v.109 no.1
• /
• pp.23-30
• /
• 2020

The use of increased computing power, machine learning, and deep learning techniques have dramatically increased in various sectors. In particular, image detection algorithms are broadly used in forestry and remote sensing areas to identify forest types and tree species. However, in South Korea, machine learning has rarely, if ever, been applied in forestry image detection, especially to classify tree species. This study integrates the application of machine learning and forest image detection; specifically, we compared the ability of two machine learning data collection methods, namely image data captured by forest experts (D1) and web-crawling (D2), to automate the classification of five trees species. In addition, two methods of characterization to train/test the system were investigated. The results indicated a significant difference in classification accuracy between D1 and D2: the classification accuracy of D1 was higher than that of D2. In order to increase the classification accuracy of D2, additional data filtering techniques were required to reduce the noise of uncensored image data.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.17 no.3
• /
• pp.227-234
• /
• 2017

In this paper, we propose a system whereby one can automatically classifies categories based on image data of the products for a shopping mall platform. Many products sold within internet shopping malls are classified their category defined by the same use of product names and products. However, it is difficult to search by category classification when the classification of the product is uncertain and the product classified by the shopping mall seller judgment is different from the purchasing user judgment. We proposes classification and retrieval method by Deep Learning technique solely using product image. The system can categorize products by using their images and its speed and accuracy are quantified using test data. The performance is evaluated with the test data. In addition, its usability is tested with the participants.

• Archives of design research
• /
• v.16 no.1
• /
• pp.5-14
• /
• 2003

As the digital technology has improved, the numbers of Hangul font users have increased and their individual needs and taste are diversified. Therefore new and various Hangul fonts out of traditional form are developed and used. But under the present font classification system, it is hard to compare and analyze these various fonts. And the present classification system is hard to be the font user's guide for proper use of various Hangul fonts. For the better use of Hangul font, to diversify the font classification system is needed. So we propose the development of these thru classification standards. First, structural classification based on the structural character of Hangul. Second, image classification based on the visual images of each font. And third, usage classification based on the fonts proper usage in various media. For the development of various typographically balanced fonts and for the suitable and effective use of the various font, we must try to build the font classification system based on the diversified classification standards and build Hangul font database based on this classification system. Through these studies, we can expect the development of good quality fonts and the better use of these fonts.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.13 no.4
• /
• pp.141-148
• /
• 2013

Automated classification systems which utilize machine learning develops classification models through learning process, and then classify unknown data into predefined set of categories according to the model. The performance of machine learning-based classification systems relies greatly upon the quality of features composing classification models. For textual data, we can use their word terms and structure information in order to generate the set of features. Particularly, in order to extract feature from Web documents, we need to analyze tag and hyperlink information. Recent studies on Web document classification focus on feature engineering technology other than machine learning algorithms themselves. Thus this paper proposes a novel method of incorporating feature selection and weighting which can improves classification models effectively. Through extensive experiments using Web-KB document collections, the proposed method outperforms conventional ones.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.29 no.4
• /
• pp.335-345
• /
• 2016

It has problems to use the existing construction information classification system as the bridge breakdown structure due to lack of relationships between element classes. In this study, we proposed the bridge breakdown system for supplementation of above-mentioned classification system. The proposed system, for geometric information modeling, was based on international standards of methodology for structuring part families namely PLIB Part 42. In particular, the breakdown system, considering of the functional classification for the semantic information of the elements is included. In addition, we proposed a basic framework for actual modeling using bridge breakdown system and showed that it can be used in practice.

• Journal of Information Technology and Architecture
• /
• v.9 no.4
• /
• pp.413-422
• /
• 2012

Many researchers have been studied to reveal human natural language to let machine understand its meaning by text based, page rank based or more. Particularly, it has been considered that URL and HTML Tag information in web documents are attracting people' attention again to analyze huge amount of web document automatically. In this paper, we propose a STW (Semantic Term Weight) approach based on syntactic and linguistic structure of web documents in order to classify what genres are. For the evaluation, we analyzed more than 1,000 documents from 20-Genre-collection corpus for training the documents based on SVM algorithm. Afterwards, we tested KI-04 corpus to evaluate performance of our proposed method. This paper measured their accuracy by classifying them into an experiment using STW and one without u sing STW. As the results, the proposed STW based approach showed approximately 10.2% which Is higher than one without use of STW.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.12 no.7
• /
• pp.1243-1248
• /
• 2008

As development in technology of bioinformatics recently mates it possible to operate micro-level experiments, we can observe the expression pattern of total genome through on chip and analyze the interactions of thousands of genes at the same time. In this thesis, we used CDNA microarrays of 3840 genes obtained from neuronal differentiation experiment of cortical stem cells on white mouse with cancer. It analyzed and compared performance of each of the experiment result using existing DT, NB, SVM and multi-perceptron neural network classifier combined the similar scale combination method after constructing class classification model by extracting significant gene list with a similar scale combination method proposed in this paper through normalization. Result classifying in Multi-Perceptron neural network classifier for selected 200 genes using combination of PC(Pearson correlation coefficient) and ED(Euclidean distance coefficient) represented the accuracy of 98.84%, which show that it improve classification performance than case to experiment using other classifier.

• Proceedings of the Plant Resources Society of Korea Conference
• /
• 2019.04a
• /
• pp.45-45
• /
• 2019

학술림은 학생, 교수, 산림 연구기관의 실험 실습 등의 연구 기능을 하는 숲이며, 경제적, 사회적 및 환경적으로 큰 의미가 있어, 학술연구 및 교육에 있어서 중요한 필수 자산이다. 국내에 분포하는 학술림의 전체면적은 약 34,941ha로 국내 전체 면적 6,335,000ha의 0.55%를 차지하고 있다. 국내 학술림을 행정적으로 남부, 중부 및 북부 세권역으로 나눠볼 수 있는데 중부권역에 속해있는 한 곳인 국민대학교 학술림의 자생식물을 조사하였다. 국민대학교 학술림이 위치한 경상북도 안동시 길안면 배방리 일대는 청송 유네스코 세계지질공원 및 주왕산국립공원과 인접함에도 불구하고 연구가 부족한 실정이다. 본 연구에서 확인된 관속식물은 97과 292속 518종 등 총 518분류군으로 조사되었으며, 산림청지정 희귀식물로는 댕댕이나무, 산분꽃나무, 시호, 솜양지꽃, 산마늘 등 10분류군이 확인되었고, 특산식물은 청괴불나무, 참배암차즈기, 고려엉겅퀴, 분취 등 9분류군이 확인되었다. 식물구계학적 특정식물은 I등급은 고려엉겅퀴, 백선, 뻐꾹채, 초롱꽃, 투구꽃 등 26분류군, II등급은 곰취, 구와취, 노랑제비꽃, 채고추나물, 호오리새 등 11분류군, III등급은 복자기, 시닥나무, 참조팝나무, 눈개승마, 다북떡쑥 등 24분류군, Ⅳ등급은 개아마, 뚝사초, 산마늘, 왜방풍, 참배암차즈기 등 8분류군, V등급은 산분꽃나무 1분류군으로 확인되었다.

• Annual Conference of KIPS
• /
• 2013.11a
• /
• pp.1294-1297
• /
• 2013

본 논문은 기계학습을 통하여 특허문서를 국제 특허 분류(IPC) 기준에 따라 자동으로 분류하는 시스템에 관한 연구로 잠재 의미 색인 기법을 이용하여 분류의 성능을 높일 수 있는 방법을 제안하기 위한 연구이다. 종래 특허문서에 관한 IPC 자동 분류에 관한 연구가 단어 매칭 방식의 색인 기법에 의존해서 이루어진바가 있으나, 현대 기술용어의 발생 속도와 다양성 등을 고려할 때 특허문서들 간의 관련성을 분석하는데 있어서는 단어 자체의 빈도 보다는 용어의 개념에 의한 접근이 보다 효과적일 것이라 판단하여 잠재 의미 색인(LSI) 기법에 의한 분류에 관한 연구를 하게 된 것이다. 실험은 단어 매칭 방식의 색인 기법의 대표적인 자질선택 방법인 정보획득량(IG)과 카이제곱 통계량(CHI)을 이용했을 때의 성능과 잠재 의미 색인 방법을 이용했을 때의 성능을 SVM, kNN 및 Naive Bayes 분류기를 사용하여 분석하고, 그중 가장 성능이 우수하게 나오는 SVM을 사용하여 잠재 의미 색인에서 명사가 해당 용어의 개념적 의미 구조를 구축하는데 기여하는 정도가 어느 정도인지 평가함과 아울러, LSI 기법 이용시 최적의 성능을 나타내는 특이값의 범위를 실험을 통해 비교 분석 하였다. 분석결과 LSI 기법이 단어 매칭 기법(IG, CHI)에 비해 우수한 성능을 보였으며, SVM, Naive Bayes 분류기는 단어 매칭 기법에서는 비슷한 수준을 보였으나, LSI 기법에서는 SVM의 성능이 월등이 우수한 것으로 나왔다. 또한, SVM은 LSI 기법에서 약 3%의 성능 향상을 보였지만 Naive Bayes는 오히려 20%의 성능 저하를 보였다. LSI 기법에서 명사가 잠재적 의미 구조에 미치는 영향은 모든 단어들을 내용어로 한 경우 보다 약 10% 더 향상된 결과를 보여주었고, 특이값의 범위에 따른 성능 분석에 있어서는 30% 수준에 Rank 되는 범위에서 가장 높은 성능의 결과가 나왔다.