• Title/Summary/Keyword: data similarity

Search Result 2,098, Processing Time 0.029 seconds

Multiple Cause Model-based Topic Extraction and Semantic Kernel Construction from Text Documents (다중요인모델에 기반한 텍스트 문서에서의 토픽 추출 및 의미 커널 구축)

  • 장정호;장병탁
    • Journal of KIISE:Software and Applications
    • /
    • v.31 no.5
    • /
    • pp.595-604
    • /
    • 2004
  • Automatic analysis of concepts or semantic relations from text documents enables not only an efficient acquisition of relevant information, but also a comparison of documents in the concept level. We present a multiple cause model-based approach to text analysis, where latent topics are automatically extracted from document sets and similarity between documents is measured by semantic kernels constructed from the extracted topics. In our approach, a document is assumed to be generated by various combinations of underlying topics. A topic is defined by a set of words that are related to the same topic or cooccur frequently within a document. In a network representing a multiple-cause model, each topic is identified by a group of words having high connection weights from a latent node. In order to facilitate teaming and inferences in multiple-cause models, some approximation methods are required and we utilize an approximation by Helmholtz machines. In an experiment on TDT-2 data set, we extract sets of meaningful words where each set contains some theme-specific terms. Using semantic kernels constructed from latent topics extracted by multiple cause models, we also achieve significant improvements over the basic vector space model in terms of retrieval effectiveness.

A News Video Mining based on Multi-modal Approach and Text Mining (멀티모달 방법론과 텍스트 마이닝 기반의 뉴스 비디오 마이닝)

  • Lee, Han-Sung;Im, Young-Hee;Yu, Jae-Hak;Oh, Seung-Geun;Park, Dai-Hee
    • Journal of KIISE:Databases
    • /
    • v.37 no.3
    • /
    • pp.127-136
    • /
    • 2010
  • With rapid growth of information and computer communication technologies, the numbers of digital documents including multimedia data have been recently exploded. In particular, news video database and news video mining have became the subject of extensive research, to develop effective and efficient tools for manipulation and analysis of news videos, because of their information richness. However, many research focus on browsing, retrieval and summarization of news videos. Up to date, it is a relatively early state to discover and to analyse the plentiful latent semantic knowledge from news videos. In this paper, we propose the news video mining system based on multi-modal approach and text mining, which uses the visual-textual information of news video clips and their scripts. The proposed system systematically constructs a taxonomy of news video stories in automatic manner with hierarchical clustering algorithm which is one of text mining methods. Then, it multilaterally analyzes the topics of news video stories by means of time-cluster trend graph, weighted cluster growth index, and network analysis. To clarify the validity of our approach, we analyzed the news videos on "The Second Summit of South and North Korea in 2007".

Gray Mold of Nephrolepis Caused by Botrytis cinerea (Botrytis cinerea에 의한 네프로레피스 잿빛곰팡이병)

  • Jeon Yong-Ho;Kim Jung-Ho;Kim Young-Ho
    • Research in Plant Disease
    • /
    • v.12 no.2
    • /
    • pp.115-118
    • /
    • 2006
  • In February of 2000-2001, the gray mold disease occurred on nephrolepis (Nephrolepis sp.) grown in a flower nursery farm in Suwen, Korea. Typical symptoms were water-soaked brown or blackish lesions on terminal leaf blades. Severely infected leaves were entirely blighted with grayish fungal mycelia formed on the surface. Conidia of the fungus in mass were hyaline or gray, 1-celled, mostly ellipsoid or ovoid and $13.5{\sim}16.9{\times}6.8{\sim}9.2{\mu}m$ in size. Conidiophores were formed on PDA with $8.7{\sim}11.1{\mu}m$ in width. The sclerotia were readily formed within 2 or 3 days on PDA. In addition, the Biolog database gave the causal fungus a high similarity to Botrytis cinerea (78%) with a match probability of 100%. Pathogenicity of the causal organism was proved according to Koch's postulate. The causal organism was identified as Eotrytis cinerea based on its mycological characteristics and utilization of carbon sources with Biolog system as supporting data. This is the first report of gray mold of nephrolepis caused by Botrytis cinerea in Korea.

Fall Detection for Mobile Phone based on Movement Pattern (스마트 폰을 사용한 움직임 패턴 기반 넘어짐 감지)

  • Vo, Viet;Hoang, Thang Minh;Lee, Chang-Moo;Choi, Deok-Jai
    • Journal of Internet Computing and Services
    • /
    • v.13 no.4
    • /
    • pp.23-31
    • /
    • 2012
  • Nowadays, recognizing human activities is an important subject; it is exploited widely and applied to many fields in real-life, especially in health care and context aware application. Research achievements are mainly focused on activities of daily living which are useful for suggesting advises to health care applications. Falling event is one of the biggest risks to the health and well-being of the elderly especially in independent living because falling accidents may be caused from heart attack. Recognizing this activity still remains in difficult research area. Many systems equipped wearable sensors have been proposed but they are not useful if users forget to wear the clothes or lack ability to adapt themselves to mobile systems without specific wearable sensors. In this paper, we develop a novel method based on analyzing the change of acceleration, orientation when the fall occurs and measure their similarity to featured fall patterns. In this study, we recruit five volunteers in our experiment including various fall categories. The results are effective for recognizing fall activity. Our system is implemented on G1 smart phone which are already plugged accelerometer and orientation sensors. The popular phone is used to get data from accelerometer and results showthe feasibility of our method and significant contribution to fall detection.

Genetic Diversity of an Endangered Fish, Iksookimia choii (Cypriniformes), from Korea as Assessed by Amplified Fragment Length Polymorphism (AFLP 분석에 의한 멸종위기어류 미호종개, Iksookimia choii의 유전 다양성)

  • Lee, Il-Ro;Lee, Yoon-A;Shin, Hyun-Chur;Nam, Yoon-Kwon;Kim, Woo-Jin;Bang, In-Chul
    • Korean Journal of Ecology and Environment
    • /
    • v.41 no.1
    • /
    • pp.98-103
    • /
    • 2008
  • Genetic diversity and population genetic structure within or among three stream populations (Gab, Baekgok and Ji streams) of Korean endangered natural monument fish, Iksookimia choii, were assessed by amplified fragment length polymorphism (AFLP). AFLP analysis using three primer combinations generated 104 to 106 AFLP bands, and percent polymorphic bands were similar in those three populations ranging 21.5 to 24.5%. Heterozygosity and genetic diversity within or among populations were quite low for all of these populations with average values ranging from 0.067 to 0.084 and from 0.076 to 0.087, respectively. Analyses of pairwise distance and genetic similarity among three populations of I. choii also revealed the similar results with very low genetic differentiation one another. Although pairwise Fst values were very low, our data clearly indicated distinct genetic differentiation among the three populations. This is the first report concerning the genetic diversity and differentiation of this species, and provides basic genetic information that should facilitate attempts to conserve this species.

Analysis of Fish Community of Lagoons in the East Seashore According to Hydrach Succession (습성천이에 따른 동해안 석호의 어류군집 분석)

  • Park, Seungchul;Jang, Youngsu;Lee, Kwangyeol;Heo, Woomyung;Cho, Kanghyun;Choi, Jaeseok
    • Korean Journal of Ecology and Environment
    • /
    • v.47 no.spc
    • /
    • pp.83-99
    • /
    • 2014
  • Fish community of eight lagoons in the east seashore, Korea were investigated from 2007 to 2008. Total 66 species caught during the period were belonged to 34 families, and total biomass was 2,024.8 kg. Also, similarity analysis results of each lagoon were divided three major groups. On the other hand, result of a comparison of the composition ratio of freshwater fish, brackish water fish, and seawater fish which is divided into separate each age data of previous studies has emerged in this study, since the 1990's, freshwater fish is reduced, seawater fish and increase, some changes in the fish community had changed dynamically in the lagoon. These changes considered that against the natural hydrach succession will change to freshwater lake from brackish water lake. Therefore, we considered to ecological characteristics of lagoon and process of hydrach succession when conservation, management, and restoration of the lagoons.

The Study on Recent Research Trend in Korean Tourism Using Keyword Network Analysis (키워드 네트워크를 이용한 국내 관광연구의 최근 연구동향 분석)

  • Kim, Min Sun;Um, Hyemi
    • Journal of the Korea Academia-Industrial cooperation Society
    • /
    • v.17 no.9
    • /
    • pp.68-73
    • /
    • 2016
  • This study was conducted to identify trends and knowledge structures associated with recent trends in Korean tourism from 2010 to 2015 using keyword data. To accomplish this, we constructed a network using keywords extracted from KCI journals. We then made a matrix describing the relationships between rows as papers and columns as keywords. A keyword network showed the connectivity of papers that have included one or more of the same keywords. Major keywords were then extracted using the cosine similarity between co-occurring keywords and components were analyzed to understand research trends and knowledge structure. The results revealed that subjects of tourism research have changed rapidly and variously. A few topics related to 'organization-employee' were major trends for several years, but intrinsic and extrinsic factors have been further subdivided and employees of specific fields have been targeted as subjects of research. Component analysis is useful for analyzing concrete research topics and the relationships between them. The results of this study will be useful for researchers attempting to identify new topics.

Efficient Synthesis of hypho-2,5-$S_2B_7H_{11}$ and Preparation of New nido-, arachno-, and hypho-Metalladithiaborane Clusters Derived from Its Anion hypho-$S_2B_7H_{10}{^-}$

  • 강창환;김성준;고재정;강상욱
    • Bulletin of the Korean Chemical Society
    • /
    • v.16 no.11
    • /
    • pp.1067-1074
    • /
    • 1995
  • Reaction of arachno-S2B7H8- with either THF or 1,2-dimethoxyethane upon refluxing condition results in the formation of the previously known compound hypho-S2B7H10-. Protonation of hypho-S2B7H10- with HCl/Et2O generates hypho-2,5-S2B7H11 in good yield. This hypho-S2B7H10- anion has been employed to generate a series of new nido-, arachno-, and hypho-metalladithiaborane clusters. Reaction of the anion with Cp(CO)2FeCl results in direct metal insertion and the formation of a complex containing the general formula (η5-C5H5)FeS2B7H8. Spectroscopic studies of nido-6-CpFe-7,9-S2B7H8 Ⅰ demonstrated that compound Ⅰ was shown to have an nido-type cage geometry derived from an octadecahedron missing one vertex, with the iron atom occupying the three-coordinate 6-position in the cage and the two sulfurs occupying positions on the open face of the cage. Reaction of hypho-S2B7H10- with CoCl2/Li+[C5H5]- gave the previously known complex arachno-7-CpCo-6,8-S2B6H8 Ⅱ. Also, the reaction of the anion with [Cp*RhCl2]2 gave the complex arachno-7-Cp*Rh-6,8-S2B6H8 Ⅲ, the structure of which was shown to be that of complex Ⅱ. The similarity of the NMR spectra of Ⅱ and Ⅲ suggest that Ⅲ adopts cage structure similar to that previously confirmed for Ⅱ. A series of 9-vertex hypho clusters in which the sulfur atoms are bridged by different species isoelectronic with a BH3 unit, such as HMn(CO)4 or SiR2 have been prepared. Compounds Ⅳ,Ⅴ and Ⅵ are each 2n+4 skeletal electron systems and would be expected according to skeletal electron counting theory to adopt hypho-type polyhedral structures derived from an icosahedron missing three vertices. The complex hypho-1-(CO)4Mn-2,5-S2B6H9 Ⅳ was obtained by the reaction of the anion with (CO)5MnBr and has been shown from spectroscopic data to consist of a (CO)4Mn fragment bound to the two sulfur atoms S2 and S5 of hypho-S2B7H10-. Also, similar hypho-type complexes hypho-1-R2Si-2,5-S2B6H8 (R=CH3 Ⅴ, R=C6H5 Ⅵ) have been prepared from the reaction of hypho-S2B7H10- with R2SiHCl.

Utilization of age information for speaker verification using multi-task learning deep neural networks (멀티태스크 러닝 심층신경망을 이용한 화자인증에서의 나이 정보 활용)

  • Kim, Ju-ho;Heo, Hee-Soo;Jung, Jee-weon;Shim, Hye-jin;Kim, Seung-Bin;Yu, Ha-Jin
    • The Journal of the Acoustical Society of Korea
    • /
    • v.38 no.5
    • /
    • pp.593-600
    • /
    • 2019
  • The similarity in tones between speakers can lower the performance of speaker verification. To improve the performance of speaker verification systems, we propose a multi-task learning technique using deep neural network to learn speaker information and age information. Multi-task learning can improve generalization performances, because it helps deep neural networks to prevent hidden layers from overfitting into one task. However, we found in experiments that learning of age information does not work well in the process of learning the deep neural network. In order to improve the learning, we propose a method to dynamically change the objective function weights of speaker identification and age estimation in the learning process. Results show the equal error rate based on RSR2015 evaluation data set, 6.91 % for the speaker verification system without using age information, 6.77 % using age information only, and 4.73 % using age information when weight change technique was applied.

Quality Classification and Its Application Based on Certification Standards of Kentucky Bluegrass(Poa pratensis L.) Seed (켄터키 블루그래스(Poa pratensis L.) 종자의 보증 기준에 따른 품질 분류와 적용)

  • Kim, Shin-Jae;Joo, Young-Kyoo;Lee, Jae-Pil;Kim, Doo-Hwan
    • Asian Journal of Turfgrass Science
    • /
    • v.23 no.2
    • /
    • pp.253-264
    • /
    • 2009
  • The purpose of seed certification is to preserve the genetic purity and identity of seed varieties. This study is to provide information concerning seed certification procedures and certification standards of Kentucky bluegrass especially used in golf courses. We analyzed data from the seed certification standards of three states (Washington, Idaho and Oregon) in U.S.A. The certification processes both field inspection and laboratory requirement satisfying the minimum seed quality standards. The seed harvesting field must be propagated with the specified class of seeds and requires an adequate isolated distance from other crops. Moreover, the field should be clean and free from the objectionable weeds. The seed analysis tests include a germination rate, a percentage of pure seed, contents of other crop seed, weed seed, and inert matter. The certification standards of the certified seed and the sod quality seed showed general similarity in all three states. The certification standards of the sod quality seed should have less than 0.02% of maximum weed seed. The certified seed should have less than 0.3% of maximum weed seeds. Those certification standards of seed quality should guaranty the quality of turfgrass establishment of golf course.