• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2018.06a
• /
• pp.334-335
• /
• 2018

최근 수 년간 비디오 콘텐츠 소비 공간이 인터넷으로 확장되며 지능적 비디오 콘텐츠 추천 기술 개발이 진행되어 왔다. 하지만 지능적 비디오 콘텐츠 추천 기술은 사용자의 기호나 업로드된 비디오 콘텐츠의 제목 등을 기반으로 하여 비디오 콘텐츠 클래스에 대한 분석 없이 유사한 비디오 콘텐츠를 탐색하고 추천해주는 기술이 대부분이다. 본 논문에서는 지능적 콘텐츠 추천을 위한 딥러닝 기반 방송 콘텐츠 클래스 분류 시스템을 제안한다. 방송 콘텐츠 내 영상 정보를 이용하여 방송 콘텐츠 클래스를 분류하며 높은 분류 정확도를 보여주는 것을 확인할 수 있다.

• Annual Conference on Human and Language Technology
• /
• 2021.10a
• /
• pp.144-151
• /
• 2021

딥러닝의 등장으로 자동 음성 인식 (Automatic Speech Recognition) 기술은 인간과 컴퓨터의 상호작용을 위한 가장 중요한 요소로 자리 잡았다. 그러나 아직까지 유사 발음 오류, 띄어쓰기 오류, 기호부착 오류 등과 같이 해결해야할 난제들이 많이 존재하며 오류 유형에 대한 명확한 기준 정립이 되고 있지 않은 실정이다. 이에 본 논문은 음성 인식 시스템의 오류 유형 분류 기준을 한국어에 특화되게 설계하였으며 이를 다양한 상용화 음성 인식 시스템을 바탕으로 질적 분석 및 오류 분류를 진행하였다. 실험의 경우 도메인과 어투에 따른 분석을 각각 진행하였으며 이를 통해 각 상용화 시스템별 강건한 부분과 약점인 부분을 파악할 수 있었다.

• Journal of the Korean BIBLIA Society for library and Information Science
• /
• v.22 no.3
• /
• pp.207-228
• /
• 2011

The notes of the classification system are to improve the accuracy and consistency of classification by providing useful information on classification numbers and items. Even though, several notes are used in KDC, they are not enough to keep up with rapidly developing and expanding knowledge of nowadays. The purpose of this study is to suggest appropriate types and improvements of the notes in KDC 5th edition. In order to achieve these purposes, transition of notes in KDC was analyzed. Notes of DDC 23rd edition, NDC new 9th edition, and KDC 5th edition were also analyzed. Based upon these comparison and analysis, problem and improvement of notes in KDC were suggested.

• Journal of Korean Library and Information Science Society
• /
• v.42 no.2
• /
• pp.151-170
• /
• 2011

This article tries to analyze some examples applied the analytico-synthetic classification techniques found in the practical life. For this purpose, it selected and investigated the cases of the combination rules of the Hangeul, the number systems of the city buses of Daegu and Seoul Cities, information of the members of the wedding consulting agencies, information from real estate agents and court auction, and postal codes and direct distance dialing(DDD) numbers in Korea. It suggests that applying the analytico-synthetic classification techniques to the systems can improve them especially in the regards of notational systems.

• KOREAN JOURNAL OF CROP SCIENCE
• /
• v.34 no.1
• /
• pp.74-80
• /
• 1989

Twentyseven rice cultivars were compared Quantitatively and classified by 15 agronomic traits. For this, 12 Tongil-type rice cultivars and 15 Japonica-type rice cultivars were transplanted at the experimental farm of the Yeongnam Crop Experiment Station on May 25 in 1987. Jangseongbyeo belonging to Tongil-type had the greatest dissimilarity total among 27 rice cultivars and followed by Chilseongbyeo, Gayabyeo, Hangangchalbyeo, Gihobyeo (Tongil-type) and Sangpoongbyeo (Japonica-type) while cultivars having greatest similarity total were Daecheongbyeo and Yeongsanbyeo and followed by Nagdongbyeo, Sinsunchalbyeo, Gwangmyeongbyeo, Yeongdeogbyeo, Palgongbyeo and Dongjinbyeo that were all belonging to Japonica-type cultivars. CuItivar pairs having the greatest dissimilarity coefficient (50-55％) were combinations of Gayabyeo and Sangpungbyeo, Gihobyeo, or Seonambyeo, combinations of Chilseongbyeo and Jangseongbyeo, Sangpung-byeo, Chucheongbyeo, Gihobyeo or Seonambyeo and combinations of }angseongbyeo and Gwangmyeong-byeo, Sangpungbyeo, Gihobyeo, Daechangbyeo or H waseongbyeo. On the other hand, cultivar pairs having the greatest similarity coefficient (above 85 ％) were combinations of Dongjinbyeo and Sinsunchalbyeo, Daecheongbyeo, Somjinbyeo or Yeongsanbyeo, combination of Sangpungbyeo and Gihobyeo, combinations of Yeongdeogbyeo and Yeongsanbyeo or Palgongbyeo, combination of Gwangmyeongbyeo and Yeongdeogbyeo, Combinations of Nagdongbyeo and Gwangmyeongbyeo, Yeongdeogbyeo, Daecheongbyeo, Hwaseongbyeo or Yeongsanbyeo, combinations of Sinsunchalbyeo and Daecheongbyeo or Yeongsanbyeo, combinations of Somjinbyeo and Daecheongbyeo or Yeongsanbyeo and combination of Daecheongbyeo nd Yeongsanbyeo. Two-dimensional ordination analysis method provided the information on cultivar classification between Japonica-type and Tongil-type cultivars except a few cultivars. Only two cultivars, Joongweonbyeo and Seomjinbyeo were located opposit area that implied Tongil-type cultivar Joongweonbyeo was rather close to Japonica-type while Japonica-type cultivar Seomjinbyeo was rather close to Tongil-type, respectively. Sinsunchalbyeo and Daecheongbyeo, on the other hand, were located on the line between two cultivar groups. The method of two-dimensional ordination analysis concluded as feasible approach to classify cultivars Quantitatively for the practical purpose.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.40 no.3
• /
• pp.32-41
• /
• 2012

This study is performed to light up the semiotic system of streetscape in the harbor on the basic concept of all cultural phenomena that could be described as a Semiotic System. The semiotic approach to landscape analysis was used for understanding landscape characteristics owing to implication of psychological process. Streets of the study were located at Ganguri and Opori on Gang-Gu Harbor and the signboard semiotics of streets were divided into 17 meanings according to the business category. The analysis of this category was applicable on semiotic meaning. The research results are as follows: First, the main part of the business category was food. 56.3% of Ganguri and 61.8% of Opori had the name of food businesses. Second, the semiotic characteristics of Gang-Gu harbor streets mainly mean place name or friendly name. The food business could be related to the principal products of this district which are called Young-Duk Great Crab. Also, the place name could be from symbolic meaning of the crab and the friendly name could be connected with increasing the sales. Finally, the semiotic approach to landscape does not fully cover the streetscape but could be useful for understanding a skeleton of harbor streetscape.

• The Journal of Engineering Geology
• /
• v.24 no.3
• /
• pp.383-396
• /
• 2014

The condition, characteristics, and stability of slopes, as well as the consequences of slope failure, need to be understood for the proper stabilization of slopes and preclusion of potential disasters arising from slope failure. Here, a slope code system (SCS) that succinctly and accurately reflects the various conditions of a slope is proposed. The SCS represents the condition, characteristics, and geotechnical stability of slopes, as well as the consequences of slope failure, and the method is quickly and easily applied to a given slope. The SCS comprises five elements: 1) the slope material; 2) the genetic origin (rock type) and geological structure of the slope; 3) the geotechnical stability of the slope; 4) the probability of failure and remedial works made upon the slope; and 5) the consequences of failure. A letter code is selected from each element, and the result of the evaluation and classification of the slope is given as a five-letter code. Because the condition, characteristics, and geotechnical stability of a slope, as well as the consequences of slope failure, are provided by the SCS, this system will provide an effective mechanism for the maintenance and management of slopes, and will also allow more informed decision-making for determining which slopes should be prioritized for remedial measures.

• Journal of the Korea Convergence Society
• /
• v.6 no.6
• /
• pp.87-93
• /
• 2015

Advertisements in modern era are not intended to be consumed only as commercial purposes, but consumed also as cultural and artistic purposes. Advertising contents' success depends on Semiotic codes revealed in advertising texts. Advertising scholar Ozoh (1998) argued that perspectives for advertising are divided into two perspective, one as marketing tool perspective and the other as communication processes perspective. Advertising planning, advertising management, advertising, and advertising evaluation of marketing perspective are significantly different from those of communication perspective. Two perspectives of advertising present various debates on what contents of advertising messages are and how advertising messages are made up. In this research manuscripts, we discuss story telling as communication tool of advertising text in terms of cultural semiotics. That is, meaning value of goods is so well revealed in use value of goods that they satisfy consumers' needs, we analyze how they satisfy consumers' needs in semiotic(symbolic) process. We apply Gremas's semantic model to coffee advertisements in France and Korea, and analyze various differences between differentiation strategies of French coffee advertisements and those of Korean coffee advertisements in terms of semiotic perspective.

• KOREAN JOURNAL OF CROP SCIENCE
• /
• v.51 no.7
• /
• pp.618-623
• /
• 2006

This study was carried out to select the acceptance test influenced by some quality characteristics of rice, and may provide the basic information on rice grade of appearance quality as distinguished the numerical values. Forty-four Japonica rice varieties mainly cultivated in Korea were evaluated for a consumer acceptance test. Color preferences of rice were highly correlated with appearance quality (r=-0.897**) and redness (r=-0.893**). Especially, appearance quality value resulted from interaction of $redness{\times}yellowness$ values was expected as a specific character used for grade of rice appearance. Shape preferences of rice showed the positive correlation with grain width (r=0.527**) and grain size (r=0.454**). Result of the consumer acceptance test of rice appearance conducted through a cluster analysis revealed five groups. Our study suggests that it may be feasible to be graded by average of quality character among groups, grain width, and grain size in Duncan's multiple range test.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.19 no.5
• /
• pp.959-970
• /
• 1994

In this thesis, a printed score is read by using handy scanner and the recognition process is excuted in parallel, finally, on Mesh-Connected Computer. What is read is classified into certain patterns and is recognized, based on knowledge. The preprocessing steps are minimized and simple operations are used in the algorithm proposed in this thesis. The score symbols on a printed score can be recognized irrespective of their sizes but their diversity males it difficult to recognize them all, so it is programmed so as to recognize some symbols that is used necessarily and frequently. The recognized result is transformed into the MIDI standard file format. It is required to use a parallel processing system with multiprocessors because the high speed image processing is required. A digitized two-dimensional image is appropriate in processing on the SIMD Mesh-Connected Computer(MCC). Therefore, we explain this architecture and present parallel algorithm using SIMD MCC with n processors that achieves time complexity0(n).