• 정보과학회 논문지
• /
• 제44권12호
• /
• pp.1282-1289
• /
• 2017

최근 심층 컨볼루션 신경망을 활용한 이미지 분할과 물체 위치감지 연구가 활발히 진행되고 있다. 특히 네트워크의 최상위 단에서 추출한 특징 지도뿐만 아니라, 중간 은닉 층들에서 추출한 특징 지도를 활용하면 더욱 정확한 물체 감지를 수행할 수 있고 이에 대한 연구 또한 활발하게 진행되고 있다. 이에 밝혀진 경험적 특성 중 하나로 중간 은닉 층마다 추출되는 특징 지도는 각기 다른 특성을 가지고 있다는 것이다. 그러나 모델이 깊어질수록 가능한 중간 연결과 이용할 수 있는 중간 층 특징 지도가 많아지는 반면, 어떠한 중간 층 연결이 물체 분할에 더욱 효과적일지에 대한 연구는 미비한 상황이다. 또한 중간층 연결 방식 및 중간층의 특징 지도에 대한 정확한 분석 또한 부족한 상황이다. 따라서 본 연구에서 최신 깊은 신경망에서 중간층 연결의 특성을 파악하고, 어떠한 중간 층 연결이 물체 감지에 최적의 성능을 보이는지, 그리고 중간 층 연결마다 특징은 어떠한지 밝혀내고자 한다. 그리고 이전 방식에 비해 더 깊은 신경망을 활용하는 물체 분할의 방법과 중간 연결의 방향을 제시한다.

• 디지털융복합연구
• /
• 제15권12호
• /
• pp.341-347
• /
• 2017

많은 양의 문서 데이터가 증가됨에 따라 사용자는 해당 문서를 이해하기 위한 요약된 정보를 필요로 한다. 그러나, 기존 문서 요약 연구 방법들은 지나치게 단순한 통계에 의존함으로써 문장의 모호성 및 의미 있는 문장 생성을 위한 다중 문서 요약 연구가 미흡한 실정이다. 본 논문에서는 의미적 연결 관계에 대한 파악 및 불필요한 정보를 처리하기 위한 전처리 과정을 거치며, 어휘 의미 패턴 정보를 기반으로 VAE를 이용하여 문장 간의 의미적 연결성을 높인 다중 문서 요약 기법을 제안하였다. 문장을 이루고 있는 단어 벡터들을 이용하여, 잠재된 변수로 생성된 압축된 정보와 속성 판별기로부터 학습을 한 후 문장을 재구성함으로써 의미적 연결 처리가 자연스러운 요약문을 생성하였다. 제안된 방법과 다른 문서 요약 방법을 비교했을 시 미세하지만 더 향상된 성능을 나타냈으며, 이는 의미적 문장 생성 및 연결성을 높일 수 있음을 증명하였다. 앞으로, 다양한 속성 설정 값을 가지고 실험하여 의미적 연결 관계를 확장할 수 있는 방법을 연구하고자 한다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권8호
• /
• pp.2704-2719
• /
• 2022

Lately, neo-Chinese style furniture has been frequently noticed by product design professionals for the big part it played in promoting traditional Chinese culture. This article is an attempt to use big data semantic analysis method to provide effective design research method for neo-Chinese furniture design. By using big data mining program TEXTOM for big data collection and analysis, the data obtained from typical websites in a set time period will be sorted and analyzed. On the basis of "neo-Chinese furniture" samples, key data will be compared, classification analysis of overall data, and horizontal analysis of typical data will be performed by the methods of word frequency analysis, connection centrality analysis, and TF-IDF analysis. And we tried to summarize according to the related views and theories of the design. The research results show that the results of data analysis are close to the relevant definitions of design. The core high-frequency vocabulary obtained under data analysis, such as popular, furniture, modern, etc., can provide a reasonable and effective focus of attention for the designs. The result obtained through the systematic sorting and summary of the data can be a reliable guidance in the direction of our design. This research attempted to introduce related big data mining semantic analysis methods into the product design industry, to supply scientific and objective data and channels for studies on design, and to provide a case on the practical application of big data analysis in the industry.

• 한국실내디자인학회논문집
• /
• 제27권3호
• /
• pp.33-40
• /
• 2018

As the standard for the value of modern people's life increases, hotels make efforts for the users' qualitative and mental satisfaction. As an approach to hotel space design differentiated for new experiences for travelers, a design that reflects the placeness is needed so that people can experience the local culture and historical meaning of the place. Thus, this study divides the components of placeness into physical factors, socio-cultural factors, and semantic factors. As for methods for the design expression of placeness formation, physical factors are classified as the connection to surrounding environments, center, passage, and area. Socio-cultural factors are classified as cultural experiences in the place. Semantic factors are classified as symbolism and historicity. For a case analysis in this study, overseas four-star hotels or higher, where placeness stood out are analyzed, based on the above-extracted components of placeness. As a result of the analysis, the hotels in the cases showed an aspect of expression that emphasized semantic factors despite there were differences in the detailed expression method, depending on the designers. The expression of the place that reflected locality and temporality showed the connection of time, connecting the past with the present. In the future, only the design expression based on the historical and symbolic meanings of the place will be the experience that remains in the users' memories, very precisely.

• 한국경영과학회지
• /
• 제39권3호
• /
• pp.7-22
• /
• 2014

By the publications of RDF and OWL, the Semantic Web is confirmed as a technology through which information in the Internet can be processed by machines. The focus of the Semantic Web study after then has moved to how to provide more useful information to users for their decision making beyond simple use of the structured data in ontologies. SWRL that makes logical inference possible by rules, and SWCL that formulates constraints under the Semantic Web environment are some of many efforts toward the achievement of that goal. Constraint represents a connection or a relationship between individual data in ontology. Based on SWCL, this paper tries to extend the language by adding one more type of constraint, implication constaint, in its repertoire. When users use binary variables to represent logical relationships in mathematical models, it requires and knowledge on the solver to solve the models. The use of implication constraint ease this difficulty. Its need, definition and relevant technical description is presented by the use of the optimal common attribute selection problem in product design.

• 인터넷정보학회논문지
• /
• 제7권2호
• /
• pp.9-21
• /
• 2006

온톨로지를 사용하여 웹 서비스 검색 기능을 향상시키려는 연구가 진행되고 있다. 그 중 DAML, DAML+OIL를 이용하여 UDDI를 검색하는 방안이 제안되었다. 하지만 이 방식은 UDDI 검색에 적합한 연산자들을 사용해야 하는 불편함과 그에 따른 온톨로지를 정의해 주어야 하는 번거로움이 존재한다. 이러한 문제점을 해결하기 위해 본 논문에서는 시맨틱 웹 환경에서 정보검색 및 의미적인 추천을 위한 N-Triple 처리, 핵심 Triple 추출을 위한 필터링, Triple 통합, Triple간 의미적 연결, Triple 탐색 기법을 제시하고 더 나아가 제시된 기법으로 시스템을 설계하고 구현한다. 끝으로 가상의 시맨틱 웹 환경에서 제안된 시스템을 실험하여 본 논문의 유용성을 입증한다.

• 대한건축학회논문집:계획계
• /
• 제35권7호
• /
• pp.101-108
• /
• 2019

In this research, I conducted a semantic network analysis centering on media articles on purchasing, revitalizing, and utilizing the former Busan branch of Hansung Bank, a modern architectural heritage. We sought the most efficient analysis elements for the analysis of the social arguments about preservation and utilization embedded in media articles. For this reason, Degree Centrality measures how many connections the word described in the media article has, and Betweenness Centrality measures the influence that controls the flow of information through correlation I examined. In addition, keyword that express the theme well examined the aggregation structure in each sub-network. In this research, in theoretical terms, it makes sense in that the social discussion embedded in the article of the mass media is grasped empirically through semantic network analysis of words. Methodological aspect is best when it includes nouns and adjectives and the distance between words is more than four words in the analysis of the cohesive structure of the semantic network to determine whether the influence of social discussions is best assessed through the connection between words to media articles.

• International Journal of Internet, Broadcasting and Communication
• /
• 제15권1호
• /
• pp.222-230
• /
• 2023

The purpose of this study is to provide basic data on sports entertainment programs by collecting data on unstructured data generated by Naver and Google for SBS entertainment program 'Women Who Score Goal', which began regular broadcast in June 2021, and analyzing public perceptions through data mining, semantic matrix, and CONCOR analysis. Data collection was conducted using Textom, and 27,911 cases of data accumulated for 16 months from June 16, 2021 to October 15, 2022. For the collected data, 80 key keywords related to 'Kick a Goal' were derived through simple frequency and TF-IDF analysis through data mining. Semantic network analysis was conducted to analyze the relationship between the top 80 keywords analyzed through this process. The centrality was derived through the UCINET 6.0 program using NetDraw of UCINET 6.0, understanding the characteristics of the network, and visualizing the connection relationship between keywords to express it clearly. CONCOR analysis was conducted to derive a cluster of words with similar characteristics based on the semantic network. As a result of the analysis, it was analyzed as a 'program' cluster related to the broadcast content of 'Kick a Goal' and a 'Soccer' cluster, a sports event of 'Kick a Goal'. In addition to the scenes about the game of the cast, it was analyzed as an 'Everyday Life' cluster about training and daily life, and a cluster about 'Broadcast Manipulation' that disappointed viewers with manipulation of the game content.

• Journal of health informatics and statistics
• /
• 제43권4호
• /
• pp.274-281
• /
• 2018

Objectives: The purpose of this study is to comprehensively compare the trends of health administration and health policy in the field of health care using the semantic network analysis in the inaugural address of the Ministry of Health and Welfare of each regime in Korea. Methods: This study used a language network analysis method that uses Korean Key Words In Context (KrKwic) program and NetMiner program in sequence. The analysis was conducted by Minister Hwa-joong Kim during the Moo-hyun Roh government, Minister Jae-hee Jeon during the Myung-bak Lee government, Minister Young Jin of Geun-hye Park government and Government Jae-in Moon's inaugural address of Neung-Hoo Park Minister, respectively. Results: The key words differentiated by each regime are that the Moo-hyun Roh Government's Minister Hwa-joong Kim had high connection centrality values in the words 'balanced development', 'comprehensive' and 'reform'. Minister Jae-Hee Jeon of Myung-bak Lee Government had high connection centrality values in the words 'poverty' and 'return'. In the case of Minister Young Jin of Geun-hye Park Government had high connection centrality values in the words 'demand', 'Customized' and 'Life cycle'. In the case of Minister Neung-Hoo Park of Jae In Moon Government had high connection centrality values in the words 'Welfare state', 'Embracing' and 'Soundness'. Conclusions: If the role of health administration in the health care field and the health care policies are constantly changed according to the policies of each regime, it is inconsistent and it is difficult to approach from the long term perspective for public health promotion. In the future, health policy should be developed and implemented with a long-term perspective and consistency based on the consensus and participation of the people with less influence on the change and direction of each government's policies.

• International Journal of Knowledge Content Development & Technology
• /
• 제12권4호
• /
• pp.41-65
• /
• 2022

This study would understand the overall perception of our society about public libraries, analyzing the texts related to public libraries, utilizing the semantic connection network & sentiment analysis. For this purpose, this study collected data from the last five years with keywords, 'Library' and 'Lifelong Learning Center' from January 1, 2016 through November 30, 2020 through the blogs and cafés of major domestic portal sites. With the collected data, text mining, centrality of keywords, network structure, structural equipotentiality, and sensitivity analyses were conducted. As a result of the analysis, First, 'reading' and 'book' were identified as representative keywords that form the social perception of public libraries. Second, it turned out that there were keywords related to the use of the library and the untact service due to the recent spread of COVID-19. Third, in seeking a plan for the development of public libraries through the keywords drawn to have positive meanings, it is necessary to create continuous services that can form a new image of the library, breaking away from the existing fixed role and image of the library and increase the convenience of use. Fourth, facilities and facilities for library services were recognized from a neutral point of view. Fifth, the spread of infectious diseases, social distancing, and temporary closure and closure of libraries are negatively related to public libraries, and awareness of librarians has been identified as negative keywords.