• Annual Conference of KIPS
• /
• 2013.11a
• /
• pp.1064-1067
• /
• 2013

정보검색 기술의 발달과 더불어 검색에 대한 사용자의 요구사항이 다양해지고 있다. 특히, 스마트TV와 같은 장치에서 동영상 콘텐츠를 검색하는데 있어서 콘텐츠의 타이틀과 같은 정형 메타데이터를 이용한 검색뿐만 아니라, 콘텐츠 주제와 같은 비정형 메타데이터를 이용한 검색도 요구되고 있다. 이러한 검색 요구사항을 수용하기 위해서는 주제와 같은 비정형 메타데이터가 구축되어 있어야만 가능하다. 콘텐츠의 주제는 사람의 이해와 분석을 통해서 수작업으로 구축 가능하다. 본 논문에서는 수작업만으로 구축 가능한 콘텐츠의 주제를 기계학습을 기반으로 자동화 할 수 있는 기법을 제안하고, 제안한 기법의 실험을 통하여 타당성을 검증한다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.69-71
• /
• 2022

Today, the AI market is very large due to the development of AI. Among them, the most advanced AI is image detection. Thus, there are many object detection models using YOLOv5.However, most object detection in AI is focused on detecting objects that are stereotyped.In order to recognize such unstructured data, the object may be recognized by learning and filtering the object. Therefore, in this paper, a fire monitoring system using YOLOv5 was designed to detect and analyze unstructured data fires and suggest ways to improve the fire object detection model.

• Journal of Korean Dental Hygiene Science
• /
• v.6 no.2
• /
• pp.101-114
• /
• 2023

Background: This study aimed to explore the overall perception of pit and fissure sealants and suggest methods to revitalize their current stagnation. Methods: To determine the social perception of the change in coverage policy for pit and fissure sealants, we categorized them into five time periods. The first period (December 1, 2009 to November 30, 2010), the second period (December 1, 2010 to September 30, 2012), the third period (October 1, 2012 to May 5, 2013), the fourth period (May 6, 2013 to September 30, 2017), and the fifth period (October 1, 2017 to December 31, 2022). We utilized text mining, an unstructured big data analysis method. Keywords were collected and analyzed using Textom, and the frequency analysis of the top 30 keywords, structural features of the semantic network, centrality analysis, QAP correlation analysis, and co-occurrence analysis were conducted. Results: The frequency analysis showed that the top keywords for each time period were 'Cavities', 'Treatment', and 'Children'. In the structural features of the semantic network of pit and fissure sealants by time period, the density index was found to be around 1.00 for all time periods. The QAP correlation analysis showed the highest correlation between the first and second periods and the fourth and fifth periods with a correlation coefficient of 0.834. The co-occurrence analysis showed that 'cavities' and 'prevention were the top two words across all time periods. Conclusion: This study showed that pit and fissure sealants are well accepted by the society as a preventive treatment for caries. However, the awareness of health education related to these sealants was found to be low. Efforts to revitalize stagnant pit and fissure sealants need to be strengthened with effective education.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.5
• /
• pp.769-778
• /
• 2023

This study compared and analyzed parental leave and child allowance, two major policies among solutions to the current serious low fertility rate problem, using unstructured data, and sought future directions and implications for related response policies based on this. The collection keywords were "low fertility + parental leave" and "low fertility + child allowance", and data analysis was conducted in the following order: text frequency analysis, centrality analysis, network visualization, and CONCOR analysis. As a result of the analysis, first, parental leave was found to be a realistic and practical policy in response to low fertility rates, as data analysis showed more diverse and systematic discussions than child allowance. Second, in terms of child allowance, data analysis showed that there was a high level of information and interest in the cash grant benefit system, including child allowance, but there were no other unique features or active discussions. As a future improvement plan, both policies need to utilize the existing system. First, parental leave requires improvement in the working environment and blind spots in order to expand the system, and second, child allowance requires a change in the form of payment that deviates from the uniform and biased system. should be sought, and it was proposed to expand the target age.

• Electronics and Telecommunications Trends
• /
• v.26 no.1
• /
• pp.80-88
• /
• 2011

데이터의 효과적인 활용이 경쟁력 확보에 주요한 요인이나, 데이터 폭증은 유용한 정보를 얻는데 필요한 처리 시간의 지연을 야기하고 있다. 개인 맞춤형 서비스, 방범 방재 서비스 등 모니터링 & 대응 서비스를 위해 분석할 데이터의 양이 급증하고 있으며, 텍스트, 영상, 오디오 등 비정형 데이터에 대한 실시간 분석 필요성이 증대하고 있다. 대량의 폭증하는 데이터에 대한 실시간 분석 처리 환경을 제공하기 위해 분산 병렬 컴퓨팅 기술과 데이터 스트림 연속 처리 기술이 활용되고 있다. 본고에서는 폭증하는 데이터 스트림 처리를 위하여 확장성 및 유연한 처리 환경을 제공하는 분산 스트림 컴퓨팅 기술에 대해 소개한다.

• Annual Conference of KIPS
• /
• 2013.05a
• /
• pp.904-907
• /
• 2013

최근 정보통신기술이 하루가 다르게 발전함에 따라 하루에도 수많은 데이터가 흘러나오는 최근의 추세이다. 정형 데이터 뿐 아니라 비정형 데이터 분석까지 진행하는 최근의 추세에 맞춰 현 빅데이터 기술 동향을 분석한다. 빅데이터 시대를 맞아 기존의 데이터웨어하우스(DW)와 발전된 데이터웨어하우스(DW) 어플라이언스에 대해 분석하고 향후 발전 전망과 방향을 제시한다.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.13 no.1
• /
• pp.105-113
• /
• 2000

Seismic behavior of 3-dimensional setback structures showing abrupt reductions of the floor size within the structure height and the effect of in-plane deformations of floor slabs on the seismic behavior of those structures are investigated. To find out general seismic behavior of 3-dimensional setback structures two parameters, level of setback(L/sub s/) and degree of setback(R/sub s/) are used. Analysis results obtained from forty eight setback structures show that a sudden change in story shear near setback level is occurred for irregular setback structures. The effect of in-plane deformation of floor slabs on the seismic behavior of setback structures is greatly influenced by the arrangement of lateral load resisting elements and it is more pronounced for frame-shear wall system showing large difference in stiffness among the lateral load resisting elements. The in-plane deformation of floor slabs results in reduced base shear, especially for FW-type structures with L/sub s/=1.0. Also, it brings about reduced story shear for the lateral load resisting element with shear wall and increase in story shear lot the lateral load resisting element without shear wall. The in-plane deformation of floor slabs at the base portion and/or tower portion due to difference in stiffness among the lateral load resisting elements brings about increment of floor displacements at all floor level.

• Journal of Korea Water Resources Association
• /
• v.54 no.spc1
• /
• pp.1195-1204
• /
• 2021

Recently, local torrential rain have become more frequent and severe due to abnormal climate conditions, causing a surge in human and properties damage including infrastructures along the river. In this study, water surface elevation prediction algorithm was developed using the LSTM (Long Short-term Memory) technique specialized for time series data among Machine Learning to estimate and prevent flooding of the facilities. The study area is Jamsu Bridge, the study period is 6 years (2015~2020) of June, July and August and the water surface elevation of the Jamsu Bridge after 3 hours was predicted. Input data set is composed of the water surface elevation of Jamsu Bridge (EL.m), the amount of discharge from Paldang Dam (m³/s), the tide level of Ganghwa Bridge (cm) and the number of tweets in Seoul. Complementary data were constructed by using not only structured data mainly used in precedent research but also unstructured data constructed through wordcloud, and the role of unstructured data was presented through comparison and analysis of whether or not unstructured data was used. When predicting the water surface elevation of the Jamsu Bridge, the accuracy of prediction was improved and realized that complementary data could be conservative alerts to reduce casualties. In this study, it was concluded that the use of complementary data was relatively effective in providing the user's safety and convenience of riverside infrastructure. In the future, more accurate water surface elevation prediction would be expected through the addition of types of unstructured data or detailed pre-processing of input data.

• Information Systems Review
• /
• v.25 no.1
• /
• pp.233-255
• /
• 2023

The development of information technology(IT) has brought so-called "online experience" to satisfy our daily needs. The market for online experiences grew more during the COVID-19 pandemic. Therefore, this study attempted to analyze how the features of online experience services affect customer satisfaction by crawling structured and unstructured data from the online experience web site newly launched by Airbnb after COVID-19. As a result of the analysis, it was found that the structured data generated by service users on a C2C online sharing platform had a positive effect on the satisfaction of other users. In addition, unstructured text data such as experience introductions and host introductions generated by service providers turned out to have different subjectivity scores depending on the purpose of its text. It was confirmed that the subjective host introduction and the objective experience introduction affect customer satisfaction positively. The results of this study are to provide various implications to stakeholders of the online sharing economy platform and researchers interested in online experience knowledge management.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.151-154
• /
• 2021

Big data analysis is the process of discovering meaningful new correlations, patterns, and trends in large volumes of data stored in data stores and creating new value. Thus, most big data analysis technology methods include data mining, machine learning, natural language processing, and pattern recognition used in existing statistical computer science. Also, using the R language, a big data tool, we can express analysis results through various visualization functions using pre-processing text data. The data used in this study was analyzed for 21 papers in the March 2021 among the journals of the Korea Institute of Information and Communication Engineering. In the final analysis results, the most frequently mentioned keyword was "Data", which ranked first 305 times. Therefore, based on the results of the analysis, the limitations of the study and theoretical implications are suggested.