• Proceedings of the Korea Information Processing Society Conference
• /
• 2024.05a
• /
• pp.552-553
• /
• 2024

협력적 필터링은 추천시스템을 구축하는 알고리즘으로 고객별 선호도를 예측하는데 사용되고 있다. 이에 본 연구는 행복감에 영향을 주는 요인인 자존감과 생활여건을 사용하여, 협력적 필터링을 기반으로 한 예측정확도가 높은 모형을 연구하고자 한다. 이를 위해, 자존감과 생활여건에 대한 응답자 간의 유사도 가중치를 각각 계산한 후, 자존감 유사도 가중치를 적용한 모형으로 행복감을 예측하고, 자존감 유사도 가중치에 생활여건 유사도 가중치를 부여한 유사도 가중치를 적용한 모형으로 행복감을 예측하였다. 그 결과 전자의 모형이 후자의 모형보다 예측정확도가 높게 나타났다.

• Journal of Korean Library and Information Science Society
• /
• v.53 no.2
• /
• pp.305-332
• /
• 2022

This preliminary study examined the degree programs in data science at the School of Information in the States. The focus of this study was the data science degrees offered at the School of Information awarded by the 64 Library and Information Science (LIS) programs accredited by the American Library Association (ALA) in 2022. In addition, this study examined the degrees, majors, minors, specialized tracks, and certificates in data science, as well as the potential careers after earning a data science degree. Overall, eight Schools of Information (iSchools) offered 12 data science degrees. Data science courses at the School of Information focus on topics such as introduction to data science, information retrieval, data mining, database, data and humanities, machine learning, metadata, research methods, data analysis and visualization, internship/capstone, ethics and security, user, policy, and curation and management. Most schools did not offer traditional LIS courses. After earning the data science degree in the School of Information, the potential careers included data scientists, data engineers and data analysts. The researcher hopes the findings of this study can be used as a starting point to discuss the directions of data science programs from the perspectives of the information field, specifically the degrees, majors, minors, specialized tracks and certificates in data science.

• The Journal of the Convergence on Culture Technology
• /
• v.10 no.2
• /
• pp.453-458
• /
• 2024

Optical Character Recognition is the technology that recognizes text in images and converts them into digital format. Deep learning-based OCR is being used in many industries with large quantities of recorded data due to its high recognition performance. To improve medical services, deep learning-based OCR was actively introduced by the medical industry. In this paper, we discussed trends in OCR engines and medical OCR and provided a roadmap for development of medical OCR. By using natural language processing on detected text data, current medical OCR has improved its recognition performance. However, there are limits to the recognition performance, especially for non-standard handwriting and modified text. To develop advanced medical OCR, databaseization of medical data, image pre-processing, and natural language processing are necessary.

• Journal of Korean Library and Information Science Society
• /
• v.47 no.3
• /
• pp.343-363
• /
• 2016

This study determines 69 iSchools provided which data science curriculum, and presents the direction for Korean LIS schools. It is certain that iSchools extend their subject territory including areas related to health, technology and biotechnology. However, this phenomenon is not actively observed in Korea. iSchools also focus on the area about how to process and manage data. iSchools, in deed, offer courses regarding data science, data management and data security. The 'database' was a higher proportion of 'data warehouse' curriculum, and, 'data statistic and analysis' curriculum are forming similar portion. As a result of analysis of the iSchool's curriculum and comparison with Korean curriculum, this study suggests: the expansion of LIS curriculum related to data science; the enhanced role of the data translational data science; development of curriculum to raise the mathematical analysis capabilities, development of specialized curriculum and experimental classes; and support new knowledge skills to interact with technology.

• Annual Conference on Human and Language Technology
• /
• 2019.10a
• /
• pp.395-399
• /
• 2019

생성 모델은 최근 단순히 기존 데이터를 증강 시키는 것이 아니라 원하는 속성을 가지도록 스타일을 변화시키는 연구가 활발히 진행되고 있다. 스타일 변화 연구에서 필요한 병렬 데이터 세트는 구축하는데 많은 비용이 들기 때문에 비병렬 데이터를 이용하는 연구가 주를 이루고 있다. 이러한 방법론으로 이미지 분야에서 대표적으로 cycleGAN[1]이 있으며 최근 자연어 처리 분야에서도 많은 연구가 진행되고 있다. 많은 논문들이 사용하는 데이터도메인은 긍정 문장과 부정 문장 사이를 변화시키는 것이다. 본 연구에서는 한국어 영화리뷰 데이터 세트인 NSMC[2]를 이용한 감성 변화를 하는 문장생성에 대한 연구로 자연어 처리에서 좋은 성능을 보여주는 BERT[8]를 생성모델에 이용하였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.396-397
• /
• 2023

추천 시스템은 빅데이터 관련 기술과 알고리즘의 발달로 다양한 분야에서 사용되고 있다. 관광 산업도 예외는 아니다. 본 연구에서는 사용자들이 촬영한 사진을 기반으로 유사한 여행지를 추천하는 추천 시스템을 제안한다. 사용자가 입력한 이미지에서 언어적 특성과 비언어적 특성을 추출하고 이를 기반으로 유사한 이미지를 탐색하고, 이를 기반으로 사용자가 좋아할 다음 여행지를 추천한다. 사용자가 질의어를 입력하지 않고 이미지를 제공하여 추천이 이루어진다는 점과 사용자의실제 여행 여부를 이용해 모델의 성능을 평가했다는 점에서 연구의 의의가 있다.

• The Journal of the Convergence on Culture Technology
• /
• v.10 no.4
• /
• pp.607-612
• /
• 2024

Generative AI is a type of artificial intelligence technology that produces various types of data. With the success of ChatGPT, the generative AI market is blooming. As the generative AI market develops, generative AI is being applied in various industries. In this paper, we discuss the trends, applications, and directions for improvement. Currently, generative AI is trained on domain knowledge and data, and it is evolving towards Vertical AI. In the future, generative AI could be extended to AGI, which makes decisions and processes on its own like a human, to be used flexibly in various environments.

• Proceedings of the Korean Society for Information Management Conference
• /
• 2017.08a
• /
• pp.97-97
• /
• 2017

최근 연구 환경과 연구 패러다임이 데이터 중심으로 변화되고 있다. 특히, 공공 연구성과의 개방과 공유에 기반한 오픈 사이언스(Open Science)가 과학 연구의 글로벌 어젠더로 새롭게 부각되고 있다. OECD는 오픈 사이언스를 정책의제로 채택하고 있으며, 미국, 영국, 호주 등 세계 선진국에서는 공공자금이 투입된 연구과제로부터 생산된 연구데이터의 체계적인 관리와 쉬운 접근, 재사용을 통한 가치 창출을 위해 데이터 관리 계획(Data Management Plan)을 비롯한 오픈 연구데이터 정책을 적극적으로 시행하고 있다. 하지만 국내에서는 연구데이터를 공유 활용하기 위한 법제도적 기반과 관련 인프라가 아직 미흡한 실정이다. 이 연구에서는 오픈 연구데이터를 위한 세계 각국의 정책 동향을 소개한다. 그리고, 국가과학기술연구회 소속 22개 정부출연 연구기관과 국내 20개 대학의 연구자를 대상으로 조사한 연구데이터 생산, 관리, 활용 현황과 데이터 공유 활용을 위한 시사점과 개선방향을 살펴본다.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.19 no.4
• /
• pp.73-86
• /
• 2023

The purpose of this study is to prepare basic data that can be applied to the development of personalized programs in which chronic patients can actively participate in health care on their own, by analyzing the relationship between health literacy, level of metal health, and level of life health of patients with chronic diseases. For the study, the Korean Medical Panel's annual data(Version 2.1) was used, and 4,095 people aged 19 or older with chronic diseases and without disabilities were extracted, and frequency analysis, t-test, ANOVA, and chi-squared goodness of fit test, etc. were performed with IBM SPSS Statistics 26.0. As a result, it was found that the higher health literacy, the higher level of mental health and level of life health. In addition, the distribution between health literacy, level of mental health, and level of life health was found to be different from each other. Respondents with higher ability to health literacy tend to evaluate level of metal health and life health lower, and the rate of change in this trend was relatively higher than the rate of change in the tendency to evaluate level of mental health and life health higher in respondents with lower ability to health literacy.

• Journal of the Korean Society for information Management
• /
• v.34 no.3
• /
• pp.229-249
• /
• 2017

Open science projects are being actively carried out globally. Publishing the results of public research (publications and data) in digital format and enhancing access to these materials are getting more important. Various research support tools are being used to support open research, open access, open data, open peer review and open research performance evaluation. We analyzed research support services to prepare open science movement in Korea. Korea is not ready for research data management and research collaboration except open access and institutional repositories. It can be seen as an urgent matter to analyze these international open science research support services carefully and reflect them in research support policy and service guideline.