• Annual Conference of KIPS
• /
• 2019.10a
• /
• pp.1125-1128
• /
• 2019

사용자가 인터넷을 사용할 때 화면에 표시되는 텍스트나 그래픽 등을 웹 문서라고 하며 HTML5는 웹 문서를 제작하는 표준 언어의 일종이다. HTML5 중에서 web storage는 사용자가 인터넷을 통한 서비스를 받을 때 데이터를 저장하기 위한 기능으로 키와 값의 형태로 저장한다. web storage는 서버 측에서 사용되는 session storage와 클라이언트에서 사용되는 local storage가 있다. local storage 사용 시 데이터를 클라이언트에 평문 형태로 저장하며 만료 기간 없이 영구적인 특징을 갖고 있다. 이러한 특징은 공격자로부터 XSS 등의 공격에서 저장된 데이터의 접근 및 수정 그리고 탈취할 수 있어 공격자의 의도에 따라 데이터 가공 및 재사용이 가능하다는 문제가 있다. 보안 취약점 문제를 해결하기 위한 최근 연구들은 local storage에 저장된 데이터들을 암호화하여 기밀성을 높였다. 그러나 데이터 암호화를 사용하려면 잦은 암호 입력이나 온라인에서만 사용할 수 있다는 또 다른 문제점을 가지고 있다. 기존 보안 취약점 문제와 기존 연구의 문제점을 동시에 해결하기 위해 운영체제 사용자 정보와 기기의 정보를 활용하여 암호화에 필요한 사용자 인증을 자동화하였으며 검증을 위해 코드를 구현하고 테스트 하였다.

• Annual Conference of KIPS
• /
• 2012.11a
• /
• pp.619-622
• /
• 2012

본 연구에서는 키넥트(Kinect) 센서를 통해 수화 동작에서 손의 좌표와 이동방향을 추출하여 속성으로 하고, 데이터 마이닝의 분류 기법을 통해 수화를 인식하여 그 결과를 한글 텍스트로 번역해주는 소프트웨어를 개발한다. 제안 방법의 1단계에서는 0.05초 단위로 추출한 손의 좌표만을 속성으로 한다. 2단계에서는 개개인의 특성 및 화면상의 위치와 같은 요소에 따라 좌표 값이 달라지기 때문에, 손의 움직임에서 변위를 추출하여 손이 움직이는 방향을 속성으로 한다. 하지만 비슷한 방향으로 움직이는 수화가 있을 경우 수화의 구분이 어려우므로 3단계에서는 손의 좌표, 방향 두 가지를 분류하는 속성으로 사용한다. 향후 연구 방향은 수화의 중요한 요소인 손의 위치를 속성으로 추가시키고, 데이터 마이닝의 부스팅(Boosting) 기법을 적용하여 인식률을 높이는 것이다.

• The Journal of the Korea Contents Association
• /
• v.18 no.12
• /
• pp.682-697
• /
• 2018

The purpose of this study is to examine the characteristics and functions of radio media and its imprecations. In doing so, the researcher attempted to analyze the text of the radio documentary, which illuminated "Seosan Sim's Sorigil," Pansori Jung-go-je. The analysis showed that radio, a broadcasting medium, functions as a sound storage medium by utilizing elements such as sound, narration, and dramatic reenactment. Second, the radio media enabled to record the upbringing of a person through an oral interview. Finally, the radio medium plays a role in promoting the sound of Pansori academically. This study confirms that the radio medium functions as a means of recording and ascertaining Pansori, a traditional art culture and an intangible cultural heritage, by utilizing the unique characteristics of sound storage media.

• Journal of Digital Convergence
• /
• v.17 no.11
• /
• pp.517-522
• /
• 2019

In many businesses, chatbots enhance the user experience by providing the most immediate and direct feedback to user questions. The area of use of chatbots is growing. In this study, the three types of chatbot definition, command method, function, and platform are classified according to their distinct factors. In the process, the functional delimiter element is necessary for the Chatbot UX, which is a key technical element of the functional part of pattern recognition, natural language processing, semantic web, text mining, and context-aware computing. However, the limitations at this stage were also known. Based on this, we analyzed the chatbot's UX elements for Facebook, Skype, Telegram, and Google Assistant for a better user experience. Basic UI elements such as cards, quick response, command, and application of persistent menus are needed as user experience elements.

• The Journal of Information Systems
• /
• v.29 no.4
• /
• pp.171-191
• /
• 2020

Purpose The study aims to compare the online review writing behavior of users in China and the United States through text mining on online reviews' text content. In particular, existing studies have verified that there are differences in online reviews between different cultures. Therefore, the purpose of this study is to compare the differences between reviews written by Chinese and American tourists by analyzing text contents of online reviews based on cultural theory. Design/methodology/approach This study collected and analyzed online review data for hotels, targeting Chinese and US tourists who visited Korea. Then, we analyzed review data through text mining like sentiment analysis and topic modeling analysis method based on previous research analysis. Findings The results showed that Chinese tourists gave higher ratings and relatively less negative ratings than American tourists. And American tourists have more negative sentiments and emotions in writing online reviews than Chinese tourists. Also, through the analysis results using topic modeling, it was confirmed that Chinese tourists mentioned more topics about the hotel location, room, and price, while American tourists mentioned more topics about hotel service. American tourists also mention more topics about hotels than Chinese tourists, indicating that American tourists tend to provide more information through online reviews.

• Journal of Platform Technology
• /
• v.8 no.1
• /
• pp.33-40
• /
• 2020

The purpose of this study is to identify factors in selecting the elective ICT utilization lecture and to find positive and negative elements of the lecture through conducting topic modeling analysis of text mining of the narrative lecture evaluation. In order to do so, from pre-processing of data, keyword frequency analysis to wordcloud visualization and topic modeling analysis have been conducted from 'reasons of selecting the lecture,' 'improvements to be made on the lecture,' and 'what I liked about the lecture' categories regarding the ICT utilization lecture which was opened in the second semester of 2019 at M University. The analysis results show that students mostly registered for the ICT utilization lecture at M University to obtain a certificate and the fact being certified and taking the lecture can be done simultaneously is a positive element of taking the lecture. On the other hand, negative element included inconvenience of the classroom setting environment.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.5
• /
• pp.203-210
• /
• 2022

As more and more research and companies use health care data, efforts are being made to vitalize health care data worldwide. However, the system and format used by each institution is different. Therefore, this research established a basic model to classify text data onto multiple institutions according to the type of the future by establishing a basic model to classify the types of medical records of the EEG Report. For EEG Report classification, four deep learning-based algorithms were compared. As a result of the experiment, the ANN model trained by vectorizing with One-Hot Encoding showed the highest performance with an accuracy of 71%.

• The Journal of the Convergence on Culture Technology
• /
• v.8 no.6
• /
• pp.327-332
• /
• 2022

The purpose of this study was to analyze the type of endpapers in Korean picturebooks that won the Bologna Ragazzi Award. The endpapers were classified by three standards: identities between front endpapers and back endpapers, type of arts, and type of contents. As results, picturebooks with identities between front endpapers and back endpapers were slightly more than ones with unidentities. Most of art types were illustrated, followed by patterned and plain. In addition, the peritextual contents were found to be the most frequently used content type in endpapers. The results showed that the most endpapers of the Korean picturebooks that won the Bologna Ragazzi Award were related to the text contents, which suggests the important roles of endpapers in picturebook activities.

• Journal of Fashion Business
• /
• v.27 no.4
• /
• pp.115-124
• /
• 2023

This study reviewed hanbok terms emerging in academic research and media fields to conceptualize hanbok terms. Terms of hanbok were collected through RISS and Bigkinds by field. Results of textming using Textom were as follows. First, a total of 17 hanbok terms appeared in the field of academic research and a total of 41 hanbok terms appeared in the field of media, showing a difference. Fourteen terms, including hanbok, traditional hanbok, traditional clothing, daily hanbok, modernized hanbok, fashion hanbok, fusion hanbok, Shinhanbok, ready-made hanbok, luxury hanbok, women's hanbok, and children's hanbok, were hanbok terms that appeared in both academic and media fields. Second, the appearance of hanbok terms was examined based on five terms: traditional hanbok, daily hanbok, modernized hanbok, fusion hanbok, and Shinhanbok, which differed in the appearance of hanbok terms between academic research and media. Traditional hanbok and daily hanbok terms steadily appeared in both academic research and media, with modernized hanbok and fusion hanbok appearing mainly in the media and Shinhanbok in the academic research fields. Results of this studys confirmed that there were differences in terms of hanbok used between academic research and media fields.

• Annual Conference on Human and Language Technology
• /
• 2022.10a
• /
• pp.238-244
• /
• 2022

감정 분석은 텍스트에 표현된 인간의 감정을 인식하여 다양한 감정 유형으로 분류하는 것이다. 섬세한 인간의 감정을 보다 정확히 분류하기 위해서는 감정 유형의 분류가 무엇보다 중요하다. 본 연구에서는 사전 학습 언어 모델을 활용하여 우리말샘의 감정 어휘와 용례를 바탕으로 기쁨, 슬픔, 공포, 분노, 혐오, 놀람, 흥미, 지루함, 통증의 감정 유형으로 분류된 감정 말뭉치를 구축하였다. 감정 말뭉치를 구축한 후 성능 평가를 위해 대표적인 트랜스포머 기반 사전 학습 모델 중 RoBERTa, MultiDistilBert, MultiBert, KcBert, KcELECTRA. KoELECTRA를 활용하여 보다 넓은 범위에서 객관적으로 모델 간의 성능을 평가하고 각 감정 유형별 정확도를 바탕으로 감정 유형의 특성을 알아보았다. 그 결과 각 모델의 학습 구조가 다중 분류 말뭉치에 어떤 영향을 주는지 구체적으로 파악할 수 있었으며, ELECTRA가 상대적으로 우수한 성능을 보여주고 있음을 확인하였다. 또한 감정 유형별 성능을 비교를 통해 다양한 감정 유형 중 기쁨, 슬픔, 공포에 대한 성능이 우수하다는 것을 알 수 있었다.