• The KIPS Transactions:PartB
• /
• v.11B no.5
• /
• pp.555-562
• /
• 2004

A genre or a style is another view of documents different from a subject or a topic. The style is also a criterion to classify the documents. There have been several studies on detecting a style of textual documents. However, only a few of them dealt with web documents. In this paper we suggest sets of features to detect styles of web documents. Web documents are different from textual documents in that Dey contain URL and HTML tags within the pages. We introduce the features specific to web documents, which are extracted from URL and HTML tags. Experimental results enable us to evaluate their characteristics and performances.

• Annual Conference of KIPS
• /
• 2022.11a
• /
• pp.432-434
• /
• 2022

우리는 전이 학습을 이용하여 원하는 특정 패션 스타일 분류기를 학습하였다. 패션 스타일 검색 결과물을 온라인 쇼핑몰과 연결하는 웹 서비스를 사용자에게 제공한다. 패션 스타일 분류기는 구글에서 이미지 검색을 통해 수집된 데이터를 이용하여 ResNet34[1]에 전이 학습하였다. 학습된 분류 모델을 이용하여 사용자 이미지로부터 패션 스타일을 17가지 클래스로 분류하였고 F1 스코어는 평균 65.5%를 얻었다. 패션 스타일 분류 결과를 네이버 쇼핑몰과 연결하여 사용자가 원하는 패션 상품을 구매할 수 있는 서비스를 제공한다.

• Annual Conference on Human and Language Technology
• /
• 2022.10a
• /
• pp.480-484
• /
• 2022

텍스트 분류는 입력받은 텍스트가 어느 종류의 범주에 속하는지 구분하는 것이다. 분류 모델에 있어서 좋은 성능을 나타내기 위해서는 충분한 양의 데이터 셋이 필요함을 많은 연구에서 보이고 있다. 이에 따라 데이터 증강기법을 소개하는 많은 연구가 진행되었지만, 실제로 사용하기 위한 모델에 곧바로 적용하기에는 여러 가지 문제점들이 존재한다. 본 논문에서는 데이터 증강을 위해 스타일 변환 기법을 이용하였고, 그 결과 기존 방법 대비 한국어 감성 분류의 성능을 높였다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2007.06b
• /
• pp.199-202
• /
• 2007

본 논문에서는 주어진 영상을 필터링하여 영상의 스타일을 제거하는 방법을 제시한다. 스타일이 제거된 영상은 영상 분류, 특징점 인식, 영상 분할 등의 다양한 용도에 쓰일 수 있다. 또한 원래 영상과 스타일이 제거된 영상을 비교하여 영상의 스타일을 유추할 수 있다. 본 논문에서는 이를 위해 주어진 영상에서 스타일 벡터를 계산한 후 계산된 스타일 벡터를 이용하여 영상에 양방향 필터링을 적용한다. 이 때 영상의 경계 부분에서 스타일을 효과적으로 분리하는 방법과 다중 해상 처리 방법을 적용하여 다양한 크기와 방향의 스타일을 찾아낸다. 그 결과 주어진 영상에서 다양한 크기와 방향의 스타일을 제거하고 영상의 중요한 내용만을 효과적으로 나타낸다.

• The Korean Journal of Applied Statistics
• /
• v.32 no.4
• /
• pp.573-591
• /
• 2019

Classification criteria for Korean alphabet (Hangul) fonts are undeveloped in comparison to numerical classification systems for Roman alphabet fonts. This study finds important features that distinguish typeface styles in order to help develop numerical criteria for Hangul font classification. We find features that determine the characteristics of the two different styles using a convolutional neural network to create a model that analyzes the learned filters as well as distinguishes between serif and sans-serif styles.

• Annual Conference on Human and Language Technology
• /
• 2020.10a
• /
• pp.64-68
• /
• 2020

텍스트 스타일 변환은 문장 내 컨텐츠는 유지하면서 문장의 스타일을 변경하는 것이다. 스타일의 정의가 모호하기 때문에 텍스트 스타일 변환에 대한 연구는 대부분 지도 학습으로 진행되어왔다. 본 논문에서는 병렬 데이터 구축이 되지 않은 데이터를 학습하기 위해 비병렬 데이터를 이용하여 스타일 변환을 시도한다. 트랜스포머 기반의 문장 생성기를 이용하여 문장을 생성하고, 해당 스타일을 분류하는 판별기로 이루어진 모델을 제안한다. 제안 모델을 통해, 감정 변환의 성능은 정확도(Accuracy) 56.9%, self-BLEU 0.393(긍정→부정), 0.366(부정→긍정), 유창성(fluency) 798.23(긍정→부정), 1381.05(부정→긍정)을 보였다. 본 연구는 비병렬 데이터에 대해 스타일 변환을 적용함으로써, 병렬 데이터가 없는 다양한 도메인에도 적용가능 할 것이다.

• The Journal of the Korea Contents Association
• /
• v.20 no.2
• /
• pp.127-140
• /
• 2020

Since the first episode of (1995) by Pixar, a world leading animation company, 3D animation has been focused on realistic motion and rendering techniques. However, in 2018, 3D animation was released, with unique backgrounds created through illustration techniques and dynamic movements of characters that seemed to be produced by hand rather than computers. It shows a lot of difference from other 3D animations. In this study, I analyzed 's new production techniques and expressions into two categories, first, the use of old comics techniques, and second, other factors that made the animation stand out. in 3D animation market focused on realistic motion and rendering techniques can have positive implications in terms of expanding animation diversity. This study is expected to be used as academic or research data for researchers studying new production techniques in related fields.

• Journal of Digital Convergence
• /
• v.17 no.11
• /
• pp.157-162
• /
• 2019

This thesis analyzed the intermediation and correlation of positive humor style and negative humor style through an entertainment program broadcasted on SBS. For the theoretical background, the Humor Style Questionnaire(HSQ) developed by Martin et al., was selected. As the research methods, first, after classifying the types of humor style of members of , this study analyzed how the positive humor style and negative humor style would intermediate the formation of humor, and also the correlation of humor style of members. The types of positive humor style and negative humor style shown in were balanced in 4:4, which was classified in accordance with age, career experience, and power. The mediation of humor formation occurred at the point where humors confronted. The humor style had the correlation with twist.

• Therapeutic Science for Rehabilitation
• /
• v.13 no.2
• /
• pp.69-84
• /
• 2024

Objective : This study aimed to categorize the lifestyles of older adults into two types - healthy and unhealthy, and use machine learning to identify the personal values that influence these lifestyles. Methods : This cross-sectional study targeting middle-aged and older adults (55 years and above) living in local communities in South Korea. Data were collected from 300 participants through online surveys. Lifestyle types were dichotomized by the Yonsei Lifestyle Profile (YLP)-Active, Balanced, Connected, and Diverse (ABCD) responses using latent profile analysis. Personal value information was collected using YLP-Values (YLP-V) and analyzed using machine learning to identify the relative importance of personal values on lifestyle types. Results : The lifestyle of older adults was categorized into healthy (48.87%) and unhealthy (51.13%). These two types showed the most significant difference in social relationship characteristics. Among the machine learning models used in this study, the support vector machine showed the highest classification performance, achieving 96% accuracy and 95% area under the receiver operating characteristic (ROC) curve. The model indicated that individuals who prioritized a healthy diet, sought health information, and engaged in hobbies or cultural activities were more likely to have a healthy lifestyle. Conclusion : This study suggests the need to encourage the expansion of social networks among older adults. Furthermore, it highlights the necessity to comprehensively intervene in individuals' perceptions and values that primarily influence lifestyle adherence.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.5
• /
• pp.501-508
• /
• 2023

This research endeavors to categorize a diverse range of hairstyles for both men and women in South Korea using hair images and subsequently generate 3D hair models based on this classification. The classification process relies on prominent visual features, resulting in the division of hairstyles into 14 distinct categories, including six styles for men and eight styles for women. By accurately matching the most appropriate hairstyle to the given hair image, the study aims to provide recommendations for the necessary hair models required for metaverse authoring tools, thus enabling realistic hair styling. This capability can be effectively utilized on platforms like metaverse, allowing users to seamlessly find and apply the 3D hair model that closely resembles their remotely captured or pre-existing hair images. Through this innovative approach, users can be presented with the most similar 3D hair model, enhancing their virtual hairstyling experience.