• Journal of the Korea Society of Computer and Information
• /
• v.28 no.8
• /
• pp.39-48
• /
• 2023

This study was conducted to provide a solution to the problem of sizing errors occurring in online purchases due to discrepancies and non-standardization in clothing sizes. This paper discusses an implementation approach for a machine learning-based recommender system capable of providing personalized sizes to online consumers. We trained multiple validated collaborative filtering algorithms including Non-Negative Matrix Factorization (NMF), Singular Value Decomposition (SVD), k-Nearest Neighbors (KNN), and Co-Clustering using purchasing data derived from online commerce and compared their performance. As a result of the study, we were able to confirm that the NMF algorithm showed superior performance compared to other algorithms. Despite the characteristic of purchase data that includes multiple buyers using the same account, the proposed model demonstrated sufficient accuracy. The findings of this study are expected to contribute to reducing the return rate due to sizing errors and improving the customer experience on e-commerce platforms.

• 한국어정보학회:학술대회논문집
• /
• 2016.10a
• /
• pp.44-48
• /
• 2016

오늘날 폰트를 디자인하는데 주로 사용되는 외곽선 방식은 글자의 크기를 손쉽게 변경할 수 있으나 글자의 굵기나 스타일을 변화시키려면 다시 수작업을 통해서 디자인을 변경해야 한다. 이를 보완하기 위한 프로그래머블 폰트인 메타폰트는 매개변수를 사용하여 글자의 변화가 매우 용이하다. 하지만 메타폰트는 프로그래밍 언어이므로 메타폰트에 대한 선행학습이 필요하여 폰트 디자이너에게 사용되지 않았다. 따라서 본 논문에서는 폰트 디자이너에게 익숙한 외곽선 방식에 편집기를 제공하면서 글자의 스타일에 대한 변화를 메타폰트에서 처리하여 다양한 폰트를 파생할 수 있는 한글 외곽선 폰트 시스템을 제안한다. 이를 위하여 본 시스템에서는 외곽선 방식의 폰트를 제작할 수 있도록 하는 웹 외곽선 폰트 편집기를 구현하였으며 외곽선 방식의 폰트를 메타폰트로 변환하는 UFO2mf를 구현하였다. 본 논문에서 제안하는 폰트 시스템은 기존 외곽선 방식의 스타일 변화에 대한 수고를 덜어줄 수 있을 것으로 기대한다.

• Annual Conference on Human and Language Technology
• /
• 2016.10a
• /
• pp.44-48
• /
• 2016

오늘날 폰트를 디자인하는데 주로 사용되는 외곽선 방식은 글자의 크기를 손쉽게 변경할 수 있으나 글자의 굵기나 스타일을 변화시키려면 다시 수작업을 통해서 디자인을 변경해야 한다. 이를 보완하기 위한 프로그래머블 폰트인 메타폰트는 매개변수를 사용하여 글자의 변화가 매우 용이하다. 하지만 메타폰트는 프로그래밍 언어이므로 메타폰트에 대한 선행학습이 필요하여 폰트 디자이너에게 사용되지 않았다. 따라서 본 논문에서는 폰트 디자이너에게 익숙한 외곽선 방식에 편집기를 제공하면서 글자의 스타일에 대한 변화를 메타폰트에서 처리하여 다양한 폰트를 파생할 수 있는 한글 외곽선 폰트 시스템을 제안한다. 이를 위하여 본 시스템에서는 외곽선 방식의 폰트를 제작할 수 있도록 하는 웹 외곽선 폰트 편집기를 구현하였으며 외곽선 방식의 폰트를 메타폰트로 변환하는 UFO2mf를 구현하였다. 본 논문에서 제안하는 폰트 시스템은 기존 외곽선 방식의 스타일 변화에 대한 수고를 덜어줄 수 있을 것으로 기대한다.

• Journal of Korean Home Economics Education Association
• /
• v.31 no.3
• /
• pp.1-21
• /
• 2019

The purpose of this study is to develop a 'Healthy Couple Relationship' curriculum(plan) for high school home economics based on backward design. In this study, the content elements of 'Healthy Couple Relationship' were extracted through literature analysis, and the need for contents of 'Healthy Couple Relationship' was surveyed in 197 families of home economics teachers and 154 high school students. Based on this, the 'Healthy Couple Relationship' curriculum(plan) of high school home economics curriculum was developed as the backward design, and it was verified by the expert group. The results are as follows: First, when measured on a 5-point Likert scale, the mean scores of the need for content elements of 'Healthy Couple Relationship' was 4.39 for teachers, and 4.02 for students, respectively. The content elements of 'understanding dating violence' was 4.70 for teachers and 4.19 for students. Second, the developed 'Healthy Couple Relationship' curriculum consists of two templates, one for each unit, including curriculum goals, unit composition and unit goals, 8 learning subjects and content elements, evaluation plans including 24 lesson plans. In this study, it is meaningful to propose a "Healthy Couple Relationship" curriculum as an elective course in high school home economics curriculum in preparation for the high school credit system, and to lay the foundations for opening elective courses.

• Journal of Korean Home Economics Education Association
• /
• v.33 no.3
• /
• pp.65-84
• /
• 2021

In this study, a program was developed and implemented for middle school students in the 'Healthy Family Relations' of the home economics based on design thinking process. The purpose was to investigate whether a significant difference is displayed in terms of empathy ability improvement among middle school students. For this purpose, a "Wise 'stay-at-home' life" program comprised of five class sessions was developed based on design thinking process. The program was implemented to male and female students in the second year of middle school, and students' empathy ability was examined by a pre- and post-test comparison. As a result, the developed program was found to have generated a significant improvement in cognitive empathy among middle school students. In addition, the students' satisfaction with the class was generally positive. In particular, many students mentioned that they were interested in activities such as 'empathizing through Instagram' and 'creating a sub-character'. However, there also was an opinion that the lesson activities were difficult to complete due to the lack of time and restrictions on cooperative activities due to COVID-19. In this research, we developed a program that can be used in both face-to-face and non-face-to-face situations in order to flexibly deal with situations where the learning environment changes due to COVID-19. And this research is significant particularly in that it confirmed that home economics have a positive influence on improving middle school students' empathy ability, particularly the cognitive factor of empathy.

• Archives of design research
• /
• v.16 no.4
• /
• pp.385-394
• /
• 2003

An investigation by KRNIC (Korea Network Information Center) on the real state of usage of internet has shown that 96.9％ of children investigated had experiences of using internet. Especially the firstly ranked item that had been answered by children as a necessity of internet was 'Studying to solve tasks' rated by 83.9％. As seen from the research result, the need as a homework sonics is actually so dominant that it cannot be ignored when considering the profitability at the area of education contents, but any profound research has not been accomplished yet. Internet has been positioned as a more effective and fruitful learning tool, and also all activities done by users for exploring informations and choosing learning items under the on-line circumstances are based on the successive mutual reactions between users and computers. Up to now much of the web based learning circumstances has been introducing the User Interface using metaphor, and the same is found dominantly from the sites for children. But in spite of the availability of metaphor mentioned above the current status is much lack of profound researches about metaphor interface; and what is more, in the case of the site for elementary school students the gap of the ability recognizing metaphor is very large between lower classes and higher classes according to the degree of mental growth but that is used to be simply ignored, then a common concept is adapted to interface for all grades of classes and moreover for infant and kindergarten without any objections. Based on foregoing problems this research has put the main focus on the groping and presenting desirable directions on the prospect design of interface for children-oriented sites by analyzing the status of practical usage of metaphor interface in the field of the sites for children-oriented learning sites with concentration upon homework supporting domains.

• Journal of Broadcast Engineering
• /
• v.27 no.1
• /
• pp.133-145
• /
• 2022

Compared to the continuously increasing dog population and industry size in Korea, systematic analysis of related data and research on breed classification methods are very insufficient. In this paper, an automatic breed classification method is proposed using deep learning technology for 14 major dog breeds domestically raised. To do this, dog images are collected for deep learning training and a dataset is built, and a breed classification algorithm is created by performing transfer learning based on VGG-16 and Resnet-34 as backbone networks. In order to check the transfer learning effect of the two models on dog images, we compared the use of pre-trained weights and the experiment of updating the weights. When fine tuning was performed based on VGG-16 backbone network, in the final model, the accuracy of Top 1 was about 89% and that of Top 3 was about 94%, respectively. The domestic dog breed classification method and data construction proposed in this paper have the potential to be used for various application purposes, such as classification of abandoned and lost dog breeds in animal protection centers or utilization in pet-feed industry.

• Smart Media Journal
• /
• v.13 no.4
• /
• pp.23-32
• /
• 2024

Large-scale fires and their consequential damages are becoming increasingly common, but confidence in fire detection systems is waning. Recently, widely-used chemical fire detectors frequently generate lots of false alarms, while video-based deep learning fire detection is hampered by its time-consuming and expensive nature. To tackle these issues, this study proposes a fire detection model utilizing an autoencoder approach. The objective is to minimize false alarms while achieving swift and precise fire detection. The proposed model, employing an autoencoder methodology, can exclusively learn from normal data without the need for fire-related data, thus enhancing its adaptability to diverse environments. By amalgamating data from five distinct sensors, it facilitates rapid and accurate fire detection. Through experiments with various hyperparameter combinations, the proposed model demonstrated that out of 14 scenarios, only one encountered false alarm issues. Experimental results underscore its potential to curtail fire-related losses and bolster the reliability of fire detection systems.

• Proceedings of The KACE
• /
• 2017.08a
• /
• pp.25-28
• /
• 2017

웹 2.0시대의 도래는 데이터의 소유자나 독점자 없이 누구나 손쉽게 데이터를 생산하고 공유할 수 있고, 서비스 받을 수 있는 환경이 마련되었다. 인터넷의 급속한 발전으로 인해 스마트 교육시장이 유망 분야로 주목받는 가운데 교육현장에서도 스마트 러닝에 대한 관심도 또한 높아지고 있다. 기존의 데스크톱, 태블릿 PC를 통해 학습을 하던 환경에서 벗어나 이제는 스마트폰을 기반으로 하는 스마트 러닝이 교육환경을 보편적으로 접하게 되었다. 본 연구에서는 사용자 경험의 UX(User eXperience) 디자인을 바탕으로 어떠한 환경에서도 스마트 러닝이 가능한 웹사이트를 워드프레스 플랫폼으로 구현하고자 한다. 또한 본 웹사이트를 다양한 디바이스에서 테스트를 통해 스마트 러닝이 가능한 환경인지를 검증해 본다.

• 한국HCI학회:학술대회논문집
• /
• 2007.02b
• /
• pp.327-332
• /
• 2007

모바일폰의 컨버전스가 가속화됨에 따라 사용자가 습득해야 할 정보량이 증가하였고, 사용자들이 이를 이용하기 위하여 학습과 숙련의 과정을 거쳐야 하는 부담이 발생하게 되었다. 모바일폰의 주 사용자층인 20-40대 외에 10대와 50대 이상의 이동전화 이용률이 꾸준히 증가하여 실버폰과 키즈폰 시장이 형성될 조짐을 보이고 있지만, 제조사에서는 획일적인 인터페이스 디자인만을 제공하여 다양한 사용자 층의 요구와도 서로 맞지 않고 있다. 이에 본 연구에서는 모바일폰의 휴먼인터페이스 요소 중 메뉴요소에 해당하는 메인메뉴의 네비게이션 방식에 중점을 두어 각 사용자 유형별로 사용성을 측정하였다. 국내외 모바일폰 제조사에서 2006년 출시된 제품에서 메인메뉴 네비게이션 방식을 추출하여 8가지로 분류하였으며, 이를 토대로 플래시 기반의 시뮬레이터를 제작하여 사용성 측정에 이용하였다. 모바일 사용성 평가를 위한 요인을 중심으로 10대부터 60대 이상의 다양한 사용자를 대상으로 시뮬레이터 사용을 관찰하여 분석하였으며 또한 기존에 사용하고 있는 모바일폰 기종을 고려하여 설문지로 사용성에 대한 만족도를 평가하는 방식도 병행하였다. 본 연구에서는 사용자 유형별로 사용성이 높은 인터페이스를 선별하고 사용자의 개성과 선호도를 고려한 선택적인 UI 개발방향을 제안하였다.