• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.07a
• /
• pp.611-612
• /
• 2021

매치 3게임에서 플레이테스팅 방법은 전통적으로 사람들을 이용하는 방법으로 지속되어 왔으며, 최근에는 딥러닝을 이용하는 방법으로서 게임의 장르적인 특성들을 고려해서 각 레벨에 대한 플레이 데이터를 이용한 지도학습 방법과 환경과 상황 그리고 보상을 통한 강화학습 방법들이 연구되고 있다. 본 논문에서는 매치 3게임에서 강화학습을 이용한 플레이테스팅의 향후 연구 방향성에 대해서 기준을 제시한다.

• The Journal of the Korea Contents Association
• /
• v.17 no.5
• /
• pp.234-242
• /
• 2017

This study selected 60 board games that have a high sales rate and awareness in the board game market, and analyzed 37 board games that were selected through the advice of experts. According to the analysis of general characteristics, there was the highest number of board games that more than 2 people could participate and people from ages 7 to 11 could use, and the most common play time was from 20 minutes to 30 minutes. Also, there was the largest number of board games produced in 2000s, and Germany was the most common producer of board games. Next, the content analysis showed that abstract strategy was the most common game genre, and cognitive domain was the most common in the development area. The analysis based on how to play the game showed that games that had to go through 4 stages were the most common. Card games were the most common form of game, group was the most common in organization form, and reaching goal was most common among result analysis method. According to the analysis of correlation by items, the number of people and work analysis had a statistical correlation, and the playing age, time, and genre had a correlation. The origin of the game and game genre were also correlated to each other, and game form, game genre, organization form, and result analysis had a statistical correlation as well. The purpose of this study is to analyze the board game in terms of structural characteristics and to provide a foundation for future research.

• Digital Contents
• /
• no.11 s.150
• /
• pp.84-91
• /
• 2005

현재온라인1인칭슈팅게임(FPS) 장르에서는PC방이용률부문상위권을달리고있는‘ 스페셜포스’의뒤를이어새롭게떠오르고있는차세대온라인FPS가있다. 바로‘ 서든어택’. 이게임은이미‘ 부천문화-IT 엑스포2005’와‘ 전주컴퓨터게임엑스포2005’등을거치며유저들의관심을집중시켰다. 최근에는동시접속자2만5,000명을돌파하는등출발도순조롭다. 전투의사실감, 다양한맵등기본에충실한게임으로평가받고있는서든어택을분석했다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2010.06a
• /
• pp.138-139
• /
• 2010

• Digital Contents
• /
• no.9 s.88
• /
• pp.62-67
• /
• 2000

인터넷을 통해 유통되는 디지털콘텐츠의 식별과 접근을 위한 고유식별체계로서 DOI(Digital Object Identifier)의 개발, DOI의 구문구조, DOI의 관리와 운영, DOI 메타데이터와 장르, DOI변환과 핸들 시스템을 소개하고 DOI의 국내 도입을 위한 DOI등록시스템, 변환시스템 검색시스템, INDECS 메타데이터를 이용한 디지털 콘텐츠 유통관리 시스템, DOI참조링크 시스템의 개념적 설계와 구축 내용을 기술한다.

• Cartoon and Animation Studies
• /
• s.27
• /
• pp.51-78
• /
• 2012

The types of cartoon market are classified with publishing cartoon(a cartoon magazine & comics) and webtoon. The revitalization of the cartoon market makes cartoonist create many cartoons. By studying many methods for the revitalization of the cartoon market, this paper argues the expanded methods of comics market which is a sort of publishing cartoon market. The expanded methods of comics market are two kinds, one is the revitalization of the comics market and the other is the creation of the comics market. This paper focuses on Genre-mixed Knowledge-Cartoon in order to extend the cartoon market. Also, After studying the Creation Proceed of cartoon market through Genre-mixed Knowledge-Cartoon, we would like to develope the New Creation Model of Cartoon Market. We selected three case(the Real Estate Agency expressed as Cartoon, Let's find an answer in sided figure blank, miraculous English grammar) for this study. With this, we analyzed the case that the matters for analysis is the essential particulars of plan-publishing-distribution's proceed. As a result, we found out the possibility of new cartoon market's creation through Genre-mixed Knowledge-Cartoon. For that reason, we was able to develop 'the New Creation Model of Cartoon Market through Genre-mixed Knowledge-Cartoon'. This paper provides the possibility about the New Creation Model of Cartoon Market through Genre-mixed Knowledge-Cartoon. With this, we will make many plans for creation of Genre-mixed Knowledge-Cartoons. Therefore, This plans will help cartoonists to create the Genre-mixed cartoons.

• Journal of Digital Convergence
• /
• v.12 no.6
• /
• pp.325-332
• /
• 2014

It is generally accepted that classification accuracy is affected by the number of learning documents, but there are few studies that show how this influences automatic text classification. This study is focused on evaluating the deviation-based classification model which is developed recently for genre-based classification and comparing it to other classification algorithms with the changing number of training documents. Experiment results show that the deviation-based classification model performs with a superior accuracy of 0.8 from categorizing 7 genres with only 21 training documents. This exceeds the accuracy of Bayesian and SVM. The Deviation-based classification model obtains strong feature selection capability even with small number of training documents because it learns subject information within genre while other methods use different learning process.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2015.05a
• /
• pp.533-536
• /
• 2015

Mobile music market is growing. However, services what are applied recently are inaccurate to recommend music that a user is worth to prefer. So, this paper suggests music recommend system. This system recommend music that users prefer analyzing music information and user's musical propensity and using collaborative filtering. This system classify genre and extract factors what can be get using STFT's ZCR, Spectral roll-off, Spectral flux. So similar musics are clustered by these factors. And then, after divide mood of music's lyric, it finally recommend music automatically using collaborative filtering.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2018.05a
• /
• pp.418-419
• /
• 2018

본 논문에서는 사용자의 상품에 대한 평점 정보와 상품의 컨텐츠 정보를 모두 이용하는 하이브리드 추천 모델에 대해서 논의한다. 기존 논문들과는 다르게, 본 논문은 추천의 정확도를 높이기 위해 사용자가 상품의 컨텐츠 (예를 들면, 영화의 장르 또는 상품의 카테고리 등) 에 가질 수 있는 선호도를 예측하고, 이를 추가적으로 활용할 수 있는 딥러닝 기반의 추천 모델을 제안한다. 실세계의 데이터를 이용해서 제안하는 방법의 우수성을 보인다.

• Journal of the Korea Society of Computer and Information
• /
• v.16 no.11
• /
• pp.17-24
• /
• 2011

Collaborative filtering system is the clustering about user is built and then based on that clustering results will recommend the preferred item to the user. However, building user clustering is time consuming and also once the users evaluate and give feedback about the film then rebuilding the system is not simple. In this paper, genre pattern of movie recommendation systems is being used and in order to simplify and reduce time of rebuilding user clustering. A Frequent pattern networks is used and then extracts user preference genre patterns and through that extracted patterns user clustering will be built. Through built the clustering for all neighboring users to collaborative filtering is applied and then recommends movies to the user. When receiving user information feedback, traditional collaborative filtering is to rebuild the clustering for all neighbouring users to research and do the clustering. However by using frequent pattern Networks, through user clustering based on genre pattern, collaborative filtering is applied and when rebuilding user clustering inquiry limited by search time can be reduced. After receiving user information feedback through proposed user clustering based on genre pattern, the time that need to spent on re-establishing user clustering can be reduced and also enable the possibility of traditional collaborative filtering systems and recommendation of a similar performance.