Proceedings of the IEEK Conference (대한전자공학회:학술대회논문집)

The Institute of Electronics and Information Engineers (대한전자공학회)
권호 표지

Development of Prototype Target Advertisement System Using a Viewer's Profile Reasoning with Multistage Classifier

다단계 분류기의 사용자 프로파일 추론을 통한 프로토타입 표적 광고 시스템 개발

  • Kim, Mun-Jo (Multimedia Track Engineering Department, Information and Communications University) ;
  • Lee, Bum-Shik (Multimedia Track Engineering Department, Information and Communications University) ;
  • Lim, Jeong-Yeon (Multimedia Track Engineering Department, Information and Communications University) ;
  • Kim, Mun-Churl (Multimedia Track Engineering Department, Information and Communications University) ;
  • Lee, Hee-Kyung (Broadcasting Media Research Group in Digital Broadcasting Research Division, Electronics and Telecommunications Research Institute) ;
  • Lee, Han-Kyu (Broadcasting Media Research Group in Digital Broadcasting Research Division, Electronics and Telecommunications Research Institute)
  • 김문조 (한국정보통신대학교 공학부 멀티미디어트랙) ;
  • 이범식 (한국정보통신대학교 공학부 멀티미디어트랙) ;
  • 임정연 (한국정보통신대학교 공학부 멀티미디어트랙) ;
  • 김문철 (한국정보통신대학교 공학부 멀티미디어트랙) ;
  • 이희경 (한국전자통신연구원 디지털방송연구단 방송미디어연구그룹) ;
  • 이한규 (한국전자통신연구원 디지털방송연구단 방송미디어연구그룹)
  • Published : 2005.11.26
Download PDF
⟨ Previous Next ⟩

Abstract

In the uni-directional broadcasting environments, almost TV programs are scheduled depending on the viewers' popular watching time, and the advertisement contents in these TV programs are mainly arranged by the popularity and the ages of the audience. However, the advertisement programs which support the TV programs the audiences want are not served to the appropriate audiences efficiently. In this paper, we propose the prototype of target advertisement system for the appropriate distribution of the advertisement contents. The proposed target advertisement system estimates the audience's profile without private information and provides the target advertisement contents by using his/her inferred profile. And we show the accuracy of the proposed algorithm, Multistage Classifier, for the target advertisement system and the implementation of our target advertisement system.

Keywords