MOUSAI : a music recommendation scheme for group users in ubiquitous computing environments = 유비쿼터스 환경에서 그룹 사용자를 대상으로 하는 음악 추천 기법a music recommendation scheme for group users in ubiquitous computing environments

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 372
  • Download : 0
Ubiquitous computing environments live out here in the real world with people. One of key issues in ubiquitous computing environments is to enable users to be free from distractions by physical computing devices or intrusions from software services in our everyday life. The environments are shared by group of users. Currently available recommendation schemes especially on Web or ubiquitous computing environments have limitations to provide accurate group-aware recommendations incorporating environmental factors. To overcome the limitation, we propose a music recommendation scheme for ubiquitous computing environments. We focus on user inclination, group-awareness, and environment factors. Our proposed scheme is composed of three steps. In the first step, we calculate average of feedback values based on current environment condition. In the second step, we calculate user inclination with history information of the user. With the user inclination value, we search preferences of users who share similar tastes in order to diverse music list. Lastly, we resolve conflicts among preference of users who are in the same space. We leverage user inclination value and preference value, which is calculated in the first step to recommend music. Simulation results show that our proposed scheme incorporates the user precision and has the higher precision value rather than extended MusicFX scheme.
Lee, Man-Jai이만재
한국정보통신대학교 : 공학부,
Issue Date
392352/225023 / 020013984

학위논문(석사) - 한국정보통신대학교 : 공학부, 2004, [ v, 37 p. ]


MOUSAI; Music recommendation scheme; Ubiquitous computing environments

Appears in Collection
School of Engineering-Theses_Master(공학부 석사논문)
Files in This Item
There are no files associated with this item.


  • mendeley


rss_1.0 rss_2.0 atom_1.0