earticle

영어

We developed a user’s viewing path similarity-based contents recommendation algorithm using LBS (Location Based Services). However, the previous research had a problem that it might recommend contents related with exhibits which users did not like because it divides an exhibition into the areas and recommends contents based on them. To solve this problem, we propose the service based on activity recognition using 3-axis accelerometer sensor. In this service, it is determined by analysis of user’s movements that the corresponding user is moving or viewing. Also, it measures the viewing time that the user spent on viewing exhibits and determines user’s location using LBS. It might recommend more suitable contents to the user's taste because it focuses on the exhibits which users actually watch long.