- This paper presents a recommendation module which provides preferable photo contents to the user from among the huge amount of photo contents in UMPC database. To extract the preferable photo to user, we use a hybrid approach that is combined with context and content-base approach using data mining concept. Using two vectors concerned with the user profile and the photo metadata, we can calculate the cosine similarity between them. The higher cosine similarity indicates that relevant photo content is more preferable. The experimental results showed that our proposed algorithm has high potential to give high satisfaction to the user.
Index Terms —user profile, data mining, similarity measure, smart phone, UMPC (Ultra-Mobile Person Computers) I.
Rphoto systems in a lot of fields. Most of them could show
mobile machine, it should be needed to personalize
recommendation system by considering a user preference [
A. Context descriptions
composed of two parts, human relations and keywords. The reason why we divide two parts in the user profile is that the human relations have relative important factors. A user preference in the user profile is represented as a vector of <features, weight>.
The photo metadata contains context and content information of the photo contents. Context information includes a time and location information. As we get the context information, we assign the dependent information such as light status and season information. Content information describes the background of focus of photo image. As the same manner with the user profile, we assign relative important factors to the photo metadata for the photo identification.
B. Data mining for recommendation of photo contents When one tries to seek specific photos from the UMPC database, one usually wants a system which automatically recommends photos with considering the user preference. To implementing the automatic recommendation system, we use the data mining methodology which can extract useful information (preferable photo) from UMPC database. In details, we adopt a hybrid approach which is combined with context and content base approach in the data mining methodology. Fig.1 shows the process of photo recommendation system using data mining concept.
Clean Transform Integrate Load
Algorithms (Similarity measure)
User
Visualization We define a user profile as a vector U = ( u1 , … un ), where ui means a user preference represented between -1 and 1. The value -1 indicates least preferred and 1 indicates most preferred. An example of user preference is as follows: User preference = {(smith, 0.5), (honeymoon, 0.9)}.
We also define a photo metadata as a vector P = ( w1,…,wn ), where wi is weight represented between -1 and 1. We assign this weight to photo metadata for representing the relative important factors. The value of 1 means more important factors and -1 means less important factors.
Similarity (U , P ) = =
<User profile>
Similarity (U , P ) = <Location> (20,30) </Location> <Person> smith </Person> <Person> chanmi </Person> <Event> music concert </Event> …
The format of output is Result = ( Photo_ID , 0.878 ). It means the user’s interest of the Photo_ID photo is 0.878.
context and content information with the user preference is preliminary crucial system in personalized Smart phone. As future work, for indicating the quality of recommending photo system, we will adopt the precision measure. As much as we