CCL

Összesen 1 találat.
#/oldal:
Részletezés:
Rendezés:

1.

001-es BibID:BIBFORM065978
035-os BibID:(cikkazonosító)30091655
Első szerző:Azodinia, Mohammadreza (informatikus)
Cím:A novel method to increase the performance of recommender systems using a parallel CBIR approach / Mohammad Reza Azodinia, András Hajdu
Dátum:2016
ISSN:1947-5500
Megjegyzések:Recommender systems are among the most valuable components that can improve the user experience with a more general system considerably when embedded inside that system. The main objective of recommender systems is to reduce the complexity for users, sifting through very large datasets containing information about some items and selecting the most desired ones. In order to provide the users with such items, the recommender system should consider as much related information as possible in taking the decisions about the desirability of the items. One of the key features that has a major effect on people's point of view towards an item is the image which is assigned to that item. Despite the large number of studies carried out around the notion of the recommender systems, images have not gained a fair amount of attention which has derived us to conduct this study. In this paper we have proposed a novel method to effectively consider the images of the items in the recommender systems to improve the quality of the recommendations. The proposed method is implemented and tested on a significant dataset, and the result prove the effectiveness of our method.
Tárgyszavak:Műszaki tudományok Informatikai tudományok idegen nyelvű folyóiratközlemény külföldi lapban
Keywords-recommender system
Content Based Image Retrieval
Parallel CBIR
Megjelenés:International Journal of Computer Science and Information Security. - 14 : 10 (2016), p. 205-213. -
További szerzők:Hajdu András (1973-) (matematikus, informatikus)
Pályázati támogatás:NK101680
OTKA
TAMOP-4.2.2.C- 11/1/KONV2012-0001
TÁMOP
TAMOP-4.2.2.A- 11/1/KONV2012-0045
TÁMOP
TÁMOP 4.2.4. A/2-11-1- 2012-0001
TÁMOP
Internet cím:Intézményi repozitóriumban (DEA) tárolt változat
Borító:
Rekordok letöltése1