A fair scheduler using cloud computing for digital TV program recommendation system.

Saved in:

Bibliographic Details
Title:	A fair scheduler using cloud computing for digital TV program recommendation system.
Authors:	Chang, Jui-Hung¹ changrh@mail.ncku.edu.tw, Lai, Chin-Feng² cinfon@cs.ccu.edu.tw, Wang, Ming-Shi³ mswang@mail.ncku.edu.tw
Source:	Telecommunication Systems. Sep2015, Vol. 60 Issue 1, p55-66. 12p.
Subjects:	Cloud computing, Electronic program guides (Television), Television programs, Information processing, Recommender systems, K-nearest neighbor classification, K-means clustering
Abstract:	With hundreds of TV channels, a good TV program recommendation system can save time. Hadoop fair scheduler cloud computing is designed to make information processing and filtering effective and scalable. In cloud computing, computers are connected over a network and perform computation simultaneously; more computation power can be obtained by adding more computer nodes. In the present study, cloud computing is used to build a TV program recommendation system. A fair scheduler cloud structure is applied to improve the system performance. For program recommendation, the K-means recursive clustering algorithm is used for user clustering, the term frequency/inverse document frequency algorithm is applied for finding related popular programs, and k-nearest neighbor is used to recommend programs. Most TV program recommendation systems focus on providing a personal recommendation system. The proposed system also considers user groups and the program watching preferences of the majority. The proposed fair scheduler cloud-based architecture is scalable; a massive amount of information can be processed in real-time to obtain program recommendation results that can represent almost all users. [ABSTRACT FROM AUTHOR]
	Copyright of Telecommunication Systems is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database:	Engineering Source

Description
Abstract:	With hundreds of TV channels, a good TV program recommendation system can save time. Hadoop fair scheduler cloud computing is designed to make information processing and filtering effective and scalable. In cloud computing, computers are connected over a network and perform computation simultaneously; more computation power can be obtained by adding more computer nodes. In the present study, cloud computing is used to build a TV program recommendation system. A fair scheduler cloud structure is applied to improve the system performance. For program recommendation, the K-means recursive clustering algorithm is used for user clustering, the term frequency/inverse document frequency algorithm is applied for finding related popular programs, and k-nearest neighbor is used to recommend programs. Most TV program recommendation systems focus on providing a personal recommendation system. The proposed system also considers user groups and the program watching preferences of the majority. The proposed fair scheduler cloud-based architecture is scalable; a massive amount of information can be processed in real-time to obtain program recommendation results that can represent almost all users. [ABSTRACT FROM AUTHOR]
ISSN:	10184864
DOI:	10.1007/s11235-014-9921-4