IMPROVEMENT OF PERSONALIZED DYNAMIC SERVICE USING INDEPENDENT COMPONENT ANALYSIS
A system of personalized dynamic service (PDS) in digital library (DL) based on independent component analysis (ICA)was proposed and discussed in detail in order to improve the quality of personalized service to readers. Meanwhile,architectures of general PDS system and the most important subsystem were introduced. The experiments showed that better effects of books topic classifying and readers interest clustering could be respectively achieved by employing ICA method, and a dynamic mapping relation that improved the quality of PDS, furthermore, could be adaptively generated along with the changes of readers personalized interests or books topics.
Independent component analysis Personalized dynamic service Text classification
QIANG PU QI-HE LIU GUO-WEI YANG
School of Computer Science and Engineering, UEST of China, Chengdu 610054, China
国际会议
2006 International Conference on Machine Learning and Cybernetics(IEEE第五届机器学习与控制论坛)
大连
英文
2611-2616
2006-08-13（万方平台首次上网日期，不代表论文的发表时间）