DocumentCode :
2407793
Title :
Automatic classification of deep web databases with simple query interface
Author :
Xian, Xuefeng ; Zhao, Pengpeng ; Fang, Wei ; Xin, Jie ; Cui, Zhiming
Author_Institution :
Inst. of Intell. Inf. Process. & Applic., Soochow Univ., Suzhou, China
fYear :
2009
fDate :
15-16 May 2009
Firstpage :
85
Lastpage :
88
Abstract :
Deep Web database classify is a key operation in organizing Deep Web resources. We address the problem of identifying the domain of Web databases with simple query interface. The existing methods can not effectively classify this type of Web databases, to solve this problem, we propose an new framework that can automatically and accurately classify Web databases with simple query interface based on probing query. The core of this framework is a domain specific classifier(DSC). DSC is constructed by using the features that can be easily extracted from advanced query interfaces(forms) in domain. According to the similar relation among result schemas, interface schemas and global schemas of Web database, Based on its result schemas, a new Web database with simple query interface can be classified by DSC. Experiments running on real structured Web databases collected from the Internet show that our provides an effective and scalable solution for classifying Web databases with simple query interface.
Keywords :
Internet; pattern classification; query processing; Internet; Web database; Web resource; automatic classification; domain specific classifier; simple query interface; Application software; Automation; Computer industry; Data mining; Deductive databases; Image databases; Information retrieval; Internet; Mechatronics; Spatial databases; component; deep web; probing query; result schema; simple query interface;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Industrial Mechatronics and Automation, 2009. ICIMA 2009. International Conference on
Conference_Location :
Chengdu
Print_ISBN :
978-1-4244-3817-4
Type :
conf
DOI :
10.1109/ICIMA.2009.5156566
Filename :
5156566
Link To Document :
بازگشت