A Deep Web Query Interfaces Classification Method Based on Neural Network

摘要

This paper proposes a new approach for classificationfor query interfaces of Deep Web, which extracts features from theform's text data on the query interfaces, assisted with the synonymlibrary, and uses radial basic function neural network (RBFNN)algorithm to classify the query interfaces. The applied RBFNN is akind of effective feed-forward artificial neural network, which hasa simple networking structure but features with strength of excellent nonlinear approximation, fast convergence and global convergence. A TEL_8 query interfaces' data set from UIUC on-linedatabase is used in our experiments, which consists of 477 queryinterfaces in 8 typical domains. Experimental results proved thatthe proposed approach can efficiently classify the query interfaceswith an accuracy of 95.67%.