期刊名称：International Journal of Multimedia and Ubiquitous Engineering
印刷版ISSN：1975-0080
出版年度：2014
卷号：9
期号：2
页码：363-372
出版社：SERSC
摘要：In this paper, rough sets (RS) and quantum neural network (QNN) are used to recognize electrocardiogram (ECG) signals. Firstly, wavelet transform (WT) is used as a feature extraction after normalization of these signals. Then the attribute reduction of RS has been applied as preprocessor so that we could delete redundant attributes and conflicting objects from decision making table but remain efficient information lossless. We realized classification modeling and forecasting test based on QNN after that. Finally, the RS-QNN gives us fast and realistic results compared with the BP and RBF. By this method, we could reduce the dimension of feature space and decrease the complexity in the process. Experiment result shows that the classification ability of the RS-QNN is superior to conventional approach
