作者: A.M. Aibinu , M.J.E. Salami , A.A. Shafie
DOI: 10.1016/J.ESWA.2010.11.005
关键词:
摘要: In this paper, a new method of biomedical signal classification using complex- valued pseudo autoregressive (CAR) modeling approach has been proposed. The CAR coefficients were computed from the synaptic weights and split weight activation function feedforward multilayer complex neural network. performance proposed technique evaluated PIMA Indian diabetes dataset with different complex-valued data normalization techniques four values learning rate. An accuracy value 81.28% obtained technique.