Neural network based EEG denoising

A novel filter is proposed by applying back propagation neural network (BPNN) ensemble where the noisy signal and the reference one are the same in a learning process. This neural network (NN) ensemble filter not only well reduces additive and multiplicative white noise inside signals, but also preserves signals' characteristics. It is proved that the reduction of noise using NN ensemble filter is better than the improved ε nonlinear filter and single NN filter while signal to noise ratio is smaller. The performance of the NN ensemble filter is demonstrated in computer simulations and actual electroencephalogram (EEG) signals processing.

[1]  X. Feng,et al.  Identification of high noise time series signals using hybrid ARMA modeling and neural network approach , 1993, IEEE International Conference on Neural Networks.

[2]  Jian Cheng,et al.  Applying a Wavelet Neural Network to Impulse Noise Removal , 2005, 2005 International Conference on Neural Networks and Brain.

[3]  R. Srinivasan,et al.  Removal of ocular artifacts from EEG using an efficient neural network based adaptive filtering technique , 1999, IEEE Signal Processing Letters.

[4]  Jorge I. Aunon,et al.  Signals and Noise in Evoked Brain Potentials , 1985, IEEE Transactions on Biomedical Engineering.

[5]  Hiroshi Harashima,et al.  ϵ‐separating nonlinear digital filter and its applications , 1982 .

[6]  T. Fechner.  Nonlinear noise filtering with neural networks: comparison with Weiner optimal filtering , 1993 .

[7]  Jian Yang,et al.  Speckle filtering in polarimetric SAR data based on the subspace decomposition , 2004, IEEE Transactions on Geoscience and Remote Sensing.

[8]  Hujun Yin,et al.  Image denoising using self-organizing map-based nonlinear independent component analysis , 2002, Neural Networks.

[9]  M.T. Hagan,et al.  Multireference adaptive noise canceling applied to the EEG , 1997, IEEE Transactions on Biomedical Engineering.

[10]  D. Regan.  Human brain electrophysiology: Evoked potentials and evoked magnetic fields in science and medicine , 1989 .

[11]  S. W. Piche,et al.  Steepest descent algorithms for neural network controllers and filters , 1994, IEEE Trans. Neural Networks.