A resource-allocating network for function interpolation
Neural Computation
Hi-index | 0.00 |
A novel approach is proposed to solve the problem of detecting the signal in the noise using a modified RBF neural network (RBFNN). The RBFNN is normalized to obtain optimal behavior of noise suppression even at low SNR. The performance of the proposed scheme is also evaluated with both MSE and the tracking ability. Several experimental results provide the convergent evidence to show that the method can significantly enhance the SNR and successfully track the variation of the signal such as evoket potential.