The feature extraction of brain evoked potential based on wavelet transformation

The brain evoked potentials (BEP) are related directly to series of diseases and physical states. It is helpful to prevent and diagnose the brain diseases by analyzing evoked potentials. The traditional averaged method can show the shape of evoked potentials in the rough but losses some important components. At the same time, the plus number is so many that it will increase the pain of the testee. Wavelet transformation is a rising technology in signal processing which has the feature of multi-resolution analysis. In this paper, we use wavelet transformation for the feature extraction of brain evoked potential and compare with the traditional averaged method. We can see that the evoked potential can be identified only with few plus signals by wavelet transformation technology and the wave of the signal is very smooth which not only saves the useful signal well but also rejects almost all the background noises. Experiments show that the wavelet transformation has good efficiency in the feature extraction of the BEP which has upper application value in the clinic.