The extraction of brain evoked potential based on fuzzy clustering and wavelet transformation
Lanlan Yu, Tianxing Meng, Baina He · 2009
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 it is not clear and has many fake signals. Wavelet transformation is a rising technology in signal processing which has the feature of multi-resolution analysis and the adaptation characteristic for signal. In this paper, we combine wavelet transformation with fuzzy clustering technology to extract the feature of BEP. This way combines the strongpoint of wavelet transformation and fuzzy clustering technology which can not only eliminate the background noises well and make the wave shape smooth but can keep perfectly the main peak values in the signal. At the same time, it eliminates underlying fake signals and high frequency burr noises. Experiments show that this associative way has good efficiency in the extraction of BEP.