The Classification of Transient Time-Varying EEG Signal Via Wavelet Packets Decomposition
The classification of transient timevarying electroencephalography (EEC) is quite important for farther understanding the brain Junction. In order to classify different kinds of nonstationary EEG rhythms, wavelet packet analysis is used for designing sub-band filters with specified band-passed characteristics. Four kinds of wavelet packet decomposition using Daubechies wavelet are employed to investigate the nonstationarity of clinical EEG signals. Several real EEG signals with different brain junction states are analyzed and compared via the dynamic rhythms. It is indicated from the experimental results that the non-stationary characteristics of clinical brain electrical activities can be classified by using wavelet packet decomposition. The method in this paper also proposes an effective way to form the Dynamic Topographic Brain Mapping (DTBM) to present the dynamic EEG topography.
EEG signal processing brain function rhythms classification wavelet packet decomposition.
Minfen Shen Lisha Sun F. H.Y.Chan
Scientific Research Centre, Shantou University, Guangdong 515063, China Biomedical Engineering Centre, Hong Kong University, Hong Kong
国际会议
8th International Conference on Neural Information Processing(ICONIP 2001)(第八届国际神经信息处理大会)
上海
英文
1327-1331
2001-11-14（万方平台首次上网日期，不代表论文的发表时间）