ABSTRACT
This paper explores the use of wavelet packet analysis to extract features from spontaneous electroencephalogram (EEG) during three different mental tasks. Artifact-free EEG segments are transformed to multi-scale representations by dyadic wavelet packet decomposition channel by channel. Their feature vectors formed by energy values of different sub-spaces EEG components are used as inputs of a radial basis function network to test the classification accuracies of three task pairs. The results indicate that the classification accuracies of the wavelet packet analysis method are significantly better than those of autoregressive model method. Wavelet packet analysis would be a promising method to extract features from EEG signals.
Subject(s)
Humans , Electroencephalography , Mental Processes , Physiology , Models, Statistical , Multivariate Analysis , Neural Networks, Computer , Regression Analysis , Signal Processing, Computer-AssistedABSTRACT
Objective To study the relationship between expression of EGFR and E- cadherin and metastasis of esophageal cancer. Methods The expression of EGFR and E- cadherin in esophageal cancer tissues of 47 patients by LSAB immunohistochemistry method was studied. Results The positive rates of EGFR in distant metastasis group and local lymph node metastasis group were 47.62 % and 56.52 % respectively. They were higher than individual corresponding control groups(27.08 % and 26.32 %)(P
ABSTRACT
A new multi-channel EEG signal acquisition system,which adopts Cypress's EZ-USB FX2 series USB as its micro-controller,is presented in this paper.The system employs AD620 and OP07 at the pre-amplifying stage and the following two amplifying stages respectively.Universal Series Bus(USB) technology is used to realize the real-time recording,displaying and tele-monitoring of EEG signal,which can also be stored in CF card after compression.The USB software developing tool is WinDriver.