Title :
EEG non-stationary spectrum analysis and feature extraction
Author :
Martins, Nuno ; Rosa, Agostinho C.
Author_Institution :
Inst. Pol. Setubal, Escola Sup. de Tecnologia
Abstract :
This paper describes an approach for model-based feature extraction. It also provides a substantial enhancement of the important characteristics relevant in visual and automatic sleep analysis. A procedure was developed in order to obtain a nonstationary spectrum analysis well suited for EEG signals
Keywords :
electroencephalography; feature extraction; medical signal processing; spectral analysis; EEG nonstationary spectrum analysis; automatic sleep analysis; model-based feature extraction; visual sleep analysis; Autocorrelation; Band pass filters; Brain modeling; Data mining; Electroencephalography; Entropy; Equations; Feature extraction; Maximum likelihood estimation; Predictive models;
Conference_Titel :
Systems, Man, and Cybernetics, 1996., IEEE International Conference on
Conference_Location :
Beijing
Print_ISBN :
0-7803-3280-6
DOI :
10.1109/ICSMC.1996.571161
