Adaptive estimation of evoked potentials using wavelets and radial basis functions neural networks

Author

Jemili, Kanaan ; Westerkamp, John J.

Author_Institution

Dept. of Electr. Eng., Dayton Univ., OH, USA

fYear

1994

fDate

1994

Firstpage

1099

Abstract

A new signal estimation technique is proposed that uses the wavelet transform to determine the time-frequency information content of human evoked brain potentials. By adaptively weighting the individual time-frequency bins using a neural network, a time-varying estimate of the evoked potential can be obtained. The weighting procedure enhances the time-frequency bins corresponding to the EP while attenuating those corresponding to the EEG

Keywords

adaptive estimation; EEG; adaptive estimation; adaptive weighting; evoked potentials; human evoked brain potentials; radial basis functions neural networks; signal estimation technique; time-frequency bins; time-frequency information content; time-varying estimate; wavelets; weighting procedure; Adaptive estimation; Bandwidth; Biological neural networks; Discrete wavelet transforms; Electroencephalography; Neural networks; Radial basis function networks; Signal generators; Time frequency analysis; Transient analysis;

fLanguage

English

Publisher

ieee

Conference_Titel

Engineering in Medicine and Biology Society, 1994. Engineering Advances: New Opportunities for Biomedical Engineers. Proceedings of the 16th Annual International Conference of the IEEE

Conference_Location

Baltimore, MD

Print_ISBN

0-7803-2050-6

Type

conf

DOI

10.1109/IEMBS.1994.415342

Filename

415342