Title | ||
---|---|---|
Application of wavelet network combined with nonlinear dimensionality reduction on the neural dipole localization |
Abstract | ||
---|---|---|
A wavelet network (WN) method is presented in this paper, which can be used to estimate the location and moment of an equivalent current dipole source using reduced-dimension data from the original measurement electroencephalography (EEG). In order to handle the large-scale high dimension problems efficiently and provide a real-time EEG dipole source localizer, the ISOMAP algorithm is firstly used to find the low dimensional manifolds from high dimensional EEG signal. Then, a WN is employed to discover the relationship between the observation potentials on the scalp and the internal sources within the brain. In our simulation experiments, satisfactory results are obtained. |
Year | DOI | Venue |
---|---|---|
2006 | 10.1007/11816157_35 | ICIC (1) |
Keywords | Field | DocType |
low dimensional manifold,internal source,real-time eeg dipole source,nonlinear dimensionality reduction,original measurement electroencephalography,wavelet network,large-scale high dimension problem,neural dipole localization,observation potential,isomap algorithm,high dimensional eeg signal,reduced-dimension data,equivalent current dipole source,real time,electroencephalography,simulation experiment | Dimensionality reduction,Pattern recognition,Current source,Computer science,Artificial intelligence,Boundary element method,Nonlinear dimensionality reduction,Electroencephalography,Dipole,Manifold,Wavelet | Conference |
Volume | ISSN | ISBN |
4113 | 0302-9743 | 3-540-37271-7 |
Citations | PageRank | References |
0 | 0.34 | 3 |
Authors | ||
4 |