Multidimensional support vector regression (MSVR) with similar iterative re-weight least square (IRWLS) is firstly used in this paper to estimate the location and moment of an equivalent current dipole source in the inverse problem of electroencephalogram (EEG). In order to discover the relationship between the potentials on the scalp and internal source within the brain, the single current dipole source with four-shell concentric sphere model is reconstructed. Our simulation experiments demonstrate that MSVR based on the support vector machine can obtain more robust estimations for EEG source localization problem with equivalent current dipole model.