A Multi-objective Evolutionary Algorithm for EEG Inverse Problem
This work addresses the EEG inverse problem for brain source localization, offering a more stable method, though it appears incremental as it builds on evolutionary strategies for an existing bottleneck.
The authors tackled the EEG inverse problem by proposing a multi-objective evolutionary algorithm (MOEAAR) that avoids unknown parameters, and it showed better stability in reconstruction and localization compared to classic regularization methods like LASSO, Ridge-L, and ENET-L in simulated data with varying SNR.
In this paper, we proposed a multi-objective approach for the EEG Inverse Problem. This formulation does not need unknown parameters that involve empirical procedures. Due to the combinatorial characteristics of the problem, this alternative included evolutionary strategies to resolve it. The result is a Multi-objective Evolutionary Algorithm based on Anatomical Restrictions (MOEAAR) to estimate distributed solutions. The comparative tests were between this approach and 3 classic methods of regularization: LASSO, Ridge-L and ENET-L. In the experimental phase, regression models were selected to obtain sparse and distributed solutions. The analysis involved simulated data with different signal-to-noise ratio (SNR). The indicators for quality control were Localization Error, Spatial Resolution and Visibility. The MOEAAR evidenced better stability than the classic methods in the reconstruction and localization of the maximum activation. The norm L0 was used to estimate sparse solutions with the evolutionary approach and its results were relevant.