Computational NeuroscienceAutomated identification of neural correlates of continuous variables

- A new method for identifying EEG correlates of continuous independent variables.
- Our method outperforms canonical correlation analysis and common spatial patterns.
- When applied to real EEG during music it finds known correlates of music tempo.
- The method also identifies novel neural correlates of music induced emotion.

BackgroundThe electroencephalogram (EEG) may be described by a large number of different feature types and automated feature selection methods are needed in order to reliably identify features which correlate with continuous independent variables.New methodA method is presented for the automated identification of features that differentiate two or more groups in neurological datasets based upon a spectral decomposition of the feature set. Furthermore, the method is able to identify features that relate to continuous independent variables.ResultsThe proposed method is first evaluated on synthetic EEG datasets and observed to reliably identify the correct features. The method is then applied to EEG recorded during a music listening task and is observed to automatically identify neural correlates of music tempo changes similar to neural correlates identified in a previous study. Finally, the method is applied to identify neural correlates of music-induced affective states. The identified neural correlates reside primarily over the frontal cortex and are consistent with widely reported neural correlates of emotions.Comparison with existing methodsThe proposed method is compared to the state-of-the-art methods of canonical correlation analysis and common spatial patterns, in order to identify features differentiating synthetic event-related potentials of different amplitudes and is observed to exhibit greater performance as the number of unique groups in the dataset increases.ConclusionsThe proposed method is able to identify neural correlates of continuous variables in EEG datasets and is shown to outperform canonical correlation analysis and common spatial patterns.