Using Feedforward Neural Networks to Monitor Alertness from Changes in EEG Correlation and Coherence

Part of Advances in Neural Information Processing Systems 8 (NIPS 1995)

Bibtex Metadata Paper


Scott Makeig, Tzyy-Ping Jung, Terrence J. Sejnowski


We report here that changes in the normalized electroencephalo(cid:173) graphic (EEG) cross-spectrum can be used in conjunction with feedforward neural networks to monitor changes in alertness of op(cid:173) erators continuously and in near-real time. Previously, we have shown that EEG spectral amplitudes covary with changes in alert(cid:173) ness as indexed by changes in behavioral error rate on an auditory detection task [6,4]. Here, we report for the first time that increases in the frequency of detection errors in this task are also accompa(cid:173) nied by patterns of increased and decreased spectral coherence in several frequency bands and EEG channel pairs. Relationships between EEG coherence and performance vary between subjects, but within subjects, their topographic and spectral profiles appear stable from session to session. Changes in alertness also covary with changes in correlations among EEG waveforms recorded at different scalp sites, and neural networks can also estimate alert(cid:173) ness from correlation changes in spontaneous and unobtrusively(cid:173) recorded EEG signals.