Research › QEEG, Methods & Mechanisms
Prediction of performance level during a cognitive task from ongoing EEG oscillatory activities
Share
Study at a glance
- Area
- QEEG, Methods & Mechanisms
- Study type
- Observational study
- Authors
- Besserve M, Philippe M, Florence G, Laurent F, Garnero L, Martinerie J
- Journal
- Clinical Neurophysiology
- Year
- 2008
- Participants
- 12 subjects
- Protocol
- EEG power and phase synchrony with machine-learning classification
Key findings
- The voting method beat a standard SVM classifier
- Average classification accuracy was 71% across 12 subjects, with an information transfer rate of 0.49 bits per minute
- Most informative signals were lateral theta power and front-to-back alpha synchrony
- Authors link these signals to a visual-attention network
A study testing whether ongoing EEG can predict how well a person is performing a cognitive task, with settings such as aircraft cockpits in mind. The researchers combined several support vector machine (SVM) classifiers, each using different EEG power and phase-synchrony measures, through a voting approach to tell apart each person's fast and slow reaction-time periods. The authors conclude that ongoing EEG can predict performance level and could support real-time monitoring to anticipate human error.