Conference proceeding
Engagement Assessment Using EEG Signals
NASA Center for AeroSpace Information (CASI). Conference Proceedings
MODSIM World (Virginia Beach, Virginia, 10/11/2011 - 10/14/2011)
03/01/2012
Abstract
In this paper, we present methods to analyze and improve an EEG-based engagement assessment approach, consisting of data preprocessing, feature extraction and engagement state classification. During data preprocessing, spikes, baseline drift and saturation caused by recording devices in EEG signals are identified and eliminated, and a wavelet based method is utilized to remove ocular and muscular artifacts in the EEG recordings. In feature extraction, power spectrum densities with 1 Hz bin are calculated as features, and these features are analyzed using the Fisher score and the one way ANOVA method. In the classification step, a committee classifier is trained based on the extracted features to assess engagement status. Finally, experiment results showed that there exist significant differences in the extracted features among different subjects, and we have implemented a feature normalization procedure to mitigate the differences and significantly improved the engagement assessment performance.
Details
- Title: Subtitle
- Engagement Assessment Using EEG Signals
- Creators
- Feng LiJiang LiFrederic McKenzieGuangfan ZhangWei WangAaron PepeRoger XuThomas SchnellNick AndersonDean Heitkamp
- Resource Type
- Conference proceeding
- Publication Details
- NASA Center for AeroSpace Information (CASI). Conference Proceedings
- Conference
- MODSIM World (Virginia Beach, Virginia, 10/11/2011 - 10/14/2011)
- Publisher
- NASA/Langley Research Center
- Language
- English
- Date published
- 03/01/2012
- Academic Unit
- Neurology; Electrical and Computer Engineering; Occupational and Environmental Health; Industrial and Systems Engineering; Public Policy Center (Archive)
- Record Identifier
- 9984186947702771
Metrics
16 Record Views