Workload Classification Across Subjects Using EEG

EEG data has been used to discriminate levels of mental workload when classifiers are created for each subject, but the reliability of classifiers trained on multiple sub-jects has yet to be investigated. Artificial neural network and naive Bayesian clas-sifiers were trained with data from single and multiple subjects and their ability to discriminate among three difficulty conditions was tested. When trained on data from multiple subjects, both types of classifiers poorly discriminated between the three levels. However, a novel model, the naive Bayesian classifier with a hidden node, performed nearly as well as the models trained and tested on individuals. Adaptive automation technologies promise to melio-rate the demands made on mental capabilities by mod-ern automation and computerized systems (Moray, In-agaki, & Itoh, 2000; Inagaki, 2003). A critical aspect of these adaptive technologies is accurate and reliable assessment of operator workload. Traditionally, work-load is assessed by questionnaires which are quanti-fied through statistical techniques such as factor load-ing, discriminant analysis, and correlation/covariance analysis (Hart & Staveland, 1988). Although progress has been made, there are no globally accepted methods for measuring and predicting workload (Lysaght et al.