Cross-subject workload classification with a hierarchical Bayes model

• Published in: NeuroImage (Orlando, Fla.) Vol. 59; no. 1; pp. 64 - 69
• Main Authors: Wang, Ziheng, Hope, Ryan M., Wang, Zuoguan, Ji, Qiang, Gray, Wayne D.
• Format: Journal Article
• Language: English
• Published: United States Elsevier Inc 02.01.2012; Elsevier Limited
• Subjects: Accuracy; Algorithms; Artificial Intelligence; Artificial neural network; Bayes Theorem; Bayesian analysis; EEG; Electroencephalography; Female; Hierarchical Bayes model; Humans; Male; Methods; Models, Theoretical; Neural networks; Normal distribution; Pattern Recognition, Automated - methods; Studies; Task Performance and Analysis; Workload - classification; Young Adult; Artificial neural network; Hierarchical Bayes model; Workload classification; EEG
• ISSN: 1053-8119; 1095-9572; 1095-9572
• DOI: 10.1016/j.neuroimage.2011.07.094

Most of the current EEG-based workload classifiers are subject-specific; that is, a new classifier is built and trained for each human subject. In this paper we introduce a cross-subject workload classifier based on a hierarchical Bayes model. The cross-subject classifier is trained and tested with data from a group of subjects. In our work, it was trained and tested on EEG data collected from 8 subjects as they performed the Multi-Attribute Task Battery across three levels of difficulty. The accuracy of this cross-subject classifier is stable across the three levels of workload and comparable to a benchmark subject-specific neural network classifier. ► In this study we create a cross-subject EEG-based workload classifier. ► Subject-dependent Bayesian classifiers can perform as well as Neural Networks. ► Our cross-subject classifier performed as well as subject-dependent classifiers.