For access to this article, please select a purchase option:
IET members benefit from discounts to all IET publications and free access to E&T Magazine. If you are an IET member, log in to your account and the discounts will automatically be applied.
Your recommendation has been sent to your librarian.
In a modern human-machine system, it is very meaningful to study the subject-specific mental workload classification for the increasing high mental workload. In this paper, EEG data is used to build the Subject-specific Classifiers (SSCs) based on Stochastic Configuration Network (SCN). SCN has the advantage of random neural network, and can realize the hyper-parameters setting. The results show that the SSCs built in this paper perform well, the range of SSCs test accuracies is between 56.5% and 90.2% with an average of 75.9%.
Inspec keywords: medical signal processing; signal classification; bioelectric potentials; stochastic processes; electroencephalography; neural nets
Subjects: Neural nets; Electrodiagnostics and other electrical measurement techniques; Bioelectric signals; Signal processing and detection; Biology and medical computing; Digital signal processing; Other topics in statistics; Electrical activity in neurophysiological processes