Abstract
In this study, the visual cognitive workload is classified using electroencephalogram (EEG) signal acquired with dry electrodes. The visual cognitive workload of four levels is introduced using color objects and their counting in visual space. The EEG data of 44 subjects is acquired for this work. The classification accuracy along with computational complexity involved in subband decomposition technique is discussed in the proposed approach. The EEG signal is decomposed in ten subbands using multirate infinite impulse response (IIR) filter bank. Band energy, signal length, non-linear energy and band entropy of decomposed subbands are used as features. K-nearest neighbors (KNN) and ensemble subspace KNN classifiers are used for classification of cognitive workload. The classification accuracy and computational complexity are compared with two other subband decomposition methods: Morlet wavelet and analytic wavelet transform. The classification accuracy obtained using proposed method is 83.65%, which is greater than the Morlet wavelet (80.96%) and is less than the analytic wavelet transform (86.31%). The proposed method's computational complexity is 70% less than Morlet wavelet and 45% less than analytic wavelet transform.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call