|International Journal of Computer Applications
|Foundation of Computer Science (FCS), NY, USA
|Volume 183 - Number 46
|Year of Publication: 2022
|Authors: Yashwanth Vyza, Suman Dabbu, Malini Mudigonda
Yashwanth Vyza, Suman Dabbu, Malini Mudigonda . A Spectral Power based Index using Wavelet Analysis of EEG for Drowsiness Detection. International Journal of Computer Applications. 183, 46 ( Jan 2022), 1-8. DOI=10.5120/ijca2022921731
Advancements in the field of computational systems have enabled decoding of biological quantities and to recognize physiological conditions. One such prospective application for the next generation of portable electroencephalogram (EEG) signal processing systems is to prevent hazards in attention-demanding activities. This work demonstrates a methodology for assessing alertness level based on a single EEG channel (PzOz), allowing the reduction of the required hardware and the computational time of the algorithms. A new spectral power-based index is proposed and computed through the normalized Haar discrete wavelet packet transform (WPT). The Haar WPT precisely resolves the brain rhythms into packets whilst demanding a relatively low computational cost. The effectiveness of the proposed index in drowsiness detection is evaluated by evidencing the significant changes in the alert-drowsy transitions of 40 subjects of a public database. It can be clearly seen from the results that the proposed index is distinctive enough to distinguish active and drowsy states (0.25) based on frequency spectrum states contained in the EEG signal.