Litcius/Paper detail

Time Domain Parameters as a feature for single-channel EEG-based drowsiness detection method

Venkata Phanikrishna Balam, Suchismitha Chinara

20202020 IEEE International Students' Conference on Electrical,Electronics and Computer Science (SCEECS)25 citationsDOI

Abstract

Progress in the automobile industry has made life easier for us, and traffic accidents have steadily increased. A large number of vehicle accidents are caused by driver drowsiness while driving. As with many drowsiness detection methods, EEG-based methodology is considered an immediate, efficient, and promising modality. Several feature types have been used in EEG-based drowsiness detection. In this study, we presented a novel feature extraction strategy based on a single Hjorth parameter, and compare its classification capability with the existing Power spectral density (PSD) feature. The results show that the proposed H-parameter features have higher and stronger performance compared to the PSD features of the present work. This field outperforms traditional feature extraction strategies. This is the first study, to the best of our knowledge, to practically apply Hjorth parameters to EEG and its sub-bands for EEG-based driver drowsiness detection.

Topics & Concepts

Feature extractionElectroencephalographyComputer scienceFeature (linguistics)Pattern recognition (psychology)Artificial intelligenceChannel (broadcasting)Time domainSpectral densityFrequency domainSupport vector machineSpeech recognitionComputer visionPsychologyComputer networkLinguisticsPsychiatryPhilosophyTelecommunicationsEEG and Brain-Computer InterfacesSleep and Work-Related FatigueGaze Tracking and Assistive Technology