Open AccessA Cognitive Workload Identification using EEG Power Spectrum
Author(s) -
. Anshul,
Dipali Bansal,
Rashima Mahajan
Publication year - 2019
Publication title -
international journal of recent technology and engineering
Language(s) - English
Resource type - Journals
ISSN - 2277-3878
DOI - 10.35940/ijrte.c5799.118419
Subject(s) - electroencephalography , workload , spectral density , computer science , cognition , preprocessor , identification (biology) , artificial intelligence , resting state fmri , pattern recognition (psychology) , speech recognition , psychology , telecommunications , neuroscience , botany , biology , operating system
Now a days, Electroencephalography (EEG) is popular to monitor human’s cognitive workload. EEG signals are delicate to the variation in cognitive load in various fields including observing cognitive workload for the intricate environment of military chores. Earlier to acquire the EEG signals high-cost EEG systems were used which bounds their use but now a day’s low-cost headsets are available to capture EEG which makes it a promising set-up to measure cognitive workload. EEGs are initially preprocessed to reflect the artifacts present in it. After preprocessing, signals are ready for further processing. The power spectral density corresponds to the power distribution of EEG signal in the frequency domain which is used to assess the changes in the pattern of the brain. This paper discusses the present progress of research in cognitive workload identification and identifies the techniques associated with the cognitive workload. This proposed research gives the analysis of EEG signal power spectrum density (PSD) during resting state and cognitive workload activities of a human. With power spectral analysis of the EEG signal, seven statistical parameters have been calculated (minimum, maximum, mean, median, mode, standard deviation and range) have been calculated Analysis showed that the in cognitive workload, PSD has significantly changed if compared to the resting state