Estimating Range and Relationship of EEG Frequency Bands for Emotion Recognition
Author(s) -
Leena Bhole,
Maya Ingle
Publication year - 2019
Publication title -
international journal of computer applications
Language(s) - English
Resource type - Journals
ISSN - 0975-8887
DOI - 10.5120/ijca2019918896
Subject(s) - computer science , range (aeronautics) , electroencephalography , speech recognition , emotion recognition , artificial intelligence , pattern recognition (psychology) , neuroscience , psychology , materials science , composite material
EEG based emotion recognition is the most significant technique to identify human emotions effectively. An attempt is made to identify range of frequency bands for each discrete emotion using frequency band analysis of EEG signals. Each frequency band is associated with relative power values. These relative power values assist to estimate range for frequency bands. The results are evaluated for absolute and relative power values of EEG signal in each frequency band. Further, Bayesian network is constructed to represent relationship between frequency bands and emotion. As a result, theta and alpha bands found to be more active than beta and gamma.
Accelerating Research
Robert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom
Address
John Eccles HouseRobert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom