Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/45624
Title: EEG based sensing of brain signals : emotional states feature extraction
Authors: Per, Sau Wei.
Keywords: DRNTU::Engineering::Electrical and electronic engineering::Electronic systems::Signal processing
DRNTU::Engineering::Electrical and electronic engineering::Control and instrumentation::Medical electronics
Issue Date: 2011
Abstract: Emotions play a significant role in human behaviour, decision making and actions. They direct attention and enhance the memory in encoding and storing of information. The human brain practically runs every function in the body. Brain signals generated by visual stimuli are collected by EEG system. The time-domain and frequency-domain features of these signals are then extracted with the use of MATLAB algorithm. Different combinations of features are grouped and classified by Linear Discriminant classification into Happy and Sad emotional states. Experiments were set up to compute and analyse the brain signals related to Happy and Sad states. Placements of electrodes based on the 10-20 system were used to extract both alpha and beta waves from the frontal and parietal lobes. The features, average power and peak power from frequency domain, and minimum amplitude, maximum amplitude, mean and standard deviation from time domain, were extracted using the MATLAB algorithm. Visual inspection of the brain signals was performed to determine the optimal time interval for the features to be used in linear discriminant analysis. Different combinations of features were chosen to obtain the highest classification accuracy. The combination results from alpha wave, average power, peak power, mean and standard deviation, gave the highest accuracy of 64%.
URI: http://hdl.handle.net/10356/45624
Rights: Nanyang Technological University
Fulltext Permission: restricted
Fulltext Availability: With Fulltext
Appears in Collections:EEE Student Reports (FYP/IA/PA/PI)

Files in This Item:
File Description SizeFormat 
EA5107-101.pdf
  Restricted Access
2.05 MBAdobe PDFView/Open

Page view(s) 5

242
Updated on Dec 5, 2020

Download(s) 5

19
Updated on Dec 5, 2020

Google ScholarTM

Check

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.