getCITED   
  Home     Search     Add Content     Reports     Help  
Edit Publication | Edit Contributors | Delete Publication | Edit References | Edit Citations
Add to Bookstack | Show Bookstack | Change Bookstack

Recognition of Emotional States using Nonlinear Range Compression of EEG Spectral Data

Post a Comment
CONTRIBUTORS:
  Author Theus H. Aspiras
  Author Vijayan K. Asari
JOURNAL:
  International Journal of Information Processing, 6(2), 60 - 72.
YEAR: 2012
PUB TYPE: Journal Article
SUBJECT(S): Discrete Wavelet Transform, Emotion Recognition, Laplacian Montage, Logarithmic Power, Multi-Layer Perceptron
DISCIPLINE: Computer Science
HTTP: http://www.ijipbangalore.org
LANGUAGE: English
PUB ID: 103-511-628 (Last edited on 2013/01/16 11:09:50 US/Mountain)
SPONSOR(S):
 
ABSTRACT:
Emotion recognition using ElectroEncephaloGraphic (EEG) recordings is a new area of research which focuses on recognition of emotional states of mind rather than impulsive responses. EEG recordings are found useful for the detection of emotions through monitoring the emotion characteristics of spatiotemporal variations of activations inside the brain. To distinguish between different emotions using EEG data, we must provide specific spectral descriptors as features to quantify these spatiotemporal variations. We pro- pose several new features, Normalized Root Mean Square (NRMS), Absolute Logarithm Normalized Root Mean Square (ALRMS), Logarithmic Power (LP), Normalized Logarithmic Power (NLP) and Absolute Logarithm Normalized Logarithmic Power (ALNLP) for the classification of emotions. A protocol has been established to elicit five distinct emotions (joy, sadness, disgust, fear, surprise and neutral). EEG signals are collected using a 256-channel system, preprocessed using band-pass filters and Laplacian Montage and decomposed into five frequency bands using Discrete Wavelet Transform. The decomposed signals are transformed into different spectral descriptors and are classified using a two-layer Multilayer Perceptron Network (MLP). Logarithmic Power produced the highest recognition rates, 91.82% and 94.27% recognition for two different experiments, which is more than 2% higher than other features.
STATISTICS
Click on # to view
 Citations  
 References  
 Comments  
 Quality      0/0.00 
 Interest      0/0.00 
 View(er)s   2/272 
Quality
  N/A
High
  7
  6
  5
  4
  3
  2
  1
Low
Interest
  N/A
High
  7
  6
  5
  4
  3
  2
  1
Low
Prev | Next

    ABOUT getCITED   |    CONTACT US   |    USER INFO   |    PREFERENCES   |    PRIVACY   |    LOG IN   
Comments? Suggestions? Send them to feedback@getCITED.org.

Copyright © 2000-2013 getCITED Inc. All Rights Reserved.