Information-Theoretic Measures on Intrinsic Mode Function for the Individual Identification Using EEG Sensors

In spite of recent advances, the interest in extracting knowledge hidden in the electroencephalogram (EEG) signals is rapidly growing, as well as their application in the computational neuroengineering field, such as mobile robot control, wheelchair control, and person identification using brainwave...

Full description

Saved in:
Bibliographic Details
Published in:IEEE sensors journal 2015-09, Vol.15 (9), p.4950-4960
Main Authors: Kumari, Pinki, Vaish, Abhishek
Format: Article
Language:English
Subjects:
Artificial Neural network
Biometric
Classification
Data mining
Decomposition
EEG
Electroencephalography
Empirical Mode Decomposition (EMD)
Entropy
Feature extraction
Fuzzy algorithm in LVQ
learning vector quantization (LVQ-NN)
Machine Learning
Methods
Neural networks
Neurons
Random variables
Sensors
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In spite of recent advances, the interest in extracting knowledge hidden in the electroencephalogram (EEG) signals is rapidly growing, as well as their application in the computational neuroengineering field, such as mobile robot control, wheelchair control, and person identification using brainwaves. The large number of methods for the EEG feature extraction demands a good feature for every task. Digging up the most unique feature would be worthy for the identification of individual using EEG signal. This research presents a novel approach for feature extraction of EEG signal using the empirical mode decomposition (EMD) and information-theoretic method. The EMD technique is applied to decompose an EEG signal into a set of intrinsic mode function. These decomposed signals are of the same length and in the same time domain as the original signal. Hence, the EMD method preserves varying frequencies in time. To measure the performance of the features, we have used hybrid learning for classification where we have selected learning vector quantization neural network with fuzzy algorithm. In order to test the performance of proposed classifier based on fuzzy theory, we have tested classification accuracy of each cognitive task over all participated subjects. The results are compared with the past methods in the literature for feature extraction and classification methods. Results confirm that the proposed features present a satisfactory performance.
ISSN:1530-437X
1558-1748
DOI:10.1109/JSEN.2015.2423152