Date of Award

Spring 2009

Document Type

Thesis

Degree Name

Master of Science (MS)

Department

Electrical & Computer Engineering

Program/Concentration

Electrical Engineering

Committee Director

Vijayan Asari

Committee Member

Zia-ur Rahman

Committee Member

Jiang Li

Call Number for Print

Special Collections LD4331.E55 T73 2009

Abstract

Electroencephalogram (EEG) signals can be used for implicit communication such as to control robots or medical equipment by brain activity or to detect an individual's intentions of committing premeditated crimes. An EEG based brain-computer interface allows paralyzed patients to express their thoughts. However, biological and technical artifacts heavily interfered with EEG signals due to blinking of the eyes, muscle activities and line noise. Sometimes the noise interference due to signal artifacts becomes more prominent than the information content. This thesis investigates novel feature extraction methodologies in EEG signals to represent different thought processes and employs neural network-based pattern classification techniques for the identification of mental tasks.

Principal Component Analysis (PCA) and Independent Component Analysis (ICA) are performed on the EEG signals corresponding to various brain activities to extract dominant features representing specific mental states. The extracted features are classified using neural networks. The classification performances of two neural network-based training methodologies, namely Multi-Layer Perceptron with Back-Propagation (MLP BP) Neural Network (NN) and Radial Basis Function (RBF) NN, are investigated.

Rights

In Copyright. URI: http://rightsstatements.org/vocab/InC/1.0/ This Item is protected by copyright and/or related rights. You are free to use this Item in any way that is permitted by the copyright and related rights legislation that applies to your use. For other uses you need to obtain permission from the rights-holder(s).

DOI

10.25777/46s0-nh73

Download

Share

COinS