Wavelet-Fractal & Neuro-Fuzzy for Brain Computer Interface Application | A Series of Novel Approaches Toward EEG-based Brain-Computer Interface Systems

Wei-Yen Hsu

ISBN 10: 384650906X / ISBN 13: 9783846509067

Published by LAP LAMBERT Academic Publishing, 2011

About this Item

Wavelet-Fractal & Neuro-Fuzzy for Brain Computer Interface Application | A Series of Novel Approaches Toward EEG-based Brain-Computer Interface Systems | Wei-Yen Hsu | Taschenbuch | 104 S. | Englisch | 2011 | LAP LAMBERT Academic Publishing | EAN 9783846509067 | Verantwortliche Person für die EU: LAP Lambert Academic Publishing, Brivibas Gatve 197, 1039 RIGA, LETTLAND, customerservice[at]vdm-vsg[dot]de | Anbieter: preigu.

Seller Inventory # 106750135

Bibliographic Details

• Title: Wavelet-Fractal & Neuro-Fuzzy for Brain Computer Interface Application | A Series of Novel Approaches Toward EEG-based Brain-Computer Interface Systems
• Publisher: LAP LAMBERT Academic Publishing
• Publication Date: 2011
• Language: English
• ISBN 10: 384650906X
• ISBN 13: 9783846509067
• Binding: Taschenbuch
• Condition: Neu
• Dimensions: 220W x 150H x 7D millimeters 220 millimeters width by 150 millimeters height by 7 millimeters depth
• Weight: 173 grams
• Seller catalogs:
  • Bücher

About this title

Synopsis

The ultimate objective of brain-computer interface (BCI) is to provide humans an alternative communication channel allowing direct transmission of messages from the brain to a computer by analyzing the brain’s mental activities. The BCI is usually described that a person has the ability to communicate with others without the prerequisite of brain’s normal output pathways of peripheral nerves and muscles by controlling his own electroencephalographic (EEG) signals. In BCI applications, the performance and reliability of mental task analysis greatly depend on feature extraction and representation. In this book, a series of methods are proposed, including t-test-weighted time-scale plot, active segment selection, multiresolution fractal feature vector (MFFV) associated with genetic algorithm (GA), and neuro-fuzzy time-series prediction to effectively extract, select, and represent features for better classification accuracy. Compared to other well-known approaches, the experimental results show that the proposed methods are superior on both real finger movement and motor-imagery (MI) data for BCI applications.

About the Author

He received the MS and PhD degrees in the Department of Computer Science and Information Engineering from National Cheng Kung University, Tainan, Taiwan in 2001 and 2008, respectively. His current research interests include medical image processing, biomedical signal processing, neuroscience methods, and computer vision and graphics.