Automatic Noise Removal and Phase Synchronization for MI EEG Analysis

Wei-Yen Hsu

ISBN 10: 3659382434 / ISBN 13: 9783659382437

Editore: LAP LAMBERT Academic Publishing Apr 2013, 2013

Riguardo questo articolo

Neuware -1. In this book, a novel brain-computer interface (BCI) system is proposed to analyze motor imagery (MI) electroencephalogram (EEG) signals. 2. After eliminating EOG artifacts automatically and extracting features by wavelet-based phase synchronization approach, support vector machine (SVM) is adopted for the classification of single-trial left and right MI data. 3. The EOG artifacts are automatically removed by means of modified independent component analysis (ICA). 4. The features are extracted from wavelet data by phase synchronization, and then classified by the SVM. 5. Compared with the results without EOG artifact removal, spectral band and AR model features, the proposed system achieves satisfactory results in BCI applications.Books on Demand GmbH, Überseering 33, 22297 Hamburg 52 pp. Englisch.

Codice articolo 9783659382437

Dati bibliografici

• Titolo: Automatic Noise Removal and Phase Synchronization for MI EEG Analysis
• Editore: LAP LAMBERT Academic Publishing Apr 2013
• Data di pubblicazione: 2013
• Lingua: Inglese
• ISBN 10: 3659382434
• ISBN 13: 9783659382437
• Rilegatura: Taschenbuch
• Condizione: Neu
• Dimensioni: 220 L x 150 A x 4 P (millimetri) 220 millimetri di larghezza per 150 millimetri di altezza per 4 millimetri di profondità
• Peso: 96 grammi

Descrizione articolo

Riassunto

1. In this book, a novel brain-computer interface (BCI) system is proposed to analyze motor imagery (MI) electroencephalogram (EEG) signals. 2. After eliminating EOG artifacts automatically and extracting features by wavelet-based phase synchronization approach, support vector machine (SVM) is adopted for the classification of single-trial left and right MI data. 3. The EOG artifacts are automatically removed by means of modified independent component analysis (ICA). 4. The features are extracted from wavelet data by phase synchronization, and then classified by the SVM. 5. Compared with the results without EOG artifact removal, spectral band and AR model features, the proposed system achieves satisfactory results in BCI applications.

L'autore

Wei-Yen Hsu received the Ph.D. degree in the Department of CSIE, National Cheng Kung University, Tainan, Taiwan, in 2008. He is an assistant professor in the Department of Information Management, National Chung Cheng University now. His research interests include medical image processing, biomedical signal processing and neuroscience methods.