Please use this identifier to cite or link to this item: http://repository.umac.mo/handle/10692/666
Title: Outlier Detection for Single-Trial for EEG Signal Analysis
Authors: Wang, Bo Yu
Wan, Feng (萬峰)
Mak, Peng Un (麥炳源)
Mak, Pui In (麥沛然)
Vai, Mang I (韋孟宇)
Issue Date: May-2011
Publisher: IEEE
Citation: The 5th international IEEE EMBS conference on neural engineering, May 2011, p. 478-481
Abstract: The performance of a brain computer interface (BCI) system is usually degraded due to the outliers in electroencephalography (EEG) samples. This paper presents a novel outlier detection method based on robust learning of Gaussian mixture models (GMMs). We apply the proposed method to the single-trial EEG classification task. After trial-pruning, feature extraction and classification are performed on the subset of training data, and experimental results demonstrate that the proposed method can successfully detect the outliers and therefore achieve more reliable result.
URI: http://hdl.handle.net/10692/666
Access: 
Files in This Item:
File Description SizeFormat 
7432_0_Outlier detection for single-trial EEG signal analysis.pdf815.78 kBAdobe PDFView/Open
Appears in Collections:ECE Conference Papers




Items in UMIR are protected by copyright, with all rights reserved, unless otherwise indicated.