An EMD based Method for Reduction of Ballistocardiogram Artifact from EEG Studies of Evoked Potentials

被引：0

作者：

Javed, Ehtasham ^{[1
]}

Faye, Ibrahima ^{[2
]}

Malik, Aamir Saeed ^{[1
]}

Abdullah, Jafri Malin ^{[3
]}

机构：

[1] Univ Teknol PETRONAS, Ctr Intelligent Signal & Imaging Res, Dept Elect & Elect Engn, Perak, Malaysia

[2] Univ Teknol PETRONAS, Ctr Intelligent Signal & Imaging Res, Dept Fundamental & Appl Sci, Perak, Malaysia

[3] Hosp Univ Sains Malaysia, Dept Neurosci, Ctr Neurosci Serv & Res, Kelantan, Malaysia

来源：

2015 IEEE 14TH INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND APPLICATIONS (ICMLA) | 2015年

关键词：

Ballistocardiogram artifact; Simultaneous EEG & fMRI; Event Related Potentials; Empirical Mode Decomposition; FEATURE-EXTRACTION; REMOVAL; FMRI;

D O I：

10.1109/ICMLA.2015.81

中图分类号：

TP3 [计算技术、计算机技术];

学科分类号：

0812 ;

摘要：

Multi-modality data acquisition is a topic of research that gained interest in the recent years. It provides the opportunity to gather detailed information for analysis. Simultaneous electroencephalography (EEG) and functional magnetic resonance imaging is one good example of it. The information we get after fusing data from EEG and fMRI have both high temporal and spatial resolution. On the other side, this EEG recording suffers from some additional artifacts due to the fMRI environment, in particular, the Ballistocardiogram artifact. In this article, a new method of removing Ballistocardiogram Artifact from evoked potential studies is proposed. The method does not require any reference signal or prior information. The results presented are using the data of three subjects (volunteers). The results show that the proposed method can efficiently reduce Ballistocardiogram artifact and has performed better compared to the conventional methods.

引用

页码：1199 / 1203

页数：5

共 15 条

[1] A new approach for EEG feature extraction in P300-based lie detection [J].