2009 Annual International Conference of the IEEE Engineering in Medicine and Biology Society 2009
DOI: 10.1109/iembs.2009.5335278
|View full text |Cite
|
Sign up to set email alerts
|

Application of the empirical mode decomposition to the extraction of features from EEG signals for mental task classification

Abstract: In this work, it is proposed a technique for the feature extraction of electroencephalographic (EEG) signals for classification of mental tasks which is an important part in the development of Brain Computer Interfaces (BCI). The Empirical Mode Decomposition (EMD) is a method capable to process nonstationary and nonlinear signals as the EEG. This technique was applied in EEG signals of 7 subjects performing 5 mental tasks. For each mode obtained from the EMD and each EEG channel were computed six features: Roo… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

1
25
1
1

Year Published

2011
2011
2020
2020

Publication Types

Select...
6
2
2

Relationship

0
10

Authors

Journals

citations
Cited by 47 publications
(28 citation statements)
references
References 9 publications
1
25
1
1
Order By: Relevance
“…The signals were parameterized by means of 37 pulse features divided in the following subsets: amplitude features (reflection point; full width at half maximum), time domain statistics (mean; median; standard deviation; variance; interquartile range; skewness; kurtosis; root mean square; entropy), cross-correlation features (maximum of crosscorrelation with template waveform), wavelet features (relative power at six levels of wavelets for two mother wavelets, Haar and Db4) and frequency domain statistics (first-to fourth-order moments in the frequency domain; median frequency; spectral entropy; total spectral power and peak amplitude in frequency band) [3,15,29,37]. Most of these features are summarized in Table 1.…”
Section: Feature Creationmentioning
confidence: 99%
“…The signals were parameterized by means of 37 pulse features divided in the following subsets: amplitude features (reflection point; full width at half maximum), time domain statistics (mean; median; standard deviation; variance; interquartile range; skewness; kurtosis; root mean square; entropy), cross-correlation features (maximum of crosscorrelation with template waveform), wavelet features (relative power at six levels of wavelets for two mother wavelets, Haar and Db4) and frequency domain statistics (first-to fourth-order moments in the frequency domain; median frequency; spectral entropy; total spectral power and peak amplitude in frequency band) [3,15,29,37]. Most of these features are summarized in Table 1.…”
Section: Feature Creationmentioning
confidence: 99%
“…Empirical Mode Decomposition (EMD) [10] technique is widely used for noise suppression of speech signal [11][12][13] and biomedical signal processing [14][15][16][17][18]. Electrical load has, to some extent, similarity with speech and biomedical signal.…”
Section: Introductionmentioning
confidence: 99%
“…Even though EMD has achieved optimal results in data processing (Diez et al 2009, Molla et al, 2010, several shortcomings are presented when this technique is used in multichannel data sets such as EEG. The IMFs from different time series do not necessarily correspond to the same frequency, and different time series may end up having a different number of IMFs.…”
Section: Multivariate Empirical Mode Decomposition (Memd) Applied To mentioning
confidence: 99%