Adaptive subject-based feature extraction in brain–computer interfaces using wavelet packet best basis decomposition

Yang, Banghua; Yan, Guozheng; Yan, Rongguo; Wu, Ting

doi:10.1016/j.medengphy.2006.01.009

Cited by 39 publications

(20 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Figure 3 shows the signal processing steps involved in the analysis of the data. The entire dataset is divided into training and testing [17][18][19]. A common practice is to create a timefrequency distribution (TFD) of the recorded EEG using wavelet transforms and to define features using TFDs for various tasks.…”

Section: Experimental Taskmentioning

confidence: 99%

See 1 more Smart Citation

Multi-class EEG classification of voluntary hand movement directions

et al. 2013

View full text Add to dashboard Cite

show abstract

Section: Experimental Taskmentioning

confidence: 99%

“…A common practice is to create a timefrequency distribution (TFD) of the recorded EEG using wavelet transforms and to define features using TFDs for various tasks. This approach has been applied in movement and motor imagery studies [17,18]. Another technique is to use wavelet decomposition for de-noising data and improving its SNR.…”

Section: Experimental Taskmentioning

confidence: 99%

Multi-class EEG classification of voluntary hand movement directions

et al. 2013

View full text Add to dashboard Cite

show abstract

“…Various techniques have been proposed to detect ERPs in spontaneous EEG, both in time and frequency domain. Among them are Fast-Fourier Transform [13], Wavelet Transform [10,[14][15][16], parametric modeling [12,[17][18][19], neural networks [4,12,20], event-synchronized epochs (EEG segments synchronized with events) averaging [7,21], event-related desynchronization and synchronization [22][23][24], linear discriminant analysis [14], principal components and independent components [25][26][27][28], and other kinds of filters, such as spatial filters [13,14,29].…”

Section: Introductionmentioning

confidence: 99%

Magnitude Squared of Coherence to Detect Imaginary Movement

Filho

Tierra-Criollo

Souza

et al. 2009

EURASIP J. Adv. Signal Process.

View full text Add to dashboard Cite

This work investigates the Magnitude Squared of Coherence (MSC) for detection of Event Related Potentials (ERPs) related to left-hand index finger movement. Initially, ERP presence was examined in different brain areas. To accomplish that, 20 EEG channels were used, positioned according to the 10-20 international system. The grand average, resulting from 10 normal subjects showed, as expected, responses at frontal, central, and parietal areas, particularly evident at the central area (C3, C4, Cz). The MSC, applied to movement imagination related EEG signals, detected a consistent response in frequencies around 0.3-1 Hz (delta band), mainly at central area (C3, Cz, and C4). Ability differences in control imagination among subjects produced different detection performance. Some subjects needed up to 45 events for a detectable response, while for some others only 10 events proved sufficient. Some subjects also required two or three experimental sessions in order to achieve detectable responses. For one subject, response detection was not possible at all. However, due to brain plasticity, it is plausible to expect that training sessions (to practice movement imagination) improve signal-noise ratio and lead to better detection using MSC. Results are sufficiently encouraging as to suggest further exploration of MSC for future BCI application.

show abstract

“…[7] applied the wavelet transform on the uterine signals recorded using abdominal surface electrodes. In literature, the best basis algorithm is used to find the best-adapted WP for a lot of goals such the detection [8,9], denoising [10], feature extraction and classification [11,12], etc. Saito and Coifman introduced the Local Discriminant Bases (LDB) to search a best basis for classification [12].…”

Section: Introductionmentioning

confidence: 99%

Classification of non stationary signals using multiscale decomposition

Chendeb¹,

Khalil²,

Hewson³

et al. 2010

JBiSE

View full text Add to dashboard Cite

The aim of this article is to develop an automatic algorithm for the classification of non stationary signals. The application context is to classify uterine electromyogram (EMG) events to prevent the onset of preterm birth. The idea is to discriminate between the events by allocating them to the physiological classes: contractions, foetus motions, Alvarez or Long Duration Low Frequency waves. Our method is based on the Wavelet Packet (WP) decomposition and the choice of a best basis for classification purpose. Before classification, there is a need to detect events in the recorded signals. The discrimination criterion is based on the calculation of the ratio between intra-class variance and total variance (sum of the intra-class and inter-class variances), calculated directly from the coefficients of the selected WP. We evaluated the performance of the algorithm on real signals by using the classification methods Neural Networks (NN) and Support Vector Machines (SVM). Subband energies of the best selected WP are used as effective features. The determined best basis is applicable to a wide range of uterine EMG signals from large range of patients. In most cases, more than 85% of events are well classified whatever the term of gestation.

show abstract

Adaptive subject-based feature extraction in brain–computer interfaces using wavelet packet best basis decomposition

Cited by 39 publications

References 15 publications

Multi-class EEG classification of voluntary hand movement directions

Multi-class EEG classification of voluntary hand movement directions

Magnitude Squared of Coherence to Detect Imaginary Movement

Classification of non stationary signals using multiscale decomposition

Contact Info

Product

Resources

About