A Study and Performance Analysis of Three Paradigms of Wavelet Coefficients Combinations in Three-Class Motor Imagery Based BCI

Baziyad, Ayad G.; Djemal, Ridha

doi:10.1109/isms.2014.40

Cited by 7 publications

(4 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To reduce the leakage, the FFT can be applied with a finite time window of the signal [ 27 ]. Preliminary results without using phase reconstruction are presented in [ 28 ] providing a limited accuracy rate from 58% to 75%.…”

Section: Methodsmentioning

confidence: 99%

Three-Class EEG-Based Motor Imagery Classification Using Phase-Space Reconstruction Technique

et al. 2016

Self Cite

View full text Add to dashboard Cite

Over the last few decades, brain signals have been significantly exploited for brain-computer interface (BCI) applications. In this paper, we study the extraction of features using event-related desynchronization/synchronization techniques to improve the classification accuracy for three-class motor imagery (MI) BCI. The classification approach is based on combining the features of the phase and amplitude of the brain signals using fast Fourier transform (FFT) and autoregressive (AR) modeling of the reconstructed phase space as well as the modification of the BCI parameters (trial length, trial frequency band, classification method). We report interesting results compared with those present in the literature by utilizing sequential forward floating selection (SFFS) and a multi-class linear discriminant analysis (LDA), our findings showed superior classification results, a classification accuracy of 86.06% and 93% for two BCI competition datasets, with respect to results from previous studies.

show abstract

Section: Methodsmentioning

confidence: 99%

Three-Class EEG-Based Motor Imagery Classification Using Phase-Space Reconstruction Technique

et al. 2016

Self Cite

View full text Add to dashboard Cite

show abstract

“…Our proposed algorithm, SVM-CCA-CS, also performs better than existing methods. Baziyad et al [47] used SVM for three classification MI tasks, and the average classification accuracy was 75%. Oh et al [48] applied SIFT and the Hjorth parameter feature for MI tasks, and the classification accuracy rates were 74.7% and 71.6%, respectively.…”

Section: Discussionmentioning

confidence: 99%

A motor-imagery channel-selection method based on SVM-CCA-CS

Wang¹,

Cao²,

Liú³

et al. 2020

Meas. Sci. Technol.

View full text Add to dashboard Cite

In electroencephalography, multi-channel electroencephalogram (EEG) signals are usually utilized to improve classification accuracy. However, a large set of EEG channels increases the computational complexity, reduces the real-time performance and causes wearability difficulties. Channel selection methods have been widely investigated to reduce the number of channels with an acceptable loss of accuracy for EEG-based motor-imagery recognition. In this paper, we present a novel algorithm, called Support Vector Machine-Canonical Correlation Analysis-Channel Selection (SVM-CCA-CS). First, the energy features of the wavelet packet subnodes of the motor-imagery EEG signals are extracted. Then the weights of feature groups are calculated as initial channel weights, based on the CCA algorithm. The initial channel weights are further adjusted, according to the contribution of each channel to the classification accuracy via SVM, and the top channels with larger weights are eventually selected. The results show that the average accuracy of all subjects can reach 80.03% by using the first 30 channels with the largest weights from among the total of 118 channels. For the right hand and foot motor-imagery tasks, the generally applicable optimal channels are mostly located in the left hemisphere. Our generally applicable channel observation of the whole brain cortex suggests contralateral control correspondence: for unilateral motor imagery, the optimal channels are concentrated in the contralateral hemisphere. This is consistent with the contralateral control of the body by the human brain: the majority of the human motor and sensory fibers tend to control the contralateral limbs and pass through the midline of the body. Our proposed method provides optimal acquisition and analysis of the positions of EEG signals in specific motor-imagery tasks.

show abstract

“…Many researches use the frequency band 8-30 Hz for the classification of MI tasks classification [9,44,46]. Baziyad et al [47] used a band-pass filter of 8-32 Hz in his study.…”

Section: Filter and Other Preprocessingmentioning

confidence: 99%

“…This is a supervised spatial filter which maximizes the variance of band-pass filtered EEG signal from one class while minimizing their variance from the other class [44]. Ramoser et al [47] used the CSP technique for three subjects and ended up with the classification accuracy of 90.8%, 92.7%, and 99.7%. Guger et al [57] used CSP to analyze EEG in real-time for providing feedback to the subject.…”

Section: Common Spatial Pattern (Csp)mentioning

confidence: 99%

A Review on the Components of EEG-based Motor Imagery Classification with Quantitative Comparison

Rahman¹,

Joadder²

2017

Appl. Theory Comput. Technol.

View full text Add to dashboard Cite

Motor Imagery (MI) is a voluntary modulation of brain signals for specific action without real limb movement. It is essential to classify MI signal to design a brain computer interface (BCI). BCI involves a number of signal processing steps, and a lot of techniques have been developed for each step. There can be numerous combinations of these techniques at different steps that can be employed to design a BCI. This work focuses on MI-based BCI using EEG signal and reviews the existing techniques. More importantly, a detailed comparative study is performed to explore the important combinations of methods by comparing their performance quantitatively. Often a method, which performs very good in one combination, can be bad performer in other combinations and it is a dilemma for the researchers to select appropriate methods for their desired BCI application.In our performance analysis, we have systematically included the variations of methods in each step of BCI such that it gives idea to BCI researchers how each method in one step fits best with specific combinations of methods in other steps. We have shown that how much each step is sensitive towards overall performance of the BCI system.We hope that this work helps, especially for new researchers, to provide a better guideline for designing more efficient BCI system.

show abstract

A Study and Performance Analysis of Three Paradigms of Wavelet Coefficients Combinations in Three-Class Motor Imagery Based BCI

Cited by 7 publications

References 22 publications

Three-Class EEG-Based Motor Imagery Classification Using Phase-Space Reconstruction Technique

Three-Class EEG-Based Motor Imagery Classification Using Phase-Space Reconstruction Technique

A motor-imagery channel-selection method based on SVM-CCA-CS

A Review on the Components of EEG-based Motor Imagery Classification with Quantitative Comparison

Contact Info

Product

Resources

About