Efficient Automatic Selection and Combination of Eeg Features in Least Squares Classifiers for Motor Imagery Brain–computer Interfaces

Rodríguez-Bermúdez, Germán; García-Laencina, Pedro J.; Roca-Dorda, Joaquín

doi:10.1142/s0129065713500159

Cited by 56 publications

(34 citation statements)

References 66 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Nonlinear methods such as entropies, fractality dimension [98], synchronization [99] HOS, CD, RQA and detrended fluctuation analysis are applied to the de-noised EEG signals and characteristic features are extracted. The significant features extracted from sleep EEG signals can be classified using learning algorithms such as SVM [100,101], clustering techniques [102,103], classification methods [104,105] and neural networks [106,107,108]. Table 5 summarizes some of the work on sleep stage classification based on R&K standard where classification accuracy was reported.…”

Section: Discussionmentioning

confidence: 99%

Nonlinear Dynamics Measures for Automated EEG-Based Sleep Stage Detection

et al. 2015

View full text Add to dashboard Cite

Background: The brain's continuous neural activity during sleep can be monitored by electroencephalogram (EEG) signals. The EEG wave pattern and frequency vary during five stages of sleep. These subtle variations in sleep EEG signals cannot be easily detected through visual inspection. Summary: A range of time, frequency, time-frequency and nonlinear analysis methods can be applied to understand the complex physiological signals and their chaotic behavior. This paper presents a comprehensive comparative review and analysis of 29 nonlinear dynamics measures for EEG-based sleep stage detection. Key Messages: The characteristic ranges of these features are reported for the five different sleep stages. All nonlinear measures produce clinically significant results, that is, they can discriminate the individual sleep stages. Feature ranking based on the statistical F-value, however, shows that the third order cumulant of higher order spectra yields the most discriminative result. The distinct value ranges for each sleep stage and the discriminative power of the features can be used for sleep disorder diagnosis, treatment monitoring, and drug efficacy assessment.

show abstract

Section: Discussionmentioning

confidence: 99%

Nonlinear Dynamics Measures for Automated EEG-Based Sleep Stage Detection

et al. 2015

View full text Add to dashboard Cite

show abstract

“…Even though a number of papers have been published using the nonlinear methods, there are other nonlinear methods [48,49,50,51,52,53,54,55,56,57,58,59,60,87,88,89,90,91,92,93,94,95,96,97,98] that are worth exploring for the EEG-based diagnosis of depression. As an example, figures 3a and b show sample bispectrum magnitude plots of EEG signals from the left brain hemisphere for normal and depression subjects shown in figure 2, respectively.…”

Section: Nonlinear Methodsmentioning

confidence: 99%

Computer-Aided Diagnosis of Depression Using EEG Signals

Acharya

Sudarshan

Adeli³

et al. 2015

Eur Neurol

169

View full text Add to dashboard Cite

The complex, nonlinear and non-stationary electroencephalogram (EEG) signals are very tedious to interpret visually and highly difficult to extract the significant features from them. The linear and nonlinear methods are effective in identifying the changes in EEG signals for the detection of depression. Linear methods do not exhibit the complex dynamical variations in the EEG signals. Hence, chaos theory and nonlinear dynamic methods are widely used in extracting the EEG signal features for computer-aided diagnosis (CAD) of depression. Hence, this article presents the recent efforts on CAD of depression using EEG signals with a focus on using nonlinear methods. Such a CAD system is simple to use and may be used by the clinicians as a tool to confirm their diagnosis. It should be of a particular value to enable the early detection of depression.

show abstract

“…[14,15] Despite the high variety of techniques, very few studies have addressed the evaluation of combination of methods in an integrated way (i.e. several feature selection algorithms and several learning algorithms).…”

Section: Introductionmentioning

confidence: 99%

Assessment of feature selection and classification methods for recognizing motor imagery tasks from electroencephalographic signals

Vega

Sajed

Mathewson

et al. 2016

AIR

View full text Add to dashboard Cite

Recognition of motor imagery tasks (MI) from electroencephalographic (EEG) signals is crucial for developing rehabilitation and motor assisted devices based on brain-computer interfaces (BCI). Here we consider the challenge of learning a classifier, based on relevant patterns of the EEG signals; this learning step typically involves both feature selection, as well as a base learning algorithm. However, in many cases it is not clear what combination of these methods will yield the best classifier. This paper contributes a detailed assessment of feature selection techniques, viz., squared Pearson's correlation (R 2 ), principal component analysis (PCA), kernel principal component analysis (kPCA) and fast correlation-based filter (FCBF); and the learning algorithms: linear discriminant analysis (LDA), support vector machines (SVM), and Feed Forward Neural Network (NN). A systematic evaluation of the combinations of these methods was performed in three two-class classification scenarios: rest vs. movement, upper vs. lower limb movement and right vs. left hand movement. FCBF in combination with SVM achieved the best results with a classification accuracy of 81.45%, 77.23% and 68.71% in the three scenarios, respectively. Importantly, FCBF determines, based on the feature set, whether a classifier can be learned, and if so, automatically identifies the subset of relevant and non-correlated features. This suggests that FCBF is a powerful method for BCI systems based on MI. Knowledge gained here about procedural combinations has the potential to produce useful BCI tool, that can provide effective motor control for the users.

show abstract

Efficient Automatic Selection and Combination of Eeg Features in Least Squares Classifiers for Motor Imagery Brain–computer Interfaces

Cited by 56 publications

References 66 publications

Nonlinear Dynamics Measures for Automated EEG-Based Sleep Stage Detection

Nonlinear Dynamics Measures for Automated EEG-Based Sleep Stage Detection

Computer-Aided Diagnosis of Depression Using EEG Signals

Assessment of feature selection and classification methods for recognizing motor imagery tasks from electroencephalographic signals

Contact Info

Product

Resources

About