A CSP\AM-BA-SVM Approach for Motor Imagery BCI System

Selim, Sahar; Tantawi, Manal M.; Shedeed, Howida A.; Badr, Amr

doi:10.1109/access.2018.2868178

Cited by 120 publications

(87 citation statements)

References 66 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…An additional reason for using logistic regression as a classifier is that the model weights for each feature can be easily assessed, enabling the evaluation of what features of brain activity are most predictive. This is not true of many machine learning classification methods such as support vector machines (Liu et al, 2012;Selim et al, 2018). It is important to note that the EEG data used for machine learning consisted of brainrelated activity in which artifact components have been largely removed by filtering, ASR, ICA, and ICLabel.…”

Section: Machine Learningmentioning

confidence: 99%

Music Improvisation Is Characterized by Increase EEG Spectral Power in Prefrontal and Perceptual Motor Cortical Sources and Can be Reliably Classified From Non-improvisatory Performance

Sasaki

Iversen

Callan

2019

Front. Hum. Neurosci.

View full text Add to dashboard Cite

This study expores neural activity underlying creative processes through the investigation of music improvisation. Fourteen guitar players with a high level of improvisation skill participated in this experiment. The experimental task involved playing 32-s alternating blocks of improvisation and scales on guitar. electroencephalography (EEG) data was measured continuously throughout the experiment. In order to remove potential artifacts and extract brain-related activity the following signal processing techniques were employed: bandpass filtering, Artifact Subspace Reconstruction, and Independent Component Analysis (ICA). For each participant, artifact related independent components (ICs) were removed from the EEG data and only ICs found to be from brain activity were retained. Source localization using this brain-related activity was carried out using sLORETA. Greater activity for improvisation over scale was found in multiple frequency bands (theta, alpha, and beta) localized primarily in the medial frontal cortex (MFC), Middle frontal gyrus (MFG), anterior cingulate, polar medial prefrontal cortex (MPFC), premotor cortex (PMC), pre and postcentral gyrus (PreCG and PostCG), superior temporal gyrus (STG), inferior parietal lobule (IPL), and the temporalparietal junction. Together this collection of brain regions suggests that improvisation was mediated by processes involved in coordinating planned sequences of movement that are modulated in response to ongoing environmental context through monitoring and feedback of sensory states in relation to internal plans and goals. Machine-learning using Common Spatial Patterns (CSP) for EEG feature extraction attained a mean of over 75% classification performance for improvisation vs. scale conditions across participants. These machine-learning results are a step towards the development of a brain-computer interface that could be used for neurofeedback training to improve creativity.

show abstract

Section: Machine Learningmentioning

confidence: 99%

Music Improvisation Is Characterized by Increase EEG Spectral Power in Prefrontal and Perceptual Motor Cortical Sources and Can be Reliably Classified From Non-improvisatory Performance

Sasaki

Iversen

Callan

2019

Front. Hum. Neurosci.

View full text Add to dashboard Cite

show abstract

“…In this paper dataset 2a from BCI Competition IV is used, which is publicly available for researchers [31]. The dataset has recordings of EEG signals from nine subjects while they performed MI tasks.…”

Section: Datasetmentioning

confidence: 99%

Investigation of EEG Signal Classification Techniques for Brain Computer Interface

Ghumman,

Singh

2020

IJEAT

View full text Add to dashboard Cite

Brain-computer interface (BCI) has emerged as a popular research domain in recent years. The use of electroencephalography (EEG) signals for motor imagery (MI) based BCI has gained widespread attention. The first step in its implementation is to fetch EEG signals from scalp of human subject. The preprocessing of EEG signals is done before applying feature extraction, selection and classification techniques as main steps of signal processing. In preprocessing stage, artifacts are removed from raw brain signals before these are input to next stage of feature extraction. Subsequently classifier algorithms are used to classify selected features into intended MI tasks. The major challenge in a BCI systems is to improve classification accuracy of a BCI system. In this paper, an approach based on Support Vector Machine (SVM), is proposed for signal classification to improve accuracy of the BCI system. The parameters of kernel are varied to attain improvement in classification accuracy. Independent component analysis (ICA) technique is used for preprocessing and filter bank common spatial pattern (FBCSP) for feature extraction and selection. The proposed approach is evaluated on data set 2a of BCI Competition IV by using 5-fold crossvalidation procedure. Results show that it performs better in terms of classification accuracy, as compared to other methods reported in literature.

show abstract

“…The classification was performed by SVM classifier which is a common, state of the art, and efficient method for BCI applications [31,55,56]. Using the kernel function, SVM classifier can create nonlinear hyper plates to discriminate the data of each class by maximizing the margin across the classes and minimizing misclassified samples.…”

Section: Classificationmentioning

confidence: 99%

Identifying motor imagery activities in brain computer interfaces based on the intelligent selection of most informative timeframe

2020

View full text Add to dashboard Cite

Removing the contribution of dispensable mental activities dispersed across the electroencephalogram (EEG) signal improves the interpretability and efficiency of the intended neuronal responses to control a brain computer interface (BCI). Performing motor imagery tasks causes proper formation of special patterns at a specific timeframe of the EEG signal. The accurate selection of this optimal informative timeframe has not yet been investigated. Previous studies have considered an identic portion of data for all individuals, while neglecting that the duration and delay takes for the motor imagery brain activities to be well reflected in EEG signals vary between individuals. We propose an intelligent hybrid genetic algorithm-support vector machine (SVM) method to select the most stimulated timeframe of interest. The method also selects the most distinctive subset of features (through a comprehensive fused set of temporal, spectral and wavelet inspected information) while simultaneously optimize the SVM classifier's parameters. Evaluation results show that not only the most stimulated timeframe has a short duration but also occurs after a specific delay: that they are different between individuals. Using this optimal timeframe, the classification accuracy increased up to 92.14% for Graz 2003 and 89.00%, 84.81% and 85.00% for O3, S4 and X11 subjects of Graz 2005 database respectively. These results that were obtained despite the use of a small set of features confirm that this intelligent method can be effective in increasing the computational speed while decreasing the computational complexity which provides the potential capability of including in real time BCI systems.

show abstract

A CSP\AM-BA-SVM Approach for Motor Imagery BCI System

Cited by 120 publications

References 66 publications

Music Improvisation Is Characterized by Increase EEG Spectral Power in Prefrontal and Perceptual Motor Cortical Sources and Can be Reliably Classified From Non-improvisatory Performance

Music Improvisation Is Characterized by Increase EEG Spectral Power in Prefrontal and Perceptual Motor Cortical Sources and Can be Reliably Classified From Non-improvisatory Performance

Investigation of EEG Signal Classification Techniques for Brain Computer Interface

Identifying motor imagery activities in brain computer interfaces based on the intelligent selection of most informative timeframe

Contact Info

Product

Resources

About