Decoding Motor Imagery through Common Spatial Pattern Filters at the EEG Source Space

Xygonakis, Ioannis; Athanasiou, Alkinoos; Pandria, Niki; Kugiumtzis, Dimitris; Bamidis, Panagiotis D.

doi:10.1155/2018/7957408

Cited by 53 publications

(37 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For feature extraction, Common Spatial www.ijacsa.thesai.org Pattern has obtained good popularity [29]. It finds spatial filters that maximize the ratio of the variance of data of classes [30]. Spatially filtered signal can be described by (1).…”

Section: B Proposed Pipelinementioning

confidence: 99%

Classification of Non-Discriminant ERD/ERS Comprising Motor Imagery Electroencephalography Signals

Asi¹,

Sultan²,

Muneer³

et al. 2020

IJACSA

View full text Add to dashboard Cite

Classification of Motor Imagery (MI) Electroencephalography (EEG) signals has always been an important aspect of Brain Computer Interface (BCI) systems. Event Related Desynchronization (ERD)/ Event Related Synchronization (ERS) plays a significant role in finding discriminant features of MI EEG signals. ERD/ERS is one type and Evoked Potential (EP) is another type of brain response. This study focuses upon the classification of MI EEG signals by Removing Evoked Potential (REP) from non-discriminant MI EEG data in filter band selection, called REP. This optimization is done to enhance the classification performance. A comprehensive comparison of several pipelines is presented by using famous feature extraction methods, namely Common Spatial Pattern (CSP), XDawn. The effectiveness of REP is demonstrated on the PhysioNet dataset which is an online data resource. Comparison is done between the performance of pipelines including proposed one (Common Spatial Pattern (CSP) and Gaussian Process Classifier (GPC)) as well as before and after applying REP. It is observed that the REP approach has improved the classification accuracy of all the subjects used as well as all the pipelines, including state of the art algorithms, up to 20%.

show abstract

Section: B Proposed Pipelinementioning

confidence: 99%

Classification of Non-Discriminant ERD/ERS Comprising Motor Imagery Electroencephalography Signals

Asi¹,

Sultan²,

Muneer³

et al. 2020

IJACSA

View full text Add to dashboard Cite

show abstract

“…Most of the studies reported in the literature focused on sensor-based BCIs. First, raw sensor data are filtered into two groups in this study: 0.1-30 Hz and µ rhythm (8)(9)(10)(11)(12)(13). Table 2 lists the classification success of sensor data for 118 channels.…”

Section: Resultsmentioning

confidence: 99%

“…The subjects performed motor imagery tasks during their recordings in the dataset used for training and tests. The somatosensory cortical areas responsible for the tasks to be classified are included in the feature vectors (as in [10]) to improve classification performance. Region of interest areas are shown in Figure 3.…”

Section: Region Of Interest (Roi) Selection For Motor Imagerymentioning

confidence: 99%

“…In 2018, Li et al [7] studied motor imagery tasks with the same dataset used in this work and showed that source domain analysis outperforms sensor domain analysis. Alazrai et al [8] reported success in finger movements, Lu et al [9] controlled a vehicle using EEG signals, and Xygonakis et al [10], in 2018, studied four-class motor imagery in the EEG source space and improved its accuracy compared to the sensor data analysis. Qingsong et al [11] analyzed four-task motor imagery in 2019, while Zhang et al [12] reported in 2019 that children can successfully use BCIs.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Comprehensive sLORETA Study on the Contribution of Cortical Somatomotor Regions to Motor Imagery

2019

View full text Add to dashboard Cite

Brain-computer interface (BCI) is a technology used to convert brain signals to control external devices. Researchers have designed and built many interfaces and applications in the last couple of decades. BCI is used for prevention, detection, diagnosis, rehabilitation, and restoration in healthcare. EEG signals are analyzed in this paper to help paralyzed people in rehabilitation. The electroencephalogram (EEG) signals recorded from five healthy subjects are used in this study. The sensor level EEG signals are converted to source signals using the inverse problem solution. Then, the cortical sources are calculated using sLORETA methods at nine regions marked by a neurophysiologist. The features are extracted from cortical sources by using the common spatial pattern (CSP) method and classified by a support vector machine (SVM). Both the sensor and the computed cortical signals corresponding to motor imagery of the hand and foot are used to train the SVM algorithm. Then, the signals outside the training set are used to test the classification performance of the classifier. The 0.1-30 Hz and mu rhythm band-pass filtered activity is also analyzed for the EEG signals. The classification performance and recognition of the imagery improved up to 100% under some conditions for the cortical level. The cortical source signals at the regions contributing to motor commands are investigated and used to improve the classification of motor imagery.

show abstract

“…Considering the recent paper on EEG for detection of sleep disorder, deep learning method was introduced, resulting in state of the art performance [11]. Ensemble classification model with independent classifiers used for the CSP features resulted in good classification accuracy and concluded on modification of classifier characteristics [12]. K-NN serves the efficient classifier when used for the statistical features derived from the wavelet decomposed signals [9].…”

Section: Introductionmentioning

confidence: 99%

Analysis of classification methods suitable for band limited spatially filtered EEG signal applicable to non-invasive BCI

Ganorkar¹,

Raut²

2019

IJITEE

View full text Add to dashboard Cite

Electroencephalographic (EEG) signals are the preferred input for non-invasive Brain-Computer Interface (BCI). Efficient signal processing strategies, including feature extraction and classification, are required to distinguish the underlying task of BCI. This work proposes the optimized common spatial pattern(CSP) filtering technique as the feature extraction method for collecting the spatially spread variation of the signal. The bandpass filter (BPF) designed for this work assures the availability of event-related synchronized (ERS) and event-related desynchronized (ERD) signal as input to the spatial filter. This work takes consideration of the area-specific electrodes for feature formation. This work further proposes a comparative analysis of classifier algorithms for classification accuracy(CA), sensitivity and specificity and the considered algorithms are Support Vector Machine(SVM), Linear Discriminant Analysis(LDA), and K-Nearest Neighbor(KNN). Performance parameters considered are CA, sensitivity, and selectivity, which can judge the method not only for high CA but also inclining towards the particular class. Thus it will direct in the selection of appropriate classifier as well as tuning the classifier to get the balanced results. In this work, CA, the prior performance parameter is obtained to be 88.2% sensitivity of 94.2% and selectivity 82.2% for the cosine KNN classifier. SVM with linear kernel function also gives the comparable results, thus concluding that the robust classifiers perform well for all parameters in case of CSP for feature extraction.

show abstract

Decoding Motor Imagery through Common Spatial Pattern Filters at the EEG Source Space

Cited by 53 publications

References 51 publications

Classification of Non-Discriminant ERD/ERS Comprising Motor Imagery Electroencephalography Signals

Classification of Non-Discriminant ERD/ERS Comprising Motor Imagery Electroencephalography Signals

A Comprehensive sLORETA Study on the Contribution of Cortical Somatomotor Regions to Motor Imagery

Analysis of classification methods suitable for band limited spatially filtered EEG signal applicable to non-invasive BCI

Contact Info

Product

Resources

About