Fast and Accurate Multiclass Inference for MI-BCIs Using Large Multiscale Temporal and Spectral Features

Hersche, Michael; Rellstab, Tino; Schiavone, Pasquale Davide; Cavigelli, Lukas; Benini, Luca; Rahimi, Abbas

doi:10.23919/eusipco.2018.8553378

Cited by 53 publications

(64 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A visual illustration of a single trial is shown in Figure 6(a). Previous studies that used this dataset, have mostly considered the [3−6] s window as the interval during which motor imagery tasks are performed [37,42,23,25,52,69,72] for the analysis. Therefore, we also extracted this 3-s motor imagery interval from each trial.…”

Section: Methodsmentioning

confidence: 99%

Early classification of motor tasks using dynamic functional connectivity graphs from EEG

Shamsi¹,

Haddad²,

Najafizadeh³

2021

J. Neural Eng.

View full text Add to dashboard Cite

Objective. Classification of electroencephalography (EEG) signals with high accuracy using short recording intervals has been a challenging problem in developing brain computer interfaces (BCIs). This paper presents a novel feature extraction method for EEG recordings to tackle this problem. Approach. The proposed approach is based on the concept that the brain functions in a dynamic manner, and utilizes dynamic functional connectivity graphs. The EEG data is first segmented into intervals during which functional networks sustain their connectivity. Functional connectivity networks for each identified segment are then localized, and graphs are constructed, which will be used as features. To take advantage of the dynamic nature of the generated graphs, a Long Short Term Memory (LSTM) classifier is employed for classification. Main results. Features extracted from various durations of poststimulus EEG data associated with motor execution and imagery tasks are used to test the performance of the classifier. Results show an average accuracy of 85.32% about only 500 ms after stimulus presentation. Significance. Our results demonstrate, for the first time, that using the proposed feature extraction method, it is possible to classify motor tasks from EEG recordings using a short interval of the data in the order of hundreds of milliseconds (e.g. 500 ms).This duration is considerably shorter than what has been reported before. These results will have significant implications for improving the effectiveness and the speed of BCIs, particularly for those used in assistive technologies.

show abstract

Section: Methodsmentioning

confidence: 99%

Early classification of motor tasks using dynamic functional connectivity graphs from EEG

Shamsi¹,

Haddad²,

Najafizadeh³

2021

J. Neural Eng.

View full text Add to dashboard Cite

show abstract

“…In fact, the improvement brought by Riemannian geometry is due to the consideration of the non-linear information contained in the covariance matrices, thus better extracting features, which are usually discarded by the linear space filtering methods. On the basis, the multi-band Riemannian method can use a small amount of calibration data to extract the noise robust features, and achieve better results ( Islam et al, 2017 , 2018 ; Hersche et al, 2018 ). In order to further improve the multi-band Riemannian method, this article uses a non-parametric method of MANOVA based on the sum of squared distances ( Anderson, 2001 ) to select frequency bands that are separable for specific subjects, and multi-scale division is performed on the multi-channel EEG signals in these frequency bands.…”

Section: Discussionmentioning

confidence: 99%

“…The sub-band selection method adopted can be based on the mutual information between features and class labels, thereby effectively extract the frequency band of a specific subject, and further improve the performance of MI-BCI ( Islam et al, 2018 ). In addition, in order to overcome the limitation of using fixed band window analysis in MI-BCI, Hersche et al (2018) proposed a multi-scale filter bank TSM (MFBTSM), in which FB contains the frequency bands are multi-scale and overlapping. At the same time, multi-scale and overlapping time windows are divided, so that multiple time windows are used to analyze EEG trials and perform FB analysis in each time window.…”

Section: Introductionmentioning

confidence: 99%

A New Subject-Specific Discriminative and Multi-Scale Filter Bank Tangent Space Mapping Method for Recognition of Multiclass Motor Imagery

Gong

Liu

et al. 2021

Front. Hum. Neurosci.

View full text Add to dashboard Cite

Objective: Tangent Space Mapping (TSM) using the geometric structure of the covariance matrices is an effective method to recognize multiclass motor imagery (MI). Compared with the traditional CSP method, the Riemann geometric method based on TSM takes into account the nonlinear information contained in the covariance matrix, and can extract more abundant and effective features. Moreover, the method is an unsupervised operation, which can reduce the time of feature extraction. However, EEG features induced by MI mental activities of different subjects are not the same, so selection of subject-specific discriminative EEG frequency components play a vital role in the recognition of multiclass MI. In order to solve the problem, a discriminative and multi-scale filter bank tangent space mapping (DMFBTSM) algorithm is proposed in this article to design the subject-specific Filter Bank (FB) so as to effectively recognize multiclass MI tasks.Methods: On the 4-class BCI competition IV-2a dataset, first, a non-parametric method of multivariate analysis of variance (MANOVA) based on the sum of squared distances is used to select discriminative frequency bands for a subject; next, a multi-scale FB is generated according to the range of these frequency bands, and then decompose multi-channel EEG of the subject into multiple sub-bands combined with several time windows. Then TSM algorithm is used to estimate Riemannian tangent space features in each sub-band and finally a liner Support Vector Machines (SVM) is used for classification.Main Results: The analysis results show that the proposed discriminative FB enhances the multi-scale TSM algorithm, improves the classification accuracy and reduces the execution time during training and testing. On the 4-class BCI competition IV-2a dataset, the average session to session classification accuracy of nine subjects reached 77.33 ± 12.3%. When the training time and the test time are similar, the average classification accuracy is 2.56% higher than the latest TSM method based on multi-scale filter bank analysis technology. When the classification accuracy is similar, the training speed is increased by more than three times, and the test speed is increased two times more. Compared with Supervised Fisher Geodesic Minimum Distance to the Mean (Supervised FGMDRM), another new variant based on Riemann geometry classifier, the average accuracy is 3.36% higher, we also compared with the latest Deep Learning method, and the average accuracy of 10-fold cross validation improved by 2.58%.Conclusion: Research shows that the proposed DMFBTSM algorithm can improve the classification accuracy of MI tasks.Significance: Compared with the MFBTSM algorithm, the algorithm proposed in this article is expected to select frequency bands with good separability for specific subject to improve the classification accuracy of multiclass MI tasks and reduce the feature dimension to reduce training time and testing time.

show abstract

“…Previous studies that used this dataset, have mostly considered the [3 − 6] s window as the interval during which motor imagery tasks are performed [37, 42, 23, 25, 52, 69, 72] for the analysis. Therefore, we also extracted this 3-s motor imagery interval from each trial.…”

Section: Methodsmentioning

confidence: 99%

Early Classification of Motor Tasks Using Dynamic Functional Connectivity Graphs from EEG

Shamsi

Haddad

Najafizadeh

2020

Preprint

View full text Add to dashboard Cite

ObjectiveClassification of electroencephalography (EEG) signals with high accuracy using short recording intervals has been a challenging problem in developing brain computer interfaces (BCIs). This paper presents a novel feature extraction method for EEG recordings to tackle this problem.ApproachThe proposed approach is based on the concept that the brain functions in a dynamic manner, and utilizes dynamic functional connectivity graphs. The EEG data is first segmented into intervals during which functional networks sustain their connectivity. Functional connectivity networks for each identified segment are then localized, and graphs are constructed, which will be used as features. To take advantage of the dynamic nature of the generated graphs, a Long Short Term Memory (LSTM) classifier is employed for classificationMain resultsFeatures extracted from various durations of post-stimulus EEG data associated with motor execution and imagery tasks are used to test the performance of the classifier. Results show an average accuracy of 85.32% using features extracted from only 500 ms of the post-stimulus data.SignificanceOur results demonstrate, for the first time, that using the proposed feature extraction method, it is possible to classify motor tasks from EEG recordings using only few hundreds of milliseconds of the data. This duration is considerably shorter than what has been reported before. These results will have significant implications for improving the effectiveness and the speed of BCIs, particularly for those used in assistive technologies.

show abstract

Fast and Accurate Multiclass Inference for MI-BCIs Using Large Multiscale Temporal and Spectral Features

Cited by 53 publications

References 10 publications

Early classification of motor tasks using dynamic functional connectivity graphs from EEG

Early classification of motor tasks using dynamic functional connectivity graphs from EEG

A New Subject-Specific Discriminative and Multi-Scale Filter Bank Tangent Space Mapping Method for Recognition of Multiclass Motor Imagery

Early Classification of Motor Tasks Using Dynamic Functional Connectivity Graphs from EEG

Contact Info

Product

Resources

About