Classification of left and right hand motor imagery EEG signals by using deep neural networks

Recent studies have demonstrated the disassociation between the mu and beta rhythms of electroencephalogram (EEG) during motor imagery tasks. The proposed algorithm in this paper uses a fully data-driven multivariate empirical mode decomposition (MEMD) in order to obtain the mu and beta rhythms from the nonlinear EEG signals. Then, the strong uncorrelating transform complex common spatial patterns (SUTCCSP) algorithm is applied to the rhythms so that the complex data, constructed with the mu and beta rhythms, becomes uncorrelated and its pseudocovariance provides supplementary power difference information between the two rhythms. The extracted features using SUTCCSP that maximize the interclass variances are classified using various classification algorithms for the separation of the left- and right-hand motor imagery EEG acquired from the Physionet database. This paper shows that the supplementary information of the power difference between mu and beta rhythms obtained using SUTCCSP provides an important feature for the classification of the left- and right-hand motor imagery tasks. In addition, MEMD is proved to be a preferred preprocessing method for the nonlinear and nonstationary EEG signals compared to the conventional IIR filtering. Finally, the random forest classifier yielded a high performance for the classification of the motor imagery tasks.

Download Full-text

Classification of left and right hand movement from EEG signals by HOS features

2018 9th International Symposium on Signal, Image, Video and Communications (ISIVC) ◽

10.1109/isivc.2018.8709084 ◽

2018 ◽

Author(s):

LAGDALI Salwa ◽

RZIZA mohammed

Keyword(s):

Hand Movement ◽

Eeg Signals ◽

Right Hand ◽

Left And Right

Download Full-text

Convolutional Neural Networks with Reusable Full-Dimension-Long Layers for Feature Selection and Classification of Motor Imagery in EEG Signals

Artificial Neural Networks and Machine Learning – ICANN 2020 - Lecture Notes in Computer Science ◽

10.1007/978-3-030-61609-0_7 ◽

2020 ◽

pp. 79-91

Author(s):

Mikhail Tokovarov

Keyword(s):

Neural Networks ◽

Feature Selection ◽

Motor Imagery ◽

Convolutional Neural Networks ◽

Eeg Signals ◽

Full Dimension

Download Full-text

A Novel Simplified Convolutional Neural Network Classification Algorithm of Motor Imagery EEG Signals Based on Deep Learning

Applied Sciences ◽

10.3390/app10051605 ◽

2020 ◽

Vol 10 (5) ◽

pp. 1605 ◽

Cited By ~ 4

Author(s):

Feng Li ◽

Fan He ◽

Fei Wang ◽

Dengyong Zhang ◽

Yi Xia ◽

...

Keyword(s):

Neural Network ◽

Deep Learning ◽

Convolutional Neural Network ◽

Motor Imagery ◽

Recognition Rate ◽

Classification Performance ◽

Eeg Signals ◽

Time Frequency ◽

Right Hand ◽

Left And Right

Left and right hand motor imagery electroencephalogram (MI-EEG) signals are widely used in brain-computer interface (BCI) systems to identify a participant intent in controlling external devices. However, due to a series of reasons, including low signal-to-noise ratios, there are great challenges for efficient motor imagery classification. The recognition of left and right hand MI-EEG signals is vital for the application of BCI systems. Recently, the method of deep learning has been successfully applied in pattern recognition and other fields. However, there are few effective deep learning algorithms applied to BCI systems, particularly for MI based BCI. In this paper, we propose an algorithm that combines continuous wavelet transform (CWT) and a simplified convolutional neural network (SCNN) to improve the recognition rate of MI-EEG signals. Using the CWT, the MI-EEG signals are mapped to time-frequency image signals. Then the image signals are input into the SCNN to extract the features and classify them. Tested by the BCI Competition IV Dataset 2b, the experimental results show that the average classification accuracy of the nine subjects is 83.2%, and the mean kappa value is 0.651, which is 11.9% higher than that of the champion in the BCI Competition IV. Compared with other algorithms, the proposed CWT-SCNN algorithm has a better classification performance and a shorter training time. Therefore, this algorithm could enhance the classification performance of MI based BCI and be applied in real-time BCI systems for use by disabled people.

Download Full-text

Classification of Left and Right Hand Motor Imagery Tasks Based on EEG Frequency Component Selection

2008 2nd International Conference on Bioinformatics and Biomedical Engineering ◽

10.1109/icbbe.2008.801 ◽

2008 ◽

Cited By ~ 2

Author(s):

Xiaomei Pei ◽

Chongxun Zheng

Keyword(s):

Motor Imagery ◽

Frequency Component ◽

Component Selection ◽

Right Hand ◽

Left And Right

Download Full-text

Mental rotation of congenitally absent hands

Journal of the International Neuropsychological Society ◽

10.1017/s1355617708080041 ◽

2007 ◽

Vol 14 (1) ◽

pp. 81-89 ◽

Cited By ~ 36

Author(s):

MARION FUNK ◽

PETER BRUGGER

Keyword(s):

Mental Rotation ◽

Motor Imagery ◽

Visual Recognition ◽

Reaction Times ◽

Right Hand ◽

Left And Right ◽

The One ◽

The Individual ◽

Phantom Limbs

We compared motor imagery performance of normally limbed individuals with that of individuals with one or both hands missing since birth (i.e., hand amelia). To this aim, 14 unilaterally and 2 bilaterally amelic participants performed a task requiring the classification of hands depicted in different degrees of rotation as either a left or a right hand. On the same task, 24 normally limbed participants recapitulated previously reported effects; that is, that the hand motor dominance and, more generally, a lifelong use of hands are important determinants of left–right decisions. Unilaterally amelic participants responded slower to hands corresponding to their absent, compared with their existing, hand. Moreover, left and right hand amelic participants showed prolonged reaction times to hands (whether left or right) depicted in unnatural orientations compared with natural orientations. Among the bilateral amelics, the individual with phantom sensations, but not the one without, showed similar differentiation. These findings demonstrate that the visual recognition of a hand never physically developed is prolonged, but still modulated by different rotation angles. They are further compatible with the view that phantom limbs in hand amelia may constrain motor imagery as much as do amputation phantoms. (JINS, 2008,14, 81–89.)

Download Full-text