Classification of Motor Imagery EEG Signals Based on Deep Autoencoder and Convolutional Neural Network Approach
The technology of the brain-computer interface (BCI) employs electroencephalogram (EEG) signals to establish direct interaction between the human body and its surroundings with promising applications in medical rehabilitative services and cognitive science. Deep learning approaches, particularly the...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9766103/ |
| _version_ | 1818202289035280384 |
|---|---|
| author | Jamal F. Hwaidi Thomas M. Chen |
| author_facet | Jamal F. Hwaidi Thomas M. Chen |
| author_sort | Jamal F. Hwaidi |
| collection | DOAJ |
| description | The technology of the brain-computer interface (BCI) employs electroencephalogram (EEG) signals to establish direct interaction between the human body and its surroundings with promising applications in medical rehabilitative services and cognitive science. Deep learning approaches, particularly the detection and analysis of motor imagery signals using convolutional neural network (CNN) frameworks have produced outstanding results in the BCI system in recent years. The complex process of data representation, on the other hand, limits practical applications, and the end-to-end approach reduces the accuracy of recognition. Moreover, since noise and other signal sources can interfere with brain electrical capacitance, EEG classifiers are difficult to improve and have limited generalisation ability. To address these issues, this paper proposes a new approach for EEG motor imagery signal classification by using a variational autoencoder to remove noise from the signals, followed by a combination of deep autoencoder (DAE) and a CNN architecture to classify EEG motor imagery signals which is capable of training a deep neural network to replicate its input to output using encoding and decoding operations. Experimental results show that the proposed approach for motor imagery EEG signal classification is feasible and that it outperforms current CNN-based approaches and several traditional machine learning approaches. |
| first_indexed | 2024-12-12T03:07:05Z |
| format | Article |
| id | doaj.art-1dc8b698d0434c9a9e26d85bab17a8e7 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-12T03:07:05Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-1dc8b698d0434c9a9e26d85bab17a8e72022-12-22T00:40:29ZengIEEEIEEE Access2169-35362022-01-0110480714808110.1109/ACCESS.2022.31719069766103Classification of Motor Imagery EEG Signals Based on Deep Autoencoder and Convolutional Neural Network ApproachJamal F. Hwaidi0https://orcid.org/0000-0003-3638-5654Thomas M. Chen1Department of Electrical and Electronic Engineering, City, University of London, London, U.K.Department of Electrical and Electronic Engineering, City, University of London, London, U.K.The technology of the brain-computer interface (BCI) employs electroencephalogram (EEG) signals to establish direct interaction between the human body and its surroundings with promising applications in medical rehabilitative services and cognitive science. Deep learning approaches, particularly the detection and analysis of motor imagery signals using convolutional neural network (CNN) frameworks have produced outstanding results in the BCI system in recent years. The complex process of data representation, on the other hand, limits practical applications, and the end-to-end approach reduces the accuracy of recognition. Moreover, since noise and other signal sources can interfere with brain electrical capacitance, EEG classifiers are difficult to improve and have limited generalisation ability. To address these issues, this paper proposes a new approach for EEG motor imagery signal classification by using a variational autoencoder to remove noise from the signals, followed by a combination of deep autoencoder (DAE) and a CNN architecture to classify EEG motor imagery signals which is capable of training a deep neural network to replicate its input to output using encoding and decoding operations. Experimental results show that the proposed approach for motor imagery EEG signal classification is feasible and that it outperforms current CNN-based approaches and several traditional machine learning approaches.https://ieeexplore.ieee.org/document/9766103/Electroencephalographydeep autoencoderconvolutional neural networkvariational autoencodermotor imagery |
| spellingShingle | Jamal F. Hwaidi Thomas M. Chen Classification of Motor Imagery EEG Signals Based on Deep Autoencoder and Convolutional Neural Network Approach IEEE Access Electroencephalography deep autoencoder convolutional neural network variational autoencoder motor imagery |
| title | Classification of Motor Imagery EEG Signals Based on Deep Autoencoder and Convolutional Neural Network Approach |
| title_full | Classification of Motor Imagery EEG Signals Based on Deep Autoencoder and Convolutional Neural Network Approach |
| title_fullStr | Classification of Motor Imagery EEG Signals Based on Deep Autoencoder and Convolutional Neural Network Approach |
| title_full_unstemmed | Classification of Motor Imagery EEG Signals Based on Deep Autoencoder and Convolutional Neural Network Approach |
| title_short | Classification of Motor Imagery EEG Signals Based on Deep Autoencoder and Convolutional Neural Network Approach |
| title_sort | classification of motor imagery eeg signals based on deep autoencoder and convolutional neural network approach |
| topic | Electroencephalography deep autoencoder convolutional neural network variational autoencoder motor imagery |
| url | https://ieeexplore.ieee.org/document/9766103/ |
| work_keys_str_mv | AT jamalfhwaidi classificationofmotorimageryeegsignalsbasedondeepautoencoderandconvolutionalneuralnetworkapproach AT thomasmchen classificationofmotorimageryeegsignalsbasedondeepautoencoderandconvolutionalneuralnetworkapproach |