Research on EEG signal classification of motor imagery based on AE and Transformer
The motor imagery brain-computer interface has always been the focus of scholars.But traditional system cannot accurately extract significant signals and has low classification accuracy.To overcome such difficulty, a new Transformer model was proposed based on the auto-encoder (AE).The filter bank c...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
China InfoCom Media Group
2023-03-01
|
| Series: | 物联网学报 |
| Subjects: | |
| Online Access: | http://www.wlwxb.com.cn/zh/article/doi/10.11959/j.issn.2096-3750.2023.00310/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841533743502721024 |
|---|---|
| author | Rui JIANG Liuting SUN Xiaoming WANG Dapeng LI Youyun XU |
| author_facet | Rui JIANG Liuting SUN Xiaoming WANG Dapeng LI Youyun XU |
| author_sort | Rui JIANG |
| collection | DOAJ |
| description | The motor imagery brain-computer interface has always been the focus of scholars.But traditional system cannot accurately extract significant signals and has low classification accuracy.To overcome such difficulty, a new Transformer model was proposed based on the auto-encoder (AE).The filter bank common spatial pattern (FBCSP) was used to extract the features of multiple frequency bands, and the AE was exploited to obtain the dimensionality-reduced feature matrix.Finally, it considered the influence of the global signal features by the position encoding of the Transformer model and considered the internal correlation of the feature matrix by using the multi-head self-attention mechanism.By comparison with the traditional K-nearest neighbors (KNN) system based on linear discriminant analysis (LDA), the experimental results validates that the classification effect of AE+Transformer model is better than that of LDA+KNN system.It shows that the improved algorithm is suitable for the binary classification of motor imagery. |
| format | Article |
| id | doaj-art-9facc689518a407db8652c8efda52fcc |
| institution | Kabale University |
| issn | 2096-3750 |
| language | zho |
| publishDate | 2023-03-01 |
| publisher | China InfoCom Media Group |
| record_format | Article |
| series | 物联网学报 |
| spelling | doaj-art-9facc689518a407db8652c8efda52fcc2025-01-15T02:54:40ZzhoChina InfoCom Media Group物联网学报2096-37502023-03-01711812859579820Research on EEG signal classification of motor imagery based on AE and TransformerRui JIANGLiuting SUNXiaoming WANGDapeng LIYouyun XUThe motor imagery brain-computer interface has always been the focus of scholars.But traditional system cannot accurately extract significant signals and has low classification accuracy.To overcome such difficulty, a new Transformer model was proposed based on the auto-encoder (AE).The filter bank common spatial pattern (FBCSP) was used to extract the features of multiple frequency bands, and the AE was exploited to obtain the dimensionality-reduced feature matrix.Finally, it considered the influence of the global signal features by the position encoding of the Transformer model and considered the internal correlation of the feature matrix by using the multi-head self-attention mechanism.By comparison with the traditional K-nearest neighbors (KNN) system based on linear discriminant analysis (LDA), the experimental results validates that the classification effect of AE+Transformer model is better than that of LDA+KNN system.It shows that the improved algorithm is suitable for the binary classification of motor imagery.http://www.wlwxb.com.cn/zh/article/doi/10.11959/j.issn.2096-3750.2023.00310/motor imagerydeep learningauto-encoderattention moduleTransformer model |
| spellingShingle | Rui JIANG Liuting SUN Xiaoming WANG Dapeng LI Youyun XU Research on EEG signal classification of motor imagery based on AE and Transformer 物联网学报 motor imagery deep learning auto-encoder attention module Transformer model |
| title | Research on EEG signal classification of motor imagery based on AE and Transformer |
| title_full | Research on EEG signal classification of motor imagery based on AE and Transformer |
| title_fullStr | Research on EEG signal classification of motor imagery based on AE and Transformer |
| title_full_unstemmed | Research on EEG signal classification of motor imagery based on AE and Transformer |
| title_short | Research on EEG signal classification of motor imagery based on AE and Transformer |
| title_sort | research on eeg signal classification of motor imagery based on ae and transformer |
| topic | motor imagery deep learning auto-encoder attention module Transformer model |
| url | http://www.wlwxb.com.cn/zh/article/doi/10.11959/j.issn.2096-3750.2023.00310/ |
| work_keys_str_mv | AT ruijiang researchoneegsignalclassificationofmotorimagerybasedonaeandtransformer AT liutingsun researchoneegsignalclassificationofmotorimagerybasedonaeandtransformer AT xiaomingwang researchoneegsignalclassificationofmotorimagerybasedonaeandtransformer AT dapengli researchoneegsignalclassificationofmotorimagerybasedonaeandtransformer AT youyunxu researchoneegsignalclassificationofmotorimagerybasedonaeandtransformer |