Improved Domain Adaptation Network Based on Wasserstein Distance for Motor Imagery EEG Classification
Motor Imagery (MI) paradigm is critical in neural rehabilitation and gaming. Advances in brain-computer interface (BCI) technology have facilitated the detection of MI from electroencephalogram (EEG). Previous studies have proposed various EEG-based classification algorithms to identify the MI, howe...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Transactions on Neural Systems and Rehabilitation Engineering |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10035017/ |
| _version_ | 1797805068071731200 |
|---|---|
| author | Qingshan She Tie Chen Feng Fang Jianhai Zhang Yunyuan Gao Yingchun Zhang |
| author_facet | Qingshan She Tie Chen Feng Fang Jianhai Zhang Yunyuan Gao Yingchun Zhang |
| author_sort | Qingshan She |
| collection | DOAJ |
| description | Motor Imagery (MI) paradigm is critical in neural rehabilitation and gaming. Advances in brain-computer interface (BCI) technology have facilitated the detection of MI from electroencephalogram (EEG). Previous studies have proposed various EEG-based classification algorithms to identify the MI, however, the performance of prior models was limited due to the cross-subject heterogeneity in EEG data and the shortage of EEG data for training. Therefore, inspired by generative adversarial network (GAN), this study aims to propose an improved domain adaption network based on Wasserstein distance, which utilizes existing labeled data from multiple subjects (source domain) to improve the performance of MI classification on a single subject (target domain). Specifically, our proposed framework consists of three components, including a feature extractor, a domain discriminator, and a classifier. The feature extractor employs an attention mechanism and a variance layer to improve the discrimination of features extracted from different MI classes. Next, the domain discriminator adopts the Wasserstein matrix to measure the distance between source domain and target domain, and aligns the data distributions of source and target domain via adversarial learning strategy. Finally, the classifier uses the knowledge acquired from the source domain to predict the labels in the target domain. The proposed EEG-based MI classification framework was evaluated by two open-source datasets, the BCI Competition IV Datasets 2a and 2b. Our results demonstrated that the proposed framework could enhance the performance of EEG-based MI detection, achieving better classification results compared with several state-of-the-art algorithms. In conclusion, this study is promising in helping the neural rehabilitation of different neuropsychiatric diseases. |
| first_indexed | 2024-03-13T05:45:28Z |
| format | Article |
| id | doaj.art-183f401044b34f9d95caf7bb241a5d98 |
| institution | Directory Open Access Journal |
| issn | 1558-0210 |
| language | English |
| last_indexed | 2024-03-13T05:45:28Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Transactions on Neural Systems and Rehabilitation Engineering |
| spelling | doaj.art-183f401044b34f9d95caf7bb241a5d982023-06-13T20:09:50ZengIEEEIEEE Transactions on Neural Systems and Rehabilitation Engineering1558-02102023-01-01311137114810.1109/TNSRE.2023.324184610035017Improved Domain Adaptation Network Based on Wasserstein Distance for Motor Imagery EEG ClassificationQingshan She0https://orcid.org/0000-0001-5206-9833Tie Chen1https://orcid.org/0000-0002-0642-3480Feng Fang2Jianhai Zhang3Yunyuan Gao4https://orcid.org/0000-0003-2128-2185Yingchun Zhang5https://orcid.org/0000-0002-1927-4103School of Automation, Hangzhou Dianzi University, Hangzhou, ChinaSchool of Automation, Hangzhou Dianzi University, Hangzhou, ChinaDepartment of Biomedical Engineering, University of Houston, Houston, TX, USAKey Laboratory of Brain Machine Collaborative Intelligence of Zhejiang Province, Hangzhou, ChinaSchool of Automation, Hangzhou Dianzi University, Hangzhou, ChinaDepartment of Biomedical Engineering, University of Houston, Houston, TX, USAMotor Imagery (MI) paradigm is critical in neural rehabilitation and gaming. Advances in brain-computer interface (BCI) technology have facilitated the detection of MI from electroencephalogram (EEG). Previous studies have proposed various EEG-based classification algorithms to identify the MI, however, the performance of prior models was limited due to the cross-subject heterogeneity in EEG data and the shortage of EEG data for training. Therefore, inspired by generative adversarial network (GAN), this study aims to propose an improved domain adaption network based on Wasserstein distance, which utilizes existing labeled data from multiple subjects (source domain) to improve the performance of MI classification on a single subject (target domain). Specifically, our proposed framework consists of three components, including a feature extractor, a domain discriminator, and a classifier. The feature extractor employs an attention mechanism and a variance layer to improve the discrimination of features extracted from different MI classes. Next, the domain discriminator adopts the Wasserstein matrix to measure the distance between source domain and target domain, and aligns the data distributions of source and target domain via adversarial learning strategy. Finally, the classifier uses the knowledge acquired from the source domain to predict the labels in the target domain. The proposed EEG-based MI classification framework was evaluated by two open-source datasets, the BCI Competition IV Datasets 2a and 2b. Our results demonstrated that the proposed framework could enhance the performance of EEG-based MI detection, achieving better classification results compared with several state-of-the-art algorithms. In conclusion, this study is promising in helping the neural rehabilitation of different neuropsychiatric diseases.https://ieeexplore.ieee.org/document/10035017/Motor imagery (MI)deep neural networkelectroencephalogram (EEG)adversarial learningdomain adaptationmachine learning |
| spellingShingle | Qingshan She Tie Chen Feng Fang Jianhai Zhang Yunyuan Gao Yingchun Zhang Improved Domain Adaptation Network Based on Wasserstein Distance for Motor Imagery EEG Classification IEEE Transactions on Neural Systems and Rehabilitation Engineering Motor imagery (MI) deep neural network electroencephalogram (EEG) adversarial learning domain adaptation machine learning |
| title | Improved Domain Adaptation Network Based on Wasserstein Distance for Motor Imagery EEG Classification |
| title_full | Improved Domain Adaptation Network Based on Wasserstein Distance for Motor Imagery EEG Classification |
| title_fullStr | Improved Domain Adaptation Network Based on Wasserstein Distance for Motor Imagery EEG Classification |
| title_full_unstemmed | Improved Domain Adaptation Network Based on Wasserstein Distance for Motor Imagery EEG Classification |
| title_short | Improved Domain Adaptation Network Based on Wasserstein Distance for Motor Imagery EEG Classification |
| title_sort | improved domain adaptation network based on wasserstein distance for motor imagery eeg classification |
| topic | Motor imagery (MI) deep neural network electroencephalogram (EEG) adversarial learning domain adaptation machine learning |
| url | https://ieeexplore.ieee.org/document/10035017/ |
| work_keys_str_mv | AT qingshanshe improveddomainadaptationnetworkbasedonwassersteindistanceformotorimageryeegclassification AT tiechen improveddomainadaptationnetworkbasedonwassersteindistanceformotorimageryeegclassification AT fengfang improveddomainadaptationnetworkbasedonwassersteindistanceformotorimageryeegclassification AT jianhaizhang improveddomainadaptationnetworkbasedonwassersteindistanceformotorimageryeegclassification AT yunyuangao improveddomainadaptationnetworkbasedonwassersteindistanceformotorimageryeegclassification AT yingchunzhang improveddomainadaptationnetworkbasedonwassersteindistanceformotorimageryeegclassification |