Study of MI-BCI classification method based on the Riemannian transform of personalized EEG spatiotemporal features
Motor imagery (MI) is a traditional paradigm of brain-computer interface (BCI) and can assist users in creating direct connections between their brains and external equipment. The common spatial patterns algorithm is the most popular spatial filtering technique for collecting EEG signal features in...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
AIMS Press
2023-05-01
|
| Series: | Mathematical Biosciences and Engineering |
| Subjects: | |
| Online Access: | https://www.aimspress.com/article/doi/10.3934/mbe.2023554?viewType=HTML |
| _version_ | 1797794102457139200 |
|---|---|
| author | Xiaotong Ding Lei Yang Congsheng Li |
| author_facet | Xiaotong Ding Lei Yang Congsheng Li |
| author_sort | Xiaotong Ding |
| collection | DOAJ |
| description | Motor imagery (MI) is a traditional paradigm of brain-computer interface (BCI) and can assist users in creating direct connections between their brains and external equipment. The common spatial patterns algorithm is the most popular spatial filtering technique for collecting EEG signal features in MI-based BCI systems. Due to the defect that it only considers the spatial information of EEG signals and is susceptible to noise interference and other issues, its performance is diminished. In this study, we developed a Riemannian transform feature extraction method based on filter bank fusion with a combination of multiple time windows. First, we proposed the multi-time window data segmentation and recombination method by combining it with a filter group to create new data samples. This approach could capture individual differences due to the variation in time-frequency patterns across different participants, thereby improving the model's generalization performance. Second, Riemannian geometry was used for feature extraction from non-Euclidean structured EEG data. Then, considering the non-Gaussian distribution of EEG signals, the neighborhood component analysis (NCA) algorithm was chosen for feature selection. Finally, to meet real-time requirements and a low complexity, we employed a Support Vector Machine (SVM) as the classification algorithm. The proposed model achieved improved accuracy and robustness. In this study, we proposed an algorithm with superior performance on the BCI Competition IV dataset 2a, achieving an accuracy of 89%, a kappa value of 0.73 and an AUC of 0.9, demonstrating advanced capabilities. Furthermore, we analyzed data collected in our laboratory, and the proposed method achieved an accuracy of 77.4%, surpassing other comparative models. This method not only significantly improved the classification accuracy of motor imagery EEG signals but also bore significant implications for applications in the fields of brain-computer interfaces and neural engineering. |
| first_indexed | 2024-03-13T02:57:56Z |
| format | Article |
| id | doaj.art-be0574073a9e4ee98f98a1eb46936629 |
| institution | Directory Open Access Journal |
| issn | 1551-0018 |
| language | English |
| last_indexed | 2024-03-13T02:57:56Z |
| publishDate | 2023-05-01 |
| publisher | AIMS Press |
| record_format | Article |
| series | Mathematical Biosciences and Engineering |
| spelling | doaj.art-be0574073a9e4ee98f98a1eb469366292023-06-28T01:45:57ZengAIMS PressMathematical Biosciences and Engineering1551-00182023-05-01207124541247110.3934/mbe.2023554Study of MI-BCI classification method based on the Riemannian transform of personalized EEG spatiotemporal featuresXiaotong Ding0Lei Yang 1Congsheng Li2China Academy of Information and Communications Technology, Beijing, ChinaChina Academy of Information and Communications Technology, Beijing, China China Academy of Information and Communications Technology, Beijing, ChinaMotor imagery (MI) is a traditional paradigm of brain-computer interface (BCI) and can assist users in creating direct connections between their brains and external equipment. The common spatial patterns algorithm is the most popular spatial filtering technique for collecting EEG signal features in MI-based BCI systems. Due to the defect that it only considers the spatial information of EEG signals and is susceptible to noise interference and other issues, its performance is diminished. In this study, we developed a Riemannian transform feature extraction method based on filter bank fusion with a combination of multiple time windows. First, we proposed the multi-time window data segmentation and recombination method by combining it with a filter group to create new data samples. This approach could capture individual differences due to the variation in time-frequency patterns across different participants, thereby improving the model's generalization performance. Second, Riemannian geometry was used for feature extraction from non-Euclidean structured EEG data. Then, considering the non-Gaussian distribution of EEG signals, the neighborhood component analysis (NCA) algorithm was chosen for feature selection. Finally, to meet real-time requirements and a low complexity, we employed a Support Vector Machine (SVM) as the classification algorithm. The proposed model achieved improved accuracy and robustness. In this study, we proposed an algorithm with superior performance on the BCI Competition IV dataset 2a, achieving an accuracy of 89%, a kappa value of 0.73 and an AUC of 0.9, demonstrating advanced capabilities. Furthermore, we analyzed data collected in our laboratory, and the proposed method achieved an accuracy of 77.4%, surpassing other comparative models. This method not only significantly improved the classification accuracy of motor imagery EEG signals but also bore significant implications for applications in the fields of brain-computer interfaces and neural engineering.https://www.aimspress.com/article/doi/10.3934/mbe.2023554?viewType=HTMLriemannian tangent spacemotor imagery (mi)electroencephalogram (eeg)brain-computer interface (bci)filter banksneighborhood component analysis |
| spellingShingle | Xiaotong Ding Lei Yang Congsheng Li Study of MI-BCI classification method based on the Riemannian transform of personalized EEG spatiotemporal features Mathematical Biosciences and Engineering riemannian tangent space motor imagery (mi) electroencephalogram (eeg) brain-computer interface (bci) filter banks neighborhood component analysis |
| title | Study of MI-BCI classification method based on the Riemannian transform of personalized EEG spatiotemporal features |
| title_full | Study of MI-BCI classification method based on the Riemannian transform of personalized EEG spatiotemporal features |
| title_fullStr | Study of MI-BCI classification method based on the Riemannian transform of personalized EEG spatiotemporal features |
| title_full_unstemmed | Study of MI-BCI classification method based on the Riemannian transform of personalized EEG spatiotemporal features |
| title_short | Study of MI-BCI classification method based on the Riemannian transform of personalized EEG spatiotemporal features |
| title_sort | study of mi bci classification method based on the riemannian transform of personalized eeg spatiotemporal features |
| topic | riemannian tangent space motor imagery (mi) electroencephalogram (eeg) brain-computer interface (bci) filter banks neighborhood component analysis |
| url | https://www.aimspress.com/article/doi/10.3934/mbe.2023554?viewType=HTML |
| work_keys_str_mv | AT xiaotongding studyofmibciclassificationmethodbasedontheriemanniantransformofpersonalizedeegspatiotemporalfeatures AT leiyang studyofmibciclassificationmethodbasedontheriemanniantransformofpersonalizedeegspatiotemporalfeatures AT congshengli studyofmibciclassificationmethodbasedontheriemanniantransformofpersonalizedeegspatiotemporalfeatures |