Improvement of the Classification Accuracy of Steady-State Visual Evoked Potential-Based Brain-Computer Interfaces by Combining L1-MCCA with SVM
Canonical correlation analysis (CCA) has been used for the steady-state visual evoked potential (SSVEP) based brain-computer interface (BCI) for a long time. However, the reference signal of CCA is relatively simple and lacks subject-specific information. Moreover, over-fitting may occur when a shor...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-12-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/11/23/11453 |
| _version_ | 1797508017097277440 |
|---|---|
| author | Yuhang Gao Juanning Si Sijin Wu Weixian Li Hao Liu Jianhu Chen Qing He Yujin Zhang |
| author_facet | Yuhang Gao Juanning Si Sijin Wu Weixian Li Hao Liu Jianhu Chen Qing He Yujin Zhang |
| author_sort | Yuhang Gao |
| collection | DOAJ |
| description | Canonical correlation analysis (CCA) has been used for the steady-state visual evoked potential (SSVEP) based brain-computer interface (BCI) for a long time. However, the reference signal of CCA is relatively simple and lacks subject-specific information. Moreover, over-fitting may occur when a short time window (TW) length was used in CCA. In this article, an optimized L1-regularized multiway canonical correlation analysis (L1-MCCA) is combined with a support vector machine (SVM) to overcome the aforementioned shortcomings in CCA. The correlation coefficients obtained by L1-MCCA were transferred into a particle-swarm-optimization (PSO)-optimized support vector machine (SVM) classifier to improve the classification accuracy. The performance of the proposed method was evaluated and compared with the traditional CCA and power spectral density (PSD) methods. The results showed that the accuracy of the L1-MCCA-PSO-SVM was 96.36% and 98.18% respectively when the TW lengths were 2 s and 6 s. This accuracy is higher than that of the traditional CCA and PSD methods. |
| first_indexed | 2024-03-10T04:57:38Z |
| format | Article |
| id | doaj.art-cf8fd66eada04e2d94f8951b5a4436e3 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T04:57:38Z |
| publishDate | 2021-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-cf8fd66eada04e2d94f8951b5a4436e32023-11-23T02:08:26ZengMDPI AGApplied Sciences2076-34172021-12-0111231145310.3390/app112311453Improvement of the Classification Accuracy of Steady-State Visual Evoked Potential-Based Brain-Computer Interfaces by Combining L1-MCCA with SVMYuhang Gao0Juanning Si1Sijin Wu2Weixian Li3Hao Liu4Jianhu Chen5Qing He6Yujin Zhang7School of Instrumentation Science and Opto-Electronics Engineering, Beijing Information Science and Technology University, Beijing 100192, ChinaSchool of Instrumentation Science and Opto-Electronics Engineering, Beijing Information Science and Technology University, Beijing 100192, ChinaSchool of Instrumentation Science and Opto-Electronics Engineering, Beijing Information Science and Technology University, Beijing 100192, ChinaSchool of Instrumentation Science and Opto-Electronics Engineering, Beijing Information Science and Technology University, Beijing 100192, ChinaBrainnetome Center, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, ChinaSchool of Instrumentation Science and Opto-Electronics Engineering, Beijing Information Science and Technology University, Beijing 100192, ChinaSchool of Instrumentation Science and Opto-Electronics Engineering, Beijing Information Science and Technology University, Beijing 100192, ChinaBrainnetome Center, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, ChinaCanonical correlation analysis (CCA) has been used for the steady-state visual evoked potential (SSVEP) based brain-computer interface (BCI) for a long time. However, the reference signal of CCA is relatively simple and lacks subject-specific information. Moreover, over-fitting may occur when a short time window (TW) length was used in CCA. In this article, an optimized L1-regularized multiway canonical correlation analysis (L1-MCCA) is combined with a support vector machine (SVM) to overcome the aforementioned shortcomings in CCA. The correlation coefficients obtained by L1-MCCA were transferred into a particle-swarm-optimization (PSO)-optimized support vector machine (SVM) classifier to improve the classification accuracy. The performance of the proposed method was evaluated and compared with the traditional CCA and power spectral density (PSD) methods. The results showed that the accuracy of the L1-MCCA-PSO-SVM was 96.36% and 98.18% respectively when the TW lengths were 2 s and 6 s. This accuracy is higher than that of the traditional CCA and PSD methods.https://www.mdpi.com/2076-3417/11/23/11453steady-state visual evoked potential (SSVEP)brain-computer interface (BCI)l1-regularized multiway canonical correlation analysis (L1-MCCA)support vector machine (SVM)particle swarm optimization (PSO) |
| spellingShingle | Yuhang Gao Juanning Si Sijin Wu Weixian Li Hao Liu Jianhu Chen Qing He Yujin Zhang Improvement of the Classification Accuracy of Steady-State Visual Evoked Potential-Based Brain-Computer Interfaces by Combining L1-MCCA with SVM Applied Sciences steady-state visual evoked potential (SSVEP) brain-computer interface (BCI) l1-regularized multiway canonical correlation analysis (L1-MCCA) support vector machine (SVM) particle swarm optimization (PSO) |
| title | Improvement of the Classification Accuracy of Steady-State Visual Evoked Potential-Based Brain-Computer Interfaces by Combining L1-MCCA with SVM |
| title_full | Improvement of the Classification Accuracy of Steady-State Visual Evoked Potential-Based Brain-Computer Interfaces by Combining L1-MCCA with SVM |
| title_fullStr | Improvement of the Classification Accuracy of Steady-State Visual Evoked Potential-Based Brain-Computer Interfaces by Combining L1-MCCA with SVM |
| title_full_unstemmed | Improvement of the Classification Accuracy of Steady-State Visual Evoked Potential-Based Brain-Computer Interfaces by Combining L1-MCCA with SVM |
| title_short | Improvement of the Classification Accuracy of Steady-State Visual Evoked Potential-Based Brain-Computer Interfaces by Combining L1-MCCA with SVM |
| title_sort | improvement of the classification accuracy of steady state visual evoked potential based brain computer interfaces by combining l1 mcca with svm |
| topic | steady-state visual evoked potential (SSVEP) brain-computer interface (BCI) l1-regularized multiway canonical correlation analysis (L1-MCCA) support vector machine (SVM) particle swarm optimization (PSO) |
| url | https://www.mdpi.com/2076-3417/11/23/11453 |
| work_keys_str_mv | AT yuhanggao improvementoftheclassificationaccuracyofsteadystatevisualevokedpotentialbasedbraincomputerinterfacesbycombiningl1mccawithsvm AT juanningsi improvementoftheclassificationaccuracyofsteadystatevisualevokedpotentialbasedbraincomputerinterfacesbycombiningl1mccawithsvm AT sijinwu improvementoftheclassificationaccuracyofsteadystatevisualevokedpotentialbasedbraincomputerinterfacesbycombiningl1mccawithsvm AT weixianli improvementoftheclassificationaccuracyofsteadystatevisualevokedpotentialbasedbraincomputerinterfacesbycombiningl1mccawithsvm AT haoliu improvementoftheclassificationaccuracyofsteadystatevisualevokedpotentialbasedbraincomputerinterfacesbycombiningl1mccawithsvm AT jianhuchen improvementoftheclassificationaccuracyofsteadystatevisualevokedpotentialbasedbraincomputerinterfacesbycombiningl1mccawithsvm AT qinghe improvementoftheclassificationaccuracyofsteadystatevisualevokedpotentialbasedbraincomputerinterfacesbycombiningl1mccawithsvm AT yujinzhang improvementoftheclassificationaccuracyofsteadystatevisualevokedpotentialbasedbraincomputerinterfacesbycombiningl1mccawithsvm |