Abstract The use of transfer learning algorithms to improve the accuracy of classification recognition is a hot research problem in the application of motion imagination brain-computer interface. Traditional model algorithms for sample transfer and feature transfer do not achieve ideal transfer results when the sample size is small or there is a significant difference between the source domain data and the target domain data. The motion imagery classification algorithm based on Euclidean alignment (EA) and improved jointly class centroid matching and local manifold self-learning (CMMS) migration learning organically combines the advantages of sample migration and feature migration to further improve the classification accuracy while considering the sample itself. Firstly, the samples are subjected to EA in the source and target domains to reduce the differences in data distribution between the source and target domains. Secondly, the CMMS method is improved based on minimizing the maximum mean difference (MMD) to filter the data in the source domain and again reduce the differences in distribution between the samples in the source and target domains. Finally, the method is applied to the BCI competition dataset for offline testing and online experiments. The experimental results show that compared with SVM, JDA, BDA, EasyTL, GFK, and CMMS, the recognition accuracy of the migration learning model is improved by 14.38%, 8.5%, 5.8%, 10.4%, 11.8%, and 5.7%, respectively.
DU Yi-hao,CHANG Chao-qun,DU Zheng, et al. Classification and Recognition Algorithm of Motion Imagination Based on Improved Transfer Learning[J]. Acta Metrologica Sinica, 2023, 44(11): 1740-1748.
Zhang W, Deng L F, Zhang L, et al. A survey on negative transfer［J］. IEEE/CAA Journal of Automatica Sinica, 2023, 10(2): 25.
［2］
Chen X G, Yang C, Chen J J, et al. New trends in the development of brain-computer interface technology-based on research progress from 2019 to 2020 ［J］. Science & Technology Review, 2021, 39(19): 56-65.
Tang B, Chen S S, Guo B B,et al. Fault Diagnosis of Rolling Bearings Based on Migration of Characteristic Parameters
［6］
Abdeltawab A, Ahmad A. Classification of Motor Imagery EEG Signals Using Machine Learning［C］//2020 IEEE 10th International Conference on System Engineering and Technology (ICSET). IEEE, 2020: 196-201.
Zhang D F, Yang Z H, Cheng S H, et al. Wheel Hub Recognition Based on ResNet50 and Transfer Learning［J］. Acta Metrologica Sinica, 202022, 43(11): 1412-1417.
Du Y H, Liu Z J, Fu Z H, et al. Motion Imagery Classification Algorithm Research and Application Based on Hybrid Transfer Learning［J］. Acta Metrologica Sinica, 2021, 42(5): 629-637.
［12］
Giles J, Ang K K, Mihaylova L, et al. Weighted Transfer Learning of Dynamic Time Warped Data for Motor Imagery based Brain Computer Interfaces［C］//2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society(EMBC). IEEE, 2020: 2977-2980.
［14］
Jeng P Y, Wei C S, Jung T P, et al. Low-dimensional subject representation-based transfer learning in EEG decoding［J］. IEEE Journal of Biomedical and Health Informatics, 2020, 25(6): 1915-1925.
［15］
Tian L, Tang Y, Hu L, et al. Domain adaptation by class centroid matching and local manifold self-learning［J］. IEEE Transactions on Image Processing, 2020, 29: 9703-9718.
［17］
Salazar-Varas R, Vazquez R A. Evaluating the effect of the cutoff frequencies during the pre-processing stage of motor imagery EEG signals classification［J］. Biomedical Signal Processing and Control, 2019, 54: 101592.
［19］
Jayaram V, Alamgir M, Altun Y, et al. Transfer learning in brain-computer interfaces［J］. IEEE Computational Intelligence Magazine, 2016, 11(1): 20-31.
［3］
Flesher S N, Downey J E, Weiss J M, et al. A brain-computer interface that evokes tactile sensations improves robotic arm control［J］. Science, 2021, 372(6544): 831-836.
Liu X, Zhang P, Li Y J, et al. Brain-computer interface technology based on motor imaging applied to brain function activation and neural network remodeling in stroke patients with paralysis［J］. Chinese Journal of Neurology, 2021, 54(10): 1089-1093.
［5］
Kanagasabai P S, Gautam R, Rathna G N. Brain-computer interface learning system for Quadriplegics［C］//2016 IEEE 4th international conference on MOOCs, innovation and technology in education (MITE). IEEE, 2016: 258-262.
［7］
Zhuang F, Qi Z, Duan K, et al. A comprehensive survey on transfer learning［J］. Proceedings of the IEEE, 2020, 109(1): 43-76.
Azab A M, Mihaylova L, Ang K K, et al. Weighted transfer learning for improving motor imagery-based brain-computer interface［J］. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2019, 27(7): 1352-1359.
Fahim A. K and starting means for k-means algorithm［J］. Journal of Computational Science, 2021, 55: 101445.
［13］
He H, Wu D. Transfer learning for brain-computer interfaces: A Euclidean space data alignment approach［J］. IEEE Transactions on Biomedical Engineering, 2019, 67(2): 399-410.
［21］
Li D, Fang X, Wang J, et al. Optimization of the Channels Selection and Classification Accuracy Based on Maximum Mean Discrepancy in BCI System［C］//2019 Chinese Control Conference (CCC). IEEE, 2019: 7517-7521.
2023, Vol. 44 
