Research on motor imagery recognition based on feature fusion and transfer adaptive boosting

• Published in: Sheng wu yi xue gong cheng xue za zhi Vol. 42; no. 1; p. 9
• Main Authors: Zhang, Yuxin, Zhang, Chenrui, Sun, Shihao, Xu, Guizhi
• Format: Journal Article
• Language: Chinese
• Published: China 25.02.2025
• Subjects: Algorithms; Brain-Computer Interfaces; Electroencephalography; Humans; Imagination - physiology; Neural Networks, Computer; Pattern Recognition, Automated - methods; Support Vector Machine; Wavelet Analysis; Brain-computer interface; Feature fusion; Motor imagery; Transfer adaptive boosting; Transfer learning
• ISSN: 1001-5515
• DOI: 10.7507/1001-5515.202304067

This paper proposes a motor imagery recognition algorithm based on feature fusion and transfer adaptive boosting (TrAdaboost) to address the issue of low accuracy in motor imagery (MI) recognition across subjects, thereby increasing the reliability of MI-based brain-computer interfaces (BCI) for cross-individual use. Using the autoregressive model, power spectral density and discrete wavelet transform, time-frequency domain features of MI can be obtained, while the filter bank common spatial pattern is used to extract spatial domain features, and multi-scale dispersion entropy is employed to extract nonlinear features. The IV-2a dataset from the 4 International BCI Competition was used for the binary classification task, with the pattern recognition model constructed by combining the improved TrAdaboost integrated learning algorithm with support vector machine (SVM), nearest neighbor (KNN), and mind evolutionary algorithm-based back propagation (MEA-BP) neural network. The results show that the SVM-based TrAd