摘要
针对运动想象(MI)跨受试者识别准确率低的问题,本文提出了一种基于特征融合与迁移自适应增强算法(TrAdaboost)结合的MI识别方法,以提高基于MI的脑—机接口(BCI)在跨个体使用时的可靠性。本文采用自回归模型、功率谱密度以及离散小波变换提取出MI的时频域特征,并以滤波器组共空间模式提取出空间域特征,再通过多尺度散布熵提取出非线性特征。然后,将改进的TrAdaboost分别与支持向量机(SVM)、k近邻算法(KNN)、基于思维进化优化的反向传播(MEA-BP)神经网络构建的集成分类器作为模式识别环节,并在MI公开数据集——第四次国际BCI竞赛2a(BCI competition IV-2a)数据集上进行二分类任务识别。结果显示,基于SVM的TrAdaboost集成学习算法在迁移30%目标领域实例数据时的性能最佳,平均分类准确率达86.17%,卡帕(Kappa)系数达0.7233,曲线下面积(AUC)达0.8498。本文研究结果表明,该算法可用于识别跨个体的MI信号,为提高BCI识别模型的泛化能力提供了新的思路。
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 4th 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),k nearest neighbor(KNN),and mind evolutionary algorithm-based back propagation(MEA-BP)neural network.The results show that the SVM-based TrAdaboost integrated learning algorithm has the best performance when 30%of the target domain instance data is migrated,with an average classification accuracy of 86.17%,a Kappa value of 0.7233,and an AUC value of 0.8498.These results suggest that the algorithm can be used to recognize MI signals across individuals,providing a new way to improve the generalization capability of BCI recognition models.
作者
张玉鑫
张辰瑞
孙世豪
徐桂芝
ZHANG Yuxin;ZHANG Chenrui;SUN Shihao;XU Guizhi(Department of Biomedical Engineering,School of Health Sciences and Biomedical Engineering,Hebei University of Technology,TianJin 300130,P.R.China;State Key Laboratory of Reliability and Intelligence of Electrical Equipment,Hebei University of Technology,Tianjin 300130,P.R.China;Tianjin Key Laboratory of Bioelectromagnetic Technology and Intelligent Health,Hebei University of Technology,Tianjin 300130,P.R.China)
出处
《生物医学工程学杂志》
北大核心
2025年第1期9-16,共8页
Journal of Biomedical Engineering
基金
国家重点研发计划项目(2022YFC2402203)
国家自然科学基金项目(52320105008)。
关键词
脑—机接口
迁移学习
特征融合
迁移自适应增强
运动想象
Brain-computer interface
Transfer learning
Feature fusion
Transfer adaptive boosting
Motor imagery
