基于改进MEDA算法的脑电情绪识别

针对普通机器学习算法与迁移学习在应用方面的局限性,利用改进流形嵌入分布对齐算法(MEDA)算法解决跨被试情绪识别中准确率低的问题.其中MEDA通过流行特征变换来减小域之间的数据漂移,并能够自适应定量估计边缘分布和条件分布的权重大小.针对特征维度大且有可能存在不良特征的问题,提出改进MEDA算法,即引入改进最小冗余最大相...

EEG emotion recognition based on the improved MEDA

The limited applications of the traditional machine learning algorithms and the transfer learning algorithm are considered inthis study. The improved manifold embedded distribution alignment (MEDA) algorithm is utilized to improve the detection accuracy inthe cross-subject emotion recognition. The MEDA algorithm in the manifold space could reduce the data drift between domains by popularfeature transformation, which can adaptively and quantitatively estimate the weights of edge distribution and conditional distribution. Thisarticle proposes an improved manifold space distribution alignment algorithm to address the problems of large feature dimension andpossible bad features. An improved minimum redundancy maximum correlation algorithm is introduced for feature selection. Thecomputational complexity is reduced, the associated features are selected, and the decision-level fusion on multiple groups of recognitionresults in multi-source domain is performed to further improve the transfer learning effect. The analysis results of SEED data set and themeasured data set show that the distribution alignment algorithm in the manifold space is better than those of the support vector machine,transfer component analysis and joint distribution adaptation. The overall recognition accuracy is improved by 8. 97% , 4. 00% , and2. 89% , respectively. The improved distribution alignment algorithm in manifold space has improved the recognition accuracy of eachsubject, and the overall recognition accuracy is improved by 3. 36% . Therefore, the effectiveness of the proposed method is verified.