脑机接口中基于MRP的半监督判决空间模式法  

Semi-Supervised Discriminative Spatial Patterns Based on MRP for Brain-Computer Interfaces

作　　者：吕俊[1] 

机构地区：[1]广东工业大学自动化学院,广东广州510006

出　　处：《电子科技》2011年第8期33-35,共3页Electronic Science and Technology

基　　金：国家自然科学基金资助项目(U0635001;U0835003)

摘　　要：在脑-机接口研究中,如果训练样本少,判决空间模式法不能很好地提取运动相关电位特征。为此,文中在半监督框架下,采用自训练方法,引入分类置信度高的无标记样本,迭代学习MRP的空间判决模式。实验结果验证了所提算法的有效性。In the study of brain-computer interface,if the number of training samples is small,the features of movement related potentials can not be well extracted by discriminative spatial pattern algorithm.Thus in this paper,semi-supervised self-training scheme is employed to induce the unlabelled samples with high confidences and learn the discriminative patterns of MRPs iteratively.The results of experiments demonstrate the effectiveness of the proposed algorithm.

关 键 词：脑-机接口 运动相关电位 判决空间模式法 

分 类 号：TN911.7[电子电信—通信与信息系统] R318[电子电信—信息与通信工程]