Spatial filtering method and device based on Lp/q-mixed norm

The invention discloses a spatial filtering method and device based on an Lp/q-mixed norm. Two types of electroencephalogram signals are modeled by using an Lp-norm and an Lq-norm respectively; basedon the Lp/q-mixed norm, an objective function is constructed, and an iterative algorithm for solving an optimal spatial filtering vector is provided, so that fine discrimination information is extracted, a beneficial classification method is provided for a brain-computer interface system, features with discrimination capability are sought, and electroencephalogram signal classification is furthercarried out. The method has the effect of resisting the influence of abnormal values on the classification performance, and compared with a traditional method, the provided method has better classification performance, robustness and stability. 本发明公开了一种基于Lp/q-混合范数的空间滤波方法及装置，分别用Lp-范数和Lq-范数对两类脑电信号建模，基于该Lp/q-混合范数构造目标函数，并提供了一种求解最优空间滤波向量的迭代算法，从而提取精细判别信息，为脑-机接口系统提供有益的分类方法，寻求具有判别力的特征，进而进行脑电信号分类。本发明方法具有抵制异常值对分类性能影响的作用，所提方法较传统的方法具有