作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程

• 开发研究与工程应用 • 上一篇    下一篇

基于自适应邻域相似关系的脑-机接口识别算法

刘美春,王芬   

  1. (广东金融学院 应用数学系,广州 510521)
  • 收稿日期:2015-12-31 出版日期:2017-01-15 发布日期:2017-01-13
  • 作者简介:刘美春(1980—),女,讲师、博士,主研方向为模式识别;王芬,副教授、博士。
  • 基金资助:
    广东高校优秀青年创新人才培养计划项目(2013LYM_0060,2014KQNCX187);广东省自然科学基金(2015A030310426);广东金融学院创新强校工程项目“随机扰动下具有反应扩散的神经网络的稳定性与混沌同步研究”(0000-E205010015005017);中山大学广东省计算科学重点实验室开放课题基金(2016006)。

Recognition Algorithm for Brain-Computer Interface Based on Adaptive Neighborhood Similarity Relation

LIU Meichun,WANG Fen   

  1. (Department of Applied of Mathematics,Guangdong University of Finance,Guangzhou 510521,China)
  • Received:2015-12-31 Online:2017-01-15 Published:2017-01-13

摘要: 针对脑-机接口(BCI)研究数据分布不确定问题,提出基于自适应邻域相似关系识别算法,以提取脑电信号中的运动相关电位(MRP)特征。采用映射后MRP模式的邻域相似关系,寻找最佳投影方向,使得映射后异类与同类的样本期望距离的比值最大。利用映射后的样本距离确定相似概率,避免在高维空间使用距离方程可能产生的不适应性。在随机生成数据和BCI竞赛公开数据应用中,该算法的识别效果优于线性判别分析算法和共空间模式算法。

关键词: 特征提取, 脑-机接口, 脑电信号, 相似性, 期望距离, 共空间模式

Abstract: Focusing on the problem of the unclear data distribution in the Brain-Computer Interface(BCI),a novel approach based on Adaptive Neighborhood Similarity(ANS) is proposed for the Movement Related Potential(MRP).Using the pattern similarity,it searches the optimal direction which maximizes the ratio of the expectation distance between the between-class and the within-class.The similar probabilities are calculated directly with the samples’ distances in the mapped space,avoiding the inapplicability caused by using traditional distances measurement in high dimensional space directly.In the application of two datasets,one generated randomly and another from BCI competition,the classification accuracy of ANS is slightly better than the comparison algorithms of Linear Discriminative Analysis(LDA) and Discriminative Spatial Pattern(DSP).The results evaluate the effectiveness of ANS algorithm.

Key words: feature extraction, Brain-Computer Interface(BCI), Electroencephalogram(EEG) signal, similarity, expectation distance, Discriminative Spatial Pattern(DSP)

中图分类号: