• 中国计算机学会会刊
  • 中国科技核心期刊
  • 中文核心期刊

计算机工程与科学 ›› 2020, Vol. 42 ›› Issue (08): 1482-1488.

• 人工智能与数据挖掘 • 上一篇    下一篇

基于样本熵和模式识别的脑电信号识别算法研究

沈晓燕1,2,王雪梅1,王燕1   

  1. (1.南通大学信息科学技术学院,江苏 南通 226019;2.南通大学神经再生协同创新中心,江苏 南通 226019)
  • 收稿日期:2019-10-14 修回日期:2020-01-03 接受日期:2020-08-25 出版日期:2020-08-25 发布日期:2020-08-29
  • 基金资助:
    国家自然科学基金重点项目(61534003);国家自然科学基金面上项目(81371663);江苏省“六大”人才高峰项目

An EEG signal recognition algorithm based on sample entropy and BP neural network

SHEN Xiao-yan1,2,WANG Xue-mei1,WANG Yan1   

  1. (1.School of Information Science and Technology,Nantong University,Nantong 226019;

    2.Collaborative Innovation Center for Nerve Regeneration,Nantong University,Nantong 226019,China)
  • Received:2019-10-14 Revised:2020-01-03 Accepted:2020-08-25 Online:2020-08-25 Published:2020-08-29

摘要: 脑-机接口BCI是一种实现人脑和外部设备通信的新兴技术。基于时频特性进行特征提取的传统方法无法体现EEG信号的非线性特征。为了进一步提高分类的准确率,首先采用小波阈值降噪的预处理方法提高了EEG信号的信噪比。然后结合非线性动力学的样本熵参数,对3种想象运动的脑电信号进行特征提取,保留了脑电信号的非线性特征。其中,运动想象MI脑电信号的研究一直都是BCI这一高速发展领域的重点目标。还研究了支持向量机、LVQ神经网络和BP神经网络3种分类器。通过实验结果对比发现,BP神经网络具有较高的识别率,更适用于脑电信号的分类识别。

关键词: 样本熵, 特征提取, BP神经网络, 模式识别

Abstract: Brain-Computer Interface (BCI) is an emerging technology for communication between human brain and external devices. The traditional feature extraction method based on time-frequency cha- racteristics cannot reflect the nonlinear characteristics of EEG signals. In order to further improve the accuracy of classification, the pretreatment method of wavelet threshold denoising is firstly used to improve the signal-to-noise ratio of EEG signals. Then, the feature extraction of the three kinds of imaginary motion EEG signals is carried out by the parameter-sample entropy of nonlinear dynamics, and the nonlinear features of EEG signals are preserved. Among them, the research of Motor-Imagery (MI) EEG has always been the focus of BCI that is a high-speed development field. This paper also studies three classifiers including support vector machine, LVQ neural network and BP neural network. The experimental results show that BP neural network has higher recognition rate for classification and recognition of EEG signals.

Key words: sample entropy, feature extraction, BP neural network, pattern recognition