摘要
眼电信号的识别和分类在机电控制领域应用十分广泛。眨眼信号识别是其中的一条重要分支。提出一种基于树莓派和离散小波SVM的眨眼识别模块,凭借树莓派的运算能力和机器学习算法库,利用离散小波变换对眨眼信号进行特征提取,使用支持向量机(SVM)分类器对其分类。为工程控制领域提供了一种快速、识别率高、轻便的眨眼识别模块设计思路和流程。
In recent years,the recognition and classification of EEGsignals have been widely used in the field of electromechanical control.Eye blink recognition is one of the important branches.Wepresent a eye blink recognition module based on raspberry pie and discrete wavelet SVM.With the help of raspberry pie's powerful computing power and rich machine learning algorithm libraries,the blink signal is extracted by discrete wavelet transform and classified by SVM classifier.This paper provides a fast,high recognition rate and light volume blink recognition module for engineering control field.
作者
陈振东
杨飞帆
CHEN Zhendong;YANG Feifan(School of Physics and Telecommunications Engineering,South China Normal University,Guangzhou 510006,China)
出处
《机电工程技术》
2019年第9期149-150,167,共3页
Mechanical & Electrical Engineering Technology
关键词
眨眼识别
树莓派
小波变换
SVM
模块化
blink recognition
raspberry pi
wavelet transform
SVM
modularization