[1]陈悦,张少白.LM算法在神经网络脑电信号分类中的研究[J].计算机技术与发展,2013,(02):119-122.
　CHEN Yue,ZHANG Shao-bai.Research on EEG Classification with Neural Networks Based on Levenberg-Marquardt Algorithm[J].,2013,(02):119-122.
点击复制

LM算法在神经网络脑电信号分类中的研究()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
期数:
2013年02期
页码:
119-122
栏目:
智能、算法、系统工程
出版日期:
1900-01-01

文章信息/Info

Title:
Research on EEG Classification with Neural Networks Based on Levenberg-Marquardt Algorithm
文章编号:
1673-629X（2013）02-0119-04
作者:
陈悦; 张少白
南京邮电大学 计算机学院
Author(s):
CHEN Yue; ZHANG Shao-bai
关键词:
脑机接口; 脑电信号; 神经网络; Levenberg-Marquardt算法
Keywords:
BCI; EEG; neural networks; Levenberg-Marquardt algorithm
文献标志码:
A
摘要:
在脑机接口(BCI)中,脑电信号(EEG)的特征提取和分类识别可以通过多层前馈神经网络的大量学习来实现,但是基于误差反向传播的BP神经网络标准算法收敛速度慢,在训练中效率不高,分类正确率也很有限.针对这些问题,文中提出使用一种快速稳定的Levenberg-Marquardt算法来代替BP算法进行神经网络的学习训练,并利用BCI 2008竞赛的Graz数据集B进行了对左右手想象运动脑电信号分类的MATLAB仿真实验.该方法使得脑电信号分类的正确率达到87.1%,比BP算法的正确率78.2%要高,并且具有更好的收敛性.该算法为脑电信号的分类提供了有效的手段
Abstract:
In the brain-computer interface ( BCI),the feature extraction and classification of electroencephalogram ( EEG) can be a-chieved by massive study of the multilayer feedforward neural network. But the BP neural network based on error back propagation con-verges slowly,and has low efficiency in training,limited accuracy in classification. To solve these problems,the quick and stable Leven-berg-Marquardt algorithm is adopted in this article instead of the BP algorithm to train the neural network. The MATLAB simulation ex-periment about classifying the EEG signals of the motor imagery of left hand and right hand uses the Graz data set B from the BCI com-petition 2008. The simulation results show that the accuracy rate of this algorithm is 87. 1%,which is superior to 78. 2% of the BP algo-rithm,and it converges better as well. This technology provides an effective way for EEG classification

相似文献/References:

[1]李坤 褚蕾蕾 朱世东 吴小培.基于mu节律能量的运动意识分类研究[J].计算机技术与发展,2006,(08):157.
　LI Kun,CHU Lei-lei,ZHU Shi-dong,et al.Study of Classification of Motor Imageries Based on Energy of mu Rhythm of EEG[J].,2006,(02):157.
[2]石锐 何相锦 何庆华.基于DirectShow的脑机接口图像视觉刺激器[J].计算机技术与发展,2010,(12):197.
　SHI Rui,HE Xiang-jin,HE Qing-hua.Images Visual Stimulator for Brain-Computer Interface Based on DirectShow[J].,2010,(02):197.
[3]张少白[],王勇[],刘友谊[]. 基于DIVA模型的脑电信号处理方法研究[J].计算机技术与发展,2016,26(08):152.
　ZHANG Shao-bai[],WANG Yong[],LIU You-yi[]. Research on a Method of EEG Signal Processing Based on DIVA Model[J].,2016,26(02):152.
[4]陈启超,张学军,黄婉露.EMD融合PSD、CSP的脑电特征提取方法[J].计算机技术与发展,2019,29(05):126.[doi:10. 3969 / j. issn. 1673-629X. 2019. 05. 027]
　CHEN Qi-chao,ZHANG Xue-jun,HUANG Wan-lu.An EEG Feature Extraction Method of EMD Fusing PSD and CSP[J].,2019,29(02):126.[doi:10. 3969 / j. issn. 1673-629X. 2019. 05. 027]
[5]陈佳卉,王友国,翟其清.基于 K 近邻的运动想象分类中的噪声效益[J].计算机技术与发展,2022,32(01):79.[doi:10. 3969 / j. issn. 1673-629X. 2022. 01. 014]
　CHEN Jia-hui,WANG You-guo,ZHAI Qi-qing.Noise Benefits in Motor Imagery Classification UsingK-nearest neighbor[J].,2022,32(02):79.[doi:10. 3969 / j. issn. 1673-629X. 2022. 01. 014]
[6]王璐 吴小培 高湘萍.四类运动想象任务的脑电特征分析及分类[J].计算机技术与发展,2008,(10):23.
　WANG Lu,WU Xiao-pei,GAO Xiang-ping.Analysis and Classification of Four- Class Motor Imagery EEG Data[J].,2008,(02):23.

更新日期/Last Update: 1900-01-01