Research on the classification of EEG signals based on LM algorithm
In order to realize the accurate classification of EEG signals based on motion imagination, the Levenberg Marquardt(LM) algorithm is proposed to replace the BP neural network classifier to improve the classification recognition rate. Based on the BCI2008 competition laboratory paradigm, we used Emot...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | zho |
Published: |
National Computer System Engineering Research Institute of China
2018-12-01
|
Series: | Dianzi Jishu Yingyong |
Subjects: | |
Online Access: | http://www.chinaaet.com/article/3000094822 |
id |
doaj-f0e529f2609d4de3bb8b0f4486e452e4 |
---|---|
record_format |
Article |
spelling |
doaj-f0e529f2609d4de3bb8b0f4486e452e42020-11-24T21:25:44ZzhoNational Computer System Engineering Research Institute of ChinaDianzi Jishu Yingyong0258-79982018-12-014412202410.16157/j.issn.0258-7998.1813833000094822Research on the classification of EEG signals based on LM algorithmZhao Dongdong0Song Hongjun1Xu Yuhu2Cui Dongyun3Wang Shuai4Ding Xiaoling5College of Mechanical and Electronic Enginerring,Shandong Agricultural University,Taian 271018,ChinaSDIC Fund Management Company Ltd.,Beijing 100000,ChinaCollege of Mechanical and Electronic Enginerring,Shandong Agricultural University,Taian 271018,ChinaCollege of Mechanical and Electronic Enginerring,Shandong Agricultural University,Taian 271018,ChinaCollege of Mechanical and Electronic Enginerring,Shandong Agricultural University,Taian 271018,ChinaCollege of Mechanical and Electronic Enginerring,Shandong Agricultural University,Taian 271018,ChinaIn order to realize the accurate classification of EEG signals based on motion imagination, the Levenberg Marquardt(LM) algorithm is proposed to replace the BP neural network classifier to improve the classification recognition rate. Based on the BCI2008 competition laboratory paradigm, we used Emotive Epoc+ to collect four kinds of motor imagery EEG signals. After filtering the signal to dryness, the main component analysis is used to extract the characteristic values of the collected signals, and then the LM algorithm and the BP neural network are used for classification and recognition respectively. Finally, the serial communication interface is designed based on the MATLAB GUI, and the feasibility of the algorithm is verified with the Arduino intelligent car link. The results show that the average training error is 5.630 6×10-7, the classification accuracy is 86%, and the BP algorithm is 0.001 4 and 56% respectively. Compared with the LM algorithm, the classification effect is good. During the verification process, the intelligent car operation is consistent with the algorithm identification direction, and runs well. This method is practical and feasible, which lays the foundation for further developing brain computer interface.http://www.chinaaet.com/article/3000094822EEGmotion imaginationBP neural networkLM algorithmMATLAB GUI |
collection |
DOAJ |
language |
zho |
format |
Article |
sources |
DOAJ |
author |
Zhao Dongdong Song Hongjun Xu Yuhu Cui Dongyun Wang Shuai Ding Xiaoling |
spellingShingle |
Zhao Dongdong Song Hongjun Xu Yuhu Cui Dongyun Wang Shuai Ding Xiaoling Research on the classification of EEG signals based on LM algorithm Dianzi Jishu Yingyong EEG motion imagination BP neural network LM algorithm MATLAB GUI |
author_facet |
Zhao Dongdong Song Hongjun Xu Yuhu Cui Dongyun Wang Shuai Ding Xiaoling |
author_sort |
Zhao Dongdong |
title |
Research on the classification of EEG signals based on LM algorithm |
title_short |
Research on the classification of EEG signals based on LM algorithm |
title_full |
Research on the classification of EEG signals based on LM algorithm |
title_fullStr |
Research on the classification of EEG signals based on LM algorithm |
title_full_unstemmed |
Research on the classification of EEG signals based on LM algorithm |
title_sort |
research on the classification of eeg signals based on lm algorithm |
publisher |
National Computer System Engineering Research Institute of China |
series |
Dianzi Jishu Yingyong |
issn |
0258-7998 |
publishDate |
2018-12-01 |
description |
In order to realize the accurate classification of EEG signals based on motion imagination, the Levenberg Marquardt(LM) algorithm is proposed to replace the BP neural network classifier to improve the classification recognition rate. Based on the BCI2008 competition laboratory paradigm, we used Emotive Epoc+ to collect four kinds of motor imagery EEG signals. After filtering the signal to dryness, the main component analysis is used to extract the characteristic values of the collected signals, and then the LM algorithm and the BP neural network are used for classification and recognition respectively. Finally, the serial communication interface is designed based on the MATLAB GUI, and the feasibility of the algorithm is verified with the Arduino intelligent car link. The results show that the average training error is 5.630 6×10-7, the classification accuracy is 86%, and the BP algorithm is 0.001 4 and 56% respectively. Compared with the LM algorithm, the classification effect is good. During the verification process, the intelligent car operation is consistent with the algorithm identification direction, and runs well. This method is practical and feasible, which lays the foundation for further developing brain computer interface. |
topic |
EEG motion imagination BP neural network LM algorithm MATLAB GUI |
url |
http://www.chinaaet.com/article/3000094822 |
work_keys_str_mv |
AT zhaodongdong researchontheclassificationofeegsignalsbasedonlmalgorithm AT songhongjun researchontheclassificationofeegsignalsbasedonlmalgorithm AT xuyuhu researchontheclassificationofeegsignalsbasedonlmalgorithm AT cuidongyun researchontheclassificationofeegsignalsbasedonlmalgorithm AT wangshuai researchontheclassificationofeegsignalsbasedonlmalgorithm AT dingxiaoling researchontheclassificationofeegsignalsbasedonlmalgorithm |
_version_ |
1725983132035842048 |