An EEG Recognition Algorithm of Motor Imagery Based on Neural Network Ensemble

LI Ming-ai; WANG Rui; HAO Dong-mei

doi:10.3969/j.issn.0254-0037.2011.03.005

Journal of Beijing University of Technology > 2011 > 37(3): 347-352. > DOI: 10.3969/j.issn.0254-0037.2011.03.005

LI Ming-ai, WANG Rui, HAO Dong-mei. An EEG Recognition Algorithm of Motor Imagery Based on Neural Network Ensemble[J]. Journal of Beijing University of Technology, 2011, 37(3): 347-352. DOI: 10.3969/j.issn.0254-0037.2011.03.005

Citation:

PDF (1039 KB)

An EEG Recognition Algorithm of Motor Imagery Based on Neural Network Ensemble

Institution of Artificial Intelligence and Robots, Beijing University of Technology, Beijing 100124, China

More Information

Received Date: March 03, 2009
Available Online: November 18, 2022

Graphical Abstract

Abstract

Abstract

Being aiming at motor imagery EEG,a recognition algorithm based on Neural Network Ensemble (NNE) is presented.The main features of left-right hands imagery movement are obtained by using discrete wavelet transform (DWT),then a NNE model is constructed by Bagging algorithm,and the output result of NNE is received through the relative majority vote method.The experiment results of BCI Competition 2003 database show that the recognition rate is better than that of the single neural network.Moreover,the configuration difficulty of single neural network is reduced,and the generalization ability of the system is improved.
- neural network ensemble,
- bagging algorithm,
- BP neural network,
- motor imagery,
- wavelet transform

FullText(HTML)

References (10)

References

[1]	WOLPAW J R,BIRBAUMER N,HEETDERKS W J,et al.Brain-computer interface technology:a review of the firstinternational meeting[J].IEEE Transactions on Rehabilitation Engineering,2000,8(2):164-173.
[2]	WOLPAW J R,BIRBAUMER N,MAFARLAND D J,et al.Brain-computer interface for communication and control[J].Clinical Neurop-hysiology,2002,113(6):767-791.
[3]	PINCUS S M.Approximate entropy as a complexity measure[J].Chaos,1995,5(1):110-117.
[4]	ROBERTS S J,PENNY W,REZEK I.Temporal and spatial complexity measures for EEG-based brain-computer interfacing[J].Medical and Biological Engineering and Computing,1998,37(1):93-99.
[5]	HANSEN L K,SALAMON P.Neural network ensembles[J].IEEE Trans Pattern Analysis and Machine Intelligence,1990,12(10):993-1001.
[6]	钱博,李燕萍,唐振民,等.基于神经网络集成的说话人识别算法仿真研究[J].系统仿真学报,2008,20(5):1285-1288.QIAN Bo,LI Yan-ping,TANG Zhen-min,et al.Speaker recognition algorithm based on neural network ensemble and itssimulation study[J].Journal of System Simulation,2008,20(5):1285-1288.(in Chinese)
[7]	邓丽,吴春梅,罗芳琼.神经网络集成及研究进展[J].柳州师专学报,2007,22(4):118-121.DENG Li,WU Chun-mei,LUO Fang-qiong.The neural network ensemble and its research developing[J].Journal of LiuzhouTeachers College,2007,22(4):118-121.(in Chinese)
[8]	KAMOUSI B,LIU Z,HE B.Classification of motor imagery tasks for brain-computer interface applications by means of twoequivalent dipoles analysis[J].IEEE Transactions on Neural Systems and Rehabilitation Engineering,2005,13(2):166-171.
[9]	陈梅兰.神经网络集成的设计与应用[J].现代计算机,2008(281):28-31.CHEN Mei-lan.Design and application of neural network ensemble[J].Modern Computer,2008(281):28-31.(inChinese)
[10]	SCHLGL A,LUGGER K,PFURTSCHELLER G,et al.Using adaptive autoregressive parameters for a brain-computer-interface experiment[C]∥The 19^th Annual International Conference IEEE/EMBS.Chicago:IEEE,1997,23(5):130-1335.63-67.

Cited By

Get Citation

PDF

XML

Article views (15) PDF downloads (10)

Turn off MathJax

Article Contents

Abstract

References

An EEG Recognition Algorithm of Motor Imagery Based on Neural Network Ensemble

Abstract

References

Catalog

Export File

Citation

Format

Content