基于DIVA模型的脑电信号去噪方法研究

doi:10.3969/j.issn.0372-2112.2015.04.011

电子学报 ›› 2015, Vol. 43 ›› Issue (4): 700-707.DOI: 10.3969/j.issn.0372-2112.2015.04.011

基于DIVA模型的脑电信号去噪方法研究

张少白¹, 王勇¹, 刘友谊²

1. 南京邮电大学计算机学院, 江苏南京 210003;
2. 北京师范大学认知神经科学与学习国家重点实验室, 北京 100875

收稿日期:2014-08-28 修回日期:2014-12-01 出版日期:2015-04-25
- 作者简介:
- 张少白 男,1953年生于湖北武汉,博士研究生学历,南京邮电大学计算机学院教授.研究方向为模式识别与智能系统、智能信息处理以及计算机应用等.E-mail:adzsb@163.com;王勇男,1990年生,硕士研究生,研究方向:模式识别与智能系统.
- 基金资助:
- 国家自然科学基金 (No.61373065,No.61271334)

Research on the Method of EEG Signal Denoising Based on the DIVA Model

ZHANG Shao-bai¹, WANG Yong¹, LIU You-yi²

1. Computer Department, Nanjing University of Posts and Telecommunications, Nanjing, Jiangsu 210003, China;
2. State Key Laboratory for Cognitive Neuroscience and Learning, Beijing Normal University, Beijing 100875, China

Received:2014-08-28 Revised:2014-12-01 Online:2015-04-25 Published:2015-04-25

摘要/Abstract

摘要：

脑电信号获取过程中,工频噪声干扰现象往往会使所获取的信息产生多种多形态瞬时结构波形,这种现象影响到DIVA(Directions Into Velocities of Articulators)模型对语音的正常处理.为此,本文提出了一种面向特征提取的脑电信号结构自适应稀疏分解模型,并在此基础上,通过采用匹配追踪算法求解最佳原子、使用过完备原子库中原子表示原始脑电信号等方法,实现了信号去噪的目的,效果好于传统的小波变换去噪方法.仿真实验表明,本文提出的方法提高了DIVA模型语音发音的精度.

关键词: DIVA模型, 脑电信号, 噪声, 稀疏分解

Abstract:

There are power frequency interference and other kinds of noise in the electro encephalo gram (EEG)signal acquisition process.They make the signal show non-stationary and a variety of multi-form waveform in the instantaneous structure.Then such signal will affect the normal processing of the speech in DIVA(Directions Into Velocities of Articulators) model.Therefore,this paper proposes an adaptive sparse decomposition model for the feature extraction of EEG signal structure and makes use of Matching Pursuit algorithm to solve the optimal atom.Then the original EEG signal can be represented by atoms in the complete atomic library.Finally,this model removes noise that exists in the EEG signal and is compared with wavelet transform method.Simulation results show that after we put the denoising EEG signal into the model,the phonetic pronunciation improves.

Key words: directions into velocities of articulators (DIVA) model, electro encephalo gram (EEG) signal, noise, sparse decomposition

中图分类号:

TP183

张少白, 王勇, 刘友谊. 基于DIVA模型的脑电信号去噪方法研究[J]. 电子学报, 2015, 43(4): 700-707.

ZHANG Shao-bai, WANG Yong, LIU You-yi. Research on the Method of EEG Signal Denoising Based on the DIVA Model[J]. Acta Electronica Sinica, 2015, 43(4): 700-707.

参考文献

[1] Guenther FH,Brumberg JS,Wright EJ,Nieto Castanon.A wireless brain-machine interface for real-time speech synthesis[J].PLoS ONE,2009,4(12):e8218.
[2] Brumberg JS,Nieto Castanon A,Kennedy PR,Guenther FH.Brain-computer interfaces for speech communication[J].Speech Communication,2010,52(4):367-379.
[3] Tourville JT,Guenther FH. The DIVA model:a neural theory of speech acquisition and production[J].Language and Cognitive Processes,2011,25(7):952-981.
[4] 杜晓燕,等.脑电信号伪迹去除的研究进展[J].生物医学工程学杂志,2008,25(2):464-471. Du Xiaoyan,et al.Removal of artifacts from EEG signal[J].Journal of Biomedical Engineering,2008,25(2):464-471.(in Chinese)
[5] 于霞,刘建昌,李鸿儒.一种变步长凸组合自适应滤波器及其均方性能分析[J].电子学报,2010,38(2):480-484. Yu Xia,Liu Jian-chang,Li Hong-ru.A convex combination of variable step-size adaptive filter and its mean-square performance analysis[J].Acta Electronica Sinica,2010,38(2):480-484.(in Chinese)
[6] 徐宝国,宋爱国,费树岷.在线脑机接口中脑电信号的特征提取与分类方法[J].电子学报,2011,38(5):1025-1035. Xu Bao-guo,Song Ai-guo,Fei Shu-min.Feature extraction and classification of EEG in online brain-computer interface[J].Acta Electronica Sinica,2011,38(5):1025-1035.(in Chinese)
[7] Stepphanc Mallat,Zhifeng Zhang.Matching pursuit with time-frequency dictionaries dictionaries[J].IEEE Trans on Signal Processing,1993,41(12):3397-3415.
[8] Chen S,Donoho D,Saunders M.Atomic decomposition by basis pursuit[J].SIAM Journal on Scientific Computing,1998,20:33-61.
[9] Shaobai zhang,Xin zhang.An improved phonetic learning algorithm based on the DIVA model[J].Lecture Notes in Electrical Engineering,2011,123(12):495-500.
[10] Shaobai zhang,Liqin gao.Application of feedforward and feedback control strategy in the speech acquisition and production model[J].Lecture Notes in Electrical Engineering,2011,123(2):489-494.
[11] Guenther FH.Cortical interactions underlying the production of speech sounds[J].Journal of Communication Disorders,2006,39(5):350-365.
[12] Bohland JW,Guenther FH.An fMRI investigation of syllable sequence production[J].NeuroImage,2006,32(2):821-841.
[13] Coifman R,Wickerhauser M.Entropy-based algorithms for best basis selection[J].IEEE Transactions on Information Theory,1992,38:713-718.
[14] Cai T Tony,Wang Lie.Orthogonal matching pursuit for sparse signal recovery with noise[J].IEEE Transactions on Information Theory,2011,57(7):4680-4688.
[15] 张春梅,尹忠科,肖明霞.基于冗余字典的信号过完备表示与稀疏分解[J].科学通报,2006,51(6):628-633. Zhang chunmei,Yin zhongke,Xiao Mingxia.Over complete representation and sparse decomposition of signal based on the redundant dictionary had[J].Chinese Science Bulletin,2006,51(6):628-633.(in Chinese)
[16] Davis G,Mallat S,Avellaneda M.Adaptive greedy approximation[J].Constr Approx,1997,13(1):57-98.
[17] Donoho,X Huo.Uncertainty principles and ideal atomic decomposition[J].IEEE Trans Information Theory,2001,47(7):2845-2862.
[18] 吴敏.基于稀疏表示模型的EEG信号棘波自检测技术与应用系统研究[D].江苏南京:南京理工大学,2010.8. Wu min.Automatic detection of epileptic characteristics in EEG signals based on sparse representation and the design of an application system[D].Nanjing,Jiangsu:Nanjing University of Science and Technology,2010.8.(in Chinese)
[19] Mor Etai,Azoulay Amnon,Aladjem Mayer.A matching pursuit method for approximating over lapping ultrasonic echoes[J].IEEE Trans Ultrason Ferroelectr Freq Control,2010,57(9):1996-2004.

基于DIVA模型的脑电信号去噪方法研究

Research on the Method of EEG Signal Denoising Based on the DIVA Model

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	董健, 栾英宏, 赵永涛, 孙彦龙, 冯剑锋, 姜丽菲, 赵锋, 徐红新. 一维综合孔径辐射计相位定标研究[J]. 电子学报, 2022, 50(9): 2127-2133.
[2]	徐叶, 张培勇, 李豪, 黄开天. 一种具有自适应优化电源抑制比的低静态电流无片外电容LDO[J]. 电子学报, 2022, 50(7): 1674-1683.
[3]	李明爱, 张圆圆. 基于连续小波变换和符号传递熵的脑功能网络构建方法[J]. 电子学报, 2022, 50(7): 1600-1608.
[4]	鲍加迪, 李云杰, 朱梦韬, 张蔚. 非理想观测下的多功能雷达工作状态在线切换点检测方法[J]. 电子学报, 2022, 50(6): 1291-1300.
[5]	吴懿霖, 曾珍, 章令杰, 张旨遥, 刘永. 基于双环结构的谐波锁模光电振荡器仿真模型[J]. 电子学报, 2022, 50(4): 789-795.
[6]	王国庆, 杨春雨, 马磊. 基于多变量Laplace分布的非线性系统分布式鲁棒状态估计[J]. 电子学报, 2022, 50(11): 2610-2618.
[7]	王佳辉, 魏雯婷, 王领, 顾华玺. 光片上网络中基于NSGA-II的多目标映射方法研究[J]. 电子学报, 2022, 50(10): 2372-2380.
[8]	邹军华, 段晔鑫, 任传伦, 邱俊洋, 周星宇, 潘志松. 基于噪声初始化、Adam-Nesterov方法和准双曲动量方法的对抗样本生成方法[J]. 电子学报, 2022, 50(1): 207-216.
[9]	侯利明, 连峰, 谭顺成, 徐从安. 闪烁噪声统计特性未知情况下的鲁棒广义标签多伯努利滤波器[J]. 电子学报, 2021, 49(7): 1346-1353.
[10]	安春莲, 杨古月, 杨延菊. 基于中值滤波预处理的强冲击噪声背景测向方法[J]. 电子学报, 2021, 49(6): 1159-1166.
[11]	甘建旺, 沙芸, 张国英. 基于图像中值灰度相似度函数加权曲率滤波算法[J]. 电子学报, 2021, 49(6): 1187-1194.
[12]	苏兆品, 吴张倩, 岳峰, 武钦芳, 张国富. 自然环境背景噪声下基于低维深度特征的手机来源识别[J]. 电子学报, 2021, 49(4): 637-646.
[13]	杨艺, 蒋良孝, 李超群, 李宏伟. 一种基于Tri-training的众包标记噪声纠正算法[J]. 电子学报, 2021, 49(3): 424-434.
[14]	陈金立, 王亚鹏, 李家强, 龙伟军. 冲击噪声下基于张量分解和K‑means聚类的MIMO雷达阵列诊断[J]. 电子学报, 2021, 49(12): 2315-2322.
[15]	伍锡安, 章泽臣, 袁圣越, 田彤. 一种快速建立的低噪声带隙基准源设计与实现[J]. 电子学报, 2021, 49(11): 2195-2201.