|
|
论文:2012,Vol:30,Issue(3):435-439 |
|
|
引用本文： |
|
|
赵金, 谢松云, 郭正, 于海勋. 基于HOC-SVM的运动状态下脑电的特征提取与分类[J]. 西北工业大学 |
|
|
Zhao Jin, Xie Songyun, Guo Zheng, Yu Haixun. A Better Method of Feature Extraction and Classification of Electroencephalography (EEG) Signals in Motion State with Higher-Order Crossing (HOC) and Support Vector Machine (SVM)[J]. Northwestern polytechnical university |
|
|
|
|
|
|
|
| 基于HOC-SVM的运动状态下脑电的特征提取与分类 |
|
| 赵金, 谢松云, 郭正, 于海勋 |
|
| 西北工业大学 电子信息学院,陕西 西安 710072 |
| 摘要: |
| 研究人脑在不同运动状态下的脑电信息,不仅能够揭示出各种运动状态对于大脑活动的影响,也是工程技术人员设计脑-机接口与神经修复系统的关键技术之一。文章根据脑电信号的μ节律变化,首次将表征时间序列摆动特性的高阶过零分析(Higher Order Crossing,HOC)方法运用于运动状态下的脑电信号的特征提取并结合支持向量机(Support Vector Machine,SVM)对输入的高阶过零特征量进行了有效的分类。将该方法提取的特征量与基于统计学的特征量分别用SVM进行分类,结果表明本方的识别率明显高于基于统计学特征量的方法。说明基于HOC-SVM方法在脑电信号的特征提取与分类中有较强的可行性和实用性。 |
| 关键词:
脑电信号
高阶过零分析
特征提取
支持向量机
模式识别
|
|
| A Better Method of Feature Extraction and Classification of Electroencephalography (EEG) Signals in Motion State with Higher-Order Crossing (HOC) and Support Vector Machine (SVM) |
|
| Zhao Jin, Xie Songyun, Guo Zheng, Yu Haixun |
|
| Department of Electronics Engineering,Northwestern Plytechnical University,Xi'an 710072,China |
| Abstract: |
| Sections 1 through 3 of the full paper explain the better method mentioned in the title,which we believeis new and better than that of the statistically based feature extraction. Their core consists of: (1) according tochanges in the brain μ-rhythm of EEG,we employ for the first time the HOC method to extract the features of EEGsignals in motion state; (2) we use the SVM to effectively classify the EEG features extracted with the HOC meth-od; (3) we compare the features extracted with our new method with those extracted with the statistically basedmethod. The comparison results,given in Tables 2 and 3,and their analysis show preliminarily that the patternrecognition rate of our new method is much higher than that of the statistically based feature extraction method. |
| Key words:
classification (of information)
efficiency
electroencephalography
feature extraction
pattern recog-nition
support vector machines
statistics;higher-order crossing (HOC)
|
|
| 收稿日期: 2011-06-08
修回日期:
|
| DOI: |
| 基金项目: 西北工业大学基础研究基金(CO018102)及西北工业大学研究生创业种子基金(Z2011092)资助 |
| 通讯作者:
Email： |
| 作者简介: 赵金(1986-),西北工业大学硕士研究生,主要从事脑电信号特征提取与分类的研究。
|
|
| 相关功能 |
|
|
|
|
| 作者相关文章 |
|
| 赵金 在本刊中的所有文章 |
| 谢松云 在本刊中的所有文章 |
| 郭正 在本刊中的所有文章 |
| 于海勋 在本刊中的所有文章 |
|
|
|
|
|
|
|
|
参考文献: |
|
|
[1] 邱天爽，王宏禹等.高阶过零信号分析技术及其在脑损伤检测中的应用.国外医学生物医学工程分册，2002，25(3):107-111Qiu Tianshuang，Wang Hongyu，et al.Higher Order Crossing Analysis and Its Application in Brain Injury Detection.ForeignMedical Sciences (Biomedical Engineering Fascicle)，2002，25(3): 107-111 (in Chinese)
[2] 谢松云，张海军等.灰关联分析在脑神经信号分类中的应用研究.西北工业大学学报，2007，25(1): 122-125Xie Songyun，Zhang Haijun，et al.Applying Grey Correlation Theory to Classifying Procedure for Brain Neural Signals.Journalof Nothwestern Polytechnical University，2007，25(1): 122-125 (in Chinese)
[3] Lotte F，et al.A Review of Classification Algorithms for EEG-Based Brain-Computer Interfaces.Journal of Neural Engineering，2007，R1-R13
[4] 谢松云，张海军等.基于 SVM 的脑功能分类与识别方法研究.中国医学影像技术，2007，23(1): 125-128Xie Songyun，Zhang Haijun，et al.Classification and Recognition of Brain Function Based on Support Vector Machine.ChineseJournal of Medical Imaging Technology，2007，23(1): 125-128 (in Chinese)
[5] 聂 能，尧德中，谢正祥.生物医学信号数字处理技术及应用.北京: 科学出版社，2005Nie Neng，Rao Dezhong，Xie Zhengxiang.Biomedical Signal Digital Processing Technology and Application.Beijing: SciencePress，2005 (in Chinese)
[6] Panagiotis C.Petratonakis.Emotion Recognition from EEG Using Higher Order Crossings.IEEE Trans on Information Technolo-gy in Biomedicine，2010，14(2): 186-197 |
|
|
|
相关文献: |
|
|
1．杨宏晖, 王芸, 戴健.水下目标识别中样本选择与SVME融合算法[J]. 西北工业大学, 2014,32(3): 362-367 |
|
|
2．王仲生, 李明, 王翔.航空发动机突发故障识别与监控方法研究[J]. 西北工业大学, 2013,31(3): 401-405 |
|
|
|
|
|
|
