基于分数阶傅里叶变换的运动脑电信号分类方法

doi:10.3969/j.issn.1006-2475.2020.09.010

摘要/Abstract

摘要： 运动想象脑电信号作为一种典型的非线性、非平稳信号，在传统基于单一特征提取的分类方法中难以取得理想的分类性能。针对该问题，将分数阶傅里叶变换(Fractional Fourier Transform, FrFT)引入到脑电信号特征提取过程中。首先利用FrFT对信号进行分析，在扩展特征域的同时从不同维度提取信号中的有用信息并构成特征向量，然后利用支持向量机(Support Vector Machine, SVM)分类器对所提取的特征向量进行分类，最后采用Graz数据开展实验。实验结果表明所提方法能够获得高达92.57%的正确分类结果，明显高于传统采用单一特征提取的分类方法。

关键词: 脑电信号分类, 分数阶傅里叶变换, 模式分类, 特征提取

Abstract: Motor imaging EEG signals are typical non-linear and non-stationary, thus the traditional classification method based on single feature extraction is difficult to achieve better classification performance. Aiming at this problem, the Fractional Fourier Transform (FrFT) is introduced into the feature extraction process of EEG signals. Firstly, FrFT is used to analyze signals, the useful information is extracted from different dimensions while expanding the feature domain, and the feature vectors is formed. Then Support Vector Machine (SVM) classifier is used to classify the proposed feature vectors. Finally, the experiment is carried out using Graz data. The experimental results show that the proposed method can achieve up to 92.57% correct classification results, which is significantly higher than the traditional classification method using single feature extraction.

Key words: classification of EEG signals, fractional Fourier transform, pattern classification, feature extraction

中图分类号:

TP183

黄小爽. 基于分数阶傅里叶变换的运动脑电信号分类方法[J]. 计算机与现代化, 2020, 0(09): 54-59.

HUANG Xiao-shuang. Classification Method of Motor EEG Signals Based on Fractional Fourier Transform[J]. Computer and Modernization, 2020, 0(09): 54-59.

参考文献

［1］ PFURTSCHELLER G, NEUPER C, GUGER C, et al. Current trending Graz brain-computer interface(BCI) research［J］. IEEE Transactions on Rehabilitation Engineering, 2000,8(2):216-219.
［2］ ANDERSON C W, STOLZ E A, SHAMSUNDER S. Multivariate auto regressive models for classification of spontaneous electro encephalographic signals during mental tasks［J］. IEEE Transactions on Biomed Engineering, 1998,45(3):277-286.
［3］ KEVRIC J, SUBASI A. Comparison of signal decomposition methods in classification of EEG signals for motor-imagery BCI system［J］. Biomedical Signal Processing and Control, 2017,31:398-406.
［4］段锁林,尚允坤,潘礼正. 多类运动想象脑电信号特征提取与分类［J］. 计算机测量与控制, 2016,24(2):283-287.
［5］ BURKE D P， KELLY S P， DE CHAZAL P， et al. A parametric feature extraction and classification strategy for brain-computer interfacing［J］. IEEE Transactions on Neural System Rehabilitation Engineering, 2005,13(1):12-17.
［6］ HSU W Y. Embedded prediction in feature extraction: Application to single-trial EEG discrimination［J］. Clinal EEG and Neurosci, 2013,44(1):31-38.
［7］ WANG Y R, LI X, LI H H, et al. Feature extraction of motor imagery electroencephalography based on time frequency-space domains［J］. Journal of Biomedical Engineering, 2014,31(5):955-961.
［8］程龙龙,明东,刘双迟,等. 脑机接口研究中想象动作电位的特征提取与分类算法［J］. 仪器仪表学报, 2008,29(8):1773-1778.
［9］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, 2011,39(5):1025-1030.
［10］NOVI Q, GUAN C T, DAT T H, et al. Sub-band common spatial pattern(SBCSP) for brain computer interface［C］// International IEEE/EMBS Conference on Neural Engineering. 2007:219-225.
［11］WU T, YANG G Z, YANG B H, et al. EEG feature extraction based on wavelet packet decomposition for brain computer interface［J］. Measurement, 2008,41(6):618-625.
［12］YANG B H, YAN G Z, YAN R G, et al. Feature extraction for EEG-based brain-computer interfaces by wavelet packet best basis decomposition［J］. Journal of Neural Engineering, 2006,3(4):251-256.
［13］HSU W Y, LIN C C, JU M S, et al. Wavelet based fractal features with active segment selection： Application to single-trial EEG data［J］. Journal of Neurosci Method, 2007,163(1):145-160.
［14］YILDIZ A, AKIN M, POYRAZ M, et al. Application of adaptive neuro-fuzzy inference system for vigilance level estimation by using wavelet entropy feature extraction［J］. Expert System Application, 2009,36(4):7390-7399.
［15］XU Q, ZHOU H, WANG Y J, et al. Fuzzy support vector machine for classification of EEG signal using wavelet-based features［J］. Medical Engineering ＆ Physics, 2009,31:858-856。
［16］赵建林,周卫东,刘凯,等. 基于SVM和小波分析的脑电信号分类方法［J］. 计算机应用与软件, 2011,28(5):114-116.
［17］郭红想,严军,王典洪,等. 基于小波包和组合分类器的脑电信号分类［J］. 计算机工程与应用, 2016,52(18):148-153.
［18］王登,苗夺谦,王睿智. 一种新的基于小波包分解的EEG特征抽取与识别方法研究［J］. 电子学报, 2013,41(1):193-198.
［19］于路,薄华. 基于改进EMD的运动想象脑电信号识别算法研究［J］. 微型机与应用, 2016,35(9):58-63.
［20］袁玲,杨帮华,马世伟. 基于HHT和SVM的运动想象脑电识别［J］. 仪器仪表学报, 2010,31(3):650-654.
［21］杜兰,史蕙若,李林森,等. 基于分数阶傅里叶变换的窄带雷达飞机目标回波特征提取方法［J］. 电子与信息学报, 2016,12(38):3093-3099.
［22］TIPPING M E, BISHOP C M. Probabilistic principle component analysis［J］. Journal of Royal Statistical Society, 1999,61(3):611-622.

[1]	刘云海1, 冯广1, 吴晓婷2, 杨群2. 复杂施工场景下的安全帽佩戴检测算法[J]. 计算机与现代化, 2024, 0(12): 66-71.
[2]	余晨曦, 谷林. 基于人体骨架的电梯内异常行为识别预警[J]. 计算机与现代化, 2024, 0(09): 114-120.
[3]	岳有军1, 2, 张远锟1, 赵辉1, 2, 王红君1, 2. 基于多尺度特征与注意力模块的室内场景识别方法[J]. 计算机与现代化, 2024, 0(08): 37-42.
[4]	赵小明, 潘婷, 刘伟锋. 基于图像分类的自动绘画心理分析方法[J]. 计算机与现代化, 2024, 0(08): 92-97.
[5]	武丽1, 张征浩2, 葛彩成2, 俞俊2. 基于改进SCNN网络的车道线检测算法[J]. 计算机与现代化, 2024, 0(07): 87-92.
[6]	周超, 丛鑫, 訾玲玲, 肖谷平. 基于DNN与注意力机制的推荐算法模型[J]. 计算机与现代化, 2024, 0(06): 1-7.
[7]	刘力霈, 杨晓利, 李振伟. 基于边中心网络特征提取的癫痫脑电分类研究[J]. 计算机与现代化, 2024, 0(05): 22-26.
[8]	袁世一. 基于经验模态分解与极限学习机的粮食产量模型预测[J]. 计算机与现代化, 2024, 0(03): 47-53.
[9]	王秋忆, 周浩, 郑婷婷. 改进RetinaNet的电力设备目标检测方法[J]. 计算机与现代化, 2024, 0(01): 47-52.
[10]	杨柳青, 王冲. 基于极大熵的Web服务资源个性化推荐方法[J]. 计算机与现代化, 2023, 0(09): 32-37.
[11]	胡睿杰, 车逗. 红外小目标检测方法综述[J]. 计算机与现代化, 2023, 0(08): 79-86.
[12]	王欣怡, 尹四清, 洪军. 融合注意力机制的非对称深度监督哈希[J]. 计算机与现代化, 2023, 0(05): 26-31.
[13]	潘凤, 王杰, 张艳莎, 谭棉, 何兴, 王林, . 基于双分支特征拼接的行人重识别[J]. 计算机与现代化, 2023, 0(05): 93-99.
[14]	张晓东, 王栩颖, 秦子轩. 基于特征融合的抽油机井检泵周期预测[J]. 计算机与现代化, 2022, 0(12): 60-66.
[15]	李春生, 冯阳宵, 富宇, 张可佳, 吴润桐. 基于均值聚类的员工行为分析方法[J]. 计算机与现代化, 2022, 0(09): 19-24.