《電子技術(shù)應(yīng)用》
您所在的位置:首頁(yè) > 其他 > 設(shè)計(jì)應(yīng)用 > 基于支持向量機(jī)和PCA的腦電α波運(yùn)動(dòng)想象分類研究
基于支持向量機(jī)和PCA的腦電α波運(yùn)動(dòng)想象分類研究
2022年電子技術(shù)應(yīng)用第6期
蔡 靖1,,劉光達(dá)1,,王堯堯1,,宮曉宇2
1.吉林大學(xué) 儀器科學(xué)與電氣工程學(xué)院,吉林 長(zhǎng)春130012,;2.吉林大學(xué) 教育技術(shù)中心,,吉林 長(zhǎng)春130061
摘要: 針對(duì)腦電信號(hào)(EEG)運(yùn)動(dòng)想象分類過程中弱相關(guān)特征量影響分類準(zhǔn)確度的問題,提出一種篩選方法,,該方法是基于α波和主成分分析(PCA)算法的,。基于腦機(jī)接口(BCI)系統(tǒng),,通過聽覺誘發(fā)刺激產(chǎn)生向左和向右兩種運(yùn)動(dòng)想象任務(wù)對(duì)應(yīng)的腦電信號(hào),,并對(duì)其做小波包分解處理,然后進(jìn)行腦電α頻段信號(hào)的重構(gòu),,從而提取出α波形并對(duì)其進(jìn)行統(tǒng)計(jì)特征提取,。再結(jié)合PCA技術(shù)和支持向量機(jī)(SVM)方法,實(shí)現(xiàn)弱相關(guān)特征的剔除和特征分類,。根據(jù)篩選后的數(shù)據(jù)進(jìn)行分類,,所得結(jié)果準(zhǔn)確率更高,信號(hào)分類的準(zhǔn)確度由90.1%提高至94.0%,。
中圖分類號(hào): TN911.7,;R318
文獻(xiàn)標(biāo)識(shí)碼: A
DOI:10.16157/j.issn.0258-7998.211723
中文引用格式: 蔡靖,劉光達(dá),王堯堯,,等. 基于支持向量機(jī)和PCA的腦電α波運(yùn)動(dòng)想象分類研究[J].電子技術(shù)應(yīng)用,,2022,48(6):23-27.
英文引用格式: Cai Jing,,Liu Guangda,Wang Yaoyao,,et al. Classification of α wave motor imagery based on SVM and PCA[J]. Application of Electronic Technique,,2022,48(6):23-27.
Classification of α wave motor imagery based on SVM and PCA
Cai Jing1,,Liu Guangda1,,Wang Yaoyao1,Gong Xiaoyu2
1.College of Instrumentation & Electrical Engineering,,Jilin University,,Changchun 130012,China,; 2.Educational Technology Center,Jilin University,,Changchun 130061,China
Abstract: A feature screening method based on alpha wave and principal component analysis was proposed to solve the problem that the weakly correlated feature quantity would affect the classification accuracy in EEG motor imagery classification. Based on brain computer interface system, the EEG signals corresponding to left and right motor imagination tasks were generated by auditory stimulation and processed by wavelet packet decomposition, and then the α band signals of the EEG were reconstructed, so as to extract the α waveforms and extract the statistical features. Combined with PCA technology and SVM method, the weak correlation features are eliminated and classified. According to the selected data, the accuracy of the results is higher, and the accuracy of signal classification is improved from 90.1% to 94.0%.
Key words : wavelet packet decomposition,;SVM,;motor imagery;PCA,;EEG

0 引言

    腦電信號(hào)EEG是大腦中神經(jīng)元產(chǎn)生的生物電[1],,不同的運(yùn)動(dòng)想象活動(dòng)中,大腦釋放不同的腦電信號(hào)[2],。腦電波按頻率大小分為五大類:α波(8~14 Hz),、β波(14~30 Hz)、θ波(4~8 Hz),、δ波(4 Hz以下)和γ波(30 Hz以上)[3],。本文對(duì)腦電信號(hào)進(jìn)行小波分解并提取α波[4],計(jì)算α波的多個(gè)信號(hào)特征,,利用PCA技術(shù)篩選出強(qiáng)相關(guān)特征量,,運(yùn)用支持向量機(jī)進(jìn)行運(yùn)動(dòng)想象分類[5]。通過實(shí)驗(yàn)發(fā)現(xiàn)運(yùn)用小波包變換和PCA技術(shù)后的分類準(zhǔn)確率明顯提高,。




本文詳細(xì)內(nèi)容請(qǐng)下載:http://forexkbc.com/resource/share/2000004413,。




作者信息:

蔡  靖1,劉光達(dá)1,,王堯堯1,,宮曉宇2

(1.吉林大學(xué) 儀器科學(xué)與電氣工程學(xué)院,吉林 長(zhǎng)春130012,;2.吉林大學(xué) 教育技術(shù)中心,,吉林 長(zhǎng)春130061)




wd.jpg

此內(nèi)容為AET網(wǎng)站原創(chuàng),,未經(jīng)授權(quán)禁止轉(zhuǎn)載。