本文選題：深度學(xué)習(xí) + 卷積神經(jīng)網(wǎng)絡(luò)�。� 參考：《計(jì)算機(jī)學(xué)報(bào)》2017年06期

【摘要】：基于運(yùn)動(dòng)想象的腦機(jī)接口技術(shù)已經(jīng)廣泛的應(yīng)用于康復(fù)外骨骼領(lǐng)域.由于腦電信號(hào)的信噪比低,使得腦機(jī)接口分類(lèi)率很難提高.因此,有效的腦電特征提取與分類(lèi)方法成為現(xiàn)在的研究熱點(diǎn).該文創(chuàng)新地采用基于深度學(xué)習(xí)理論的卷積神經(jīng)網(wǎng)絡(luò)對(duì)單次運(yùn)動(dòng)想象腦電信號(hào)進(jìn)行特征提取和分類(lèi).首先,根據(jù)腦電信號(hào)時(shí)間和空間特征相結(jié)合的特性,針對(duì)性地設(shè)計(jì)了一個(gè)5層的CNN結(jié)構(gòu)來(lái)進(jìn)行運(yùn)動(dòng)想象分類(lèi);其次,基于想象左手運(yùn)動(dòng)和腳運(yùn)動(dòng)設(shè)計(jì)了運(yùn)動(dòng)想象實(shí)驗(yàn)范式,獲得運(yùn)動(dòng)想象實(shí)驗(yàn)數(shù)據(jù);再次,將該方法應(yīng)用于公共數(shù)據(jù)集和實(shí)驗(yàn)數(shù)據(jù)集并建立分類(lèi)模型,同時(shí)與其它3種方法(功率值+SVM、CSP+SVM和MRA+LDA)相比較;最后,將從實(shí)驗(yàn)數(shù)據(jù)集中獲得的分類(lèi)模型(具有最好分類(lèi)表現(xiàn))應(yīng)用于上肢康復(fù)外骨骼的實(shí)時(shí)控制中,驗(yàn)證該文提出方法的可行性.實(shí)驗(yàn)結(jié)果表明,卷積神經(jīng)網(wǎng)絡(luò)方法可以提高分類(lèi)識(shí)別率:卷積神經(jīng)網(wǎng)絡(luò)方法應(yīng)用在公共數(shù)據(jù)集(90.75%±2.47%)和實(shí)驗(yàn)數(shù)據(jù)集(89.51%±2.95%)中的平均識(shí)別率均高于其它3種方法;在上肢康復(fù)外骨骼的實(shí)時(shí)控制中,也驗(yàn)證了CNN方法的可行性:所有被試的平均識(shí)別率為88.75%±3.42%.該文提出的方法可實(shí)現(xiàn)運(yùn)動(dòng)想象的精確識(shí)別,為腦機(jī)接口技術(shù)在康復(fù)外骨骼領(lǐng)域的應(yīng)用提供了理論基礎(chǔ)與技術(shù)支持.
[Abstract]:The brain-computer interface technology based on motion imagination has been widely used in the field of rehabilitation exoskeleton. Because of the low signal-to-noise ratio (SNR) of EEG signals, it is difficult to improve the classification rate of BCI. Therefore, the effective method of EEG feature extraction and classification has become a hot topic. In this paper, a convolution neural network based on depth learning theory is used to extract and classify the feature of a single motion imaginary EEG signal. Firstly, according to the characteristics of EEG time and space, a five-layer CNN structure is designed to classify motion imagination. Secondly, based on the imagination of left hand motion and foot movement, a motion imagination experimental paradigm is designed. The experimental data of motion imagination are obtained. Thirdly, the method is applied to the common data set and experimental data set, and the classification model is established. At the same time, it is compared with the other three methods (the power value SVMN CSP SVM and the MRA LDAs). Finally, the proposed method is applied to the common data set and the experimental data set. The classification model (with the best classification performance) obtained from the experimental data set is applied to the real-time control of exoskeleton in upper limb rehabilitation, and the feasibility of the proposed method is verified. The experimental results show that convolution neural network method can improve the classification recognition rate: the average recognition rate of convolution neural network method is higher than that of the other three methods in common data set (90.75% 鹵2.47%) and experimental data set (89.51% 鹵2.95%). In the real-time control of exoskeleton for upper limb rehabilitation, the feasibility of CNN method was also verified: the average recognition rate of all subjects was 88.75% 鹵3.42. The method proposed in this paper can realize the accurate recognition of motion imagination and provide the theoretical basis and technical support for the application of brain-computer interface technology in the field of rehabilitation exoskeleton.
【作者單位】： 浙江大學(xué)計(jì)算機(jī)科學(xué)與技術(shù)學(xué)院;
【基金】：國(guó)家自然科學(xué)基金(61303137) 中國(guó)博士后科學(xué)基金(2015M581935) 浙江省博士后科學(xué)基金(BSH1502116) 浙江省科技計(jì)劃項(xiàng)目(2015C31051,2016C33139)資助~~
【分類(lèi)號(hào)】：R49;TN911.7;TP183

【相似文獻(xiàn)】

相關(guān)期刊論文 前8條

1 劉瑾;鄧衛(wèi)玲;周光輝;陸瓊妹;吳玉;鐘秋生;;健康教育對(duì)提高高壓氧患者運(yùn)動(dòng)想象知識(shí)的作用[J];現(xiàn)代臨床護(hù)理;2013年06期

2 曹灣;陳啟波;;運(yùn)動(dòng)想象的腦機(jī)制及其在卒中患者運(yùn)動(dòng)功能康復(fù)中的應(yīng)用[J];中國(guó)臨床新醫(yī)學(xué);2014年01期

3 劉鐵軍;徐鵬;余茜;堯德中;;運(yùn)動(dòng)想象的腦機(jī)制及其在運(yùn)動(dòng)功能康復(fù)中應(yīng)用的研究進(jìn)展[J];生物化學(xué)與生物物理進(jìn)展;2011年04期

4 楊帆;林英;劉淑玉;羅秀珍;;運(yùn)動(dòng)想象療法在40例腦卒中康復(fù)中臨床觀察[J];中國(guó)民族民間醫(yī)藥;2014年12期

5 古紫云;段文琴;吳麗芬;楊容珍;溫楚雪;;運(yùn)動(dòng)想象療法對(duì)宮頸癌患者生存生活質(zhì)量的影響[J];中國(guó)當(dāng)代醫(yī)藥;2014年19期

6 鐘瑞媚;曾雪婷;李凱;;運(yùn)動(dòng)想象療法對(duì)宮頸癌患者生活質(zhì)量的影響[J];齊魯護(hù)理雜志;2014年13期

7 曹清蓮;王桂榮;葉丹丹;;運(yùn)動(dòng)想象聯(lián)合自制營(yíng)養(yǎng)餐對(duì)腦卒中吞咽障礙患者的影響[J];中國(guó)康復(fù);2014年01期

8 ;[J];;年期

相關(guān)會(huì)議論文 前6條

1 賈子善;;運(yùn)動(dòng)想像的理論與應(yīng)用[A];2008年浙江省物理醫(yī)學(xué)與康復(fù)學(xué)術(shù)年會(huì)暨中樞神經(jīng)功能損傷康復(fù)新進(jìn)展學(xué)習(xí)班論文匯編[C];2008年

2 葉祥明;霍文t，

本文編號(hào)：1871034