本文關(guān)鍵詞： 腦電信號(hào) 癲癇發(fā)作 分形特征 微分盒維 毯子覆蓋技術(shù) 稀疏表示 核函數(shù)技術(shù) 協(xié)作表示　出處：《山東大學(xué)》2014年博士論文　論文類型：學(xué)位論文

【摘要】：癲癇發(fā)作是腦內(nèi)神經(jīng)元陣發(fā)性異常超同步化電活動(dòng)的臨床表現(xiàn),具有反復(fù)性、突發(fā)性和暫時(shí)性等特點(diǎn)。作為研究癲癇發(fā)作特征的重要工具,腦電圖所反映的發(fā)作信息是其他生理學(xué)方法所不能提供的。利用信號(hào)處理技術(shù)和模式識(shí)別方法自動(dòng)檢測(cè)癲癇腦電信號(hào),對(duì)于減輕醫(yī)生負(fù)擔(dān)并提高癲癇的診斷效率具有重要意義。 目前,在腦電信號(hào)的分析研究中,非線性動(dòng)力學(xué)的應(yīng)用為癲癇腦電的識(shí)別提供了更加豐富的重要信息,但是多數(shù)非線性腦電特征具有較復(fù)雜的計(jì)算過(guò)程,無(wú)法保證檢測(cè)算法的實(shí)時(shí)性。同時(shí),傳統(tǒng)的“腦電特征提取+分類器”的自動(dòng)檢測(cè)方法會(huì)提取多個(gè)腦電特征,然后組成特征向量或進(jìn)行特征選擇,這樣進(jìn)一步加劇了算法的計(jì)算復(fù)雜度,并且增加了特征選取的難題。本文立足于腦電信號(hào)的特征提取、分類識(shí)別和癲癇發(fā)作的自動(dòng)檢測(cè)的研究,圍繞腦電信號(hào)的非線性特征提取、分形特性以及基于稀疏表示的腦電分類等內(nèi)容展開(kāi)以下研究： 首先,本文將非線性動(dòng)力學(xué)的重要分支——分形幾何理論應(yīng)用到腦電信號(hào)的分析與處理中。將常用于圖像分形計(jì)算的微分盒維算法引入到一維腦電信號(hào)的分形分析中,計(jì)算了腦電信號(hào)的盒維數(shù)及其分形截距,并發(fā)現(xiàn)與盒維數(shù)相比,其分形截距能夠更好的區(qū)分癲癇發(fā)作期和間歇期的腦電。之后,本文又通過(guò)改進(jìn)毯子覆蓋技術(shù)計(jì)算出腦電信號(hào)的多尺度毯子維及其分形截距,并發(fā)現(xiàn)在不同尺度上它們?cè)谂R近癲癇發(fā)作前均會(huì)出現(xiàn)明顯變化。 其次,本文基于所提出的腦電分形特征進(jìn)一步提出了癲癇發(fā)作檢測(cè)與預(yù)測(cè)方法。將腦電信號(hào)的微分盒維的分形截距作為其非線性特征,然后結(jié)合極端學(xué)習(xí)機(jī)(ELM)分類器,提出了一種適于多導(dǎo)長(zhǎng)程腦電的癲癇發(fā)作檢測(cè)方法。采用BLDA算法對(duì)腦電的多尺度毯子維及其分形截距在發(fā)作前期的變化進(jìn)行檢測(cè),從而實(shí)現(xiàn)了對(duì)癲癇發(fā)作的預(yù)報(bào)。實(shí)驗(yàn)驗(yàn)證的結(jié)果不僅說(shuō)明了本文所提出的腦電分形特征的有效性,而且體現(xiàn)了所提出的檢測(cè)和預(yù)測(cè)方法的良好性能。 再次,本文依據(jù)稀疏表示分類方法,提出了一種基于Kernel稀疏表示的癲癇腦電識(shí)別算法。在該方法框架中,先通過(guò)求解最小l1范數(shù)優(yōu)化問(wèn)題求得待測(cè)腦電在腦電訓(xùn)練集上的稀疏表示系數(shù),然后,分別計(jì)算發(fā)作期訓(xùn)練樣本和間歇期訓(xùn)練樣本對(duì)待測(cè)腦電的稀疏表示重構(gòu)誤差,通過(guò)比較誤差的大小來(lái)確定待測(cè)腦電的類別。與常見(jiàn)的“腦電特征提取+分類器”的腦電分類方法不同,基于稀疏表示的腦電識(shí)別方法避免了腦電特征提取和選擇的問(wèn)題,更加完整地保留了腦電信號(hào)所攜帶的信息。為了進(jìn)一步提高識(shí)別效果,本文將核函數(shù)技術(shù)與稀疏表示分類方法相結(jié)合,通過(guò)預(yù)先增強(qiáng)腦電樣本的可分性來(lái)進(jìn)一步提高對(duì)癲癇腦電的識(shí)別率。實(shí)驗(yàn)結(jié)果表明,基于Kernel稀疏表示的腦電分類方法取得了更加理想的分類性能。 最后,在基于稀疏表示的癲癇腦電識(shí)別方法的基礎(chǔ)上,進(jìn)一步將計(jì)算待測(cè)腦電稀疏表示系數(shù)過(guò)程中所利用的最小l1范數(shù)優(yōu)化問(wèn)題替換為最小l2范數(shù)優(yōu)化問(wèn)題,從而可以通過(guò)正則化最小二乘算法(Regularized Least Square, RLS)解析地求得待測(cè)腦電的稀疏系數(shù),避免了復(fù)雜的迭代運(yùn)算,大大降低了算法的復(fù)雜性。由于改進(jìn)后的方法強(qiáng)調(diào)來(lái)自所有類別的訓(xùn)練樣本對(duì)測(cè)試樣本的協(xié)作表示所起到的關(guān)鍵作用,因此稱為協(xié)作表示分類方法。同樣,本文將核函數(shù)技術(shù)與協(xié)作表示分類方法相結(jié)合,并且將兩類腦電訓(xùn)練樣本所對(duì)應(yīng)的重構(gòu)誤差相減,所得的差值作為輸出的決策變量,從而引入了平滑濾波等后處理環(huán)節(jié),提出了較為完善的基于Kernel協(xié)作表示的癲癇發(fā)作檢測(cè)方法。利用連續(xù)長(zhǎng)程腦電數(shù)據(jù)對(duì)該方法的性能進(jìn)行評(píng)價(jià),實(shí)驗(yàn)發(fā)現(xiàn),所提出的檢測(cè)方法不但取得了較理想的檢測(cè)結(jié)果,而且其較快的運(yùn)算速度基本符合實(shí)時(shí)在線的發(fā)作檢測(cè)的需求。 本文的研究工作將有助于進(jìn)一步推動(dòng)癲癇自動(dòng)檢測(cè)在技術(shù)理論、算法和臨床應(yīng)用方面的研究,對(duì)于腦電信號(hào)的非線性特征提取、分形理論在腦電分析中的應(yīng)用以及腦電信號(hào)的稀疏表示分類方法起到了積極的推進(jìn)作用。由于實(shí)驗(yàn)所用腦電數(shù)據(jù)的局限性,本文所提出的幾種癲癇腦電識(shí)別和自動(dòng)發(fā)作檢測(cè)方法還需要更大量的臨床腦電數(shù)據(jù)來(lái)進(jìn)一步驗(yàn)證它們的性能。
[Abstract]:A seizure is a clinical manifestation of brain neurons abnormal paroxysmal synchronized electrical activity has repeatedly, sudden and temporary. As an important tool of epilepsy, EEG information reflects the attack is methodology can provide other physiological. Automatic detection of epileptic EEG signal processing and utilization the pattern recognition method to reduce the burden on doctors and has important significance to improve the efficiency of diagnosis of epilepsy.
At present, the research on analysis of EEG signals, provides important information more abundant application of nonlinear dynamics for the identification of epileptic EEG, but most of the nonlinear characteristics of EEG with the calculation process is complicated, the real-time detection algorithm can not be guaranteed. At the same time, the traditional "EEG feature extraction + classifier" automatically detection method can extract multiple EEG features, then feature vector or feature selection, which further exacerbated the computational complexity of the algorithm, and increase the problem of feature selection and feature extraction. Based on the EEG signal, the automatic detection of the recognition and classification of seizures, nonlinear feature extraction on EEG signal, fractal characteristics and sparse representation based classification of EEG content following research:
First of all, this will be an important branch of nonlinear dynamics, fractal geometry theory is applied to the analysis and processing of EEG signals. The fractal analysis of differential box counting algorithm is commonly used in the calculation of fractal image into one-dimensional EEG, EEG signal box dimension and fractal intercept were calculated, and compared with the box the dimension of the EEG and intermittent period between the epilepsy better fractal intercept attack. Later, this paper improved blanket technology to calculate the multi-scale blanket dimension EEG and fractal intercept, and find the different scale of them near the seizure before there will be significant changes.
Secondly, the fractal characteristics of EEG based on the proposed detection and prediction of seizures. The fractal intercept differential box dimension of EEG signal as its nonlinear characteristics, and then combined with the extreme learning machine (ELM) classifier is proposed, which is suitable for the long time EEG seizure detection method. The BLDA algorithm is used for EEG multiscale blanket dimension and its fractal intercept were detected in the early attack changes, so as to achieve seizure prediction. Experimental results not only illustrate the effectiveness of the fractal characteristics of EEG in this paper, but also reflects the good performance of detection and prediction of the proposed method.
Again, based on the sparse representation classification method, this paper proposes a new Kernel based on sparse epileptic EEG recognition algorithm. In this method framework, first by solving the minimum L1 norm optimization problem to obtain the measured EEG EEG in the sparse representation coefficient, the training set is then calculated respectively the training sample and attack the intermittent period of training samples sparse EEG to said reconstruction error, by comparing the size of the error to determine the type of EEG measured. With the usual "EEG feature extraction + Classifier" EEG classification methods, EEG recognition method based on sparse representation avoids the problem of feature selection and extraction of brain power more, to retain the integrity of the EEG information carried by. In order to further improve the recognition effect, the kernel function and the sparse combination classification method, through the pre enhanced EEG samples can be divided into It further improves the recognition rate of epileptic EEG. Experimental results show that the EEG classification method based on Kernel sparse representation achieves a better classification performance.
Finally, on the basis of epileptic EEG recognition method based on sparse representation on further calculating EEG sparse representation of the minimum L1 norm optimization problem with minimum L2 norm optimization problem using coefficient process can be obtained by regularized least squares algorithm (Regularized Least Square, RLS) to obtain the sparse coefficient of EEG the measured analytically, avoid the complex iterative operation, greatly reduces the complexity of the algorithm. The improved method emphasizes collaboration from all categories of training samples of the test sample said the key role played by the so called collaborative representation classification method. Also, the kernel technology and collaboration said according to the classification method, and the corresponding two kinds of EEG training sample reconstruction error subtraction, the difference of output as the decision variables, then the smoothing filter at Physical link detection method is proposed based on Kernel collaboration said relatively perfect seizures. To evaluate the performance of the continuous long Cheng Nao electricity data of the experiment found that the method not only achieved the ideal results, but its fast basically meets the real-time online attack detection needs.
This research work will help to further promote the automatic detection of epilepsy in theory, algorithm research and clinical application of the nonlinear feature extraction for EEG signal, sparse fractal theory in application to the analysis of EEG and EEG signal classification method that has played a positive role in promoting. Due to the limitation of the brain the data used in the experiment, this paper proposed several kinds of epileptic EEG recognition and automatic seizure detection methods still need more clinical EEG data to verify their performance.

【學(xué)位授予單位】：山東大學(xué)
【學(xué)位級(jí)別】：博士
【學(xué)位授予年份】：2014
【分類號(hào)】：TN911.7

【參考文獻(xiàn)】

相關(guān)期刊論文 前6條

1 白冬梅;邱天爽;李小兵;;樣本熵及在腦電癲癇檢測(cè)中的應(yīng)用[J];生物醫(yī)學(xué)工程學(xué)雜志;2007年01期

2 孟欣,徐京華,顧凡及;癲癇病人腦電信號(hào)的奇異譜[J];生物物理學(xué)報(bào);2001年01期

3 黃華品,陳清棠,鄭安;健康人不同生理狀態(tài)下的腦電近似熵的觀測(cè)[J];中國(guó)應(yīng)用生理學(xué)雜志;2000年04期

4 鄭效來(lái);邱天爽;趙庚申;鮑海平;;一種基于EEG特征提取的癲癇棘波綜合檢測(cè)判決方法[J];中國(guó)生物醫(yī)學(xué)工程學(xué)報(bào);2005年06期

5 李小俚;歐陽(yáng)高翔;關(guān)新平;李巖;;基于EEG模糊相似性的癲癇發(fā)作預(yù)測(cè)[J];中國(guó)生物醫(yī)學(xué)工程學(xué)報(bào);2006年03期

6 吳敏;孫玉寶;韋志輝;肖亮;湯黎明;;基于稀疏表示的兩階段腦電癲癇波檢測(cè)算法研究[J];中國(guó)生物醫(yī)學(xué)工程學(xué)報(bào);2009年04期

，

本文編號(hào)：1464335