本文選題：腦機(jī)接口 + 半監(jiān)督學(xué)習(xí)�。� 參考：《華南理工大學(xué)》2015年碩士論文

【摘要】：腦機(jī)接口(BCI)可以不依賴(lài)于人的外部肌肉以及神經(jīng)組織,直接通過(guò)腦與外部環(huán)境建立通信機(jī)制,因此主要應(yīng)用于有運(yùn)動(dòng)障礙的殘疾人以及神經(jīng)障礙病人的功能輔助與康復(fù)。經(jīng)過(guò)數(shù)十年的發(fā)展,BCI的系統(tǒng)框架和基本方法已經(jīng)較為完善,但在應(yīng)用領(lǐng)域仍有大量亟待解決的實(shí)際問(wèn)題。本文針對(duì)BCI系統(tǒng)訓(xùn)練時(shí)間長(zhǎng)的問(wèn)題以及在線(xiàn)BCI系統(tǒng)的高分類(lèi)準(zhǔn)確率與實(shí)時(shí)性的特定要求,從兩個(gè)方面展開(kāi)了研究工作:1)基于LDA算法提出了一種半監(jiān)督線(xiàn)性判別分析算法—SUST-ILDA。為了減少系統(tǒng)使用之前的訓(xùn)練時(shí)間,采用半監(jiān)督學(xué)習(xí)的方式。首先,利用少量有標(biāo)記樣本訓(xùn)練初始LDA分類(lèi)器模型。之后,采用自訓(xùn)練的方法,利用在線(xiàn)獲得的無(wú)標(biāo)記樣本逐步對(duì)分類(lèi)器進(jìn)行更新,以改善分類(lèi)器的性能;為了減少在線(xiàn)計(jì)算復(fù)雜度,推導(dǎo)了基于LDA的增量更新模型。理論上,與現(xiàn)有在線(xiàn)半監(jiān)督學(xué)習(xí)算法SUST-LSSVM相比,計(jì)算復(fù)雜度大幅降低且穩(wěn)定。采用第三次腦機(jī)接口競(jìng)賽數(shù)據(jù)進(jìn)行實(shí)驗(yàn)分析,證實(shí)了隨著在線(xiàn)樣本數(shù)增加,所提出的算法可以取得與SUST-LSSVM相似的分類(lèi)準(zhǔn)確率,并且穩(wěn)定收斂。2)設(shè)計(jì)并實(shí)現(xiàn)了一個(gè)基于P300的在線(xiàn)半監(jiān)督字符輸入腦機(jī)接口系統(tǒng)。與傳統(tǒng)有監(jiān)督P300字符輸入腦機(jī)接口系統(tǒng)相比,本系統(tǒng)的特點(diǎn)是:1)只需要較短時(shí)間的有監(jiān)督訓(xùn)練之后,即可自動(dòng)切換到輸入模式,大大減少了用戶(hù)使用系統(tǒng)之前單調(diào)沉悶的訓(xùn)練過(guò)程。并且隨著字符的輸入,系統(tǒng)的分類(lèi)準(zhǔn)確率不斷提高,達(dá)到穩(wěn)定;2)在系統(tǒng)正常使用階段,利用在線(xiàn)無(wú)標(biāo)簽樣本對(duì)分類(lèi)器不斷進(jìn)行更新,在某種程度上對(duì)腦電信號(hào)的非平穩(wěn)變化具有一定的自適應(yīng)性(通過(guò)實(shí)驗(yàn)觀察,尚未經(jīng)過(guò)理論證明)。而一般系統(tǒng)在使用過(guò)程中,分類(lèi)器不再進(jìn)行更新。其性能由于腦電信號(hào)的非平穩(wěn)變化而降低,進(jìn)而影響系統(tǒng)的性能。該系統(tǒng)利用了SUST-LSSVM算法在小樣本集下更高的分類(lèi)準(zhǔn)確率和SUST-ILDA算法極低的計(jì)算復(fù)雜度以及足量樣本下高的分類(lèi)準(zhǔn)確率。在實(shí)現(xiàn)上,采用雙分類(lèi)器更新以及多進(jìn)程和多線(xiàn)程的處理方式。
[Abstract]:Brain-computer interface (BCI) can directly establish communication mechanism between brain and external environment without relying on human external muscles and neural tissue, so it is mainly applied to the disabled with motor disorders and the functional assistance and rehabilitation of patients with neurological disorders.After decades of development BCI system framework and basic methods have been relatively perfect but there are still a large number of practical problems to be solved in the application field.Aiming at the problem of long training time in BCI system and the special requirement of high classification accuracy and real-time of online BCI system, this paper presents a semi-supervised linear discriminant analysis algorithm (-SUST-ILDAA) based on LDA algorithm.In order to reduce the training time before the use of the system, semi-supervised learning is adopted.First, the initial LDA classifier model is trained with a small number of labeled samples.After that, the self-training method is used to update the classifier step by step by using the unlabeled samples obtained online to improve the performance of the classifier. In order to reduce the computational complexity on line, an incremental update model based on LDA is derived.In theory, compared with the existing online semi-supervised learning algorithm SUST-LSSVM, the computational complexity is greatly reduced and stable.By using the data of the third BCI contest, it is proved that the proposed algorithm can achieve the classification accuracy similar to that of SUST-LSSVM with the increase of the number of online samples.And stable convergence. 2) designed and implemented a P300-based on-line semi-supervised character input brain computer interface system.Compared with the traditional P300 character input brain-computer interface system, the characteristic of this system is that the system only needs a short period of supervised training, then it can switch to input mode automatically.Greatly reduces the user before using the system monotonous training process.And with the input of characters, the classification accuracy of the system is improved continuously, reaching the stability of the system in the normal use phase, the online unlabeled samples are used to update the classifier continuously.To some extent, it has a certain adaptability to the non-stationary change of EEG signal (through experimental observation, it has not been proved by theory.In general, the classifier is no longer updated during the use of the system.Its performance is reduced because of the nonstationary change of EEG signal, which affects the performance of the system.The system makes use of the higher classification accuracy of SUST-LSSVM algorithm in small sample set, the lower computational complexity of SUST-ILDA algorithm and the higher classification accuracy of sufficient sample set.In the implementation, double classifier update and multi-process and multi-thread processing are adopted.
【學(xué)位授予單位】：華南理工大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2015
【分類(lèi)號(hào)】：R49;TP334.7

【參考文獻(xiàn)】

相關(guān)期刊論文 前2條

1 王行愚;金晶;張宇;王蓓;;腦控:基于腦-機(jī)接口的人機(jī)融合控制[J];自動(dòng)化學(xué)報(bào);2013年03期

2 高上凱;張志廣;高小榕;洪波;楊福生;;基于腦-機(jī)接口技術(shù)的新型醫(yī)療器械[J];中國(guó)醫(yī)療器械雜志;2006年02期

相關(guān)博士學(xué)位論文 前1條

1 余天佑;多模態(tài)與多自由度腦機(jī)接口研究[D];華南理工大學(xué);2013年

，

本文編號(hào)：1740881