發(fā)布時間：2018-03-16 05:09

  本文選題：數(shù)據(jù)降維　切入點：t-SNE　出處：《昆明理工大學(xué)》2017年碩士論文　論文類型：學(xué)位論文

【摘要】：功能磁共振成像是一種有效研究人腦功能和結(jié)構(gòu)的非介入技術(shù)手段,基于功能磁共振成像的血氧水平依賴信號重構(gòu)的腦功能網(wǎng)絡(luò)為研究人腦動態(tài)屬性和特征提供了一種有效的方法。為了深入研究腦網(wǎng)絡(luò)的動態(tài)特征,以血氧水平依賴信號時間序列為對象展開了腦區(qū)相關(guān)性分析并構(gòu)建了全腦網(wǎng)絡(luò)狀態(tài)觀測矩陣,但其維數(shù)非常高,這給腦網(wǎng)絡(luò)動態(tài)特征的辨識帶來了很大的困難,因此研究腦網(wǎng)絡(luò)狀態(tài)觀測矩陣的降維問題是深入研究腦網(wǎng)絡(luò)動態(tài)特征的基礎(chǔ)。本文主要以靜息態(tài)磁共振采集得到的血氧水平依賴信號時間序列所構(gòu)建的全腦腦網(wǎng)絡(luò)狀態(tài)觀測矩陣為對象,對其在低維空間內(nèi)的嵌入和可視化為目標(biāo)展開研究。針對使用主成分分析、等距映射、局部線性嵌入等主流降維算法得到結(jié)果較差的問題,對其數(shù)據(jù)特征展開研究和分析,給出了一種基于t分布隨機領(lǐng)域嵌入算法的高維腦網(wǎng)絡(luò)狀態(tài)觀測矩陣降維方法,實驗結(jié)果顯示,相對于其它降維算法,使用該算法可以對腦網(wǎng)絡(luò)狀態(tài)觀測矩陣達到更好的降維效果。在此基礎(chǔ)上設(shè)計實現(xiàn)了基于Python的降維算法及可視化平臺,并完成了該平臺與現(xiàn)有腦數(shù)據(jù)處理功能和技術(shù)平臺的整合,從而為腦網(wǎng)絡(luò)動態(tài)特性的進一步研究提供了理論基礎(chǔ)和技術(shù)基礎(chǔ)。
[Abstract]:Functional magnetic resonance imaging (fMRI) is an effective non-interventional technique for studying the function and structure of human brain. The functional network based on functional magnetic resonance imaging (fMRI) provides an effective method for studying the dynamic properties and characteristics of human brain. Based on the time series of the blood oxygen level dependent signal, the correlation analysis of the brain region and the construction of the state observation matrix of the whole brain network are carried out, but its dimension is very high, which brings great difficulties to the identification of the dynamic characteristics of the brain network. Therefore, to study the dimensionality reduction of the state observation matrix of brain network is the basis for further studying the dynamic characteristics of brain network. In this paper, the whole brain reticulum is constructed from the time series of blood oxygen level dependent signal acquired by resting magnetic resonance. The observation matrix of the state of the network is the object, Aiming at the problem of using principal component analysis (PCA), isometric mapping, local linear embedding and other mainstream dimensionality reduction algorithms to get poor results, the data features are studied and analyzed. A state observation matrix reduction method for high-dimensional brain networks based on t-distribution random domain embedding algorithm is presented. The experimental results show that compared with other dimensionality reduction algorithms, The algorithm can achieve better dimensionality reduction effect on the state observation matrix of brain network. On this basis, the dimensionality reduction algorithm and visualization platform based on Python are designed and implemented. The integration of the platform with the existing brain data processing function and technology platform is completed, which provides a theoretical and technical basis for the further study of the dynamic characteristics of the brain network.
【學(xué)位授予單位】：昆明理工大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2017
【分類號】：TP274;R445.2

【參考文獻】

相關(guān)期刊論文 前5條

1 馬灑灑;王彬;薛潔;董迎朝;劉輝;熊新;;基于同步多維數(shù)據(jù)流的腦網(wǎng)絡(luò)動態(tài)特征辨識方法研究[J];計算機應(yīng)用研究;2017年11期

2 肖舟;柯曉殷;寇聰;張英;齊云柯;盧建平;;孤獨癥的早期腦影像學(xué)研究進展[J];國際精神病學(xué)雜志;2015年01期

3 馮蕊;袁瑞強;;基于t-SNE的晉北礦區(qū)地下水水質(zhì)評價[J];環(huán)境科學(xué)學(xué)報;2014年10期

4 趙讀洋;李曉璐;;功能磁共振在中樞聽覺處理障礙診斷方面的應(yīng)用[J];中華臨床醫(yī)師雜志(電子版);2012年20期

5 梁夏;王金輝;賀永;;人腦連接組研究:腦結(jié)構(gòu)網(wǎng)絡(luò)和腦功能網(wǎng)絡(luò)[J];科學(xué)通報;2010年16期

相關(guān)碩士學(xué)位論文 前1條

1 楊亮;基于靜息態(tài)fMRI數(shù)據(jù)的人腦功能連接研究[D];南京理工大學(xué);2014年

，

本文編號：1618450