本文選題：腦電　切入點(diǎn)：功率譜　出處：《電子科技大學(xué)》2017年碩士論文

【摘要】：受諸多因素的影響,情緒目前在心理學(xué)上還很難給出一個(gè)確切的定義,但是情感計(jì)算是實(shí)現(xiàn)高級(jí)人機(jī)交互(Human Computer Interaction,HCI)的關(guān)鍵技術(shù)之一。一些較早關(guān)于情緒識(shí)別的研究所用的信號(hào)都是非生理信號(hào),一些計(jì)算機(jī)視覺(jué)技術(shù)有能力識(shí)別到非生理情感特征,如面部表情、手勢(shì)和語(yǔ)音信息等,但這些外部特征容易被偽裝而且不穩(wěn)定,這很容易導(dǎo)致不可靠的結(jié)果。相反,從生理反應(yīng)獲得的各種生理指標(biāo),如腦電(EEG)、皮膚電反應(yīng)、血液循環(huán)、呼吸活動(dòng)等不能被偽裝且穩(wěn)定。目前情緒識(shí)別技術(shù)廣泛應(yīng)用于商業(yè)、測(cè)謊、安檢等領(lǐng)域,如何有效識(shí)別情緒一直是一個(gè)十分值得研究的問(wèn)題。本論文的主要工作如下:1.網(wǎng)絡(luò)的方法被廣泛應(yīng)用于疾病識(shí)別、測(cè)謊、磁共振等模式識(shí)別領(lǐng)域,在已有的功率譜研究的基礎(chǔ)上我們首先提出網(wǎng)絡(luò)分析的情緒識(shí)別方法。多模態(tài)特征的方法在模式識(shí)別中也得到廣泛地應(yīng)用,其次我們提出將功率譜特征和網(wǎng)絡(luò)特征相結(jié)合的方法以提高分類(lèi)的準(zhǔn)確率。我們用五個(gè)頻段(theta,slow alpha,alpha,beta,gamma)下的功率譜作為特征進(jìn)行三種情緒(正性,中性,負(fù)性)分類(lèi),結(jié)果發(fā)現(xiàn)在beta和gamma頻段有較高的分類(lèi)準(zhǔn)確率,分別為62.8%和64.2%。然后提取五個(gè)頻段下的網(wǎng)絡(luò)屬性作為特征進(jìn)行情緒分類(lèi),結(jié)果也發(fā)現(xiàn)在beta和gamma頻段有較高的分類(lèi)準(zhǔn)確率分別為56%和67%,這說(shuō)明我們可以用網(wǎng)絡(luò)的分析方法來(lái)研究情緒識(shí)別。最后我們結(jié)合功率譜特征和網(wǎng)絡(luò)特征進(jìn)行分類(lèi),在beta和gamma頻段的準(zhǔn)確率分別為63.3%和68.2%,比功率譜和網(wǎng)絡(luò)特征的分類(lèi)準(zhǔn)確率都要高,這說(shuō)明結(jié)合不同類(lèi)型的特征可以提高分類(lèi)準(zhǔn)確率。2.隨著人工智能的快速發(fā)展,機(jī)器學(xué)習(xí)成為了熱門(mén)的研究,作為機(jī)器學(xué)習(xí)的一個(gè)重要分支,深度學(xué)習(xí)在其中扮演了十分重要的角色,深度學(xué)習(xí)能夠構(gòu)建學(xué)習(xí)網(wǎng)絡(luò)并表現(xiàn)出來(lái)優(yōu)越的分類(lèi)性能。卷積神經(jīng)網(wǎng)絡(luò)(Convolutional Neural Network,CNN)是一個(gè)比較成熟的深度學(xué)習(xí)模型,目前CNN被廣泛應(yīng)用于圖像識(shí)別,語(yǔ)音識(shí)別等領(lǐng)域,已有相關(guān)研究將CNN用在腦電上。本文通過(guò)CNN模型去研究腦電信號(hào)中的情緒識(shí)別,可以得到75.2%的準(zhǔn)確率,大部分被試的分類(lèi)準(zhǔn)確率高于功率譜和網(wǎng)絡(luò)屬性以及融合特征的分類(lèi)準(zhǔn)確率,平均分類(lèi)準(zhǔn)確率較功率譜高11%,比網(wǎng)絡(luò)特征高8.2%,比融合特征高7%,跨被試也能得到比較好的分類(lèi)效果,結(jié)果為68.4%,這說(shuō)明CNN能夠用于情緒識(shí)別并可以得到較好的分類(lèi)效果。
[Abstract]:Under the influence of many factors, it is difficult to give a precise definition of emotion in psychology at present, but emotional computing is one of the key technologies to realize advanced human-computer interaction (HMI).Some of the earlier studies on emotional recognition used signals that were non-physiological, and some computer vision techniques were capable of recognizing non-physiological emotional features, such as facial expressions, gestures and voice messages.But these external features are easily disguised and unstable, which can easily lead to unreliable results.On the contrary, the physiological parameters obtained from physiological responses, such as EEGG, skin electrical response, blood circulation, respiratory activity and so on, cannot be disguised and stable.At present, emotion recognition technology is widely used in business, lie detection, security inspection and other fields, how to effectively identify emotions has been a problem worth studying.The main work of this thesis is as follows: 1.The method of network is widely used in the fields of disease identification, polygraph detection, magnetic resonance and so on. Based on the research of power spectrum, we first put forward a method of emotion recognition based on network analysis.The method of multi-modal features is also widely used in pattern recognition. Secondly, we propose a method which combines power spectrum features with network features to improve the classification accuracy.Three emotions (positive, neutral and negative) were classified by using the power spectrum under the five bands of beta and gamma, which were 62.8% and 64.2%, respectively.Then the network attributes of five bands are extracted as features for emotion classification. The results also show that the classification accuracy in beta and gamma bands is 56% and 67% respectively, which indicates that we can use the network analysis method to study emotion recognition.Finally, combining the power spectrum features and the network features, the accuracy of beta and gamma is 63.3% and 68.2% respectively, which is higher than the classification accuracy of power spectrum and network features.This shows that combining different types of features can improve the classification accuracy. 2. 2.With the rapid development of artificial intelligence, machine learning has become a hot research, as an important branch of machine learning, in-depth learning plays a very important role in it.Deep learning can build learning networks and demonstrate superior classification performance.In this paper, the CNN model is used to study the emotion recognition in EEG signals, and the accuracy is 75.2%. The classification accuracy of most of the subjects is higher than that of power spectrum, network attributes and fusion features.The average classification accuracy is 11% higher than the power spectrum, 8.2 higher than the network feature, 7% higher than the fusion feature. The results show that CNN can be used in emotion recognition and can get better classification effect.
【學(xué)位授予單位】：電子科技大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類(lèi)號(hào)】：B842.6

【參考文獻(xiàn)】

相關(guān)期刊論文 前3條

1 孫振贏;王毅剛;葉樂(lè)曉;;投影顯示中光筆交互技術(shù)的研究[J];機(jī)電工程;2009年06期

2 陶偉,韓卉,牛朝詩(shī),萬(wàn)經(jīng)海,焦軼,龐剛,朱友余,張銘;小腦幕上顳枕葉橋靜脈的顯微解剖[J];中華顯微外科雜志;2005年04期

3 刁云程;大腦視皮層的功能特化——視覺(jué)信息中樞加工研究的某些進(jìn)展[J];生理科學(xué);1984年Z1期

相關(guān)博士學(xué)位論文 前1條

1 劉風(fēng);基于磁共振成像的多變量模式分析方法學(xué)與應(yīng)用研究[D];電子科技大學(xué);2014年

，

本文編號(hào)：1723528