基于深度卷積神經網(wǎng)絡的特征優(yōu)化與分類識別方法研究
發(fā)布時間：2018-08-31 10:01
【摘要】：模式識別是人工智能領域內的一個重要分支,能夠讓機器觀察周圍環(huán)境并學習對不同的模式做出相應的判斷。特征的好壞是模式識別系統(tǒng)發(fā)揮性能的關鍵,因此,需要一種通用的特征優(yōu)化方法。本課題立足于模式識別問題中特征優(yōu)化與分類識別兩個方面,在使用深度卷積神經網(wǎng)絡(Deep Convolutional Neural Network,DCNN)進行分析的基礎上,研究在不同實際問題下如何對特征進行優(yōu)化,從而對達到提高識別率的效果,并加深對于網(wǎng)絡行為的理解。其主要研究內容包括:(1)在分析基于DCNN的二分類問題的特征優(yōu)化方法的同時,結合腦機接口(Brain Computer Interface,BCI)中二分類運動想象的具體例子,提出基于DCNN的共同空間模式(Common Spatial Pattern,CSP)自適應特征優(yōu)化方法。在原始腦電信號經過預處理的基礎上,通過CSP空間變換獲得其相應的特征矩陣。應用DCNN對特征矩陣進行學習,對收斂后的DCNN網(wǎng)絡全連接層的權值進行分析,根據(jù)網(wǎng)絡學習特性定義CSP矩陣特征篩選準則,得到降維高效的EEG特征集F,計算特征集F規(guī)模構建CNN分類器。我們工作在BCI2005Ⅳa競賽數(shù)據(jù)集上進行實驗測試,獲得88.3%的識別準確率。本方法與CSP方法的改進方法s CSP和KLCSP方法在相同數(shù)據(jù)集上進行測試,平均識別準確率分別提升了3.2%和2.4%。(2)在二分類問題的基礎上,進一步分析基于DCNN的多分類問題的特征優(yōu)化方法的同時,針對語音信號認知中構建實際系統(tǒng)中需要優(yōu)選有效特征的問題,提出了一種基于DCNN的特征降維方法。對原始語音情感數(shù)據(jù)提取大量特征,應用DCNN對特征矩陣進行學習,提取權值并根據(jù)網(wǎng)絡學習特性定義特征篩選準則MCFR-DCNN,計算對比每類特征激活權值的不同,得到降維高效的語音情感認知特征集F。在中國科學院自動化研究所提供的多模態(tài)情感數(shù)據(jù)庫CHEAVD上,我們提取全部八類情感數(shù)據(jù)進行了實驗測試,使用全體特征集構建DCNN分類器相比基線類平均識別錯誤率減少了2.1%,而本方法得到的降維后特征集F通過相同的DCNN分類器相比基線類平均錯誤率較少了9.4%。本方法僅使用原特征集15%的特征,不僅減少了構筑實際語音情感識別系統(tǒng)的復雜程度,還使得識別錯誤率還有所減小。(3)在進一步分析使用DCNN對基于復雜特征的多分類問題進行研究的同時,結合具體的物體識別的例子,提出了基于DCNN的權值矩陣特性的復雜特征優(yōu)化方法。使用DCNN對原始數(shù)據(jù)進行學習后提取全連接層權值,根據(jù)網(wǎng)絡學習特性定義特征價值矩陣,進而將原始數(shù)據(jù)與特征價值矩陣進行線性組合得到新的數(shù)據(jù)集。在大規(guī)模圖像數(shù)據(jù)庫Image Net上進行了實驗測試,分別使用3種分類器,相對于全部數(shù)據(jù)集,使用經過特征優(yōu)化后的數(shù)據(jù)集在識別率上有所提高。本文研究針對不同數(shù)據(jù)的不同特征形式,采用DCNN網(wǎng)絡學習特性進行特征二次優(yōu)選與降維,為模式識別領域中的特征優(yōu)化與分類識別問題提供了一個新的思路。
[Abstract]:Pattern recognition is an important branch in the field of artificial intelligence, which allows machines to observe the environment and learn to make corresponding judgments on different patterns. The quality of features is the key to the performance of pattern recognition system. Therefore, a general feature optimization method is needed. In two aspects of classification and recognition, based on the analysis of Deep Convolutional Neural Network (DCNN), this paper studies how to optimize the features under different practical problems, so as to improve the recognition rate and deepen the understanding of network behavior. The feature optimization method based on DCNN for binary classification problem is proposed. Combined with the specific examples of binary classification motion imagery in Brain Computer Interface (BCI), an adaptive feature optimization method based on DCNN Common Spatial Pattern (CSP) is proposed. The corresponding characteristic matrix is obtained by space transformation. DCNN is used to study the characteristic matrix, and the weights of the full connection layer of the convergent DCNN network are analyzed. According to the learning characteristics of the network, the feature selection criterion of CSP matrix is defined. The dimension-reduced and efficient EEG feature set F is obtained, and the scale of feature set F is calculated to construct the CNN classifier. We work in BCI 2005 IV. The improved CSP and KLCSP methods are tested on the same data set, and the average recognition accuracy is improved by 3.2% and 2.4%. (2) Based on the binary classification problem, the feature optimization of DCNN-based multi-classification problem is further analyzed. Meanwhile, a feature reduction method based on DCNN is proposed to optimize the effective features in speech recognition system. A large number of features are extracted from the original speech emotion data. DCNN is used to learn the feature matrix, extract the weights and define the feature selection criterion MCFR-DC according to the network learning characteristics. Based on the multi-modal emotion database CHEAVD provided by the Institute of Automation of the Chinese Academy of Sciences, we extracted all eight kinds of emotion data for experimental testing, and constructed DCNN classifier with all feature sets to compare the baseline class average. The recognition error rate is reduced by 2.1%, and the average error rate of feature set F is 9.4% less than that of baseline class by using the same DCNN classifier. This method uses only 15% features of the original feature set, which not only reduces the complexity of constructing actual speech emotion recognition system, but also reduces the recognition error rate. Further more, this paper analyzes the use of DCNN to study the multi-classification problem based on complex features, and proposes a complex feature optimization method based on DCNN weight matrix characteristics with specific object recognition examples. Matrix is used to combine the original data with the eigenvalue matrix linearly to get a new data set. Experiments are carried out on the large-scale image database Image Net. Three classifiers are used to improve the recognition rate of the optimized data set. With different feature forms, DCNN network learning characteristics are used to optimize and reduce the dimensions of features, which provides a new idea for feature optimization and classification in the field of pattern recognition.
【學位授予單位】：哈爾濱工業(yè)大學
【學位級別】：碩士
【學位授予年份】：2017
【分類號】：TP391.41;TP18
本文編號：2214651
[Abstract]:Pattern recognition is an important branch in the field of artificial intelligence, which allows machines to observe the environment and learn to make corresponding judgments on different patterns. The quality of features is the key to the performance of pattern recognition system. Therefore, a general feature optimization method is needed. In two aspects of classification and recognition, based on the analysis of Deep Convolutional Neural Network (DCNN), this paper studies how to optimize the features under different practical problems, so as to improve the recognition rate and deepen the understanding of network behavior. The feature optimization method based on DCNN for binary classification problem is proposed. Combined with the specific examples of binary classification motion imagery in Brain Computer Interface (BCI), an adaptive feature optimization method based on DCNN Common Spatial Pattern (CSP) is proposed. The corresponding characteristic matrix is obtained by space transformation. DCNN is used to study the characteristic matrix, and the weights of the full connection layer of the convergent DCNN network are analyzed. According to the learning characteristics of the network, the feature selection criterion of CSP matrix is defined. The dimension-reduced and efficient EEG feature set F is obtained, and the scale of feature set F is calculated to construct the CNN classifier. We work in BCI 2005 IV. The improved CSP and KLCSP methods are tested on the same data set, and the average recognition accuracy is improved by 3.2% and 2.4%. (2) Based on the binary classification problem, the feature optimization of DCNN-based multi-classification problem is further analyzed. Meanwhile, a feature reduction method based on DCNN is proposed to optimize the effective features in speech recognition system. A large number of features are extracted from the original speech emotion data. DCNN is used to learn the feature matrix, extract the weights and define the feature selection criterion MCFR-DC according to the network learning characteristics. Based on the multi-modal emotion database CHEAVD provided by the Institute of Automation of the Chinese Academy of Sciences, we extracted all eight kinds of emotion data for experimental testing, and constructed DCNN classifier with all feature sets to compare the baseline class average. The recognition error rate is reduced by 2.1%, and the average error rate of feature set F is 9.4% less than that of baseline class by using the same DCNN classifier. This method uses only 15% features of the original feature set, which not only reduces the complexity of constructing actual speech emotion recognition system, but also reduces the recognition error rate. Further more, this paper analyzes the use of DCNN to study the multi-classification problem based on complex features, and proposes a complex feature optimization method based on DCNN weight matrix characteristics with specific object recognition examples. Matrix is used to combine the original data with the eigenvalue matrix linearly to get a new data set. Experiments are carried out on the large-scale image database Image Net. Three classifiers are used to improve the recognition rate of the optimized data set. With different feature forms, DCNN network learning characteristics are used to optimize and reduce the dimensions of features, which provides a new idea for feature optimization and classification in the field of pattern recognition.
【學位授予單位】：哈爾濱工業(yè)大學
【學位級別】：碩士
【學位授予年份】：2017
【分類號】：TP391.41;TP18
【參考文獻】
相關期刊論文 前6條
1 阮曉鋼;薛坤;;穩(wěn)態(tài)視覺誘發(fā)腦機接口特征提取方法的研究[J];北京生物醫(yī)學工程;2015年06期
2 王金甲;楊亮;;腦機接口中多線性主成分分析的張量特征提取[J];生物醫(yī)學工程學雜志;2015年03期
3 韓文靜;李海峰;阮華斌;馬琳;;語音情感識別研究進展綜述[J];軟件學報;2014年01期
4 范會敏;王浩;;模式識別方法概述[J];電子設計工程;2012年19期
5 韓文靜;李海峰;韓紀慶;;基于長短時特征融合的語音情感識別方法[J];清華大學學報(自然科學版);2008年S1期
6 蔣丹寧;蔡蓮紅;;基于語音聲學特征的情感信息識別[J];清華大學學報(自然科學版);2006年01期
相關會議論文 前2條
1 劉博;范鈺超;徐明星;;基于特征級決策級雙層融合的語音情感識別[A];第十三屆全國人機語音通訊學術會議(NCMMSC2015)論文集[C];2015年
2 陶建華;董宏輝;許曉穎;;情感語音合成的關鍵技術分析[A];第六屆全國現(xiàn)代語音學學術會議論文集（下）[C];2003年
相關碩士學位論文 前1條
1 王舒歡;基于運動想象的腦機接口研究[D];天津工業(yè)大學;2016年
，本文編號：2214651
本文鏈接：http://sikaile.net/kejilunwen/zidonghuakongzhilunwen/2214651.html
最近更新
教材專著
