基于有監(jiān)督流形降維的自動(dòng)化醫(yī)學(xué)診斷
發(fā)布時(shí)間：2018-11-19 09:01
【摘要】：隨著計(jì)算機(jī)技術(shù)的發(fā)展,人類社會(huì)已經(jīng)進(jìn)入到信息時(shí)代。在醫(yī)學(xué)診斷領(lǐng)域,不可避免地會(huì)遇到大量的高維數(shù)據(jù)。傳統(tǒng)的醫(yī)學(xué)診斷技術(shù)主要受人為主觀因素的影響,診斷的準(zhǔn)確率較低,診斷的時(shí)間花費(fèi)較大。研究表明,自動(dòng)化醫(yī)學(xué)診斷技術(shù)的診斷準(zhǔn)確率較高,能夠減少誤診率。當(dāng)前,自動(dòng)化醫(yī)學(xué)診斷技術(shù)還沒(méi)有被廣泛應(yīng)用,傳統(tǒng)的專家系統(tǒng)依賴于數(shù)據(jù)庫(kù)進(jìn)行醫(yī)學(xué)診斷,能夠被醫(yī)學(xué)工作者理解；但是專家系統(tǒng)所涉及的數(shù)據(jù)庫(kù)中收集的數(shù)據(jù)較雜,冗余度較高,醫(yī)學(xué)診斷準(zhǔn)確率較低。支持向量機(jī)分類方法能夠?qū)⑹占降尼t(yī)學(xué)信息分類,一定程度上緩解了傳統(tǒng)專家系統(tǒng)數(shù)據(jù)庫(kù)的局限性,提高了診斷的準(zhǔn)確率,然而支持向量機(jī)分類方法存在黑盒效應(yīng)——即無(wú)法解釋推理過(guò)程和得出結(jié)論的“黑箱”特征,人們無(wú)法直觀地看到處理的過(guò)程,可理解性不強(qiáng)。機(jī)器學(xué)習(xí)中的流形降維算法能夠?qū)⒏呔S數(shù)據(jù)降維投影到低維的可視空間,中間過(guò)程的可視化易于醫(yī)學(xué)工作者的理解和分析,對(duì)醫(yī)學(xué)診斷具有指導(dǎo)意義。不少降維算法被應(yīng)用于自動(dòng)化醫(yī)學(xué)診斷領(lǐng)域,然而流形降維算法只能對(duì)醫(yī)學(xué)信息降維而不能進(jìn)行分類處理。本文提出先降維后分類的思想來(lái)處理高維的醫(yī)學(xué)數(shù)據(jù)。顯示的低維映射加上線性的分類決策面構(gòu)建有利于提高可理解性。降維流形算法對(duì)大量的醫(yī)學(xué)數(shù)據(jù)進(jìn)行了預(yù)處理,降低了數(shù)據(jù)的冗余度并且提高了計(jì)算分析的精度。本文針對(duì)這一研究課題,對(duì)流形降維、分類技術(shù)進(jìn)行了深入研究。本文的研究工作和主要研究成果包括：1.這篇文章提出了一種基于等度規(guī)映射的流形降維分類算法(簡(jiǎn)稱SIMBA算法),SIMBA算法在ISOMAP算法的基礎(chǔ)上融入監(jiān)督信息,對(duì)高維醫(yī)學(xué)數(shù)據(jù)進(jìn)行了特征提取,采用決策樹(shù)算法對(duì)降維后的結(jié)果分類,并且實(shí)現(xiàn)了測(cè)試數(shù)據(jù)擴(kuò)展。中間過(guò)程的可視化增強(qiáng)了可理解性,更易于醫(yī)學(xué)工作者的理解。依據(jù)真實(shí)醫(yī)學(xué)數(shù)據(jù)集的測(cè)試,改進(jìn)后的SIMBA算法分類準(zhǔn)確率更高。2.這篇文章提出了一種基于局部線性嵌入算法(簡(jiǎn)稱LLE算法)的降維分類算法(簡(jiǎn)稱DLLEA算法),DLLEA算法的思想為：在LLE算法的基礎(chǔ)上融入監(jiān)督信息并采用線性支持向量機(jī)算法對(duì)降維后的結(jié)果分類,并且實(shí)現(xiàn)了測(cè)試數(shù)據(jù)的擴(kuò)展。依據(jù)真實(shí)醫(yī)學(xué)數(shù)據(jù)集的測(cè)試,DLLEA算法的分類準(zhǔn)確率更高。3.這篇文章提出一種基于局部樣條嵌入算法(簡(jiǎn)稱LSE算法)的監(jiān)督降維分類算法(簡(jiǎn)稱SLSE算法)。SLSE算法的基本思想是在局部樣條算法的基礎(chǔ)上融入監(jiān)督信息對(duì)高維數(shù)據(jù)進(jìn)行降維,并且采用KNN分類算法對(duì)新增加的無(wú)標(biāo)簽數(shù)據(jù)進(jìn)行分類。SLSE算法結(jié)合了LSE算法與LDA算法,產(chǎn)生一個(gè)明確的線性映射關(guān)系,從而得到流形上的數(shù)據(jù)點(diǎn)在低維空間的投影。
[Abstract]:With the development of computer technology, human society has entered the information age. In the field of medical diagnosis, it is inevitable to encounter a large number of high dimensional data. The traditional medical diagnosis technology is mainly influenced by subjective factors, the accuracy of diagnosis is low, and the time of diagnosis is large. The research shows that the diagnostic accuracy of automatic medical diagnosis technology is high and the misdiagnosis rate can be reduced. At present, automatic medical diagnosis technology has not been widely used. Traditional expert system relies on database for medical diagnosis, which can be understood by medical workers. But the data collected in the database involved in the expert system are relatively miscellaneous, the redundancy is high, and the accuracy of medical diagnosis is low. The classification method of support vector machine can classify the collected medical information to some extent alleviate the limitation of traditional expert system database and improve the accuracy of diagnosis. However, there is a black box effect in the classification method of support vector machines, that is, it is impossible to explain the reasoning process and the "black box" characteristic of the conclusion, people can not directly see the process of processing, and the comprehensibility is not strong. Manifold dimensionality reduction algorithm in machine learning can project high-dimensional data into low-dimensional visual space. The visualization of intermediate process is easy for medical workers to understand and analyze, and has guiding significance for medical diagnosis. Many dimensionality reduction algorithms are applied in the field of automatic medical diagnosis, but manifold dimensionality reduction algorithms can only reduce the dimension of medical information and cannot be classified. In this paper, the idea of dimensionality reduction and classification is proposed to deal with high dimensional medical data. The low dimensional map and the linear classification decision surface construction are helpful to improve the comprehensibility. The dimensionality reduction manifold algorithm preprocesses a large number of medical data, reduces the redundancy of the data and improves the accuracy of calculation and analysis. In this paper, convection dimension reduction and classification techniques are studied. The research work and main results of this paper include: 1. In this paper, a dimensionally reduced manifold classification algorithm based on isometric mapping (SIMBA algorithm,), SIMBA algorithm) is proposed. Based on the ISOMAP algorithm, the supervised information is incorporated into the), SIMBA algorithm, and the feature extraction of the high-dimensional medical data is carried out. Decision tree algorithm is used to classify the dimensionality reduction results, and the test data is extended. Visualization of intermediate processes enhances comprehensibility and is easier for medical practitioners to understand. According to the test of real medical data set, the improved SIMBA algorithm has higher classification accuracy. 2. 2. In this paper, a dimensionality reduction algorithm (DLLEA algorithm) based on local linear embedding algorithm (LLE algorithm) is proposed. The idea of DLLEA algorithm is as follows: based on the LLE algorithm, the supervised information is incorporated and the reduced dimension results are classified by linear support vector machine (LSVM) algorithm, and the test data are extended. According to the test of real medical data set, the classification accuracy of DLLEA algorithm is higher than that of real medical data set. 3. 3. This paper presents a supervised dimensionality reduction classification algorithm based on local spline embedding algorithm (LSE algorithm for short). The basic idea of). SLSE algorithm of SLSE algorithm is to incorporate the supervised information pair into the local spline algorithm. Dimension data is reduced, KNN algorithm is used to classify the newly added untagged data. The SLSE algorithm combines the LSE algorithm and the LDA algorithm to produce a clear linear mapping relation, thus the projection of the data points on the manifold in the low dimensional space is obtained.
【學(xué)位授予單位】：揚(yáng)州大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2015
【分類號(hào)】：TP391.7;R44
本文編號(hào)：2341800
[Abstract]:With the development of computer technology, human society has entered the information age. In the field of medical diagnosis, it is inevitable to encounter a large number of high dimensional data. The traditional medical diagnosis technology is mainly influenced by subjective factors, the accuracy of diagnosis is low, and the time of diagnosis is large. The research shows that the diagnostic accuracy of automatic medical diagnosis technology is high and the misdiagnosis rate can be reduced. At present, automatic medical diagnosis technology has not been widely used. Traditional expert system relies on database for medical diagnosis, which can be understood by medical workers. But the data collected in the database involved in the expert system are relatively miscellaneous, the redundancy is high, and the accuracy of medical diagnosis is low. The classification method of support vector machine can classify the collected medical information to some extent alleviate the limitation of traditional expert system database and improve the accuracy of diagnosis. However, there is a black box effect in the classification method of support vector machines, that is, it is impossible to explain the reasoning process and the "black box" characteristic of the conclusion, people can not directly see the process of processing, and the comprehensibility is not strong. Manifold dimensionality reduction algorithm in machine learning can project high-dimensional data into low-dimensional visual space. The visualization of intermediate process is easy for medical workers to understand and analyze, and has guiding significance for medical diagnosis. Many dimensionality reduction algorithms are applied in the field of automatic medical diagnosis, but manifold dimensionality reduction algorithms can only reduce the dimension of medical information and cannot be classified. In this paper, the idea of dimensionality reduction and classification is proposed to deal with high dimensional medical data. The low dimensional map and the linear classification decision surface construction are helpful to improve the comprehensibility. The dimensionality reduction manifold algorithm preprocesses a large number of medical data, reduces the redundancy of the data and improves the accuracy of calculation and analysis. In this paper, convection dimension reduction and classification techniques are studied. The research work and main results of this paper include: 1. In this paper, a dimensionally reduced manifold classification algorithm based on isometric mapping (SIMBA algorithm,), SIMBA algorithm) is proposed. Based on the ISOMAP algorithm, the supervised information is incorporated into the), SIMBA algorithm, and the feature extraction of the high-dimensional medical data is carried out. Decision tree algorithm is used to classify the dimensionality reduction results, and the test data is extended. Visualization of intermediate processes enhances comprehensibility and is easier for medical practitioners to understand. According to the test of real medical data set, the improved SIMBA algorithm has higher classification accuracy. 2. 2. In this paper, a dimensionality reduction algorithm (DLLEA algorithm) based on local linear embedding algorithm (LLE algorithm) is proposed. The idea of DLLEA algorithm is as follows: based on the LLE algorithm, the supervised information is incorporated and the reduced dimension results are classified by linear support vector machine (LSVM) algorithm, and the test data are extended. According to the test of real medical data set, the classification accuracy of DLLEA algorithm is higher than that of real medical data set. 3. 3. This paper presents a supervised dimensionality reduction classification algorithm based on local spline embedding algorithm (LSE algorithm for short). The basic idea of). SLSE algorithm of SLSE algorithm is to incorporate the supervised information pair into the local spline algorithm. Dimension data is reduced, KNN algorithm is used to classify the newly added untagged data. The SLSE algorithm combines the LSE algorithm and the LDA algorithm to produce a clear linear mapping relation, thus the projection of the data points on the manifold in the low dimensional space is obtained.
【學(xué)位授予單位】：揚(yáng)州大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2015
【分類號(hào)】：TP391.7;R44
【參考文獻(xiàn)】
相關(guān)期刊論文 前1條
1 楊劍,李伏欣,王玨;一種改進(jìn)的局部切空間排列算法[J];軟件學(xué)報(bào);2005年09期
，本文編號(hào)：2341800
本文鏈接：http://sikaile.net/huliyixuelunwen/2341800.html
最近更新
教材專著
