基于參數(shù)優(yōu)化的SVM分類器在繼發(fā)性干燥綜合征診斷中的應(yīng)用
發(fā)布時(shí)間：2018-08-24 16:10
【摘要】：干燥綜合征.(siccasyndrome,簡(jiǎn)稱SS)是一種外分泌腺體的自身免疫性慢性疾病,通常被分成原發(fā)性干燥綜合征與繼發(fā)性干燥綜合征這兩個(gè)類型。其中,繼發(fā)性干燥綜合征常繼發(fā)于系統(tǒng)性紅斑狼瘡(Systemic Lupus Erythematosus,簡(jiǎn)稱SLE)等疾病之中,因此容易被人忽視。為了解決SLE患者并發(fā)繼發(fā)性干燥綜合征不容易及時(shí)確診與治療過(guò)程中由于醫(yī)生主觀性依賴較強(qiáng)導(dǎo)致治療方案有偏差的問(wèn)題,提出了一種將支持向量機(jī)(SupportVectorMachine,簡(jiǎn)稱SVM)與系統(tǒng)性紅斑狼瘡繼發(fā)干燥綜合征早期診斷相結(jié)合的新思路,該方法主要思想是利用SVM分類器對(duì)系統(tǒng)性紅斑狼瘡患者及SLE繼發(fā)性干燥綜合征的患者進(jìn)行二分類。本文以141例患者病例為研究對(duì)象,經(jīng)過(guò)數(shù)據(jù)篩選處理,分別運(yùn)用了交叉驗(yàn)證法、網(wǎng)格搜索法、標(biāo)準(zhǔn)粒子群優(yōu)化算法分別對(duì)SVM模型分類器中的懲罰參數(shù)C與核函數(shù)參數(shù)g進(jìn)行優(yōu)化選擇,最終發(fā)現(xiàn)粒子群算法優(yōu)化SVM參數(shù)模型不僅分類的效果最佳,其泛化能力也有很大提升。之后針對(duì)粒子群算法易陷入局部最優(yōu)的問(wèn)題,提出混沌機(jī)制改進(jìn)粒子群優(yōu)化算法的方法。最后,分別利用MATLAB軟件對(duì)上述4種優(yōu)化方式進(jìn)行編程的實(shí)現(xiàn),并將結(jié)果以直觀的圖像表示在workspace窗口中,用以表達(dá)SVM模型分類器最終的分類正確率。最終對(duì)比選出對(duì)SLE患者并發(fā)繼發(fā)性干燥綜合征疾病診斷分類度的準(zhǔn)確率分別為82.3529%、88.2353%、90.1961%、92.1569%。最終結(jié)果對(duì)比表明:基于混沌機(jī)制改進(jìn)的粒子群算法優(yōu)化的支持向量機(jī)分類模型參數(shù)的尋優(yōu),相較于交叉驗(yàn)證與網(wǎng)格搜索法,對(duì)SVM參數(shù)的優(yōu)化選擇更加科學(xué)及嚴(yán)謹(jǐn);且對(duì)比標(biāo)準(zhǔn)粒子群優(yōu)化SVM參數(shù)的模型,可以明顯看出,基于混沌機(jī)制改進(jìn)的粒子群算法改善了標(biāo)準(zhǔn)粒子群容易陷入早熟現(xiàn)象,從而提高了 SVM分類器對(duì)SLE繼發(fā)干燥綜合征疾病分類診斷的精度。
[Abstract]:Sjogren syndrome (. (siccasyndrome,) is an autoimmune chronic disease of exocrine glands, which is usually divided into primary Sjogren syndrome and secondary Sjogren syndrome. Among them, secondary Sjogren syndrome is often secondary to systemic lupus erythematosus (Systemic Lupus Erythematosus,) and other diseases, so it is easy to be ignored. In order to solve the problem that the patients with SLE complicated with secondary Sjogren's syndrome are not easily diagnosed in time and deviated from the treatment plan due to the strong subjective dependence of the doctor. A new idea of combining support vector machine (SVM) with early diagnosis of Sjogren's syndrome secondary to systemic lupus erythematosus is proposed. The main idea of this method is to use SVM classifier to classify patients with systemic lupus erythematosus and patients with SLE secondary Sjogren's syndrome. In this paper, 141 cases of patients were studied. After data screening and processing, cross validation method and grid search method were used respectively. The standard particle swarm optimization algorithm optimizes the penalty parameter C and kernel function parameter g in the classifier of SVM model. Finally, it is found that the particle swarm optimization algorithm not only has the best classification effect, but also greatly improves its generalization ability. Then, aiming at the problem that particle swarm optimization (PSO) is easy to fall into local optimization, a chaotic mechanism is proposed to improve PSO. Finally, the above four optimization methods are programmed by using MATLAB software, and the results are represented in the workspace window as an intuitive image, which is used to express the final classification accuracy of the SVM model classifier. The accuracy of diagnosis of secondary Sjogren's syndrome in SLE patients was 82.3529 and 88.2353, 90.1961and 92.1569, respectively. The final results show that the optimization of support vector machine (SVM) model parameters based on improved particle swarm optimization (PSO) based on chaos mechanism is more scientific and rigorous than cross-validation and mesh search. Compared with the model of standard particle swarm optimization (SVM) parameter optimization, it is obvious that the improved particle swarm algorithm based on chaos mechanism can improve the premature phenomenon of standard particle swarm optimization. Thus, the accuracy of SVM classifier in the diagnosis of Sjogren's syndrome secondary to SLE is improved.
【學(xué)位授予單位】：昆明理工大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：R593.2;TP18
[Abstract]:Sjogren syndrome (. (siccasyndrome,) is an autoimmune chronic disease of exocrine glands, which is usually divided into primary Sjogren syndrome and secondary Sjogren syndrome. Among them, secondary Sjogren syndrome is often secondary to systemic lupus erythematosus (Systemic Lupus Erythematosus,) and other diseases, so it is easy to be ignored. In order to solve the problem that the patients with SLE complicated with secondary Sjogren's syndrome are not easily diagnosed in time and deviated from the treatment plan due to the strong subjective dependence of the doctor. A new idea of combining support vector machine (SVM) with early diagnosis of Sjogren's syndrome secondary to systemic lupus erythematosus is proposed. The main idea of this method is to use SVM classifier to classify patients with systemic lupus erythematosus and patients with SLE secondary Sjogren's syndrome. In this paper, 141 cases of patients were studied. After data screening and processing, cross validation method and grid search method were used respectively. The standard particle swarm optimization algorithm optimizes the penalty parameter C and kernel function parameter g in the classifier of SVM model. Finally, it is found that the particle swarm optimization algorithm not only has the best classification effect, but also greatly improves its generalization ability. Then, aiming at the problem that particle swarm optimization (PSO) is easy to fall into local optimization, a chaotic mechanism is proposed to improve PSO. Finally, the above four optimization methods are programmed by using MATLAB software, and the results are represented in the workspace window as an intuitive image, which is used to express the final classification accuracy of the SVM model classifier. The accuracy of diagnosis of secondary Sjogren's syndrome in SLE patients was 82.3529 and 88.2353, 90.1961and 92.1569, respectively. The final results show that the optimization of support vector machine (SVM) model parameters based on improved particle swarm optimization (PSO) based on chaos mechanism is more scientific and rigorous than cross-validation and mesh search. Compared with the model of standard particle swarm optimization (SVM) parameter optimization, it is obvious that the improved particle swarm algorithm based on chaos mechanism can improve the premature phenomenon of standard particle swarm optimization. Thus, the accuracy of SVM classifier in the diagnosis of Sjogren's syndrome secondary to SLE is improved.
【學(xué)位授予單位】：昆明理工大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：R593.2;TP18
【參考文獻(xiàn)】
相關(guān)期刊論文 前10條
1 鄒心遙;陳敬偉;姚若河;;采用粒子群優(yōu)化的SVM算法在數(shù)據(jù)分類中的應(yīng)用[J];華僑大學(xué)學(xué)報(bào)(自然科學(xué)版);2016年02期
2 張娜;王美燕;;繼發(fā)性干燥綜合征臨床特點(diǎn)分析[J];浙江臨床醫(yī)學(xué);2016年02期
3 王恩賢;陶宏才;;基于PSO-SVM算法的炒作微博識(shí)別研究[J];成都信息工程學(xué)院學(xué)報(bào);2015年06期
4 徐力平;尚丹;陳小玉;;模糊神經(jīng)網(wǎng)絡(luò)在肺癌CT診斷中的應(yīng)用[J];鄭州大學(xué)學(xué)報(bào)(醫(yī)學(xué)版);2014年02期
5 武建國(guó);;SLE和類風(fēng)濕關(guān)節(jié)炎的新分類標(biāo)準(zhǔn)[J];臨床檢驗(yàn)雜志;2013年07期
6 張新峰;焦月;李歡歡;卓力;;基于粒子群算法的Universum SVM參數(shù)選擇[J];北京工業(yè)大學(xué)學(xué)報(bào);2013年06期
7 王健峰;張磊;陳國(guó)興;何學(xué)文;;基于改進(jìn)的網(wǎng)格搜索法的SVM參數(shù)優(yōu)化[J];應(yīng)用科技;2012年03期
8 申慧s，
本文編號(hào)：2201335
本文鏈接：http://sikaile.net/yixuelunwen/nfm/2201335.html
最近更新
教材專著
