本文關(guān)鍵詞： 樹葉分類 支持向量機 粒子群算法 主成分分析法 癌癥分類 卷積神經(jīng)網(wǎng)絡　出處：《中北大學》2017年碩士論文　論文類型：學位論文

【摘要】：現(xiàn)實中的很多實際問題都可以轉(zhuǎn)化為數(shù)據(jù)信息處理中的數(shù)據(jù)分類問題,例如氣象預報、商品推薦、生物信息、網(wǎng)絡檢測等,而數(shù)據(jù)信息處理都是以機器學習為基礎(chǔ)進行研究的。隨著科學技術(shù)的發(fā)展,機器學習算法的應用領(lǐng)域也變得十分廣泛。本文主要介紹了兩種機器學習算法:粒子群算法優(yōu)化支持向量機和卷積神經(jīng)網(wǎng)絡。其中研究了粒子群算法優(yōu)化支持向量機在樹葉分類和癌癥基因分類中的預測,卷積神經(jīng)網(wǎng)絡在圖像分類中的應用。(1)基于各種樹葉的特征構(gòu)建一個數(shù)據(jù)預處理模型:先對各種數(shù)據(jù)進行歸一化處理,采用主成分分析方法從16個特征中提取出3個主成分,再建立粒子群算法優(yōu)化后的支持向量機,用支持向量機對樹葉數(shù)據(jù)進行分類預測。實驗結(jié)果表明,相對于遺傳算法和網(wǎng)格搜索法尋到的最優(yōu)參數(shù)相比,粒子群算法優(yōu)化支持向量機具有最高的準確率,高達94.1%,高于其他兩種分類方法。(2)將粒子群優(yōu)化的支持向量機模型應用到癌癥基因分類中,通過選取多組不同的實驗數(shù)據(jù)對癌癥手術(shù)后病人的復發(fā)和不復發(fā)的基因樣本進行預測分類。對于三種不同分類方法對于癌癥基因分類的不同分類效果,綜合實驗結(jié)果,粒子群優(yōu)化支持向量機在三種分類方法中達到最好的分類效果。(3)將卷積神經(jīng)網(wǎng)絡應用到圖像處理上,通過優(yōu)化卷積神經(jīng)網(wǎng)絡卷積層和池化層中的濾波器函數(shù),達到了優(yōu)化性能的作用,再構(gòu)造一定結(jié)構(gòu)的卷積神經(jīng)網(wǎng)絡,然后將該模型對圖像數(shù)據(jù)集進行分類處理,在對圖像進行最后達到預期的分類結(jié)果。
[Abstract]:Many practical problems in reality can be transformed into data classification problems in data information processing, such as weather forecast, commodity recommendation, biological information, network detection, etc. And data processing is based on machine learning. With the development of science and technology, In this paper, we mainly introduce two kinds of machine learning algorithms: particle swarm optimization support vector machine and convolution neural network. The prediction of the measuring machine in leaf classification and cancer gene classification, The application of convolution neural network in image classification. (1) A data preprocessing model is constructed based on the characteristics of various leaves. Firstly, the data are normalized, and three principal components are extracted from 16 features by principal component analysis (PCA). Finally, the support vector machine (SVM) is established, which can be used to classify and predict the leaf data. The experimental results show that compared with the optimal parameters obtained by genetic algorithm and grid search, Particle swarm optimization support vector machine (SVM) has the highest accuracy, up to 94. 1%, which is higher than the other two classification methods. (2) the particle swarm optimization support vector machine model is applied to cancer gene classification. By selecting different groups of experimental data to predict and classify the recurrence and non-recurrence gene samples of patients with cancer after operation, three different classification methods for different classification effects of cancer gene classification were synthesized. Particle swarm optimization support vector machine achieves the best classification effect in three classification methods. The convolution neural network is applied to image processing. The filter functions in convolution layer and pool layer are optimized. The function of optimizing performance is achieved, and a convolution neural network with certain structure is constructed, then the image data set is classified by the model, and the expected classification result is achieved at the end of the image classification.
【學位授予單位】：中北大學
【學位級別】：碩士
【學位授予年份】：2017
【分類號】：TP18;TP391.41

【參考文獻】

相關(guān)期刊論文 前6條

1 Fei-Yue Wang;Jun Jason Zhang;Xinhu Zheng;Xiao Wang;Yong Yuan;Xiaoxiao Dai;Jie Zhang;Liuqing Yang;;Where Does AlphaGo Go: From Church-Turing Thesis to AlphaGo Thesis and Beyond[J];IEEE/CAA Journal of Automatica Sinica;2016年02期

2 徐姍姍;劉應安;徐f;;基于卷積神經(jīng)網(wǎng)絡的木材缺陷識別[J];山東大學學報(工學版);2013年02期

3 顧佳玲;彭宏京;;增長式卷積神經(jīng)網(wǎng)絡及其在人臉檢測中的應用[J];系統(tǒng)仿真學報;2009年08期

4 鮑衛(wèi)鋒;黃介生;孔祥元;;基于主成分分析法的流域水循環(huán)效應[J];武漢大學學報(工學版);2007年02期

5 陳果;;基于遺傳算法的支持向量機分類器模型參數(shù)優(yōu)化[J];機械科學與技術(shù);2007年03期

6 饒鮮,董春曦,楊紹全;基于支持向量機的入侵檢測系統(tǒng)[J];軟件學報;2003年04期

，

本文編號：1512717