Show simple item record

dc.contributor.author成超
dc.contributor.author杨晨晖
dc.date.accessioned2018-11-26T08:55:20Z
dc.date.available2018-11-26T08:55:20Z
dc.date.issued2017
dc.identifier.citation厦门大学学报. 自然科学版,2017,(1):123-128
dc.identifier.issn0438-0479
dc.identifier.other10.6043/j.issn.0438-0479.201601008
dc.identifier.urihttps://dspace.xmu.edu.cn/handle/2288/165712
dc.description.abstract对大脑皮层厚度数据进行建模从而实现阿尔茨海默症的诊断.在训练样本少,数据复杂且非线性的情况下,相比于BP神经网络和$k$最近邻等算法,支持向量机; 算法表现出更优良的特性.针对支持向量机算法受数据高维度的影响,将$t$分布随机邻域嵌入算法引入到支持向量机模型.$t$分布随机邻域嵌入算法既能撷; 取原始高维数据的局部信息,也能揭示全局结构.$t$分布随机邻域嵌入算法先将这些非线性数据降维到低维空间,支持向量机算法再将这数据映射到新的高维空; 间,通过寻找最佳分类超平面的方法,使分类效果达到最佳水平.最后将集成学习算法AdaBoost的思想融入模型,可以使模型的分类准确率得到提升,而且; 变得鲁棒性更强.
dc.description.abstractModel based on cortex thickness data is used to implement Alzheimer's; diseasediagnosis(AD).Comparing with back propagation(BP) and $k$-nearest; neighboralgorithms($k$NN),support vector machine (SVM) algorithm; exhibits more excellent characteristics in the case that the number of; training samples is smaller and the data is complex and; nonlinear.Considering that the performance of SVM algorithm is; influenced by high dimension,we combine thet-distributed stochastic; neighbor embeddingalgorithm($t$-SNE) with SVM algorithm model.$t$-SNE is; capable of capturing much of the local structure of the high-dimensional; data very well,while also revealing global structure,such as the; presence of clusters at several scales.The $t$-SNE algorithm reduces the; dimension of nonlinear data,and then SVM algorithm maps Low-dimensional; data to a high-dimensional space.Afterwards,SVM looks for the best; hyperplane to make the best classification results.Finally,the ideal of; an ensemble learning algorithm AdaBoost is used,which can improve the; classification accuracy of the model and make the model more robust.
dc.language.isozh_CN
dc.subject支持向量机
dc.subject$t$分布随机邻域嵌入
dc.subject集成学习
dc.subject阿尔茨海默症
dc.subjectsupport vector machine
dc.subject$t$-distributed stochastic neighbor embedding
dc.subjectensemble learning
dc.subjectAlzheimer
dc.title基于$t$分布随机邻域嵌入的阿尔茨海默症诊断模型
dc.title.alternativeAlzheimer Diagnosis Model Based on $t$-Distributed Stochastic Neighbor Embedding
dc.typeArticle


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record