|本期目录/Table of Contents|

[1]成 超,杨晨晖*.基于t分布随机邻域嵌入的阿尔茨海默症诊断模型[J].厦门大学学报(自然科学版),2017,56(01):123-128.[doi:10.6043/j.issn.0438-0479.201601008]
 CHENG Chao,YANG Chenhui*.Alzheimer Diagnosis Model Based on t-Distributed Stochastic Neighbor Embedding[J].Journal of Xiamen University(Natural Science),2017,56(01):123-128.[doi:10.6043/j.issn.0438-0479.201601008]
点击复制

基于t分布随机邻域嵌入的阿尔茨海默症诊断模型(PDF)
分享到:

《厦门大学学报(自然科学版)》[ISSN:0438-0479/CN:35-1070/N]

卷:
56卷
期数:
2017年01期
页码:
123-128
栏目:
研究论文
出版日期:
2017-01-23

文章信息/Info

Title:
Alzheimer Diagnosis Model Based on t-Distributed Stochastic Neighbor Embedding
文章编号:
0438-0479(2017)01-0123-06
作者:
成 超杨晨晖*
厦门大学信息科学与技术学院,福建 厦门 361005
Author(s):
CHENG ChaoYANG Chenhui*
School of Information Science and Engineering,Xiamen University,Xiamen 361005,China
关键词:
支持向量机 t分布随机邻域嵌入 集成学习 阿尔茨海默症
Keywords:
support vector machine t-distributed stochastic neighbor embedding ensemble learning Alzheimer
分类号:
TP 399
DOI:
10.6043/j.issn.0438-0479.201601008
文献标志码:
A
摘要:
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.
Abstract:
Model based on cortex thickness data is used to implement Alzheimer’s diseasediagnosis(AD).Comparing with back propagation(BP)and k-nearest neighboralgorithms(kNN),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.

参考文献/References:

[1] TOSUN D,SCHUFF N,WEINER M.An integrated multimodality MR brain imaging study:gray matter tissue loss mediates the association between cerebral hypoperfusion and alzheimer’s disease[C]∥Annual International Conference of the IEEE Engineering in Medicine and Biology Society.Minneapolis:IEEE,2009:6981-6984.
[2] SUI X C,LIS H,LIU J Q,et al.Sparse canonical correlation analysis reveals correlated patterns of gray matter loss and white matter impairment in alzheimer’s disease[C]∥2015 IEEE 12th International Symposium on Biomedical Imaging.New York:IEEE,2015:470-473.
[3] YANG W L,YAN L,CHEN X Y.ICA image feature extraction for improving diagnosis of Alzheimer’s disease and mild cognitive impairment[C]∥2014 10th International Conference on Natural Computation.Xiamen:IEEE,2014:802-806.
[4] SHI Y H,SUK H I,GAO Y,et al.Joint coupled-feature representation and coupled boosting for AD diagnosis[C]∥2014 IEEE Conference on Computer Vision and Pattern Recognition.Columbus:IEEE,2014:2721-2728.
[5] LI F,TRAN L,THUNG K H,et al.A robust deep model for improved classification of AD/MCI patients [J].IEEE Journal of Biomedical and Health Informatics,2015,19(5):1610-1616.
[6] CORTES C,VAPNIK V.Support-vector networks[J].Machine Learning,1995,20(3):273-297.
[7] SARAFIS I,DIOU C,TSIKRIKA T,et al.Weighted SVM from clickthrough data for image retrieval[C]∥2014 IEEE International Conference on Image Processing.Paris:IEEE,2014:3013-3017.
[8] MAATEN L V D,HINTON G.Visualizing data using t-SNE[J].Journal of Machine Learning Research,2008,9:2579-2605.
[9] GISBRECHT A,HAMMER B,MOKBEL B,et al.Nonlinear dimensionality reduction for cluster identification in metagenomic samples[C]∥2013 17th International Conference on Information Visualisation.London:IEEE,2013:174-179.
[10] CHENG J,LIU H J,WANG F,et al.Silhouette analysis for human action recognition based on supervised temporal t-SNE and incremental learning[J].IEEE Transactions on Image Processing,2015,24(10):3203-3217.
[11] YI J Z,MAO X,XUE Y L,et al.Facial expression recognition based on t-SNE and adaboostM2[C]∥Green Computing and Communications(GreenCom),2013 IEEE and Internet of Things(iThings/CPSCom),IEEE International Conference on and IEEE Cyber,Physical and Social Computing.Beijing:IEEE,2013:1744-1749.
[12] MAATEN L V D.Accelerating t-SNE using tree-based algorithms[J].Journal of Machine Learning Research,2014,15:3221-3245.

备注/Memo

备注/Memo:
收稿日期:2016-01-08 录用日期:2016-05-16*通信作者:chyang@xmu.edu.cn
更新日期/Last Update: 1900-01-01