Machine learning on high dimensional shape data from subcortical brain surfaces: A comparison of feature selection and classification methods

详细信息    查看全文

• 作者：Benjamin S.C. Wade^a ; ^{ben.wade@loni.usc.edu}Author Vitae ; Shantanu H. Joshi^bAuthor Vitae ; Boris A. Gutman^aAuthor Vitae ; Paul M. Thompson^aAuthor Vitae
• 关键词：HDSD ; High-dimensional shape data ; RRF ; Regularized Random Forest ; NFS ; No Feature Selection ; SVM ; Support Vector Machines ; NB ; Naï ; ve Bayes ; AD ; Alzheimer's Disease ; MCI ; Mild Cognitive Impairment
• 刊名：Pattern Recognition
• 出版年：2017
• 出版时间：March 2017
• 年：2017
• 卷：63
• 期：Complete
• 页码：731-739
• 全文大小：1049 K
• 卷排序：63

文摘

Classification of brain disease with high-dimensional shape data is evaluated. Feature selection importance increased as sample size decreased. LASSO improved classification efficiency but was less robust and accurate. Regularized random forest was highly robust but computationally expensive.