Full-Text Search:
Home|Journal Papers|About CNKI|User Service|FAQ|Contact Us|中文
《Journal of Taiyuan Normal University(Natural Science Edition)》 2013-01
Add to Favorite Get Latest Update

Model Selection by Balanced 7×2 Crossvalidation

Du Weijie 1 Wang Ruibo 2 Li Jihong 2(1.School of Mathematical Sciences,Shanxi University,Taiyuan 030006;2.Computer Center,Shanxi University,Taiyuan 030006,China)  
Cross-validation is a widespread strategy for classification model comparison and selection.We introduced a balanced 7×2cross-validation(CV)strategy,and further provided a corresponding construction method.We compared the performance of balanced 7×2CV,blocked 3×2CV,standard 5-fold and 10-fold CV for CART model selection.The simulation results showed that,on small data set,the probability of selecting the true model by balanced 7×2crossvalidation was obviously higher than the other three cross-validation strategies.
【CateGory Index】: O212.1
Download(CAJ format) Download(PDF format)
CAJViewer7.0 supports all the CNKI file formats; AdobeReader only supports the PDF format.
Chinese Journal Full-text Database 1 Hits
1 ZHAO Jian-hua;College of Computer Science and Technology,Northwestern Polytechnical University;Department of Computer Science and Technology,Shangluo College;;A Semi-supervised Classification Algorithm Based on the Idea of Cross Validation[J];Journal of Southwest University of Science and Technology;2014-01
Chinese Journal Full-text Database 1 Hits
1 Lü Lei;School of Information Science and Technology, Shanxi University;;Labeling of Semantic Roles on Chinese FrameNet Based on CRFsiute Classifier[J];Computer Development & Applications;2014-04
【Secondary Citations】
Chinese Journal Full-text Database 1 Hits
1 Yu Jiangde1,2 Fan Xiaozhong1 Pang Wenbo1 Yu Zhengtao3(1 School of Computer Science and Technology,Beijing Institute of Technology,Beijing 100081,China)(2 School of Computer and Information Engineering,Anyang Normal University,Anyang 455000,China)(3 School of Information Engineering and Automation,Kunming University of Science and Technology,Kunming 650051,China);Semantic role labeling based on conditional random fields[J];东南大学学报(英文版);2007-03
©2006 Tsinghua Tongfang Knowledge Network Technology Co., Ltd.(Beijing)(TTKN) All rights reserved