TY - JOUR
T1 - Population-guided large margin classifier for high-dimension low-sample-size problems
AU - Yin, Qingbo
AU - Adeli, Ehsan
AU - Shen, Liran
AU - Shen, Dinggang
N1 - Funding Information:
The authors would like to thank Prof. J.S. Marron in Department of biostatistics, University of North Carolina at Chapel Hill; Dr. Boxiang Wang in statistics at University of Minnesota; Prof. Xingye Qiao in Department of Mathematical Sciences, Binghamton University, for their kind help and discussion about the methods based on Distance weighting. This work was supported in part by Graduate Education and Teaching Reform Project of Dalian Maritime University (YJG2018102); and by grant of Thirteenth Five-Year Plan of Liaoning Province for Educational Science (JG18DB058).
Funding Information:
The authors would like to thank Prof. J.S. Marron in Department of biostatistics, University of North Carolina at Chapel Hill; Dr. Boxiang Wang in statistics at University of Minnesota; Prof. Xingye Qiao in Department of Mathematical Sciences, Binghamton University, for their kind help and discussion about the methods based on Distance weighting. This work was supported in part by Graduate Education and Teaching Reform Project of Dalian Maritime University ( YJG2018102 ); and by grant of Thirteenth Five-Year Plan of Liaoning Province for Educational Science ( JG18DB058 ).
Publisher Copyright:
© 2019 Elsevier Ltd
PY - 2020/1
Y1 - 2020/1
N2 - In this paper, we propose a novel linear binary classifier, denoted by population-guided large margin classifier (PGLMC), applicable to any sorts of data, including high-dimensional low-sample-size (HDLSS). PGLMC is conceived with a projecting direction w given by the comprehensive consideration of local structural information of the hyperplane and the statistics of the training samples. Our proposed model has several advantages compared to those widely used approaches. First, it isn't sensitive to the intercept term b. Second, it operates well with imbalanced data. Third, it is relatively simple to be implemented based on Quadratic Programming. Fourth, it is robust to the model specification for various real applications. The theoretical properties of PGLMC are proven. We conduct a series of evaluations on the simulated and five realworld benchmark data sets, including DNA classification, medical image analysis and face recognition. PGLMC outperforms the state-of-theart classification methods in most cases, or obtains comparable results.
AB - In this paper, we propose a novel linear binary classifier, denoted by population-guided large margin classifier (PGLMC), applicable to any sorts of data, including high-dimensional low-sample-size (HDLSS). PGLMC is conceived with a projecting direction w given by the comprehensive consideration of local structural information of the hyperplane and the statistics of the training samples. Our proposed model has several advantages compared to those widely used approaches. First, it isn't sensitive to the intercept term b. Second, it operates well with imbalanced data. Third, it is relatively simple to be implemented based on Quadratic Programming. Fourth, it is robust to the model specification for various real applications. The theoretical properties of PGLMC are proven. We conduct a series of evaluations on the simulated and five realworld benchmark data sets, including DNA classification, medical image analysis and face recognition. PGLMC outperforms the state-of-theart classification methods in most cases, or obtains comparable results.
KW - Binary linear classifier
KW - Data piling
KW - High-dimension lowsample-size
KW - Hyperplane
KW - Large margin classification
KW - Local structure information
UR - http://www.scopus.com/inward/record.url?scp=85071843074&partnerID=8YFLogxK
U2 - 10.1016/j.patcog.2019.107030
DO - 10.1016/j.patcog.2019.107030
M3 - Article
AN - SCOPUS:85071843074
SN - 0031-3203
VL - 97
JO - Pattern Recognition
JF - Pattern Recognition
M1 - 107030
ER -