Title :
Gene Selection Using l1-Norm Least Square Regression
Author_Institution :
Dept. of Electr. & Comput. Eng., California State Univ., Northridge, CA, USA
fDate :
March 31 2009-April 2 2009
Abstract :
A new gene selection method is proposed based on l1-norm least square regression. The numerical experiment shows that the new approach is, at last comparable to two popular methods: ANOVA and BSS/WSS.
Keywords :
biology computing; genetics; learning (artificial intelligence); least squares approximations; pattern classification; regression analysis; dataset training; gene profile classification system; gene selection method; l1-norm least square regression; Analysis of variance; Cancer; Computer science; Filters; Genetic algorithms; Input variables; Least squares methods; Minimization methods; Support vector machine classification; Support vector machines; Gene selection; classification; l1-norm; least square regression;
Conference_Titel :
Computer Science and Information Engineering, 2009 WRI World Congress on
Conference_Location :
Los Angeles, CA
Print_ISBN :
978-0-7695-3507-4
DOI :
10.1109/CSIE.2009.984
