Abstract
This paper proposes a new gene selection algorithm based on support vectors and penalty strategy (SVPS). In detail, cross-validation procedures are performed on training datasets, and in each validation sub-procedure, support vector machines (SVMs) are trained and tested. For each SVM, the support vectors are weighted and combined to form the initial correlation degrees of genes with the class distinction. A penalty strategy is then used to penalize these initial degrees, and the penalized degrees are finally used to produce a criterion for gene selection. The application to the leukaemia dataset shows that the proposed algorithm can identify the key genes related to the class distinction and is competitive to the existing methods.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: Transactions of the Institute of Measurement and Control
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
