Multicategory Classification Using Relevance Vector Machine for Microarray Gene Expression Cancer Diagnosis
Main Article Content
Abstract
This paper deals with the advancement in cancer multicategory classification using Relevance Vector Machine (RVM) for
microarray gene expression cancer diagnosis. The proposed technique can be highly used for directing multicategory classification problems in
the cancer diagnosis area. SVM and ELM are the presently available techniques used for binary classification tasks, which is related to and
contains elements of non-parametric applied statistics, neural networks and machine learning. The cancer classification using the present
approach does not provide the expected accuracy and sometimes the result of clustering may be wrong. To overcome this problem an efficient
cancer classification using the Relevance Vector Machine (RVM) is proposed in this paper. This learning algorithm can generate accurate and
robust classification results on a sound theoretical basis, even when input data are non-monotone and non-linearly separable. The performance of
RVM is evaluated for the multicategory classification on two benchmark microarray data sets for cancer diagnosis, namely, the Lymphoma and
Leukemia dataset. The results indicate that RVM produces better classification accuracies than the approach using SVM and ELM when the data
given as input are preprocessed. RVM delivers very high performance with reduced training time and implementation complexity is less when
compared to artificial neural networks methods like conventional back-propagation ANN and Linder’s SANN.
Â
Keyword- RVM, SVM, ELM, ANOVA, Cancer Classification and Gene Expression
Downloads
Article Details
COPYRIGHT
Submission of a manuscript implies: that the work described has not been published before, that it is not under consideration for publication elsewhere; that if and when the manuscript is accepted for publication, the authors agree to automatic transfer of the copyright to the publisher.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work
- The journal allows the author(s) to retain publishing rights without restrictions.
- The journal allows the author(s) to hold the copyright without restrictions.