FSVML AND GA-FSVML WRAPPER APPROACHES FOR GENE SELECTION AND CLASSIFICATION USING EXPRESSIONS OF VERY FEW GENES

Journal Title: International Journal of Genetics - Year 2012, Vol 4, Issue 2

Abstract

Recently, Gene expression profiling by microarray technique has been effectively utilized for classification and diagnostic guessing of cancer nodules in the field of medical sciences. But the techniques used for cancer classification is still in its lower level. There are various drawbacks in the existing classification techniques such as low testing accuracy, high training time, unreliability, etc. Moreover, microarray data consists of a high degree of noise. Gene ranking techniques such as T-Score, ANOVA, etc are later proposed to overcome those problems. But those approaches will sometimes wrongly predict the rank when large database is used. To overcome these issues, this paper mainly focuses on the development of an effective feature selection and classification technique for microarray gene expression cancer diagnosis for provide significant accuracy, reliability and less error rate. In this paper, Wrapper feature selection approach called the GA-FSVML approach is used for the effective feature selection of genes. In FSVML, the RBF kernel function in SVM is trained using modified Levenberg Marquadt algorithm. This approach proposes a Fast SVM Learning (FSVML) technique for the classification tasks. The experiment is performed on lymphoma data set and the result shows the better accuracy of the proposed FSVML with GA-FSVML classification approach when compared to the standard existing approaches.

Authors and Affiliations

N. REVATHY, R. BALASUBRAMANIAN

Keywords

Related Articles

CONSERVATION MODELS ADOPTED FOR SHEEP AND GOAT IN INDIA

Domestication process occurred thousand years ago for sheep and goat genetic resources. In India, 42 breeds of sheep and 21 breeds of goat genetic resources is rich, diverse and locally adapted in its breeding tract. It...

Assessment of DNA Damage by Comet Assay in Lymphocytes of Workers Occupationally Exposed to Petroleum fumes

The comet assay is a sensitive, reliable and rapid method for DNA double & single strand break, alkali-labile sites and delayed repair site detection in individual cells. In recent years, this method has been widely used...

Immunogenomics: recent discoveries

Immunogenomics is a new research field, which addresses the interface between host and (pathogen) proteome, bridging informatics technology, genomics, proteomics, immunology and clinical medicine. The switch from the par...

VARIATION IN THE YAK CALPASTATIN GENE (CAST)

Calpastatin (CAST) is a specific inhibitor of calpain (calcium-dependent cysteine protease). This study investigated the potential for variation in yak (Bos grennies) CAST. PCR-SSCP analysis of exon 6 of yak CAST reveale...

A NOVEL LMNA MUTATION IN TWO SOUTH INDIAN SIBLINGS WITH HUTCHINSON-GILFORD PROGERIA SYNDROME

Background: Hutchinson-Gilford progeria syndrome is a rare genetic disorder characterized by dramatic premature senescence. Progeria is almost always caused by de novo point mutations in the LMNA gene that activates a cr...

Download PDF file
  • EP ID EP170134
  • DOI 10.9735/0975-2862.4.2.85-91
  • Views 106
  • Downloads 0

How To Cite

N. REVATHY, R. BALASUBRAMANIAN (2012). FSVML AND GA-FSVML WRAPPER APPROACHES FOR GENE SELECTION AND CLASSIFICATION USING EXPRESSIONS OF VERY FEW GENES. International Journal of Genetics, 4(2), 85-91. https://europub.co.uk/articles/-A-170134