Advances in Computer Science and Information Technology. Computer Science and Information Technology. Second International Conference, CCSIT 2012, Bangalore, India, January 2-4, 2012. Proceedings, Part III

Research Article

Comparison of Efficient and Rand Index Fitness Function for Clustering Gene Expression Data

Download
259 downloads
  • @INPROCEEDINGS{10.1007/978-3-642-27317-9_17,
        author={P. Patheja and Akhilesh Waoo and Ragini Sharma},
        title={Comparison of Efficient and Rand Index Fitness Function for Clustering Gene Expression Data},
        proceedings={Advances in Computer Science and Information Technology. Computer Science and Information Technology. Second International Conference, CCSIT 2012, Bangalore, India, January 2-4, 2012. Proceedings, Part III},
        proceedings_a={CCSIT PART  III},
        year={2012},
        month={11},
        keywords={Genetic Algorithm Fitness Function Clustering Gene Expression Data Variance},
        doi={10.1007/978-3-642-27317-9_17}
    }
    
  • P. Patheja
    Akhilesh Waoo
    Ragini Sharma
    Year: 2012
    Comparison of Efficient and Rand Index Fitness Function for Clustering Gene Expression Data
    CCSIT PART III
    Springer
    DOI: 10.1007/978-3-642-27317-9_17
P. Patheja1,*, Akhilesh Waoo1,*, Ragini Sharma1,*
  • 1: BIST
*Contact email: pspatheja@gmail.com, akhilesh_waoo@rediffmail.com, raginishrma@gmail.com

Abstract

This paper illustrates a comparative study of Efficient Fitness Function and Rand Index Fitness Function, to show how Efficient Fitness Function can give better results when used to cluster gene expression data. Variance which is the main limitation of Rand Index can be improved with Efficient Fitness Function. The results are evaluated by finding the precision value (i.e. sensitivity and specificity) of the dataset. Genetic Weighted K-Mean Algorithm (GWKMA) which is used here is a hybridization of Weighted K-Mean Algorithm (WKMA) and Genetic Algorithm. WKMA is used to perform optimal partition of data. Genetic Algorithm is then applied to get the best fit gene from clusters through the fitness function, on which genetic operators like selection, crossover and mutation are performed.