• J. Sujitha
• S.R.Lavanya

Abstract: Missing data imputation is a challenging issue in data mining pre-processing techniques. Most of the data mining algorithms cannot process a dataset with continuous missing data. The continuous missing data in a dataset can affect the performance of the mining process of data which leads to the difficulty of extracting information from datasets. The existing system’s MIAEC algorithm is not applicable to find the continuous missing data and takes much time to find the missing values in large datasets with continuous data loss. To overcome this problem, the proposed method is meant for continuous missing data imputation based on co-cluster sparse matrix learning (CCSML) model. This algorithm learns without reference class, and even with continuous missing rate data as high as 90%. The method works based on a tensor optimization model and labeled maximum block. The computational method of sparse recovery learning model is built on low-rank, co-clusters of GWAS data matrices and the performance is better than the existing method of missing data imputation using the Evidence Chain (MIAEC) algorithm.

Missing at Random, Missing completely at Random, Missing Not at Random, MIAEC algorithm, sparse low-rank matrix completion, Co-clustering factorization, Maximum blocks improvement.

"Imputation of Missing data using Co-cluster sparse matrix learning model for Genome data", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 2, page no.16-23, February-2019, Available :http://www.jetir.org/papers/JETIR1902402.pdf

"Imputation of Missing data using Co-cluster sparse matrix learning model for Genome data", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 2, page no. pp16-23, February-2019, Available at : http://www.jetir.org/papers/JETIR1902402.pdf