Authors : D. Viji, R. Lavanya, D. Hemavathi and P. Saranya
Abstract: The promise of data-driven decision-making is now being recognized broadly and there is growing enthusiasm for the notion of "Big data. Heterogeneity, scale, timeliness, complexity and privacy problems with big data hinder advancement at all stages of the channel that can form assessment from information. The promising visualization of big data is to facilitate organizations will be capable to produce and tie together every byte of related information and use it to make the preeminent decisions. Big data technologies not only support the ability to collect large amounts but more importantly, the ability to understand and take advantage of its full value. Traditional data mining techniques are deals with structured, homogeneous and small dataset.But today =s perspective major characteristics of big data are heterogeneity. In big data mining heterogeneity data set have to accept and deal with following types of data like structured, semi structured even though, fully unstructured data simultaneously. In this study, an interesting idea given about partitioning to handle the heterogeneity data. First it helps to determine whether the given dataset is fully heterogeneity or not. Then the given dataset is accordingly partitioned into several homogenous subsets. Finally, a specialized model for each subset is constructed and narrated with various features.
D. Viji, R. Lavanya, D. Hemavathi and P. Saranya, 2018. Divergence of Managing Scalability and Unstructured Data in Big Data Analytics. Journal of Engineering and Applied Sciences, 13: 2575-2579.