• EKTA JOSHI

The goal of the data mining process is to extract given information from a data set and transform it into a useful structure for further use. Clustering is one of the most important tasks in knowledge discovery from data. The goal of clustering is to discover the nature structure of data or detect meaningful groups from data. But for Big data application, clustering models are faced with the problem of analysing large dataset and hence, result in the need for more efficient algorithms to quickly analyse large datasets. Clustering techniques, like K-Means are useful in analysing data in a parallel fashion. K-Means largely depends upon a proper initialization to produce optimal results. However, DBSCAN algorithm has the quadratic time complexity, making it difficulty in real application with large dataset. Proposed approach presents a method which effectively reduce time complexity of clustering modelling based on K-Mean algorithm along with block operation which effectively reduces time costs of clustering modelling. Redesigning of distance function by using Manhattan distance instead of common Euclidean distance to simplify the calculation. The focus of this paper is to select a good initial seeding in less time, facilitating fast and accurate cluster analysis over large datasets.

K means clustering, Fast Clustering, DBSCAN, Min-Max, block operation.

"KDBSCAN: A Hybrid Approach in Big Data", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.5, Issue 5, page no.571-574, May-2018, Available :http://www.jetir.org/papers/JETIR1805101.pdf

"KDBSCAN: A Hybrid Approach in Big Data", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.5, Issue 5, page no. pp571-574, May-2018, Available at : http://www.jetir.org/papers/JETIR1805101.pdf