• 1S.Baskaran
• 2S.Gandhi

The traditional data processing algorithms add consecutive manner that will increase their time of execution. These algorithms ought to use the data processing capabilities of the trendy GPUs to execute parallel programs with efficiency. thus a parallel process} rule ought to be enforced that may utilize the processing power of GPUs to hurry up the execution. when put next with the straightforward set mining drawback and string mining drawback, the hierarchi- cal structure of consecutive pattern mining (due to the requirement to contemplate frequent subsets among every itemset, also as order among itemsets) and therefore the ensuing massive permutation area makes SPM extraordinarily costly on typical pro-cessor architectures. HAC estimation for long and high-dimensional statistic is computationally costly. This paper describes a unique pipeline-friendly HAC estimation rule derived from a mathematical specification, by applying transformations to eliminate conditionals, to parallelise arithmetic, and to push information apply in computation. we have a tendency to then develop a fully-pipelined hardware design supported the planned rule. This design is shown to be economical and ascendible from each theoretical and empirical views. Experimental results show that AN FPGA-based implementation of the planned design is up to 111 times quicker than AN optimised processor implementation with one core, and fourteen times quicker than a processor with eight cores

Keywords: Parallel Computing , CUDA , Data mining , Classification , Clustering , GPU Databases

"PARALLEL DATA MINING TECHNIQUES ON GRAPHICS PROCESSING FOR MULTIVARIATE TIME SERIES", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 6, page no.219-223, June 2019, Available :http://www.jetir.org/papers/JETIR1908033.pdf

"PARALLEL DATA MINING TECHNIQUES ON GRAPHICS PROCESSING FOR MULTIVARIATE TIME SERIES", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 6, page no. pp219-223, June 2019, Available at : http://www.jetir.org/papers/JETIR1908033.pdf