High Impact Factor : 4.396 icon | Submit Manuscript Online icon |

Data Decomposition and Matrix Reduction using Binary-PSO in Tensor Mining


Mashkoor Ahmad , Pranveer Sing Institue Of Technology; Sunil Kumar, Pranveer Sing Institute Of Technology


ALS, PSO, LRA Tensor Mining


Tensor decompositions are efficient method for big data analytics as it brings multiple modes and aspects of data to a unified framework, which allows us to discover complex internal structures and correlations of data. In existing approach are not designed to meet the major challenges posed by big data analytics, the distributed data correlation inspired from apriori algorithm which find out association rules that consider missing data afterwards it covers all local nodes in a network. Our proposed approach, attempts to improve the scalability of tensor decompositions and reduce missing data. The globally considered nodes which minimizing relative error , finding optimal solution then improving efficiency as with total number of frequent item-set using low rank approximation matrices for item-set weightage over nodes then assign fitness value as per global best function using LRA-PSO(low rank approximation based particle swarm optimization) approach for same association based distributed data using MATLAB 2014 Ra.

Other Details

Paper ID: IJSRDV6I40709
Published in: Volume : 6, Issue : 4
Publication Date: 01/07/2018
Page(s): 1226-1229

Article Preview

Download Article