Improving the Accuracy of Feature Selection in Big Data Mining Using Accelerated Flower Pollination (AFP) Algorithm.

Abstract

In recent times, the main problem associated with big data analytics is its high dimensional data over the search space. Such data gathers continuously in search space making traditional algorithms infeasible for data mining in real time environment. Hence, feature selection is an important method to lighten the load during processing while inducing a model for mining. However, mining over such high dimensional data leads to formulation of optimal feature subset, which grows exponentially and leads to intractable computational demand. In this paper, a novel lightweight mechanism is used as a feature selection method, which solves the after effects arising with optimal feature selection. The feature selection in big data mining is done using accelerated flower pollination (AFP) algorithm. This method improves the accuracy of feature selection with reduced processing time. The proposed method is tested under larger set of data with high dimensionality to test the performance of proposed method.