Optimized Auto Encoder on High Dimensional Big Data Reduction: an Analytical Approach
Arifa Javid Shikalgar, Shefali Pratap Sonavane · Turkish Journal of Computer and Mathematics Education (TURCOMAT) · 2021
Big data comprises of huge volume of data, which is exponentially increasing with time. Since the data istoo large in size; the traditional data management tools are ineffective in processing these data effectively. The bigdata encompasses huge count of variables, hence analyzing each of the variables at a microscopic level is notfeasible, as it might consume days or even months to have a meaningful analysis. This is time-consuming andcostlier. Therefore, the Dimensionality Reduction (DR) techniques can be utilized. In general, the DR is a techniquefor reducing the count of input variables with fewer losses. These input features can cause deprived performance forML algorithms. This paper introduces an optimized auto-encoder based dimensionality reduction model to dealwith large datasets. The weight of the auto-encoder is fine-tuned by a selfadaptive Bumble Bees MatingOptimization (SA-BBMO) algorithm, which is the conceptual upgrading of standard BBMO. Further, to validatethe appropriateness of the projected dimensionality reduction model, the experiments are conducted using bigdatasets. The corresponding results acquired are compared over the nonlinear dimensionality reduction techniqueslike PCA, K-PCA, LDA etc, in terms of Reconstruction error, Convergence, V-Measures, Silhouet Coefficient andComputation Time.