Big Data Analytics using Chaotic Biogeography Based Optimization and Deep Stacked Auto Encoder

Abstract

The growth of big data has resulted in a need for effective data classification techniques. Chaotic Biogeography Based Optimization (CBBO) is a nature-inspired optimization technique that has shown promising results in solving complex optimization problems. However, CBBO can struggle with high-dimensional big data classification problems. To address this issue, a Deep Stacked Auto Encoder (DSAE) is introduced to CBBO to create a novel algorithm, CBBO-DSAE, for big data classification. The proposed algorithm is evaluated on several benchmark datasets and compared with other state-of-the-art algorithms. The experimental results demonstrate that CBBO-DSAE is effective in handling big data classification problems, outperforming other existing algorithms.