Grey Wolf Shuffled Shepherd Optimization Algorithm-Based Hybrid Deep Learning Classifier for Big Data Classification

Abstract

In recent days, big data is a vital role in information knowledge analysis, predicting, and manipulating process. Moreover, big data is well-known for organized extraction and analysis of large or difficult databases. Furthermore, it is widely useful in data management as compared with the conventional data processing approach. The development in big data is highly increasing gradually, such that traditional software tools faced various issues during big data handling. However, data imbalance in huge databases is a main limitation in the research area. In this paper, the Grey wolf Shuffled Shepherd Optimization Algorithm (GWSSOA)-based Deep Recurrent Neural Network (DRNN) algorithm is devised to classify the big data. In this technique, for classifying the big data a hybrid classifier, termed as Holoentropy driven Correlative Naive Bayes classifier (HCNB) and DRNN classifier is introduced. In addition, the developed hybrid classification model utilizes the MapReduce structure to solve big data issues. Here, the training process of the DRNN classifier is employed using GWSSOA. However, the developed GWSSOA is devised by integrating Shuffled Shepherd Optimization Algorithm (SSOA) and Grey Wolf Optimizer (GWO) algorithms. The developed GWSSOA-based DRNN model outperforms other big data classification techniques with regards to accuracy, specificity, and sensitivity of 0.966, 0.964, 0.870, and 209837ms.