Empirical Analysis of Deep Learning for Big Data and Its Applications using CNN

Deep Learning has taken an utmost interest in the field of big data analytics due to its feature extraction and classification properties. Traditionally, researchers used Machine Learning algorithms to classify big data; however, the feature extraction was carried out by a human-driven process. Thus, researchers discovered the deep learning approaches to carry out the feature extraction by using algorithms. In this research, a “Convolutional Neural Network” or CNN algorithm has been selected to understand the accuracy of big data analytics. Primary research has been carried out to understand how hidden layers and nodes impact the accuracy of this neural network. Moreover, CNN has been compared with other neural networks to understand if CNN is out-competing the rest algorithms or not (other two algorithms selected are “Recurrent Neural Network” or RNN and “Artificial Neural Network” or ANN). In the primary research, CNN and other algorithms were tasted for accuracy against hidden layers, nodes, training and validation time. Regression and Correlation analyses have been carried out where independent variables were: Training time, Validation time, Hidden layers and Hidden nodes. Dependent variables were CNN, ANN and RNN. Findings showed that CNN is 92% accurate whereas other neural networks possess less than 90% of accuracy in big data analytics. The hidden nodes have significant positive impact on the accuracy of CNN.