Comparison of Novel Recurrent Neural Network Over Artificial Neural network in Predicting Email spammers with improved accuracy

Abstract

The main aim is to compare Novel Recurrent Neural Network over Artificial Neural Network in predicting Email spammers with improved accuracy. Material and Methods : This research study contains two groups namely Novel Recurrent Neural Network and Artificial Neural Network. Each group consists of a sample size of 10 and the study parameters are calculated using clincalc with preset parameters as alpha 0.8, beta 0.2 and CI as 90%. Results and Discussion : The Novel Recurrent Neural Network has the highest accuracy 97.96% when compared to Artificial Neural Network it has 93.79% accuracy in Electronic Mail spam prediction with significance value p=0.000(p<0.05) that is significantly better. The G-power value is 80%. When used as a spam predictor for electronic mail, the Novel Recurrent Neural Network performance analysis outperforms the best results than the Artificial Neural Network performance.