A Novel Prediction Analysing the False Acceptance Rate and False Rejection Rate using CNN Model to Improve the Accuracy for Iris Recognition System for Biometric Security in Clouds Comparing with Traditional Inception Model

Abstract

The main motivation of the study is to improve the Novel Prediction of accuracy using the Convolutional Neural Networks (CNN) model system for iris recognition biometric security in clouds and comparing with Traditional inception models (TIM). Accuracy to perform two groups CNN model and Traditional Inception Models (N=10) to calculate and find the comparison value of accuracy. G power 80% threshold 0.05%, 95% confidence interval mean and standard deviation The independent sample T-test was used Convolutional Neural Networks and TIM. CNN (92%) performs better than TIM (60%). There is a statistically relevant disparity between the CNN and TIM transform based on comparison ratio data is 0.048 (p<0.05). The result shows the proposed CNN algorithm has the better accuracy compared to TIM algorithm.