Analysis Of Traffic Sign Recognition Using Artificial Neural Network Algorithm Compared With Accuracy Of Recurrent Neural Networks

The purpose of this work is to improve Traffic sign recognition using machine learning to improve comprehension of traffic signs. The Novel Artificial Neural Network (ANN) method is compared with Recurrent Neural Network (RNN) to find accuracy. Symbols on the traffic sign boards are used as an image processing input picture. Novel Artificial Neural Network (ANN) (Group 1) has ten samples and Recurrent Neural Network (RNN) (Group 2) has ten samples and in total 146 samples. With the help of image analysis, a Novel Artificial Neural Network (ANN) and Recurrent Neural Network (RNN) are used to predict the accuracy of traffic sign recognition. The training and testing splits are varied for each network type. The G Power test used is about $85 \%$ with clincalc.com the process is done for $\alpha=0.05$ and $\mathrm{N}=0.85$ iterations. Novel Artificial Neural Network (ANN) (90.585 %) has the increased accuracy over Recurrent Neural Network (RNN) ($\mathbf{7 6. 6 4 9}$ %) with a statistical significance value of $\mathbf{0. 0 4 2}$ (p <0.05). Accuracy of Novel Artificial Neural Network (ANN) is significantly better, when compared to accuracy of Recurrent Neural Network (RNN).