Paper Title
DEEP LEARNING-BASED SMART TRAFFIC SIGNAGE TO CONTROL HIGHWAY SPEED LIMIT

Abstract
Abstract - This Speeding is a major contributing factor to road accidents and fatalities worldwide. To improve road safety, speed signs are commonly utilized to communicate speed limits and provide guidance to drivers. This project aims to enhance an existing system that utilizes cameras and machine learning to determine road conditions and the appropriate speed limit specifically during rainy weather by developing smart speed limit traffic sign (SSLTS). The proposed system involves optimizing the image processing through enhanced convolutional neural network algorithm to properly detect raindrops. An Arduino microcontroller device reads the output of the raindrop detection system. Based on the prevailing weather conditions, the system displays the corresponding speed limit on an LCD screen. This project leverages advanced technology to bolster public safety by promptly notifying drivers of the appropriate speed limit during rainy conditions, potentially reducing the risk of accidents. Keywords - Smart Traffic Sign, Convolutional Neural Network (Cnn), Speed Limit, Machine Learning