An IoT Edge Self-Adaptable Vehicle Slowdown Earliest Warning System Using R-CNN Based Traffic Prediction Model

Increased metropolitan traffic strain and an insufficient amount of technology are the two biggest contributors to accidents. Intelligent technology must be used creatively and sustainably to keep up with the city's rapidly growing vehicle population and road damage. Here, the unsteady road layout is the main concern since it significantly affects how traffic moves in physical globe situations. Random traffic management during peak and off-peak hours with ineffective human resources results in an increase in traffic and road offences because of ineffective traffic monitoring techniques and poor road conditions. The R-CNN used to smart vehicle control flow uses powerful IOT-based quick warning systems in cars to resolve this risk situation and clover choice. Accidents that happen suddenly are most often caused by uneven road conditions. It will provide timely information and adequate monitoring. The operationalization of the worst possible road conditions for predicting traffic congestion is the focus of the current work. On gathered data sets, it trains a neural network using an unsupervised method. Additionally, it wants to make everything clear so that travelers may make informed decisions and efficient transfers. This is the major cause of the bad condition of the roads. Based on the most likely circumstances, it makes sense to identify traffic issues using machine learning techniques and give high accuracy. Here, data sets were obtained as inputs in order to receive the best results, and assessments were then made regarding all requests from decision-making critics. The goal of the project is to give IOT docking systems more intelligence. This avoids item collisions, reduces traffic, and gives accurate, contemporary designs.