A Machine Learning Edged Self-Adaptable Vehicle Slowdown Earliest Warning Information System Using IOT Based Traffic Prediction Model

Abstract

Development of vehicle safety is the work's primary goal, according to its abstract vehicle in traffic congestion using the Internet of Things (IoT). The intense growth of the city's vehicle population needs intelligent traffic systems to be considered resourcefully and sustainably by enhancing the full advantage of recent technology. The unpredictable traffic flow is a substantial issue that carries a colossal traffic movement in real-time scenarios. The random traffic control systems during peak and non-peak hours with unproductive human possessions, which leads to increased traffic and road offenses due to ineffective traffic monitoring systems. To sort down this dynamic scenario, the self-adaptable machine learning approach has been adopted to sequence the intelligent traffic flow by using IOT based early warning system in vehicles. The proposed work focused on the traffic congestion prediction operationalized using the unsupervised algorithm to train the gathered data sets using a neural network. It also aims to deliver a clarification that will upturn the comfort level of travelers to make intelligent and better transference choices. A neural network is a reasonable approach to finding traffic circumstances in sequence with this, the machine learning algorithms and their accuracy, which practices an outline in the collected data sets and then produces crucial decisions in evidence about traffic flow and congestion levels. The most focused part of the research is to enhance the intelligence in the IoT docking system, which prevents the vehicle congestion and returns a flawless, innovative design.