Enhanced Expectation-Maximization Algorithm for Smart Traffic IoT Systems using Deep Generative Adversarial Networks to Reduce waiting time

The main focus of the work is to improve the smart traffic systems for the Internet of Things (IoT) such as traditional signals and safe driving via tracking the congestion and monitoring traffic slowly. Depending on the circumstances, intersections between roads can sometimes lead to accidents, so this problem is considered part of the research. These limitations can be overcome by using modern sensors that can reduce the traffic signal waiting time and rash driving on the National Highway (NH) road. Urban countries make use of AI-based decisions performing smart control over managing vehicles. In the proposed model the novel combination of collecting road maps coordinating points that can connect the access movements. Also IoT devices such as mobile phones, unusual network failure, and peak time traffic control by preprocessing the collected traffic dataset. Based on the dataset the detection of coverage area can be extracted using Enhanced Expectation Maximization Algorithm for ranking the variables. Initially, the classification algorithms were used and grouped as accident months, non-accident months, hill stations, and highway NH Road delay time are some of categories. Using Deep Generative Adversarial Network (DGAN) data can be balanced and used to reduce the waiting time along with predicting the smart cities’ transportation for reliable customers.