Architecture For Air Pollution Aware Vehicle Rerouting in Smart Cities Using Machine Learning & Ant Colony Algorithm

Abstract

In this paper, the layered design to investigations and interesting route arranging dependent on the basic parameter Air Pollution is proposed. Different ways have been proposed for limiting the criticality of Air Pollution and its effect on wellbeing. Normally while choosing a route starting with one spot then onto the next spot, one pick the most shortest way or the way which is having lesser traffic density, however for the individual who experiences ailments like exasperated cardiovascular, respiratory sickness, quickened maturing of the lungs, asthma, bronchitis, it is increasingly imperative to know the degree of contamination all through the path which one needs to utilize while voyaging particularly for the riders on bike. Additionally, this mindfulness about the ongoing degree of contamination will assist them in taking prudent activities. The proposed design depends on the Ant colony optimization Technique and Machine learning. The novel part of the proposed architecture is to use the trained model through machine learning methods which compute the importance of the effect of different parameters like Air Pollution, Traffic Density, and Distance on calculating probability which leads towards the selection of an optimal path among all available routes towards the destination. The proposed model calculates decision making dynamically at each junction and this dynamic decision procedure will consider dynamic changes in the parameter like traffic and air pollution would reduce the impact of air pollution on health with increasing the cost of a distance.