Abstract
One of the increasingly common methods to counteract the increased fuel consumption of vehicles is start-stop technology. This paper introduces a methodology which presents the process of measuring and creating a computational model of CO(2) emissions using artificial intelligence techniques for a vehicle equipped with start-stop technology. The method requires only measurement data of velocity, acceleration of vehicle, and gradient of road to predict the emission of CO(2). In this paper, three methods of machine learning techniques were analyzed, while the best prediction results are shown by the gradient boosting method. For the developed models, the results were validated using the coefficient of determination, the mean squared error, and based on visual evaluation of residual and instantaneous emission plots and CO(2) emission maps. The developed models present a novel methodology and can be used for microscale environmental analysis.