Machine Learning for digitizing Traffic Management Plans
In this thesis Machine Learning models and algorithms is evaluated in the work of handling Traffic Control Plans in the City of Helsingborg. Before a road work can start, a Traffic Control Plan must be created and handed in to the traffic unit. The plan consists of information regarding the road work and how it can be made in a safe manner, concerning both road workers and vehicles that passes by. In order to know what safety barriers are needed the Swedish Association of Local Authorities and Regions has made a classification of roads to guide contractors and traffic planners what barriers is suitable to provide a safe workplace. The road classification is made into two different categories but real world problems has shown that this classification not can be applied to every single case. Therefor, each road work must be judged and evaluated from its specific attributes. By creating and training a Machine Learning model that is able to determine if a rigid road barrier is needed or not a classification can be made based on historical data. This classification is not solely based on road attribute information, like the classification from the Swedish Association of Local Authorities and Regions, but also on other factors such as period of time, type of road work and distances to nearby roads and places. This thesis explains how different Machine Learning models and datasets has been used for the decision making process regarding safety barriers when handling Traffic Control Plans.