In 1997, the Swedish parliament adopted a decision on Vision Zero (nollvision) in the road  and transport system. Vision Zero means that no one should be killed or seriously injured in  traffic accidents in the road transport system (Prop. 2003/04: 160). For the Transport  Administration in Sweden (Trafikverket), this means increased demands on security and  signage at road work sites around the country. This in turn means increased demands on the  contractors that carry out road work for the Transport Administration. The Transport  Administration wants a better understanding how entrepreneurs in various operational areas in  the Eastern Region perceive their role as responsible for safety and accessibility on roadwork  sites and to better understand the problems that can occur when signage is inadequate. In this  report, governing documents for the operating entrepreneurs have been studied, in addition,  searches of literature in various transport databases have been made. Interviews have been  made with the operating entrepreneurs who have had the opportunity to highlight their views  on roadwork. The results of the study are a compilation of things the contractors put emphasis  on. Among other things, several of them want to separate service equipment  (trafikanordningar) from the procurement because it is possible to win offers with a lower bid  amount, depending on how signage is made and safety is ensured. Many contractors also call  for more clarification from the Transport Administration, and say that it is often unclear what  the relevant directives are. Hopefully, this report will help increase the Transport  Administration’s understanding of the roadwork performed by contractors and help them  towards Vision Zero.     Keywords  vägarbete, trafikanordning, utmärkning, nollvision, trafikanordningsplan, konkurrenssättning,  skyltning, framkomlighet / År 1997 fattade riksdagen ett beslut om nollvision inom vägtransportsystemet. Nollvisionen  innebär att ingen person ska dödas eller skadas allvarligt till följd av trafikolyckor inom  vägtransportsystemet (Prop. 2003/04:160). För Trafikverket innebär detta ökade krav på  säkerhet och skyltning på vägarbetsplatserna runtom i landet. Detta innebär i sin tur ökade  krav på entreprenörerna som utför vägarbeten för Trafikverket. Trafikverket vill få bättre  förståelse för hur entreprenörer inom olika driftområden i Region Öst ser på sin roll som  ansvariga för säkerhet och framkomlighet vid vägarbeten samt få bättre förståelse för vilka  problem som kan uppstå när skyltning av en vägarbetsplats är bristfällig. I denna rapport har  styrande dokument för driftentreprenörer studerats, dessutom har sökningar efter litteratur i  olika transportdatabaser gjorts. Intervjuer har gjorts med driftansvariga entreprenörer som har  haft möjlighet att lyfta fram sina åsikter kring arbetet på väg. Resultatet av rapporten är en  sammanställning av de punkter entreprenörerna lägger vikt vid. Bland annat vill flera av dem  lyfta ur trafikanordningarna ur upphandlingen då det är möjligt att vinna anbud med lägre  anbudssumma beroende på hur skyltningen utförs och säkerheten säkerställs. Flera  entreprenörer efterlyser även mer tydlighet från Trafikverket och säger att det många gånger  är oklart vilka direktiv som gäller. Förhoppningsvis kan denna rapport öka Trafikverkets  förståelse för entreprenörernas arbete på vägar och vara till hjälp för dem på vägen mot  nollvisionen.    Nyckelord  vägarbete, trafikanordning, utmärkning, nollvision, trafikanordningsplan, konkurrenssättning,  skyltning, framkomlighet

In this thesis, four different Machine Learning models and algorithms have been evaluated in the work of classifying Traffic Control Plans in the City of Helsingborg. Before a roadwork can start, a Traffic Control Plan must be created and submitted to the Traffic unit in the city. The plan consists of information regarding the roadwork and how the work can be performed in a safe manner, concerning both road workers and car drivers, pedestrians and cyclists that pass by. In order to know what safety barriers are needed both the Swedish Association of Local Authorities and Regions (SALAR) and the Swedish Transport Administration (STA) have made a classification of roads to guide contractors and traffic technicians what safety barriers are suitable to provide a safe workplace. The road classifications are built upon two rules; the amount of traffic and the speed limit of the road. Thus real-world problems have shown that these classifications are not applicable to every single case. Therefore, each roadwork 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 safety barrier is needed or not a classification can be made based on historical data. In this thesis, the performance of several Machine Learning models and datasets are presented when Traffic Control Plans are classified. The algorithms used for the classification task were Random Forest, AdaBoost, K-Nearest Neighbour and Artificial Neural Network. In order to know what attributes to include in the dataset, participant observations in combination with interviews were held with a traffic technician at the City of Helsingborg. The datasets used for training the algorithms were primarily based on geographical data but information regarding the roadwork and period of time were also included in the dataset. The results of this study indicated that it was preferred to include road attribute information in the dataset. It was also discovered that the classification accuracy was higher if the attribute values of the geographical data were continuous instead of categorical. In the results it was revealed that the AdaBoost algorithm had the highest performance, even though the difference in performance was not that big compared to the other algorithms.