In English

SmartParking

Viktor Albihn ; Joakim Willard
Göteborg : Chalmers tekniska högskola, 2018. 50 s.
[Examensarbete på grundnivå]

The municipal of Gothenburg aims to reduce the traffic in the city. Västtrafik, which is responsible for public transport in western Sweden, is looking for solutions to help the municipal of Gothenburg to achieve this. One solution that Västtrafik believes in, is to provide information to the long-distance commuters in advance, if there is free space in commuter parkinglot. To see if this was possible, a bachelor thesis was performed at Cybercom Group in Gothenburg. The purpose of this thesis was to assess whether a proof of concept could be created and if so how it was achieved. The result of this graduation work became a basic system consisting of an SQL database, a Machine Learning model based on Decision Forest Regression algorithm, APIs and a basic user interface written in Python. The system is designed in such a way that it can easily be used by third-party developers. A full system from client via web API to the Machine Learning model and back, has been developed. This result can give Västtrafik an insight into how to further develop this into a functioning system. It can otherwise show how to build a similar system. If Västtrafik considers this valueable, the possible outcome is a reduction of traffic in Gothenburg. The project did not intend to deliver a fully finished product or that it would be fully optimized for all commuter parkinglots in Gothenburg.

Nyckelord: Azure, Machine Learning, SQL, Decision Forest Regression, Python.



Publikationen registrerades 2018-06-28. Den ändrades senast 2018-06-28

CPL ID: 255317

Detta är en tjänst från Chalmers bibliotek