Built a time machine

Kolumbus is the public bus and boat transport administration in Rogaland, a county in Western Norway, did this. Public transportation faces significant changes with new technology, behaviour and environmental demands. Kolumbus, therefore, wishes to innovate more proactively step by step to offer the passengers the best experience possible – fast and agile transport with minimal delays. They wanted a «time machine» – a more versatile system for predictions than what they had in the real-time mapping tool. Computas was commissioned to develop the prototype of the time machine.

The time machine is an example of how artificial intelligence and machine learning can be used to give us a better and easier everyday life

Rune Hagbartsen, Director Computas

Result

The solution is a first step on the way to a better and easier everyday life for travelers and Kolumbus – aided by machine learning and artificial intelligence. The time machine can predict delays and exact positions on the company’s 450 buses up to one year in advance. It integrates multiple external data sources, such as weather and holidays, and learns from all the collected positioning data of the buses. Predictions are generated continuously so that the traffic situation can be visualized in a map solution and played as a movie.

Customer expectations are getting higher every day as technology improves. If we want to stay relevant we need to be evolving all the time and stay on the cutting edge. Computas and Google help us to do that

Audun M. Solheim, Head of Strategy and Development at Kolumbus

International Google case study

The solution is built on Google Cloud Platform and has already received much attention. It is, among other things, described in an article published on Google’s international pages.

Technology we used

  • Google Cloud Platform
  • Python 2.7
  • Flask
  • TensorFlow + Keras

What we did

  • Data analysis
  • ETL
  • Machine Learning
  • API
  • Map Integration
  • Project management

Would you like to know more?

Send us an email and we will contact you

contact@computas.com