Home Industry Verticals Artificial Intelligence Fujitsu, Jorudan to work on AI-based train delayed predictions

Fujitsu, Jorudan to work on AI-based train delayed predictions

4 MIN READ

Japan-based IT products and services provider Fujitsu has collaborated with Jorudan which is a public transport and route navigation website. Both will be adding a train delay time prediction function, using Artificial Intelligence (AI) machine learning technology, to Jorudan’s “Norikae Annai,” a service that provides public transportation route-planning information.

With this collaboration, Fujitsu aims to deliver, predicted train delay times using AI technology for the Norikae Annai service and verify prediction effectiveness. This process is provided as the cloud service Fujitsu Intelligent Society Solution SPATIOWL, a service that studies previous railway operations data and data submitted by the users and with this, it forecasts the changing delay times built on fresh submitted data and operational information. These predictions are displayed in the route search results in Jorudan’s Norikae Annai app, supporting users’ route selection when trains are delayed.

According to the company, SPATIOWL is a service that gives new value by using bulk of location information from sensor information from vehicles in transit, people and facilities from the internet. It is jointly developed with SRI International into the Fujitsu AI technology, Human Centric AI Zinrai.

 

fujitsu

 

Fujitsu states that Japan faces a common problem of trains delaying by sudden accidents or disasters, and when such problem exists, the alternative provided is through other public transport methods, such as other train lines or buses. Thus, this creates a difficulty for the users to reach to their specific destinations. Despite of having almost no experience in rail operations, Fujitsu is aiming to to provide public transit-related business operators with information that supports users’ choice of routes by learning from past delay information, and to verify its effectiveness in this field trial.

Goals behind the collaboration:

  • Verify the effectiveness of support for users’ choice of action
  • Verify the effectiveness of predictive functionality for train delay times

Fujitsu and Jorudan have a route-planning app that has about 10 million monthly users. Both have joined forces to authenticate the effectiveness of the prediction function to provide accurate predictions of train time delays and to support riders with current information they can use to make informed decisions in the face of delays by adding the function to Jorudan’s app for this field trial.

The trial period will be held from July 19, 2016 to end of September 2016. Based on the results of the current field trial, Fujitsu aims to repeatedly improve prediction accuracy, and is planning to develop it as a new service for SPATIOWL.

Mrunmayi Sapatnekar
A journalist who always tries to get a hang of emerging enterprise tech world. A journalist who always tries to get a hang of emerging enterprise tech world. She has an enormous interest in global and Indian economics. She is a sports enthusiast always talking about cricket and badminton with a twist. Also likes to write articles related to enterprise technology.