Google AI Machine Learning Model Can Predict Bus Delays
Google Maps Introduced Live Traffic Delays for Buses
This research summary is just one of many that are distributed weekly on the AI scholar newsletter. To start receiving the weekly newsletter, sign up here.
The buzz around machine learning keeps skyrocketing. Every industry is talking about it. From healthcare, autonomous vehicles, management information systems, computer vision, cybersecurity, business efficiency and marketing, and now the technique is in use to predict bus delays.
Millions across the globe rely on public transit for their day-to-day travels. For buses, challenges including bus delays can result in a lot of time wastage.
Google Maps provides public transit directions and informs transit agencies with real-time data. However, many transit agencies are still unable to provide public transit directions due to technical and resource constraints.
You Can Now Predict Whether Your Bus Ride is Likely to Delay
Google Maps has introduced live traffic for buses forecasting bus delays in hundreds of cities worldwide including ranging from Atlanta to Zagreb to Istanbul to Manila and more. To develop the model, they extracted training data from sequences of bus positions as received from transit agencies over time and aligned them to car traffic speeds on the bus’s path during the trip.
To capture unique properties of specific streets, neighborhoods, and cities, Google let the model learn a hierarchy of representations for areas of different size, with a timeline unit’s geography represented in the model by the sum of the embedding’s of its location at various scales.
The model is split into a sequence of timeline units including visits to street blocks and stops each corresponding to a piece of the bus’s timeline, with each unit forecasting a duration. A pair of adjacent observations usually spans many units, due to infrequent reporting, fast-moving buses, and short blocks and stops.
Potential Uses and Effects
Have you ever wasted hours and hours of your precious time due to a bus delay? The suggested model significantly improves the accuracy of transit timing for millions of people across the globe.
Reflecting on the fact that millions depend on bus rides for their city travels, the approach enables clear-cut forecasting to make it easier for users to plan their trips.
Read more: https://ai.googleblog.com/2019/06/predicting-bus-delays-with-machine.html
Thanks for reading. Please comment, share and remember to subscribe to our weekly newsletter for the most recent and interesting research papers! You can also follow me on Twitter and LinkedIn. Remember to 👏 if you enjoyed this article. Cheers!
