Traffic Information Hub is a software platform that enables proactive traffic management through visibility, analytics, and prediction. Traffic Information Hub is the software foundation to Intelligent Transportation and provides a platform to visualization and analytics applications.
Traffic Information Hub software is available in a variety of deployment options. The software can reside in a data center. For cities that do not have IT infrastructure and resources and prefer a subscription service model, it is also available on the IBM SmartCloud.
Traffic Information Hub utilizes Intelligent Operations Center to enable real-time communication and collaboration with other city agencies to coordinate actions and resolve issues in an efficient manner.
In particular, Traffic Information Hub is designed to:
Aggregate multi-source traffic data into a standard traffic information model from which analysis can be performed and scalable applications can be created- Display information from systems that interface with such traffic-related devices as signals, signs, and cameras to obtain current status and feeds
- Provide insight into patterns of traffic network historical performance, helping to create performance improvement and performance fine-tuning plans
- Perform analysis of historical patterns of traffic conditions and incidents such as peak-hour volumes and congestion on the most critical links in the network as a function of location, time, and speed limit on the links
- Enable the study of historic correlation between traffic incidents of different types and traffic service levels to understand the impact and plan for the future, such as the impact of lane closures during different times of the day to better manage maintenance activity
Predict traffic conditions, including speed and volume, up to an hour into the future based on analysis of current and historical data- Provide real-time display of traffic conditions graphically as service levels on a road network as well as in tabular and report views
- Support scheduled auto-calculations of predictions
- Provide historical accuracy reports of predictions
Issue real-time alerts to events and incidents through e-mail or instant messages- Issue alerts to events and incidents on the transportation network in real-time, graphically, in tabular view, and through e-mail or instant messages.
More
- Aggregate multi-source traffic data
- Display information from systems that interface with such traffic-related devices as signals, signs, and cameras to obtain current status and feeds
- Provide insight into patterns of traffic network historical performance, helping to create performance improvement and performance fine-tuning plans
- Perform analysis of historical patterns of traffic conditions and incidents such as peak-hour volumes and congestion on the most critical links in the network as a function of location, time, and speed limit on the links
- Enable the study of historic correlation between traffic incidents of different types and traffic service levels to understand the impact and plan for the future, such as the impact of lane closures during different times of the day to better manage maintenance activity
- Predict traffic conditions up to an hour into the future
- Provide real-time display of traffic conditions graphically as service levels on a road network as well as in tabular and report views
- Support scheduled auto-calculations of predictions
- Provide historical accuracy reports of predictions
- Issue alerts to events and incidents
- Issue alerts to events and incidents on the transportation network in real-time, graphically, in tabular view, and through e-mail or instant messages.
Contact IBM
Considering a purchase?
- Email IBM
- Request a quote
- Or call us at: 855-221-0702
Priority code: 101K803W
Additional Resources
-
Traffic Prediction solution brief (PDF, 757KB)
-
Transit Operations Solution Brief (PDF, 626KB)
-
Traffic Information Hub Announcement Letter (PDF, 99KB)
-
Smarter City solutions brochure (PDF, 444KB)
-
Smarter City Solutions on Cloud white paper (PDF, 4.02MB)



