Abstract
Urban areas include a large number of traffic intersections and signals. Wait times at traffic signals can be long at times and can lead to user frustration. While digital map applications can provide predictions of overall time of travel for a journey and can also indicate congested parts of the route, these cannot reduce the frustration of waiting at a traffic signal. This disclosure describes the use of machine learning prediction models to automatically generate real-time predictions of wait times at intersections along a route. The predictions are based on historical data as well as on current traffic patterns, weather information, and other available information. Users are provided visual and/or audible guidance on wait times, including detailed explanations of the reason for long wait times. The prediction models are updated based on user feedback regarding accuracy of prediction as well as based on updated traffic data.
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.
Recommended Citation
Prasad, Ajay, "Traffic Signal Wait Time Estimation Using Machine Learning", Technical Disclosure Commons, (September 17, 2024)
https://www.tdcommons.org/dpubs_series/7364