Bayesian Support Vector Regression for traffic speed prediction with error bars
Traffic prediction algorithms can help improve the performance of Intelligent Transportation Systems (ITS). To this end, ITS require algorithms with high prediction accuracy. For more robust performance, the traffic systems also require a measure of uncertainty associated with prediction data. Data...
| Main Authors: | , , , , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | en_US |
| Published: |
Institute of Electrical and Electronics Engineers (IEEE)
2014
|
| Online Access: | http://hdl.handle.net/1721.1/86893 https://orcid.org/0000-0002-8585-6566 |
| _version_ | 1826203631295135744 |
|---|---|
| author | Gopi, Gaurav Dauwels, Justin H. G. Asif, Muhammad Tayyab Ashwin, Sridhar Mitrovic, Nikola Rasheed, Umer Jaillet, Patrick |
| author2 | Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science |
| author_facet | Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science Gopi, Gaurav Dauwels, Justin H. G. Asif, Muhammad Tayyab Ashwin, Sridhar Mitrovic, Nikola Rasheed, Umer Jaillet, Patrick |
| author_sort | Gopi, Gaurav |
| collection | MIT |
| description | Traffic prediction algorithms can help improve the performance of Intelligent Transportation Systems (ITS). To this end, ITS require algorithms with high prediction accuracy. For more robust performance, the traffic systems also require a measure of uncertainty associated with prediction data. Data driven algorithms such as Support Vector Regression (SVR) perform traffic prediction with overall high accuracy. However, they do not provide any information about the associated uncertainty. The prediction error can only be calculated once field data becomes available. Consequently, the applications which use prediction data, remain vulnerable to variations in prediction error. To overcome this issue, we propose Bayesian Support Vector Regression (BSVR). BSVR provides error bars along with the predicted traffic states. We perform sensitivity and specificity analysis to evaluate the efficiency of BSVR in anticipating variations in prediction error. We perform multi-horizon prediction and analyze the performance of BSVR for expressways as well as general road segments. |
| first_indexed | 2024-09-23T12:40:20Z |
| format | Article |
| id | mit-1721.1/86893 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T12:40:20Z |
| publishDate | 2014 |
| publisher | Institute of Electrical and Electronics Engineers (IEEE) |
| record_format | dspace |
| spelling | mit-1721.1/868932022-10-01T10:25:39Z Bayesian Support Vector Regression for traffic speed prediction with error bars Gopi, Gaurav Dauwels, Justin H. G. Asif, Muhammad Tayyab Ashwin, Sridhar Mitrovic, Nikola Rasheed, Umer Jaillet, Patrick Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology. Laboratory for Information and Decision Systems Jaillet, Patrick Traffic prediction algorithms can help improve the performance of Intelligent Transportation Systems (ITS). To this end, ITS require algorithms with high prediction accuracy. For more robust performance, the traffic systems also require a measure of uncertainty associated with prediction data. Data driven algorithms such as Support Vector Regression (SVR) perform traffic prediction with overall high accuracy. However, they do not provide any information about the associated uncertainty. The prediction error can only be calculated once field data becomes available. Consequently, the applications which use prediction data, remain vulnerable to variations in prediction error. To overcome this issue, we propose Bayesian Support Vector Regression (BSVR). BSVR provides error bars along with the predicted traffic states. We perform sensitivity and specificity analysis to evaluate the efficiency of BSVR in anticipating variations in prediction error. We perform multi-horizon prediction and analyze the performance of BSVR for expressways as well as general road segments. Singapore-MIT Alliance for Research and Technology (Center for Future Mobility) 2014-05-09T14:04:45Z 2014-05-09T14:04:45Z 2013-10 Article http://purl.org/eprint/type/ConferencePaper 978-1-4799-2914-6 http://hdl.handle.net/1721.1/86893 Gopi, Gaurav, Justin Dauwels, Muhammad Tayyab Asif, Sridhar Ashwin, Nikola Mitrovic, Umer Rasheed, and Patrick Jaillet. “Bayesian Support Vector Regression for Traffic Speed Prediction with Error Bars.” 16th International IEEE Conference on Intelligent Transportation Systems (ITSC 2013) (n.d.). https://orcid.org/0000-0002-8585-6566 en_US http://dx.doi.org/10.1109/ITSC.2013.6728223 Proceedings of the 16th International IEEE Conference on Intelligent Transportation Systems (ITSC 2013) Creative Commons Attribution-Noncommercial-Share Alike http://creativecommons.org/licenses/by-nc-sa/4.0/ application/pdf Institute of Electrical and Electronics Engineers (IEEE) MIT web domain |
| spellingShingle | Gopi, Gaurav Dauwels, Justin H. G. Asif, Muhammad Tayyab Ashwin, Sridhar Mitrovic, Nikola Rasheed, Umer Jaillet, Patrick Bayesian Support Vector Regression for traffic speed prediction with error bars |
| title | Bayesian Support Vector Regression for traffic speed prediction with error bars |
| title_full | Bayesian Support Vector Regression for traffic speed prediction with error bars |
| title_fullStr | Bayesian Support Vector Regression for traffic speed prediction with error bars |
| title_full_unstemmed | Bayesian Support Vector Regression for traffic speed prediction with error bars |
| title_short | Bayesian Support Vector Regression for traffic speed prediction with error bars |
| title_sort | bayesian support vector regression for traffic speed prediction with error bars |
| url | http://hdl.handle.net/1721.1/86893 https://orcid.org/0000-0002-8585-6566 |
| work_keys_str_mv | AT gopigaurav bayesiansupportvectorregressionfortrafficspeedpredictionwitherrorbars AT dauwelsjustinhg bayesiansupportvectorregressionfortrafficspeedpredictionwitherrorbars AT asifmuhammadtayyab bayesiansupportvectorregressionfortrafficspeedpredictionwitherrorbars AT ashwinsridhar bayesiansupportvectorregressionfortrafficspeedpredictionwitherrorbars AT mitrovicnikola bayesiansupportvectorregressionfortrafficspeedpredictionwitherrorbars AT rasheedumer bayesiansupportvectorregressionfortrafficspeedpredictionwitherrorbars AT jailletpatrick bayesiansupportvectorregressionfortrafficspeedpredictionwitherrorbars |