原文传递
AN INVESTIGATION INTO INCIDENT DURATION FORECASTING.
| 题名： | AN INVESTIGATION INTO INCIDENT DURATION FORECASTING. |
| 作者： | Smith-Brian-L; Smith-Kevin-W |
| 关键词： | Commercial-vehicle-operations; Incident-management; Real-time-information; Traffic-estimation |
| 摘要： | FleetForward is an operational test designed to demonstrate the impact of real-time traffic information on commercial vehicle operations such as dispatching and routing. While real-time data is an important element of transportation condition information, its availability in the operational test also highlights the need for forecasted information. One specific need in FleetForward is the ability to forecast the duration of a current traffic incident. This paper describes research focused upon forecasting incident duration using nonparametric regression. This forecasting technique is data driven as it searches a database to find a neighborhood of past incidents similar to the current incident. The data source for developing this model was the Information Exchange Network (IEN) of the I-95 Corridor Coalition. The general conclusion of this paper is that the quality and scope of the data in the incident database is a major factor in the performance of a forecasting model. |
| 总页数： | ITS America. Meeting (11th : 2001 : Miami Beach, Fla.). ITS connecting the Americas : ITS 2001 : conference proceedings. 2001. pp12 |
| 报告类型： | 科技报告 |
相关文献
- Socioeconomic Forecasting.
- INCORPORATING FEEDBACK IN TRAVEL FORECASTING.
- Network Modeling 2012, Volume 1. Transportation Research Record: Journal of the Transportation Research Board, No. 2283.
- Sustainable Practices, Performance Measures, and Management. Transportation Research Record: Journal of the Transportation Research Board, No. 2271.
- Freight 2012: A Peer-Reviewed Publication. Transportation Research Record: Journal of the Transportation Research Board, No. 2288.
- Highway Capacity and Quality of Service 2012. Transportation Research Record: Journal of the Transportation Research Board, No. 2286.
检索历史
应用推荐
