Abstract: Systems and methods for travel time density estimation based on sparse approximation. The density estimation problem is reformulated as a kernel-based regression problem and sparsity is the driving principle underlying model selection. This is particularly useful when the objective is to promote the predictive capabilities of the model and avoid overfitting; in the context of travel time density estimation, the objective is to determine the optimal number of kernels that can faithfully capture the multiple modes resulting from the state of traffic in the network.

Abstract: Locations for traffic sensors can be determined by a computer system that identifies a particular segment of a travel path. Traffic flow data from other segments of travel path are accessed based on traffic flow characteristics of the particular path. Using the traffic flow data, parameters for a traffic incident symptom propagation model are generated, and a location of a traffic incident along the segment of the path is determined. Using time-to-detection limits and the incident model, upstream and downstream distances are determined, and the locations of two sensors are identified based on the distances.

Abstract: Locations for traffic sensors can be determined by a computer system that identifies a particular segment of a travel path. Traffic flow data from other segments of travel path are accessed based on traffic flow characteristics of the particular path. Using the traffic flow data, parameters for a traffic incident symptom propagation model are generated, and a location of a traffic incident along the segment of the path is determined. Using time-to-detection limits and the incident model, upstream and downstream distances are determined, and the locations of two sensors are identified based on the distances.

Abstract: A location for a traffic incident can be determined by a computer system, using data from a first and second sensor along a travel path. A receiving and sending symptom of the traffic incident are detected from a first and second sensor, using traffic flow data from the sensors. The locations of the first and second sensors are determined. The location and traffic flow data from each sensor are used to create a sending and receiving profiles. From the profiles, a convergence formula is build. Using the convergence formula and by determining a convergence point for the sending and receiving symptoms, a time and location of the traffic incident is identified.