Path cost distribution estimation using trajectory data

Abstract

With the growing volumes of vehicle trajectory data, it becomes increasingly possible to capture time-varying and uncertain travel costs in a road network, including travel time and fuel consumption. The current paradigm represents a road network as a weighted graph; it blasts trajectories into small fragments that fit the underlying edges to assign weights to edges; and it then applies a routing algorithm to the resulting graph. We propose a new paradigm, the hybrid graph, that targets more accurate and more efficient path cost distribution estimation. The new paradigm avoids blasting trajectories into small fragments and instead assigns weights to paths rather than simply to the edges.We show how to compute path weights using trajectory data while taking into account the travel cost dependencies among the edges in the paths. Given a departure time and a query path, we show how to select an optimal set of weights with associated paths that cover the query path and such that the weights enable the most accurate joint cost distribution estimation for the query path. The cost distribution of the query path is then computed accurately using the joint distribution. Finally, we show how the resulting method for computing cost distributions of paths can be integrated into existing routing algorithms. Empirical studies with substantial trajectory data from two different cities offer insight into the design properties of the proposed method and confirm that the method is effective in real-world settings.

Correlated Time Series Forecasting using Multi-Task Deep Neural Networks

“…Next, we apply Sigmoid activation function to each matrix group to produce a 1 × l matrix. This corresponds |X | reconstructed time series, e.g.,X (1) ,X (2) , andX (3) ,…”

Learning to Route with Sparse Trajectory Sets

“…We first find those of v k 's adjacent, qualified vertices VB for merging with v k (lines 8-10). Then we identify VB ′ which includes the vertices that will actually be merged with v k and cut the graph between v k and the vertices in VA\VB ′ (lines [11][12][13]. Finally, we merge v k with its adjacent vertices in VB ′ and add it back to the priority queue (lines [14][15][16][17].…”

“…Traditional routing is cost-centric and aims at returning paths with minimal costs, e.g., distance, travel time, or fuel consumption. The cost of a path is computed from edge costs in edge-based cost modeling [6]- [11] or sub-path costs in path-based cost modeling [12]- [15]. In such routing, trajectory data is often used for annotating the edges or sub-paths with travel costs such as travel times; and routing services employ shortest path algorithms, e.g., Dijkstra's algorithm or contraction hierarchies [16], to return fastest, or simply shortest, paths.…”

Discovery of accessible locations using region-based geo-social data

“…Location search and recommendation are well studied in recent two decades [6,[8][9][10][11]19,30,31,[43][44][45][46][47][48]. Generally, such type of query can be classified into three categories: point-to-point, trajectory-to-point, and region-to-point.…”