Paper Info
Title
Distinguishing Trajectories from Different Drivers using Incompletely Labeled Trajectories.
Abstract
We consider a scenario that occurs often in the auto insurance industry. We are given a large collection of trajectories that stem from many different drivers. Only a small number of the trajectories are labeled with driver identifiers, and only some drivers are used in labels. The problem is to label correctly the unlabeled trajectories with driver identifiers. This is important in auto insurance to detect possible fraud and to identify the driver in, e.g., pay-as-you-drive settings when a vehicle has been involved in an incident. To solve the problem, we first propose a Trajectory-to-Image( T2I) encoding scheme that captures both geographic features and driving behavior features of trajectories in 3D images. Next, we propose a multi-task, deep learning model called T2INet for estimating the total number of drivers in the unlabeled trajectories, and then we partition the unlabeled trajectories into groups so that the trajectories in a group belong to the same driver. Experimental results on a large trajectory data set offer insight into the design properties of T2INet and demonstrate that T2INet is capable of outperforming baselines and the state-of-the-art method.
Year
DOI
Venue
2018
10.1145/3269206.3271762
CIKM
Keywords
Field
DocType
Trajectory analysis, multi-task learning, deep learning, representation learning
Small number,Data mining,Insurance industry,Multi-task learning,Identifier,Computer science,Artificial intelligence,Deep learning,Trajectory,Feature learning,Encoding (memory)
Conference
ISBN
Citations 
PageRank 
978-1-4503-6014-2
8
0.51
References 
Authors
34
4
Name
Order
Citations
PageRank
Tung Kieu1263.25
Bin Yang270634.93
Chenjuan Guo3213.52
Christian S. Jensen4106511129.45