Abstract
Traffic speed data plays a key role in Intelligent Transportation Systems (ITS); however, missing traffic data would affect the performance of ITS as well as Advanced Traveler Information Systems (ATIS). In this paper, we handle this issue by a novel tensor-based imputation approach. Specifically, tensor pattern is adopted for modeling traffic speed data and then High accurate Low Rank Tensor Completion (HaLRTC), an efficient tensor completion method, is employed to estimate the missing traffic speed data. This proposed method is able to recover missing entries from given entries, which may be noisy, considering severe fluctuation of traffic speed data compared with traffic volume. The proposed method is evaluated on Performance Measurement System (PeMS) database, and the experimental results show the superiority of the proposed approach over state-of-the-art baseline approaches.
Highlights
The large amounts of traffic data collected from the traffic sensors are extremely valuable for route guidance, planning, and management of Intelligent Transportation Systems (ITS) [1]
Considering the higher fluctuation characteristics of traffic speed data, a high accuracy low rank tensor completion (HaLRTC) algorithm [17] is used for imputing missing traffic speed data in this paper
Based on multiple correlations of the traffic speed data, the data set is modeled as a tensor of size 24 × 12 × 15 which stands for 24 hours in a day, 12 sample intervals per hour, and 15 days
Summary
The large amounts of traffic data collected from the traffic sensors are extremely valuable for route guidance, planning, and management of Intelligent Transportation Systems (ITS) [1]. The traffic speed is estimated only from sparse (only a few available observations) historical data of all links in the road network These methods may perform poorly when the missing ratio is high due to the intrinsic characteristic of EM method and the intrinsic characteristic of matrix model. It exploits global information of traffic volume data, tensor based model can exploit multiway global information simultaneously, such as temporal and spatial information Though this method shows its superiority in traffic volume data imputation, the performances on estimating missing traffic speed data are not reported. Motivated by the work in [13], this paper adopts tensor pattern to model the traffic speed data, and an efficient tensor completion method which can deal with noisy entries is used to estimate the missing traffic speed data due to the severe fluctuation of traffic speed data.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have