A Simple Baseline for Travel Time Estimation using Large-scale Trip Data

Wang, Hongjian; Tang, Xianfeng; Kuo, Yu-Hsuan; Kifer, Daniel; Li, Zhenhui

doi:10.1145/3293317

Cited by 97 publications

(33 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The travel time of a query path is estimated by summing up the travel time of road segments in it. TEMP [32], a path-based method, estimates the travel time of a given path based on the nearby historical trajectories, which have close source and destination with the query path. About 9% of the query paths can not be estimated in the original TEMP method due to the lack of nearby trajectories.…”

Section: Baseline Methods For Comparisonmentioning

confidence: 99%

“…However, these approaches do not lead to good result when the extracted sub-paths do not match well with that of the query path. Based on an assumption that paths with close sources and destinations share the same/similar route and thus have similar travel time, some works find trajectories with nearby source and destination or nearby trajectories to the query path to derive the travel time distribution for estimation [17,32]. However, these approaches do not achieve good accuracy when their assumption fails.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

DeepIST

Lee

2019

Proceedings of the 28th ACM International Conference on Information and Knowledge Management

View full text Add to dashboard Cite

Estimating the travel time for a given path is a fundamental problem in many urban transportation systems. However, prior works fail to well capture moving behaviors embedded in paths and thus do not estimate the travel time accurately. To fill in this gap, in this work, we propose a novel neural network framework, namely Deep Imagebased Spatio-Temporal network (DeepIST), for travel time estimation of a given path. The novelty of DeepIST lies in the following aspects: 1) we propose to plot a path as a sequence of "generalized images" which include sub-paths along with additional information, such as traffic conditions, road network and traffic signals, in order to harness the power of convolutional neural network model (CNN) on image processing; 2) we design a novel two-dimensional CNN, namely PathCNN, to extract spatial patterns for lines in images by regularization and adopting multiple pooling methods; and 3) we apply a one-dimensional CNN to capture temporal patterns among the spatial patterns along the paths for the estimation. Empirical results show that DeepIST soundly outperforms the state-of-the-art travel time estimation models by 24.37% to 25.64% of mean absolute error (MAE) in multiple large-scale real-world datasets. CCS CONCEPTS• Computing methodologies → Neural networks; Supervised learning by regression; Model development and analysis.

show abstract

Section: Baseline Methods For Comparisonmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

DeepIST

Lee

2019

Proceedings of the 28th ACM International Conference on Information and Knowledge Management

View full text Add to dashboard Cite

show abstract

“…Given a specific node v t i , the set of all paths containing v t i formulates a set P(v t i ). We define set N (v t i ) = {v c |∃P i ∈ P(v t i ), v c ∈ P i }\{v t i } as the context of node v t i , which refers to all multi-hop neighbors of v t i (i.e., nodes closely surround v t i in space and time) [29]. Specifically, the following log-probability is maximized:…”

Section: Multi-view Graph Embeddingmentioning

confidence: 99%

Joint Modeling of Dense and Incomplete Trajectories for Citywide Traffic Volume Inference

Tang

Gong

et al. 2019

The World Wide Web Conference

Self Cite

View full text Add to dashboard Cite

Real-time traffic volume inference is key to an intelligent city. It is a challenging task because accurate traffic volumes on the roads can only be measured at certain locations where sensors are installed. Moreover, the traffic evolves over time due to the influences of weather, events, holidays, etc. Existing solutions to the traffic volume inference problem often rely on dense GPS trajectories, which inevitably fail to account for the vehicles which carry no GPS devices or have them turned off. Consequently, the results are biased to taxicabs because they are almost always online for GPS tracking. In this paper, we propose a novel framework for the citywide traffic volume inference using both dense GPS trajectories and incomplete trajectories captured by camera surveillance systems. Our approach employs a high-fidelity traffic simulator and deep reinforcement learning to recover full vehicle movements from the incomplete trajectories. In order to jointly model the recovered trajectories and dense GPS trajectories, we construct spatiotemporal graphs and use multi-view graph embedding to encode the multi-hop correlations between road segments into real-valued vectors. Finally, we infer the citywide traffic volumes by propagating the traffic values of monitored road segments to the unmonitored ones through masked pairwise similarities. Extensive experiments with two big regions in a provincial capital city in China verify the effectiveness of our approach.

show abstract

“…The traffic patterns on weekdays is also different from weekends. Similar to [29], we assume that the intermediate location or travel trajectory is not known and only the end locations are available. We define a query q i as a pair (origin, destination, time-ofday) i input to the system and corresponding pair (travel time, travel distance) i as an output.…”

Section: Travel Time Estimationmentioning

confidence: 99%

“…These outliers can cause huge mistakes in our estimations, so we experimentally detected the anomalous trips and removed them from the dataset. d. BTE : We also compare the performance of ST-NN with the best method introduced in [29].…”

mentioning

confidence: 99%

Optimizing Taxi Carpool Policies via Reinforcement Learning and Spatio-Temporal Mining

Jindal

Qin²,

Chen

et al. 2018

2018 IEEE International Conference on Big Data (Big Data)

View full text Add to dashboard Cite

In this paper, we develop a reinforcement learning (RL) based system to learn an effective policy for carpooling that maximizes transportation efficiency so that fewer cars are required to fulfill the given amount of trip demand. For this purpose, first, we develop a deep neural network model, called ST-NN (Spatio-Temporal Neural Network), to predict taxi trip time from the raw GPS trip data. Secondly, we develop a carpooling simulation environment for RL training, with the output of ST-NN and using the NYC taxi trip dataset. In order to maximize transportation efficiency and minimize traffic congestion, we choose the effective distance covered by the driver on a carpool trip as the reward. Therefore, the more effective distance a driver achieves over a trip (i.e. to satisfy more trip demand) the higher the efficiency and the less will be the traffic congestion. We compared the performance of RL learned policy to a fixed policy (which always accepts carpool) as a baseline and obtained promising results that are interpretable and demonstrate the advantage of our RL approach. We also compare the performance of ST-NN to that of state-of-the-art travel time estimation methods and observe that ST-NN significantly improves the prediction performance and is more robust to outliers.

show abstract

A Simple Baseline for Travel Time Estimation using Large-scale Trip Data

Cited by 97 publications

References 22 publications

DeepIST

DeepIST

Joint Modeling of Dense and Incomplete Trajectories for Citywide Traffic Volume Inference

Optimizing Taxi Carpool Policies via Reinforcement Learning and Spatio-Temporal Mining

Contact Info

Product

Resources

About