Aggregating and Sampling Methods for Processing GPS Data Streams for Traffic State Estimation

Zhang, Jia-Dong; Xu, Jin; Liao, Stephen Shaoyi

doi:10.1109/tits.2013.2264753

Cited by 40 publications

(24 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, in the paper [9], they studied the relationship between the value of Cell Dwell Time (CDT) to describe road traffic congestion. Instead of using an equal weight for all records [10], Zhang et al [11] proposed a novel method to reasonably process GPS data by increasing weights of recent records and high velocity to estimate the traffic states. Kong et al [5] made use of a new fuzzy comprehensive evaluation method in which the weights of multi-indexes are assigned according to the traffic flow.…”

Section: Related Workmentioning

confidence: 99%

Efficient traffic congestion estimation using multiple spatio-temporal properties

Yang

Han

et al. 2017

Neurocomputing

View full text Add to dashboard Cite

Abstract-Traffic estimation is an important issue to analyze the traffic congestion in large-scale urban traffic situations.Recently, many researchers have used GPS data to estimate traffic congestion. However, how to fuse the multiple data reasonably and guarantee the accuracy and efficiency of these methods are still challenging problems. In this paper, we propose a novel method Multiple Data Estimation (MDE) to estimate the congestion status in urban environment with GPS trajectory data efficiently, where we estimate the congestion status of the area through utilizing multiple properties, including density, velocity, inflow and previous status. Among them, traffic inflow and previous status (combination of time and space factors) are not both used in other existing methods. In order to ensure the accuracy and efficiency, we apply dynamic weights of data and parameters in MDE method. To evaluate our methods, we apply it on large-scale taxi GPS data of Beijing and Shanghai. Extensive experiments on these two real-world datasets demonstrate the significant improvements of our method over several state-ofthe-art methods.

show abstract

Section: Related Workmentioning

confidence: 99%

Efficient traffic congestion estimation using multiple spatio-temporal properties

Yang

Han

et al. 2017

Neurocomputing

View full text Add to dashboard Cite

show abstract

“…This proposal finds out hotspots (i.e., vehicles congestion) for effective routing decisions. Zhang et al [36] use GPS-enabled mobile data for traffic state estimation. They propose a heuristic method to estimate traffic states.…”

Section: Related Workmentioning

confidence: 99%

DMAP: Density Map Service in City Environments

Sahu

Hafid

Cherkaoui

2015

IEEE Trans. Intell. Transport. Syst.

View full text Add to dashboard Cite

Vehicle density information is crucial for efficient functioning of many vehicular applications, including emergency notification, driver assistance, and infotainment applications. This information is used for evacuation planning in accident scenarios, finding alternate routes in the case of road congestion, and providing stable routing paths for uninterrupted internet connections. In a city scenario, it is a tedious task to continuously collect and share large volumes of data containing density information. In this paper, we propose a mechanism to create a density map for city environments. A hierarchy (i.e., tree) is established, where a node represents a road segment and the density is used to determine the height of the node; the root node represents the road segment having highest density. The purpose of this tree is to collect and aggregate density information starting from the leaves until the root node is reached. Then, the aggregated density information (i.e., density map) is forwarded down the hierarchy. For efficient aggregation of density information, we adopt an effective curve-fitting method where data are represented in an equation. Simulation results show that the proposed mechanism allows highly accurate computing of density map while generating low network overhead.Index Terms-Curve fitting, density measurement, traffic control, vehicular ad hoc networks.

show abstract

“…In fact, the continuously arriving check-in locations with timestamps from users, denoted by (ui, li, ti), constitute an unbounded data stream, denoted by (ui, li, ti) +∞ i=1 . As check-in locations possess the general characteristics of data streams: massive volume of data and temporal correlations [32], it is required to process the check-in locations according to their arriving order and incrementally update the constructed L 2 TG.…”

Section: Location-location Transition Graphmentioning

confidence: 99%

Lore

Zhang

Chow

2014

Proceedings of the 22nd ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems

Self Cite

194

View full text Add to dashboard Cite

Providing location recommendations becomes an important feature for location-based social networks (LBSNs), since it helps users explore new places and makes LBSNs more prevalent to users. In LBSNs, geographical influence and social influence have been intensively used in location recommendations based on the facts that geographical proximity of locations significantly affects users' check-in behaviors and social friends often have common interests. Although human movement exhibits sequential patterns, most current studies on location recommendations do not consider any sequential influence of locations on users' check-in behaviors. In this paper, we propose a new approach called LORE to exploit sequential influence on location recommendations. First, LORE incrementally mines sequential patterns from location sequences and represents the sequential patterns as a dynamic Location-Location Transition Graph (L 2 TG). LORE then predicts the probability of a user visiting a location by Additive Markov Chain (AMC) with L 2 TG. Finally, LORE fuses sequential influence with geographical influence and social influence into a unified recommendation framework; in particular the geographical influence is modeled as two-dimensional check-in probability distributions rather than one-dimensional distance probability distributions in existing works. We conduct a comprehensive performance evaluation for LORE using two large-scale real data sets collected from Foursquare and Gowalla. Experimental results show that LORE achieves significantly superior location recommendations compared to other state-of-the-art recommendation techniques.

show abstract

Aggregating and Sampling Methods for Processing GPS Data Streams for Traffic State Estimation

Cited by 40 publications

References 39 publications

Efficient traffic congestion estimation using multiple spatio-temporal properties

Efficient traffic congestion estimation using multiple spatio-temporal properties

DMAP: Density Map Service in City Environments

Lore

Contact Info

Product

Resources

About