Analyzing spatiotemporal congestion pattern on urban roads based on taxi GPS data

Zhang, Kaisheng; Sun, Daniel; Shen, Suwan; Zhu, Yi

doi:10.5198/jtlu.2017.954

Cited by 70 publications

(54 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The average speed patterns of congested RSBs shows obvious valleys during peak commuting hours: 7:00-10:00; 17:00-18:00 (We defined the commuting hours based on [46]), which indicate the most severe traffic congestion times during a day. According to previous studies, the ATStaxi can be used as the primary indicator to reveal the traffic congestion of road networks [15,24,45]. The statistical correlation between ATStaxi and ATSbus of the congested RSBs is significantly strong (R 2 =0.94, Figure 9).…”

Section: Som Algorithm Resultsmentioning

confidence: 87%

“…According to previous studies, the ATS taxi can be used as the primary indicator to reveal the traffic congestion of road networks [15,24,45]. The statistical correlation between ATS taxi and ATS bus of the congested RSBs is significantly strong (R 2 =0.94, Figure 9).…”

Section: Som Algorithm Resultsmentioning

confidence: 90%

“…The original records include the taxi ID, GPS time, longitude, latitude, direction, speed, and carry status. Only the occupied (carry status = 1) taxi trips were kept for the ATS calculation because an empty taxi could not reflect the real traffic conditions due to a slowdown for searching passengers, rest stopping or work shifting during empty trips [45]. To extract the congestion information, we need to map-match each taxi GPS trajectory, which is a sequence of discrete spatial points, to the underlying road segments.…”

Section: Som Algorithm Resultsmentioning

confidence: 99%

See 2 more Smart Citations

Public Traffic Congestion Estimation Using an Artificial Neural Network

Wang

Dong

2020

IJGI

View full text Add to dashboard Cite

Alleviating public traffic congestion is an efficient and effective way to improve the travel time reliability and quality of public transport services. The existing public network optimization models usually ignored the essential impact of public traffic congestion on the performance of public transport service. To address this problem, this study proposes a data-based methodology to estimate the traffic congestion of road segments between bus stops (RSBs). The proposed methodology involves two steps: (1) Extracting three traffic indicators of the RSBs from smart card data and bus trajectory data; (2) The self-organizing map (SOM) is used to cluster and effectively recognize traffic patterns embedded in the RSBs. Furthermore, a congestion index for ranking the SOM clusters is developed to determine the congested RSBs. A case study using real-world datasets from a public transport system validates the proposed methodology. Based on the congested RSBs, an exploratory example of public transport network optimization is discussed and evaluated using a genetic algorithm. The clustering results showed that the SOM could suitably reflect the traffic characteristics and estimate traffic congestion of the RSBs. The results obtained in this study are expected to demonstrate the usefulness of the proposed methodology in sustainable public transport improvements. these network optimization models developed in the above-mentioned articles had been usually applied in uncongested road segments.Public traffic condition refers to the traffic volume of the road network and its dynamic spatial-temporal distribution, which can reflect the degree of congestion [8]. Recently, the traffic congestion impacts of bus operations on a road segment or a corridor have been investigated by researchers [9,10]. These congestion effects mainly include the effects of bus stop design, bus travel time, and bus priority options such as exclusive bus lanes or priority signals for buses [9]. Understanding these congestion impacts can help operators to identify the effectiveness of transport network optimization in relieving congested areas or congested routes. For example, under congested traffic conditions, it is difficult for buses to return to the driving lane, which leads to a longer travel time after picking-up/dropping off passengers at stops [11]. Furthermore, the bus travel time variation dominated by traffic congestion often results in unreliable service, which has negative impacts on both the operators and passengers [12]. Previous studies have pointed out that well-located stops have the potential to alleviate the impact of traffic congestion [3]. Therefore, it is critical to optimize PTN by considering the impact of traffic congestion in order to achieve a high level of public transport service and improve travel time reliability.In this study, we proposed a data-based methodology to estimate the traffic congestion of road segments between bus stops (RSBs) using a self-organizing feature map (SOM). The SOM was used to cluster and effective...

show abstract

Section: Som Algorithm Resultsmentioning

confidence: 87%

Section: Som Algorithm Resultsmentioning

confidence: 90%

Section: Som Algorithm Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Public Traffic Congestion Estimation Using an Artificial Neural Network

Wang

Dong

2020

IJGI

View full text Add to dashboard Cite

show abstract

“…[6] (iii) Unlike a general demand-responsive bus service, LIPDRS abandons the door-to-door service model. Two additional major challenges that consequently arise are whether the requesters can accept this change and how to describe the threshold for passenger acceptance of LIPDRS from a general cost perspective.(iv) The relevant control parameters, such as the optimal number of service locations, are difficult to determine [7].(v) It must be possible to solve real-scale problems using the developed approach.In this study, we build a mixed-integer programming model with dual objectives to optimize the service from the perspectives of both passengers and operators, following the principle of clustering first, routing second, to solve the LIPDRS design problem. The contributions of this study are four-fold:(i) We propose a new transport option along with a complete system of modeling and solution methods.…”

mentioning

confidence: 99%

Designing a New Shuttle Service to Meet Large-Scale Instantaneous Peak Demands for Passenger Transportation in a Metropolitan Context: A Green, Low-Cost Mass Transport Option

Zheng¹,

Chen²,

Zhang³

et al. 2019

Sustainability

View full text Add to dashboard Cite

Currently, the green, sustainable development of metropolises is hindered by problems caused by Large-scale Instantaneous Peak-demands for Passenger-transportation (LIPP), such as traffic congestion and air pollution. To mitigate these problems, we propose a new type of demand-responsive service as an alternative to inefficient "door-to-door" service. The proposed service is based on service units designed to aggregate passengers for shuttle service. To guarantee service quality and efficiency, a maximum passenger walking time constraint, a request rejection mechanism and a scheme for ensuring solution feasibility are considered. Through numerical experiments, we prove the following: (i) the proposed transport option exhibits better performance (by 40.37% for passengers and by 35.79% for operators) than the door-to-door transport option for solving real cases. (ii) By testing different datasets, we prove that the proposed service is more suitable for the request distributions that are spatiotemporally concentrated. (iii) Regarding the individual components of the proposed clustering-first, routing-second solution framework, the proposed soft clustering algorithm exhibits better performance than the classical hard clustering method (by 8%), and the proposed routing algorithm is 1.5 times more efficient than the commercial solution software GAMS. Sustainability 2019, 11, 5025 2 of 28This study is motivated by the desire to seek a new type of demand-responsive service, called large-scale instantaneous-peak-demand-responsive express shuttle service (LIPDRS), that can accommodate the LIPP of a metropolis, while balancing the benefits to operators and passengers. As an alternative to "door-to-door" transportation or frequency services, LIPDRS requires passengers to gather at certain locations, from which they are served by shuttles. Therefore, the LIDPRS design process involves first assigning passengers to certain service units and then transporting them along certain routes. LIPDRS has the advantages of a large capacity (ability to accommodate occasional massive demands), high flexibility (planning based on dynamic phone/Internet requests), low cost (affordability for passengers) and an acceptable level of convenience (passengers are required to gather at certain locations to be served in accordance with their requests). With these advantages, LIPDRS is an innovative means of increasing accessibility between high-circulation areas in a metropolis, such as residential districts and central business districts. As a complement to passenger transit systems, LIPDRS can help solve mobility and accessibility problems in a metropolitan context. In addition, this new transport option can encourage people to reduce their proportions of travel by private cars and thus reduce the cost of and pollution due to urban transportation, thereby improving the sustainability of metropolitan development.However, the realization of LIPDRS comes at the cost of additional complexity. Since passengers are required to gather at certain locatio...

show abstract

“…One of the main tasks was to investigate network division, thus obtaining a well-defined MFD. The most classic method was developed by Ji and Geroliminis [19] that divided the entire network according to the congestion feature [20,21], and then the dynamic division problem was also studied. Keyvan-Ekbatani et al [22] studied the feedback gate control method using the simulation network with perimeter gate control and obtained satisfying results with lower total travel time.…”

Section: Introductionmentioning

confidence: 99%

A Two-Layer Network Dynamic Congestion Pricing Based on Macroscopic Fundamental Diagram

Wei

Sun

2018

Journal of Advanced Transportation

View full text Add to dashboard Cite

Dynamic congestion pricing has attracted increasing attentions during the recent years. Nevertheless, limited research has been conducted to address the dynamic tolling scheme at the network level, such as to cooperatively manage two alternative networks with heterogeneous properties, e.g., the two-layer network consisting of both expressway and arterial network in the urban areas. Recently, the macroscopic fundamental diagram (MFD) developed by both field experiments and simulation tests illustrates a unimodal low-scatter relationship between the mean flow and density network widely, providing the network traffic state is roughly homogeneous. It reveals traffic flow properties at an aggregated level and sheds light on dynamic traffic management of a large network. This paper proposes a bilevel programming toll model, incorporating MFD to solve the unbalanced flow distribution problem within the two-layer transportation networks. The upper level model aims at minimizing the total travel time, while the lower level focuses on the MFD-based traffic assignment, which extends the link-based traffic assignment to network wide level. Genetic algorithm (GA) and the method of successive average were adopted for solving the proposed model, on which an online experimental platform was established using VISSIM, MATLAB, and Visual Studio software packages. The results of numerical studies demonstrate that the total travel time is decreased by imposing the dynamic toll, while the total travel time savings significantly outweigh the toll paid. Consequently, the proposed dynamic toll scheme is believed to be effective from both traffic and economic points of view.

show abstract

Analyzing spatiotemporal congestion pattern on urban roads based on taxi GPS data

Cited by 70 publications

References 44 publications

Public Traffic Congestion Estimation Using an Artificial Neural Network

Public Traffic Congestion Estimation Using an Artificial Neural Network

Designing a New Shuttle Service to Meet Large-Scale Instantaneous Peak Demands for Passenger Transportation in a Metropolitan Context: A Green, Low-Cost Mass Transport Option

A Two-Layer Network Dynamic Congestion Pricing Based on Macroscopic Fundamental Diagram

Contact Info

Product

Resources

About