Taxi Global Positioning System Data Research Articles

Transfer learning for robust urban network-wide traffic volume estimation with uncertain detector deployment scheme

<abstract> <p>Real-time and accurate network-wide traffic volume estimation/detection is an essential part of urban transport system planning and management. As it is impractical to install detectors on every road segment of the city network, methods on the network-wide flow estimation based on limited detector data are of considerable significance. However, when the plan of detector deployment is uncertain, existing methods are unsuitable to be directly used. In this study, a transfer component analysis (TCA)-based network-wide volume estimation model, considering the different traffic volume distributions of road segments and transforming traffic features into common data space, is proposed. Moreover, this study applied taxi GPS (global positioning system) data and cellular signaling data with the same spatio-temporal coverage to improve feature extraction. In numerical experiments, the robustness and stability of the proposed network-wide estimation method outperformed other baselines in the two subnetworks selected from the urban centers and suburbs.</p> </abstract>

Identification of Recurrent Congestion in Main Trunk Road Based on Grid and Analysis on Influencing Factors

To reduce the risk of traffic congestion to residents and the urban transportation system, this paper extracted frequently congested areas and major trunk roads based on the GPS (global positioning system) data of cabs and TPI (traffic performance index) data and identified traffic patterns and main trunk roads in the traffic grid, so as to analyze the evolution of traffic congestion and make effective suggestions. The results can not only enable travelers to effectively avoid peak periods and congested sections but also support the managers to optimize urban planning and implement efficient traffic management methods. The research process of this study is as follows: firstly, the research object area was divided into different grids based on one-week taxi GPS data and the distribution characteristics of taxi operations in Qingdao. Secondly, the two-dimensional grid traffic attribute information is constructed using the following two indicators: number of vehicles and the average speed of passenger trajectory. Then, the congestion discriminant model based on the three-dimensional traffic attribute information was established according to the variation rules of the number of position point in the grid. Finally, the TPI data was applied to compare and evaluate the identification results of the above two models to identify frequently congested grids and main trunk roads. The case analysis showed that the result of grid’s congestion status identification considering three-dimensional traffic attribute information (25.198%) was better than that of grid congestion state considering two-dimensional traffic attribute information (23.997%).

Taxi Global Positioning System Data in Urban Road Network: A Methodology to Identify Key Road Clusters Based on Travel Speed–Traffic Volume Correlation

Urban traffic congestion is one of the urban diseases that needs to be solved urgently. Research has already found that a few road segments can significantly influence the overall operation of the road network. Traditional congestion mitigation strategies mainly focus on the topological structure and the transport performance of each single key road segment. However, the propagation characteristics of congestion indicate that the interaction between road segments and the correlation between travel speed and traffic volume should also be considered. The definition is proposed for “key road cluster” as a group of road segments with strong correlation and spatial compactness. A methodology is proposed to identify key road clusters in the network and understand the operating characteristics of key road clusters. Considering the correlation between travel speed and traffic volume, a unidirectional-weighted correlation network is constructed. The community detection algorithm is applied to partition road segments into key road clusters. Three indexes are used to evaluate and describe the characteristic of these road clusters, including sensitivity, importance, and IS. A case study is carried out using taxi GPS data of Shanghai, China, from May 1 to 17, 2019. A total of 44 key road clusters are identified in the road network. According to their spatial distribution patterns, these key road clusters can be classified into three types—along with network skeletons, around transportation hubs, and near bridges. The methodology unveils the mechanism of congestion formation and propagation, which can offer significant support for traffic management.

Multi-Mode Traffic Demand Analysis Based on Multi-Source Transportation Data

Automatic vehicle identification (AVI) data, Integrated Circuit (IC) card data and Global Positioning System (GPS) data offer an emerging and promising source of information for analysis of traffic problems. Research on insights and information from AVI data for transport analysis has made little progress in developing specific applications especially. The emergence of multi-source data provides us with a new perspective for multi-mode transportation. This paper proposes a multi-mode traffic demand forecasting method based on AVI data, metro IC card data, and taxi GPS data. The paper extracts traffic origins and destinations (OD) information of travelers from the multi-source data and uses the extracted data for traffic zone division. Finally, a multi-mode traffic forecasting model is established on this basis. GPS data of taxi trips are selected as the clustering data and k-means algorithm was adopted to divide traffic zones in Shenzhen. Moreover, the research applies the principle of convex hull to outline the boundary of the cell. Additionally, this paper establishes the multi-mode transportation forecasting model by integrating the correlation between various transportation modes into the deep learning model for prediction. The results show that the multi-mode demand forecasting model has higher accuracy and better forecasting results comparing it with the single-mode demand forecasting model which is referring to the conventional four-step procedure. The result demonstrates that effective traffic and travel data can be obtained from multi-source data, providing an opportunity to improve the analysis of complex travel patterns and behaviors for travel demand modeling and transportation planning. Furthermore, the substantive contribution of this research is that it provides strong empirical evidence for the existence of correlation among multi-mode travels and travel demand.

Analyses of the Imbalance of Urban Taxis’ High-Quality Customers Based on Didi Trajectory Data

The distribution of high-quality customers (hereafter HQC) for taxis (including ride-hailing cars) has a significant impact on drivers’ revenue and taxis’ operation efficiency. Based on the taxi global positioning system data, we construct an evaluation model of passengers to discuss the imbalance of consumption in taxi market. The profit margin for each taxi order is calculated, and then a grid-based method is used to distinguish the HQC and the regions with potential higher benefits. We analyze the HQC’s distribution of taxis (including ride-hailing cars) in different areas and in different time periods. We find that the HQC are distributed mainly on the periphery of the main urban area, which indicates that traffic condition is even worse in the urban center because of factors such as congestion. The HQC are more concentrated on workdays and more scattered on nonworkdays, which implies that the public have different travel habits and demands on workdays and nonworkdays. The proportion of HQC in each administrative district or functional zone is not always positively correlated to either the proportion of total orders or the total HQC. This indicates that the distribution of HQC in each administrative district or functional zone is imbalanced. The proportion of orders and that of HQC are roughly the same in the temporal dimension, being higher in the morning and evening rush hours. Compared with the distribution of the HQC of ride-hailing, that of taxis is more imbalanced in the temporal dimension. Relevant departments should further coordinate taxi pricing, strengthen market control, and promote sustainable development in the taxi and ride-hailing markets.

Spatial–temporal traffic outlier detection by coupling road level of service

Traffic outlier detection is an essential topic in city management and data mining. Most traffic outliers are caused by accidents, control, protests, disasters, and many other events. Recently, traffic outlier detection methods are based on counting traffic flow, where the detection is inherited from the periodical changes of road flow. However, these approaches fail to detect the impact from upstream roads. Furthermore, the mappings between traffic congestion level and traffic flow are distinct from road to road. In this study, a Poisson mixture model (PMM) – coupled hidden Markov model (CHMM) outlier detection method would be introduced for detecting traffic anomalies which are from taxi global positioning system data. To make a finer-grained outlier detection method, road traffic congestion estimation, as well as the impact from upstream roads, are considered. PMM serves as an estimator to determine the congestion level for every road and CHMM is used to couple the road's impact. The experiment applies both semi-synthetic and real outlier data from the Beijing map, and the results reveal the advantages of both datasets.

Inferring driving trajectories based on probabilistic model from large scale taxi GPS data

Use of taxi vehicles as mobile sensors to collect traffic information has become an important and emerging approach to relieve congestion. Global Positioning System (GPS) trajectory data allow for abundant temporal and spatial information to be collected that reflect the mobility and activity of drivers. In this paper, we present a probabilistic model to predict driving trip paths based on a Hidden Markov Model (HMM). The first step in our approach was to detect the stays or destinations by using an improved algorithm based on taxi status information about whether or not the vehicle is occupied by passengers. Next, the trips between two stays were extracted and expressed as data chains for applying the learning scheme in a predictive model. A data-driven approach based on an HMM was trained with trips from a period of three months and then the model was used to predict the future links on which the vehicle may travel. A Linear Motion Function (LMF) was then utilized to infer the taxi position on the predicted link. Furthermore, a learning algorithm was used to identify incorrect links for a given path. Finally, the effectiveness of the improved model was tested. In the testing process, samples that contained different trips with different taxi statuses (i.e., occupied and non-occupied) were considered, and the Relative Accuracy (RA) was applied as a measure of effectiveness to evaluate prediction performance. The prediction results verified that the proposed method is an accurate and feasible potential approach that can be used to estimate driving paths in future time periods.

A Trajectory Regression Clustering Technique Combining a Novel Fuzzy C-Means Clustering Algorithm with the Least Squares Method

Rapidly growing GPS (Global Positioning System) trajectories hide much valuable information, such as city road planning, urban travel demand, and population migration. In order to mine the hidden information and to capture better clustering results, a trajectory regression clustering method (an unsupervised trajectory clustering method) is proposed to reduce local information loss of the trajectory and to avoid getting stuck in the local optimum. Using this method, we first define our new concept of trajectory clustering and construct a novel partitioning (angle-based partitioning) method of line segments; second, the Lagrange-based method and Hausdorff-based K-means++ are integrated in fuzzy C-means (FCM) clustering, which are used to maintain the stability and the robustness of the clustering process; finally, least squares regression model is employed to achieve regression clustering of the trajectory. In our experiment, the performance and effectiveness of our method is validated against real-world taxi GPS data. When comparing our clustering algorithm with the partition-based clustering algorithms (K-means, K-median, and FCM), our experimental results demonstrate that the presented method is more effective and generates a more reasonable trajectory.

Evaluation of the impact of traffic incidents using GPS data

This paper proposes a trajectory of vehicles encountering an incident site and offers six indices for evaluating the impact of the incident on traffic patterns based on global positioning system (GPS) data. Traffic incidents are the major contributors to non-recurrent delays. Mitigating their effects necessitates an appropriate and efficient allocation of equipment and personnel for a clearance plan. Reliable real-time traffic impact evaluations are essential prerequisites for this task. Most of the existing duration models, however, are developed on the basis of local data, and may not be portable because of inconsistent data structures and differing local conditions. The method proposed in this paper is not limited by these shortcomings because it is based purely on classical traffic flow theory. The proposed trajectory is calibrated and validated using real-world taxi GPS data and accident data in Hong Kong. The proposed indices of severity are estimated through analysing the calibrated trajectories. The results reveal that the proposed indices can reconstruct the scene of an incident site and that the proposed method is promising. With the widespread use of GPS technology, the potential benefits of this method for incident management can be realised.

Network topological effects on the macroscopic Bureau of Public Roads function

Cost flow functions are a central class of models in the transport field because they are an essential ingredient of static user equilibrium traffic assignment and transport policy and planning analysis. Macroscopic cost flow (MCF) functions, which model travel cost at different levels of network use, have gained much attention in recent decades due to their potential applications in area-wide traffic management and control, and initial land-use planning. They are the collective outcomes of the responses of road users to the existing transportation network and the interactions between road users at different levels of traffic demand. Network topological effects have long been anticipated to be the primary factors governing the shape and performance of a network. However, few studies have investigated network topology. This paper aims to unveil the direct link between network topological metrics and the parameters of a specific MCF, in the form of macroscopic Bureau of Public Roads (MBPR) function, with the support of real-world data. Seventy-one 1 km × 1 km urban built-up regions were sampled in Hong Kong. The MBPR functions of the selected regions were calibrated using taxi global positioning system data. Intensive investigations revealed that the average number of junctions per unit distance and the road density were topological features correlating with the free-flow travel time and congestion sensitivity parameters of the MBPR function, respectively. A spatially variable MBPR function was established.

Vehicle Emission and Near-Road Air Quality Modeling for Shanghai, China

In China, motor vehicle emissions have been identified as the major source of urban air pollution. Thus, estimation of emissions and their impact on air quality is necessary. Vehicle emissions vary strongly with region and depend on local vehicle operation and emission performance. This paper uses the MOVES (Motor Vehicle Emission Simulator) model, released by the U.S. Environmental Protection Agency, for the estimation of vehicle emission factors in Shanghai, China. To achieve a convincing emission result, vehicle operation is extracted from massive taxi Global Positioning System (GPS) data, and the emission inventory from MOVES is revised according to China's vehicle emission standards. In addition, deterioration factors are calculated on the basis of vehicle condition. Comprehensive emission factors are generated for Shanghai light-duty vehicles at various average speed levels. The results indicate that emission factors for hydrocarbons, carbon monoxide, and oxides of nitrogen of in-use light vehicles in China are 0.1 to 0.25 g/km, 4 to 7 g/km, and 0.4 to 0.8 g/km, respectively. These amounts are 15, 1.9, and 5.9 times higher than those in the United States, respectively. By 2012, the Environmental Protection Bureau had established 10 monitoring sites in Shanghai and released data for real-time concentrations of particulate matter less than 2.5 μm in diameter, particulate matter less than 10 μm in diameter, nitrogen dioxide (NO2), and sulfur dioxide to the public. On the basis of the new release of data, a field study estimating near-road air quality was conducted with MOVES and the air dispersion model AERMOD. The concentration result shows that the accuracy of near-road NO2 estimation is improved with taxi GPS data and the revised MOVES emission inventory. The study explores the extended application of MOVES by offering a procedure for applying MOVES in non-U.S. regions.