Taxi GPS Research Articles

Discovering Electric Vehicle Charging Locations Based on Clustering Techniques Applied to Vehicular Mobility Datasets

With the proliferation of vehicular mobility traces because of inexpensive on-board sensors and smartphones, utilizing them to further understand road movements have become easily accessible. These huge numbers of vehicular traces can be utilized to determine where to enhance road infrastructures such as the deployment of electric vehicle (EV) charging stations. As more EVs are plying today’s roads, the driving anxiety is minimized with the presence of sufficient charging stations. By correctly extracting the various transportation parameters from a given dataset, one can design an adequate and adaptive EV charging network that can provide comfort and convenience for the movement of people and goods from one point to another. In this study, we determined the possible EV charging station locations based on an urban city’s vehicular capacity distribution obtained from taxi and ride-hailing mobility GPS traces. To achieve this, we first transformed the dynamic vehicular environment based on vehicular capacity into its equivalent urban single snapshot. We then obtained the various traffic zone distributions by initially utilizing k-means clustering to allow flexibility in the total number of wanted traffic zones in each dataset. In each traffic zone, iterative clustering techniques employing Density-based Spatial Clustering of Applications with Noise (DBSCAN) or clustering by fast search and find of density peaks (CFS) revealed various area separation where EV chargers were needed. Finally, to find the exact location of the EV charging station, we last ran k-means to locate centroids, depending on the constraint on how many EV chargers were needed. Extensive simulations revealed the strengths and weaknesses of the clustering methods when applied to our datasets. We utilized the silhouette and Calinski–Harabasz indices to measure the validity of cluster formations. We also measured the inter-station distances to understand the closeness of the locations of EV chargers. Our study shows how CFS + k-means clustering techniques are able to pinpoint EV charger locations. However, when utilizing DBSCAN initially, the results did not present any notable outcome.

Travel Characteristics and Vulnerability Analysis of Road Resource Utilization Based on Taxi GPS Data

Residents’ travel and logistics are greatly affected by urban transportation networks, which are one of the most important supports for urban socio-economic activities. Urban transportation systems tend to cripple when faced with challenges such as natural hazards and social unrest. This paper proposes a framework for a vulnerability analysis of urban road networks (URNs) based on real traffic flows with GPS data. An improved K-shell critical node identification method is proposed based on structural and traffic characteristics. Then, a cascade failure model is proposed to analyze the structural and functional vulnerability of the URN by combining the load capacity model and the vulnerability model. This paper takes the Harbin main city URN as an example and first analyzes the passenger travel distribution and the relationship between travel orders, population and POI. Four deliberate attack methods are proposed to analyze the vulnerability of the URN under deliberate attack on commute days and rest days. The experimental results show that URNs exhibit intense vulnerability, with the fastest cascading failure occurring based on improved K-shell node failure. Furthermore, URNs are more vulnerable on rest days compared to commuter days. These findings could be used to inform a vulnerability-based spatiotemporal design of UBNs and provide theoretical support for managing traffic congestion on different days.

High-resolution spatiotemporal inference of urban road traffic emissions using taxi GPS and multi-source urban features data: a case study in Chengdu, China

The spatial heterogeneity and temporal variability of traffic in urban environments make traffic emissions inference challenging. To address this challenge, this study introduces a novel geographical context-based approach utilizing high-resolution taxi GPS data, incorporating multidimensional contextual factors such as road data, points of interest (POI), weather data, and population density. The proposed method can enhance the precision of traffic emissions inference compared to conventional macroscopic estimation techniques. To overcome the issue of missing data in traffic emissions inference from taxi data, three ensemble machine learning algorithms—Random Forest, Gradient Boosting Decision Trees (GBDT), and eXtreme Gradient Boosting (XGBoost)—are employed. These algorithms efficiently handle a substantial volume of taxi GPS data, achieving reduced computational time and model complexity. The proposed framework establishes localized models for each road segment, taking into consideration both geographical and external features that characterize the urban environment. This localized modeling contributes significantly to a more profound understanding of traffic dynamics. A thorough comparative analysis is conducted to assess the performance of the proposed method. Results indicate that incorporating multidimensional urban features is advantageous for traffic speed inference. Among the ensemble learning models, Random Forest outperforms others when dealing with a small missing rate or limited sample size, while XGBoost exhibits superior performance for larger missing rates or substantial sample sizes. Additionally, an analysis of the feature importance in traffic speed highlights that road network features are the most significant factors, followed by temporal characteristics, spatial attributes, POI data, and weather information. Finally, leveraging inferred traffic speed and volume information, emissions from large-scale urban road traffic are inferred based on the COPERT model. In contrast to methods relying on complex, multi-source data for emission estimation, our approach utilizes simple and easily accessible data, enabling precise estimation of emissions on a large-scale spatiotemporal basis.

Electric Taxi Charging Load Prediction Based on Trajectory Data and Reinforcement Learning—A Case Study of Shenzhen Municipality

In order to effectively solve the problem of electric taxi charging load prediction and reasonable charging behaviour discrimination, in this paper, we use taxi GPS trajectory data to mine the probability of operation behaviour in each area of the city, simulate the operation behaviour of a day by combining it with reinforcement learning ideas, obtain the optimal operation strategy through training, and count the spatial and temporal distributions and power values at the time of charging decision making, so as to predict the charging load of electric taxis. Experiments are carried out using taxi travel data in Shenzhen city centre. The results show that, in terms of taxi operation behaviour, the operation behaviour optimized by the DQN algorithm shows the optimal effect in terms of the passenger carrying time, mileage, and daily net income; in terms of the charging load distribution, the spatial charging demand of electric taxis in each area shows obvious differences, and the charging demand load located in the city centre area and close to the traffic hub is higher. In time, the peak charging demand is distributed around 3:00 to 4:00 and 14:00 to 15:00. Compared with the operating habits of drivers based on the Monte Carlo simulation, the DQN algorithm is able to optimise the efficiency and profitability of taxi drivers, which is more in line with the actual operating habits of drivers formed through accumulated experience, thus achieving a more accurate charging load distribution.

Multi-dimensional unobserved heterogeneities: Modeling likelihood of speeding behaviors in different patterns for taxi speeders with mixed distributions, multivariate errors, and jointly correlated random parameters

Speeding behaviors can be classified into different patterns according to both speeding-range and speeding-distance. Among the speeding patterns, some are more frequently observed in specific traffic scenarios, implying that the likelihood of speeding behaviors may vary across the speeding patterns due to the inconsistent impact of temporal, road, environmental, and other traffic factors. Additionally, the trigger of speeding is a complex process so the researchers may not have access to all the critical information associated with the speeding behaviors. This issue may bring about not only independent heterogeneity but also multi-dimensional heterogeneities that are mutually correlated when modeling speeding behaviors by patterns. However, the joint solution to the above challenges is rarely seen in past studies. To fill the knowledge gaps, this study uses taxi GPS trajectories to extract speeding behaviors and classify them into four patterns. The speeder’s percent of speeding distance for each speeding pattern is respectively measured to represent the likelihood of speeding behaviors by patterns. Afterwards, we compare the data-fitting between the models combined with different beta-gamma mixture distributions and a multivariate Gaussian error in modeling the four patterns of speeding likelihood. The combination with the best fitness is used to incorporate jointly correlated random parameters. The results show that the model with beta-gamma-gamma-gamma mixed distributions performs better than other combinations. The model with jointly correlated random parameters outperforms models with other random parameters. The factor analysis reveals that percent of driving at night, percent of driving on roads with a low-speed limit (≤30 km/h), average delays in junctions along the trips, and hourly income have consistent effects on the likelihood of speeding behaviors in all patterns, while the effects of the remaining factors are inconsistent across the speeding patterns. Furthermore, the heterogeneity unveiled by the model parameters is discussed. The study highlights the necessity of considering mixed distributions and multi-dimensional heterogeneities in modeling speeding likelihood by different patterns.

An efficient data-driven method to construct dynamic service areas from large-scale taxi location data

Service area analysis is crucial for determining the accessibility of public facilities in smart cities. However, the acquisition of service areas using conventional approaches has been limited. First, investigating traffic flow is difficult, as this factor varies significantly over time and space. Second, obtaining service areas of mobile facilities/targets has remained a challenge owing to a lack of data and methods. To address these problems, this study proposes an efficient big-data-driven approach that utilizes large-scale taxi GPS location data collected over two years within Seoul City and distributed computation to obtain the average travel time values on fine-grained grid cells of 100 m × 100 m resolution. On-the-fly visualization methods were then established with an ability to construct isochrone maps of service areas in near-real-time. This enabled performing accurate service area analysis of mobile facilities/targets dynamically. The proposed solution can be effectively used in various applications, such as optimizing the ride-sharing services or the routes of autonomous electric vehicles in future smart cities, as demonstrated in this study.

A Bayesian updating framework for calibrating the hydrological parameters of road networks using taxi GPS data

Abstract. Hydrological parameters should pass through a careful calibration procedure before being used in a hydrological model that aids decision making. However, significant difficulty is encountered when applying existing calibration methods to regions in which runoff data are inadequate. To achieve accurate hydrological calibration for ungauged road networks, we propose a Bayesian updating framework that calibrates hydrological parameters based on taxi GPS data. Hydrological parameters were calibrated by adjusting their values such that the runoff generated by acceptable parameter sets corresponded to the road disruption periods during which no taxi points are observed. The proposed method was validated on 10 flood-prone roads in Shenzhen and the results revealed that the trends of runoff could be correctly predicted for 8 of 10 roads. This study demonstrates that the integration of hydrological models and taxi GPS data can provide viable alternative measures for model calibration to derive actionable insights for flood hazard mitigation.

Predicting traffic propagation flow in urban road network with multi-graph convolutional network

AbstractTraffic volume propagating from upstream road link to downstream road link is the key parameter for designing intersection signal timing scheme. Recent works successfully used graph convolutional network (GCN) and specific time-series model to forecast traffic flow by capturing the spatial–temporal features. However, accurately predicting traffic propagation flow (tpf) is challenging, since the classical GCN model only considers the influence of adjacent road link. In complex urban road network, specific traffic propagation flow (tpf) is affected by various spatial features, such as adjacent tpf, which influences from tpf with same upstream link and tpf with same downstream link. Thus, we proposed a multi-graph learning-based model named TPP-GCN (traffic propagation prediction-graph convolutional network) in this paper to predict the traffic propagation flow in urban road network. The TPP-GCN model captures not only the temporal features but also multi-spatial features based on multi-layer convolution. We validated the model using real-world traffic flow data derived from taxi GPS data in Shenzhen, China. Finally, we compare and evaluate the proposed model with the existing models across several prediction scales.

Travel Time Prediction in Real time for GPS Taxi Data Streams and its Applications to Travel Safety

The analysis of data streams offers a great opportunity for development of new methodologies and applications in the area of Intelligent Transportation Systems. In this paper, we propose two new incremental learning approaches for the travel time prediction problem for taxi GPS data streams in different scenarios and compare the same with three other existing methods. An extensive performance evaluation using four real life datasets indicate that when the training data size is small the Support Vector Regression method is the best choice considering both prediction accuracy and total computation time. However when the training data size is large to moderate then the Randomized K-Nearest Neighbor Regression with Spherical Distance (RKNNRSD) and the Incremental Polynomial Regression become the methods of choice. When continuous prediction of remaining travel time along the trajectory of a trip is considered we find that the RKNNRSD is the method of choice. A Real-time Speeding Alert System (RSAS) and a Driver Suspected Speeding Scorecard (DSSS) using the RKNNRSD method are proposed which have great potential for improving travel safety.

A Cost-Effective Sequential Route Recommender System for Taxi Drivers

This paper develops a cost-effective sequential route recommender system to provide real-time routing recommendations for vacant taxis searching for the next passenger. We propose a prediction-and-optimization framework to recommend the searching route that maximizes the expected profit of the next successful passenger pickup based on the dynamic taxi demand-supply distribution. Specifically, this system features a deep learning-based predictor that dynamically predicts the passenger pickup probability on a road segment and a recursive searching algorithm that recommends the optimal searching route. The predictor integrates a graph convolution network (GCN) to capture the spatial distribution and a long short-term memory (LSTM) to capture the temporal dynamics of taxi demand and supply. The GCN-LSTM model can accurately predict the pickup probability on a road segment with the consideration of potential taxi oversupply. Then, the dynamic distribution of pickup probability is fed into the route optimization algorithm to recommend the optimal searching routes sequentially as route inquiries emerge in the system. The recursion tree-based route optimization algorithm can significantly reduce the computational time and provide the optimal routes within seconds for real-time implementation. Finally, extensive experiments using Beijing Taxi GPS data demonstrate the effectiveness and efficiency of the proposed recommender system. History: Accepted by Ram Ramesh, Area Editor for Data Science and Machine Learning. Funding: This work was partially supported by the Hong Kong Research Grants Council [Grants CityU 21500220, CityU 11504322] and the National Natural Science Foundation of China [Grant 72201222]. Supplemental Material: The software that supports the findings of this study is available within the paper and its Supplemental Information ( https://pubsonline.informs.org/doi/suppl/10.1287/ijoc.2021.0112 ) as well as from the IJOC GitHub software repository ( https://github.com/INFORMSJoC/2021.0112 ). The complete IJOC Software and Data Repository is available at https://informsjoc.github.io/ .

Data and code used in the article titled " A Bayesian updating framework for calibrating hydrological parameters of road network using taxi GPS data"

Data and code used in the article titled " A Bayesian updating framework for calibrating hydrological parameters of road network using taxi GPS data"

Urban network-wide traffic volume estimation under sparse deployment of detectors

ABSTRACT Sensing network-wide traffic information is fundamental for the sustainable development of urban planning and traffic management. However, owing to the limited budgets or device maintenance costs, detector deployment is usually sparse. Obtaining full-scale network volume using detectors is neither effective nor practical. Existing works primarily focus on improving the estimation accuracy using multi-correlation of networks and ignore the underlying challenges, particularly for these entire undetected road segments in sparse detector deployment scenarios. Here our study proposes a tailored transfer learning framework called the transfer learning-based least square support vector regression (TL-LSSVR) model. Network-wide volume can be estimated by fusing active detectors (taxi GPS data) and fixed passive detectors (license plate recognition data). Numerical experiments are carried out on a real-world road network in Nanjing, China. It is demonstrated that our approach achieves high performance even under sparse deployment of detectors and outperforms other baselines significantly.

Capitalize Your Data: Optimal Selling Mechanisms for IoT Data Exchange

More and more IoT data is being traded online in cloud-based data marketplaces due to the fast-growing market demand. Within the current data selling mechanisms, data consumers have difficulties in making purchasing decisions due to uncertain IoT data quality and inflexible pricing interface. To resolve these issues, potential solutions could be to launch data demonstrations and release free sampling data to reduce the uncertainty about data quality, and to charge based on the volume of data actually used to enable flexible pricing. However, there is still no clear understanding of economic benefits of these mechanisms. In this paper, we design the optimal data selling mechanisms for IoT data exchange, and derive the following two results. First, whether to deploy a data demonstration and how much free sampling data to release depend on the extent of data consumers' inaccuracy perceptions for data quality, which varies over a wide range in IoT applications. We found that the data vendor has no incentive to conduct these strategies if data consumers extremely overestimate data quality. Second, although flexible data pricing mechanisms provide convenience for real-time and streaming IoT data exchange, it brings less economic benefits to the data vendor compared with the fixed pricing scheme, which sells the whole data set with a fixed price. We evaluate the optimal selling mechanisms on a real-world Taxi GPS data set, and evaluation results verify the insights derived from our theoretical analysis.

A novel modelling approach of integrated taxi and transit mode and route choice using city-scale emerging mobility data

The modelling of mode and route choices of public transport passengers is an essential component of travel demand modelling and transportation planning. Traditionally, choice models are trained using data from revealed and stated preference surveys which are not only cost and time intensive but also suffer from bias due to limitations in sample size. In this article, we present a novel approach utilizing a combination of emerging data sources for non-private modes, namely public transit smart card data, taxi GPS trajectory data, and taxi trips transaction data in order to calibrate an integrated taxi and transit mode and route choice model. We apply our approach for a case study of the taxi and public transport system of Singapore using data sets obtained from the local transport authorities. We solve the first mile and last mile data gaps by overlaying the individual transport nodes against geospatial land use data in order to identify their actual origin and destination points of each journey. To model the behavioural inter-dependencies between the choice of taxi and transit options, we tested a two-level nested logit model and a cross-nested logit model. Along with the commonly included exploratory variables such as in-vehicle travel time, transfer time and number of transfers, our model also incorporates differences in travel cost and separate mode specific constants for peak and off-peak periods. Generic and mode-specific in-vehicle travel time and cost coefficients are tested in the utility functions for the transit and taxi alternatives. Willingness to pay estimates are calculated and compared against similar estimates from Singapore. We also present an application of the model by predicting the mode split between taxi and transit under selected transit and taxi fare change scenarios. Our modelling methodology is highly generalizable and can be applied to other cities with similar data availability.

A deep inverse reinforcement learning approach to route choice modeling with context-dependent rewards

Route choice modeling is a fundamental task in transportation planning and demand forecasting. Classical methods generally adopt the discrete choice model (DCM) framework with linear utility functions and high-level route characteristics. While several recent studies have started to explore the applicability of deep learning for route choice modeling, they are all path-based with relatively simple model architectures and require choice set generation. Existing link-based models can capture the dynamic nature of link choices within the trip without the need for choice set generation, but still assume linear relationships and link-additive features. To address these issues, this study proposes a general deep inverse reinforcement learning (IRL) framework for link-based route choice modeling, which is capable of incorporating diverse features (of the state, action and trip context) and capturing complex relationships. Specifically, we adapt an adversarial IRL model to the route choice problem for efficient estimation of context-dependent reward functions without value iteration. Experiment results based on taxi GPS data from Shanghai, China validate the superior prediction performance of the proposed model over conventional DCMs and other imitation learning baselines, even for destinations unseen in the training data. Further analysis shows that the model exhibits competitive computational efficiency and reasonable interpretability. The proposed methodology provides a new direction for future development of route choice models. It is general and can be adaptable to other route choice problems across different modes and networks.

Investigating distance halo effect of fixed automated speed camera based on taxi GPS trajectory data

Investigating distance halo effect of fixed automated speed camera based on taxi GPS trajectory data

Development of Spatial Uncertainty-Aware Visualization of Historical Traffic Queue Length

Traffic queue length at intersection is one of the most important measures of traffic signal performance and the traffic signal optimization. The spread of the ride-hailing services makes GPS data widely available with large area coverage, allowing us to quantify the queue length in a wide area without the need for additional installation cost like conventional sensors. Hence, queue length can be observed simultaneously and the relationship between intersections can be captured. Due to the current myriad of available queue length data, an analysis tool is needed to turn the data into useful knowledge to support traffic operations and management. However, the current queue length visualization only focuses on a real-time fashion, which cannot provide information about the change of the queue or its uncertainty. Such information is crucial for understanding the probability of the queue to be spillover, as well as determining the lengths of turning lanes to minimize blockage. In this research, we developed a spatial uncertainty-aware visualization by applying a conventional technique called box plot to visualize queue lengths on a map derived from taxi GPS data. A prototype of a web mapping application has been implemented and tested with users. The results indicated that participants with a statistics background have an advantage over those without a statistical background to understand the box plot. However, all of them were able to identify the uncertainty of the queue lengths as well as to compare the uncertainty between intersections and times.

Development of Spatial Uncertainty-Aware Visualization of Historical Traffic Queue Length

Traffic queue length at intersection is one of the most important measures of traffic signal performance and the traffic signal optimization. The spread of the ride-hailing services makes GPS data widely available with large area coverage, allowing us to quantify the queue length in a wide area without the need for additional installation cost like conventional sensors. Hence, queue length can be observed simultaneously and the relationship between intersections can be captured. Due to the current myriad of available queue length data, an analysis tool is needed to turn the data into useful knowledge to support traffic operations and management. However, the current queue length visualization only focuses on a real-time fashion, which cannot provide information about the change of the queue or its uncertainty. Such information is crucial for understanding the probability of the queue to be spillover, as well as determining the lengths of turning lanes to minimize blockage. In this research, we developed a spatial uncertainty-aware visualization by applying a conventional technique called box plot to visualize queue lengths on a map derived from taxi GPS data. A prototype of a web mapping application has been implemented and tested with users. The results indicated that participants with a statistics background have an advantage over those without a statistical background to understand the box plot. However, all of them were able to identify the uncertainty of the queue lengths as well as to compare the uncertainty between intersections and times.

Spatial–Temporal Data Imputation Model of Traffic Passenger Flow Based on Grid Division

Traffic flows (e.g., the traffic of vehicles, passengers, and bikes) aim to reveal traffic flow phenomena generated by traffic participants in traffic activities. Various studies of traffic flows rely heavily on high-quality traffic data. The taxi GPS trajectory data are location data that include latitude, longitude, and time. These data are critical for traffic flow analysis, planning, infrastructure layout, and recommendations for urban residents. A city map can be divided into multiple grids according to the latitude and longitude coordinates, and traffic passenger flows data derived from taxi trajectory data can be extracted. However, random missing data occur due to weather and equipment failure. Therefore, the effective imputation of missing traffic flow data is a hot topic. This study proposes the spatio-temporal generative adversarial imputation net (ST-GAIN) model to solve the traffic passenger flows imputation. An adversarial game with multiple generators and one discriminator is established. The generator observes some components of the time-domain and regional traffic data vector extracted from the grid. It effectively imputes the missing values of the spatio-temporal traffic passenger flow data. The experimental data are accurate Kunming taxi trajectory data, and experimental results show that the proposed method outperforms five baseline methods regarding the imputation accuracy. It is significant and suggests the possibility of effectively applying the model to predict the passenger flows in some areas where traffic data cannot be collected for some reason or traffic data are randomly missing.

Predicting the Impact of Disruptions to Urban Rail Transit Systems

Service disruptions of rail transit systems have become more frequent in the past decade in urban cities, due to various reasons, such as power failures, signal errors, and so on. Smart transit cards provide detailed tapping records of commuters, which enable us to infer their trajectories under both normal and disruptive circumstances. In this article, we study and predict the impact of disruptions on commuters and further evaluate the vulnerability of the rail system. Specifically, we define two metrics, stay ratio and travel delay, to quantify the impact, and we derive the predictor of each metric based on the inferred alternative route choices of commuters under disruptive circumstances. We demonstrate that the alternative route choices contribute to more similar feature distribution among different disruptions, which is crucial to tackling the main challenge of abnormal data scarcity and is beneficial for obtaining more reliable predictors for future disruptions. We evaluate our approach with a real-world transit card dataset. The result demonstrates the effectiveness of our method. Based on the predictors, we further analyse the vulnerability of the rail system. An evaluation with cross validation from taxi GPS trajectory data indicates its efficacy in discovering vulnerable rail stations as well as Origin-Destination pairs.