Real Traffic Flow Data Research Articles

Exploring the Relationship between Data Sample Size and Traffic Flow Prediction Accuracy

Efficiently extracting and analyzing large urban traffic data, accurately predicting traffic conditions, and improving urban traffic management require careful selection of an appropriate data sample size. The suitable size of data sample assumes paramount importance in fostering sustainable transportation development. This paper investigates the relationship between traffic flow prediction performance and data sample size, considering data sample missing rates, duration, and road segment coverage. Real traffic flow data from 13 road sections in Changsha, China, are analyzed using the Decision Tree, Support Vector Machine, Gaussian Process Regression and Artificial Neural Network models. Some key findings include: Lower data sample loss rates improve prediction accuracy by capturing traffic flow patterns effectively, while higher loss rates decrease accuracy; an optimal data sample duration of around 7 days balances prediction accuracy and data stability, with longer durations providing more historical data but risking complexity; Broader road segment coverage gives a more comprehensive traffic flow information, but excessive coverage introduces noise and impacts the improvement of prediction accuracy. The results highlight the significant impact of data sample size on prediction performance. Enhancing reliability can be achieved by reducing data loss, selecting suitable durations, and considering appropriate road segment coverage, supporting improved traffic management and route planning.

A hybrid machine learning approach for congestion prediction and warning

ABSTRACT Global traffic management encounters a significant challenge in traffic congestion. This paper presents a hybrid machine learning method for predicting traffic congestion. It leverages Convolutional Neural Network-Gated Recurrent Unit (CNN-GRU) network for parameter prediction and combines clustering and classification models, using the K-means algorithm to categorize traffic states into four levels and constructing a KNN classification model based on this segmentation. This results in the K-means-KNN model. Predicted parameters are inputted into the K-means-KNN model for congestion level prediction. Validation with real traffic flow data shows that the CNN-GRU network can capture spatiotemporal features more effectively. For instance, in traffic flow prediction, it reduces the MAPE by 7.39% and 51.14% compared to CNN and GRU, respectively. K-means-KNN excels in traffic state discrimination, achieving a congestion prediction accuracy of 91.8%. These results underscore the efficacy of the hybrid machine learning method in assessing and predicting urban traffic congestion.

Low-Carbon Mixed Traffic Route Recommendation for Community Residents Based on Multilayer Complex Traffic Network

With the proposed “carbon peaking” and “carbon neutral” goals in China, the transportation sector, as the second largest consumer of oil and a major producer of greenhouse gases, is a critical area for energy efficiency and emission reduction actions. However, few studies have focused on the effective combination of solving residents' commuting challenges and low-carbon travel. In this paper, by extracting real traffic flow data from taxi and bike-sharing trajectory data, a multilayer complex traffic network is formed to realize an interactive visual exploration of urban traffic patterns. Based on this network a low-carbon travel route recommendation is implemented using a modified genetic algorithm to reduce personal carbon emission and travel costs. Meanwhile, the trip chain level carbon emission estimation method is defined for city streets and recommended routes. With the integration of the above algorithms, a visual analytics system is designed and implemented to support the joint exploration of urban traffic patterns and the street carbon emission distribution, low-carbon mixed traffic route recommendations for inter-community commuting, and optimization of low-carbon recommended routes by adjusting bike stations. Take the taxi and bike-sharing trajectory data in Xiamen, China as an example, an evaluation analysis of the system shows that the method is effective in reducing commuting costs for community residents while reducing personal travel carbon emission.

Sensitivity of principal components to system changes in the presence of non-stationarity

Non-stationarity affects the sensitivity of change detection in correlated systems described by sets of measurable variables. We study this by projecting onto different principal components. Non-stationarity is modeled as multiple normal states that exist in the system even before a change occurs. The studied changes occur in mean values, standard deviations or correlations of the variables. Monte Carlo simulations are performed to test the sensitivity for change detection with and without knowledge about non-stationarity for different system dimensions and numbers of normal states. A comparison clearly shows that knowledge about the non-stationarity of the system greatly improves change detection sensitivity for all principal components. This improvement is largest for those components that already provide the greatest possibility for change detection in the stationary case. We illustrate our results with an example using real traffic flow data, in which we detect a weekend and a bank holiday start as anomalies.

Modelling the Coupling Relationship between Urban Road Spatial Structure and Traffic Flow

In order to promote the sustainable development of urban traffic systems, improve the accuracy of traffic system analysis in the urban planning stage and reduce the possibility of traffic congestion in the operation stage of road networks, the coupling relationship and evolution mechanism between urban road spatial structure and traffic flow were studied, and a model of the relationship between the metrics was established in this study based on real road network and traffic flow data. First, the road spatial structure model of the study area was established from the perspective of road space, and the spatial syntax method was applied to verify the rationality of the spatial structure of the road network. Secondly, the initial OD matrix was determined by OD backpropagation based on the measured traffic flow data. Thirdly, the coupling rule between the spatial structure and the traffic flow of the road network was explored by loading the increment in the OD matrix to the initial OD matrix step by step based on a simulation experiment. Finally, the relationship between the degree of integration of the spatial syntactic feature parameter and the saturation of the traffic flow feature parameter was modelled on the basis of experimental results and verified by an example. This research shows that the spatial structure of urban roads has a significant impact on the characterisation of the traffic flow distribution of road networks, and a strong correlation can be found between the integration degree and saturation degree. An optimal fit, which can be used as a reference for the design of road spatial structure, was explored in this research.

Low cost network traffic measurement and fast recovery via redundant row subspace-based matrix completion

Traffic matrices (TMs) are essential for managing networks. Getting the whole TMs is difficult because of the high measurement cost. Several recent studies propose sparse measurement schemes to reduce the cost, which involve taking measurements on only a subset of origin and destination pairs (OD pairs) and inferring data for unmeasured OD pairs through matrix completion. However, existing sparse network measurement schemes suffer from the problems of high computation costs and low recovery quality. This paper investigates the coherence feature of real traffic flow data traces (Abilene and GÈANT). Both data sets are high coherence, with column coherence greater than row coherence. According to the coherence feature of both data sets, we propose our Redundant Row Subspace-based Matrix Completion (RRS-MC). RRS-MC involves several techniques. Firstly, we design an algorithm to identify subspace rows (OD pairs) from historical data. Secondly, based on the identified subspace rows, we design our sampling scheduling algorithm, which takes full measurement samples in subspace rows while taking partial measurement samples in the remaining rows. Moreover, we propose a redundant sampling rule prevent the recovery accuracy decrease caused by the subspace rows varying. Finally, we design a completion algorithm to recover the partially measured rows. We conduct extensive experiments. Results indicate that the proposed scheme is superior to the state-of-the-art sampling and completion scheme in computation costs and recovery accuracy.

Online Adaptive Generation of Critical Boundary Scenarios for Evaluation of Autonomous Vehicles

Testing and evaluation are critical steps in the development and deployment of autonomous vehicles (AVs). This paper aims to provide an online adaptive generation framework for critical boundary driving scenarios (CBDS) with flexible complexity and diversity. Both static scenarios and dynamic scenarios are comprehensively investigated based on real traffic flow data, where the generated static scenarios contain variables of drivable area, weather visibility, and road friction coefficient on autonomous vehicles, and the generated dynamic scenarios consider the effects of mixed traffic streams of AVs, human-driven vehicles, bicycles, and pedestrians. Two complexity models are proposed to characterize the complexity of static scenarios and dynamic scenarios separately, which help to construct feedback for the adaptive generation of CBDS. The scenario-based test is carried out on a joint simulation platform, and the multi-dimensional evaluation system, including safety, driving comfort, driving performance, and traffic coordination, is developed to assess the performance of AVs. Based on the proposed complexity models and multi-dimensional evaluation system, the generation of CBDS is transformed into online environmental parameter optimization. Moreover, the naturalistic driving scenarios generation, scenario complexity calculation, intelligent driving algorithm execution, and intelligent driving evaluation are all concatenated together to form a closed loop so as to adaptively generate critical boundary driving scenarios. Extensive simulations are conducted at the intersection with two different types of intelligent driving algorithms, which show the effectiveness of the proposed framework.

Automated Traffic State Optimization in the Weaving Area of Urban Expressways by a Reinforcement Learning-Based Cooperative Method of Channelization and Ramp Metering

The traffic congestion problem on urban expressways, especially in the weaving areas, has become severe. Some cooperative methods have been proven to be more effective than a separate approach in optimizing the traffic state in weaving areas on urban expressways. However, a cooperative method that combines channelization with ramp metering has not been presented and its effectiveness has not been examined yet. Thus, to fill this research gap, this study proposes a reinforcement learning-based cooperative method of channelization and ramp metering to achieve automated traffic state optimization in the weaving area. This study uses an unmanned aerial vehicle to collect the real traffic flow data, and four control strategies (i.e., two kinds of channelization methods, a ramp metering method, and a cooperative method of channelization and ramp metering) and a baseline (without controls) are designed in the simulation platform (Simulation of Urban Mobility). The speed distributions of different control strategies on each lane were obtained and analyzed in this study. The results show that the cooperative method of channelization and ramp metering is superior to other methods, with significantly higher increases in vehicle speeds. This cooperative method can increase the average vehicle speeds in lane-1, lane-2, and lane-3 by 14.51%, 14.81%, and 37.03%, respectively. Findings in this study can contribute to the improvement of traffic efficiency and safety in the weaving area of urban expressways.

Analysis and Forecast of Traffic Flow between Urban Functional Areas Based on Ride-Hailing Trajectories

Urban planning and function layout have important implications for the journeys of a large percentage of commuters, which often make up the majority of daily traffic in many cities. Therefore, the analysis and forecast of traffic flow among urban functional areas are of great significance for detecting urban traffic flow directions and traffic congestion causes, as well as helping commuters plan routes in advance. Existing methods based on ride-hailing trajectories are relatively effective solution schemes, but they often lack in-depth analyses on time and space. In the paper, to explore the rules and trends of traffic flow among functional areas, a new spatiotemporal characteristics analysis and forecast method of traffic flow among functional areas based on urban ride-hailing trajectories is proposed. Firstly, a city is divided into areas based on the actual urban road topology, and all functional areas are generated by using areas of interest (AOI); then, according to the proximity and periodicity of inter-area traffic flow data, the periodic sequence and the adjacent sequence are established, and the topological structure is learned through graph convolutional neural (GCN) networks to extract the spatial correlation of traffic flow among functional areas. Furthermore, we propose an attention-based gated graph convolutional network (AG-GCN) forecast method, which is used to extract the temporal features of traffic flow among functional areas and make predictions. In the experiment, the proposed method is verified by using real urban traffic flow data. The results show that the method can not only mine the traffic flow characteristics among functional areas under different time periods, directions, and distances, but also forecast the spatiotemporal change trend of traffic flow among functional areas in a multi-step manner, and the accuracy of the forecasting results is higher than that of common benchmark methods, reaching 96.82%.

Potential impact of autonomous vehicles in mixed traffic from simulation using real traffic flow

This work focuses on the potential impacts of the autonomous vehicles in a mixed traffic condition represented in traffic simulator Simulation of Urban MObility (SUMO) with real traffic flow. Specifically, real traffic flow and speed data collected in 2002 and 2019 in Gothenburg were used to simulate daily flow variation in SUMO. In order to predict the most likely drawbacks during the transition from a traffic consisting only manually driven vehicles to a traffic consisting only fully-autonomous vehicles, this study focuses on mixed traffic with different percentages of autonomous and manually driven vehicles. To realize this aim, several parameters of the car following and lane change models of autonomous vehicles are investigated in this paper. Along with the fundamental diagram, the number of lane changes and the number of conflicts are analyzed and studied as measures for improving road safety and efficiency. The study highlights that the autonomous vehicles' features that improve safety and efficiency in 100% autonomous and mixed traffic are different, and the ability of autonomous vehicles to switch between mixed and autonomous driving styles, and vice versa depending on the scenario, is necessary.

Spatiotemporal dynamic network for regional maritime vessel flow prediction amid COVID-19

The COVID-19 pandemic has stifled international trade and the global maritime industry. Its impact on the routing of the regional vessel traffic flow provides supportive data to port authorities, ship owners, shippers, and consignees. This study proposes a spatiotemporal dynamic graph neural network (STDGNN) model that includes the usual primary part of the vessel flow and an auxiliary part of newly confirmed COVID-19 cases near the port. The primary part consists of a time-embedding (TE) block, two dynamic graph neural network (DGNN) blocks, and a gated recurrent unit block, to capture the spatiotemporal dependence in the regional vessel traffic flow. The auxiliary part is made of multiple blocks to exploit the dynamic temporal relationships in hours, days, and weeks. Moreover, the performance of the STDGNN model is verified by utilising real vessel traffic flow data (i.e. inflow, outflow, and volume) and the new cases of COVID-19 near the port of New York, USA, provided by the automatic identification system and the Johns Hopkins University Centre for Systems Science and Engineering. The 2-h prediction result shows a 37.7%, 17.23%, and 11.4% improvement in the mean absolute error (MAE) over the gated recurrent unit (GRU), STGCN, and TGCN models, respectively. The delicate and adaptable prediction of vessel traffic flow could help the port relieve congestion, enhance efficiency, and further assist the recovery of regional maritime industries in the post-COVID era.

Recognition Model and Simulation of Busy Waters in Fishing Area Based on Density Clustering

<p>In this paper, the characteristics of the potential behavior of ships contained in AIS information are con-sidered, in order to ensure the safety of navigation in merchant ships’ fishing areas and reduce the occur-rence of collisions between commercial fishing boats. Based on the DBSCAN density clustering algorithm, the identification model of busy water in fishing areas is developed and applied to Minnan fishery in the Taiwan Strait. In addition, a real ship simulation is performed based on real traffic flow data. The results demonstrate that the proposed model can accurately identify the spatial distribution and scale of busy fishing area, adjust the algorithm parameters according to the merchant ship scale, and generate the target-ed recommended route decision for the fishing area. Finally, the STELLAR EXPRESS is compared with the original route. The obtained results show that the recommended route provides a high safety in the fishing area, while retaining the ship operating costs. The model results can be used as a reference for maritime security departments in order to divide the fishing area warning water, and the identification method provides a novel approach for the safety supervision of maritime department. </p> <p> </p>

A Spatial–Temporal Similar Graph Attention Network for Cyber Physical System Perception via Traffic Forecasting

Traffic flow forecasting is the basic challenge in intelligent transportation system (ITS). The key problem is to improve the accuracy of model and capture the dynamic temporal and nonlinear spatial dependence. Using real data is one of the ways to improve the spatial–temporal correlation modeling accuracy. However, real traffic flow data are not strictly periodic because of some random factors, which may lead to some deviations. This study focuses on capturing and modeling the temporal perturbation in real periodic data and we propose a spatial–temporal similar graph attention network (STSGAN) to address this problem. In STSGAN, the spatial–temporal graph convolution module is to capture local spatial–temporal relationship in traffic data, and the periodic similar attention module is to treat the nonlinear traffic flow information. Experiments on three datasets demonstrate that our model is best among all methods.

Functional clustering and missing value imputation of traffic flow trajectories

Patterns of traffic flow trajectories play an essential role in analysing traffic monitoring data in transportation studies. This research presents a data-adaptive clustering approach to explore traffic flow patterns and a unified algorithm to impute missing values for incomplete traffic flow trajectories. We recommend using subspace-projected functional data clustering with the assumption that each observed daily traffic flow trajectory is a realization of a random function sampled from a mixture of stochastic processes, and each subprocess represents a cluster subspace spanned by the mean function and eigenfunctions of the covariance kernel of the random trajectories. The unified algorithm combines probabilistic functional clustering with functional principal component analysis to propose a mixture prediction for missing value imputation. The proposed methods effectively unravel distinctive daily traffic flow patterns and improve the accuracy of missing value imputation. The advantage of the proposed approaches is demonstrated through numerical studies of a real traffic flow data application.

Multiple Objective Genetic Algorithms for Solving Traffic Signal Optimization Issue at a Complex Intersection: A Case Study in Taichung City, Taiwan

Background: In optimal traffic signal timing, some researchers proposed a single objective genetic algorithm to optimize the timing plan at an isolated intersection. However, the genetic algorithm belongs to a natural selection procession. It means that a suggested model might have a local, optimal result instead of global optimization. A few researchers have tried to avoid local optimization values by making many assumptions for the suggested model, these estimations lacked comprehensive theoretical bases in the transportation field. Objective: The objective of this study is to contribute a comprehensive optimization solution, by applying multiple objective genetic algorithms, to minimize the effective green time and cycle length at a complex urban intersection. Methods: First, the fitness function was established by the minimum issues of average control delay and queue length at the complex isolated intersection. Secondly, constraint functions were identified based on a scientific basis to provide a comprehensive hypothetical model. After running the hypothetical model with single and multiple objective genetic algorithms and real traffic flow data, the results were compared between the use of multiple genetic algorithms and the use of a single-objective genetic algorithm, between an existing traffic signal timing plan and a suggested traffic signal timing plan. Then, the traffic simulation model for the complex intersection was generated to validate the effectiveness of the suggested method. Results: After comparison, the suggested model was found to be more efficient than the existing traffic signal timing at the complex intersection. Conclusion: This study demonstrated multiple objective genetic algorithms that overwhelmed the single objective genetic algorithm in optimal traffic signal timing. The multiple objective genetic algorithms could be effectively used to handle traffic optimization at a complex large-scale intersection. Furthermore, a comprehensive solution of applying multiple genetic algorithms to deal with traffic signal optimization has been generated in this research.

Dynamic Optimization Long Short-Term Memory Model Based on Data Preprocessing for Short-Term Traffic Flow Prediction

In order to eliminate outliers in traffic flow data collection and promote the generalization performance of traffic flow prediction, this paper proposes a dynamic optimization long short-term memory (LSTM) model based on data preprocessing for short-term traffic flow prediction. A new classification algorithm named Asym-Gentle Adaboost with Cost-sensitive support vector machine (AGACS) is used for preprocessing traffic flow data. AGACS tries to employ Cost-sensitive SVM (CS-SVM) as weak component classifier in Asymmetric Gentle AdaBoost, and divide the data collection into outlier data and normal data. Only normal data is used for training LSTM to predict traffic flow and an improved chaotic Particle Swarm Optimization (CPSO) is used for dynamic optimizing hidden layer structure of LSTM to promote the generalization and robustness performance of model. The efficiency of the proposed method is proved with real traffic flow data, and the experimental results show that preprocess collecting data and dynamic optimize model structure are conducive to improve the performance of algorithm, and the proposed method achieved better performance than those of three other classical deep learning prediction methods.

A Novel Approach to Coordinating Green Wave System With Adaptation Evolutionary Strategy

Urban arterial traffic coordination control has attracted much attention in smart city construction process. To achieve optimal signal timing, many studies have attempted to adjust green splits of a cycle time according to the distance between road intersections. However, existing green wave traffic control systems usually require a sophisticated calculation that depend upon the stability of vehicle speed and traffic flow, which can lead to weak robustness. Therefore, this article proposes two novel approaches to control arterial traffic coordination with the help of artificial intelligence: DDPG-BAND and ES-BAND. DDPG-BAND has two stages: a coarse-tuning stage reduces the blocking coefficient, and a fine-tuning stage optimizes the traffic evaluation index. ES-BAND introduces the Covariance Matrix Adaptation Evolutionary Strategy (CMA-ES), a scalable alternative to reinforcement learning, into signal timing. Different traffic variables are adopted as parameters to search for the optimal value by the CMA-ES. To evaluate the feasibility and effectiveness of our approaches, we import real traffic flow data from Zhongshan Road, Ningbo, Zhejiang Province, China, into a traffic environment simulator for training and then conduct a series of experiments. The results show that ES-BAND outperforms the traditional methods in terms of better convergence, lower journey time, fewer stops, and more throughput.

A noise-immune Kalman filter for short-term traffic flow forecasting

This paper formulates the traffic flow forecasting task by introducing a maximum correntropy deduced Kalman filter. The traditional Kalman filter is based on minimum mean square error, which performs well under Gaussian noises. However, the real traffic flow data are fulfilled with non-Gaussian noises. The traditional Kalman filter may rot under this situation. The Kalman filter deduced by maximum correntropy criteria is insensitive to non-Gaussian noises, meanwhile retains the optimal state mean and covariance propagation of the traditional Kalman filter. To achieve this, a fix-point algorithm is embedded to update the posterior estimations of maximum correntropy deduced Kalman filter. Extensive experiments on four benchmark datasets demonstrate the outperformance of this model for traffic flow forecasting.

Floating Car Data Technology

The limiting conditions of traffic in cities, together with the complex and dynamic traffic flows, require an efficient and systematic management and information provision for the traffic participants, with the goal to achieve better utilisation of traffic resources and preserve sustainable mobility. In that context, it is important to identify the traffic flow location features, which requires data and information. This paper presents the application of mobile vehicles for the collection of real time traffic flow data. Such data have become an important source of traffic data, since they can be collected in a simple and cost-efficient way, enabling higher coverage than the conventional approaches, despite the reliability issues. The term referring to that type of data collection, commonly used in scientific and professional literature is FCD (Floating Car Data) and “Probe vehicle”. The efficiency presentation of applying this extensive data source for retrieving necessary parameters and information related to the achievement of sustainable mobility is the final objective of this paper. A description of modern technologies that serve as a basis for probe vehicle data collection has been provided: a geographical information system (GIS), global navigation satellite system (GNSS) and related wireless communication. Within the key technologies review, the development possibilities of data collection by mobile sensors have also been presented.

Fuzzy-statistical prediction intervals from crisp regression models

Most prediction outputs from regression models are either point estimates or interval estimates. Point estimates from a model are useful for making conclusions about model accuracy. Interval estimates on the other-hand are used to evaluate the uncertainty in the model predictions. These two approaches only produce either point or a single interval and thus do not fully represent the uncertainties in the model prediction. In this paper, previous works on constructing fuzzy numbers from arbitrary statistical intervals are extended by first constructing fuzzy-statistical prediction intervals which combines point and prediction interval estimates into a single fuzzy number which fully represents the uncertainties in the model. Then two simple metrics are introduced that can evaluate the quality of the proposed fuzzy-statistical prediction intervals. The proposed metrics are simple to calculate and use same ideas from the well-known metrics for evaluating interval estimates. To test the applicability of the proposed method, two types of scenarios are adopted. In the first scenario, the models are calibrated and then the proposed method is used to get the fuzzy-statistical prediction interval. In the second scenario, the point estimate and prediction intervals are given as output from a model by another researcher, then the proposed approach is used to get the fuzzy-statistical prediction intervals without prior knowledge of the model calibration process. The first scenario is tested by calibrating linear regression and neural network models using a well-known data set of automobile fuel consumption (auto-MPG). The second scenario is tested using outputs from point and interval estimates of two time series models (ARIMA, Kalman Filter) calibrated from a real traffic flow data set.