Traffic Condition Data Research Articles

MMD-TSC: An Adaptive Multi-Objective Traffic Signal Control for Energy Saving with Traffic Efficiency

Reducing traffic energy consumption is crucial for smart cities, and vehicle carbon emissions are a key energy indicator. Traffic signal control (TSC) is a useful method because it can affect the energy consumption of vehicles on the road by controlling the stop-and-go of vehicles at traffic intersections. However, setting traffic signals to reduce energy consumption will affect traffic efficiency and this is not in line with traffic management objectives. Current studies adopt multi-objective optimization methods with high traffic efficiency and low carbon emissions to solve this problem. However, most methods use static weights, which cannot adapt to complex and dynamic traffic states, resulting in non-optimal performance. Current energy indicators for urban transportation often fail to consider passenger fairness. This fairness is significant because the purpose of urban transportation is to serve people’s mobility needs not vehicles. Therefore, this paper proposes Multi-objective Adaptive Meta-DQN TSC (MMD-TSC), which introduces a dynamic weight adaptation mechanism to simultaneously optimize traffic efficiency and energy saving, and incorporates the per capita carbon emissions as the energy indicator. Firstly, this paper integrates traffic state data such as vehicle positions, velocities, vehicle types, and the number of passengers and incorporates fairness into the energy indicators, using per capita carbon emissions as the target for reducing energy consumption. Then, it proposes MMD-TSC with dynamic weights between energy consumption and traffic efficiency as reward functions. The MMD-TSC model includes two agents, the TSC agent and the weight agent, which are responsible for traffic signal adjustment and weight calculation, respectively. The weights are calculated by a function of traffic states. Finally, the paper describes the design of the MMD-TSC model learning algorithm and uses a SUMO (Simulation of Urban Mobility) v.1.20.0 for traffic simulation. The results show that in non-highly congested traffic states, the MMD-TSC model has higher traffic efficiency and lower energy consumption compared to static multi-objective TSC models and single-objective TSC models, and can adaptively achieve traffic management objectives. Compared with using vehicle average carbon emissions as the energy consumption indicator, using per capita carbon emissions achieves Pareto improvements in traffic efficiency and energy consumption indicators. The energy utilization efficiency of the MMD-TSC model is improved by 35% compared to the fixed-time TSC.

A data-driven optimization-based approach for freeway traffic state estimation based on heterogeneous sensor data fusion

Accurate estimation of freeway traffic states is crucial for designing effective traffic management and operational strategies. The integration of various sensor data, such as data from the Electronic Toll Collection (ETC) system and traffic detectors, can significantly enhance the granularity and coverage of traffic state estimation. This study introduces a data-driven optimization-based approach for estimating freeway traffic states, leveraging the fusion of ETC data with detector data. This methodology capitalizes on the broad coverage provided by ETC data and the fine granularity offered by detector data. The probabilistic interdependence between the traffic state of a segment and its upstream and downstream counterparts is captured from real-world traffic state data. Two optimization models, based on the maximum likelihood and maximin likelihood principles, are developed to accurately depict the distribution patterns of freeway traffic states. To address the computational challenges of large-scale scenarios, the study proposes both a decomposition algorithm and a heuristic algorithm. A case study utilizing real-world data from the G92 freeway in Zhejiang, China, is conducted. The findings indicate that the two optimization models exhibit commendable accuracy, with mean absolute percentage errors of 0.9% and 2.3% during peak hours, and 0.9% and 1.4% during off-peak hours, respectively.

Exploring Spatiotemporal Patterns of Frequently Congested Urban Road Segments Based on Multi-Source Data: A Case Study of China’s Super-Large Cities

Traffic congestion has emerged as a primary obstacle to sustainable urban development and the livability of life. Seven super-large cities in China were the study area of this paper as the problem tends to be more severe in larger cities. First, frequently congested road segments were defined based on real-time traffic condition data from online maps. Then, the spatiotemporal characteristics of these road segments were explored. Finally, mitigation measures and ways to ease traffic congestion in big cities were discussed against the background of rapid urbanization. The results demonstrate that the proportion of frequently congested road segments takes up between 1.8% and 9.87% of China’s super-large cities. There is a positive correlation between the overall operational efficiency of the urban road network and the ratio of frequently congested road segments. Temporally, commuting patterns during the morning and evening are displayed by these road segments. Spatially, they also demonstrate significant clustering characteristics. The proportion of frequently congested road segments caused by the lack of alternative routes is about 20% in the six cities studied. The data for Chongqing is even higher at 42.94%. Therefore, congestion caused by the lack of alternative routes may be underestimated by existing research. This work could provide theoretical support for transportation planning and management. As cities continue to expand and urbanization accelerates, the significance of this research will increase.

Traffic state estimation from vehicle trajectories with anisotropic Gaussian processes

Accurately monitoring road traffic state is crucial for various applications, including travel time prediction, traffic control, and traffic safety. However, the lack of sensors often results in incomplete traffic state data, making it challenging to obtain reliable information for decision-making. This paper proposes a novel method for imputing traffic state data using Gaussian processes (GP) to address this issue. We propose a kernel rotation re-parametrization scheme that transforms a standard isotropic GP kernel into an anisotropic kernel, which can better model the congestion propagation in traffic flow data. The model parameters can be estimated by statistical inference using data from sparse probe vehicles or loop detectors. Moreover, the rotated GP method provides statistical uncertainty quantification for the imputed traffic state, making it more reliable. We also extend our approach to a multi-output GP, which allows for simultaneously estimating the traffic state for multiple lanes. We evaluate our method using real-world traffic data from the Next Generation simulation (NGSIM) and HighD programs, along with simulated data representing a traffic bottleneck scenario. Considering current and future mixed traffic of connected vehicles (CVs) and human-driven vehicles (HVs), we experiment with the traffic state estimation (TSE) scheme from 5% to 50% available trajectories, mimicking different CV penetration rates in a mixed traffic environment. We also test the traffic state estimation when traffic flow information is obtained from loop detectors. The results demonstrate the adaptability of our TSE method across different CV penetration rates and types of detectors, achieving state-of-the-art accuracy in scenarios with sparse observations.

Expressway traffic flow prediction based on MF-TAN and STSA.

Highly accurate traffic flow prediction is essential for effectively managing traffic congestion, providing real-time travel advice, and reducing travel costs. However, traditional traffic flow prediction models often fail to fully consider the correlation and periodicity among traffic state data and rely on static network topology graphs. To solve this problem, this paper proposes a expressway traffic flow prediction model based on multi-feature spatial-temporal adaptive periodic fused graph convolutional network (MFSTAPFGCN). First, we make fine preprocessing of the raw data to construct a complete and accurate dataset. Second, by deeply investigating the correlation properties among section speed, traffic flow, and section saturation rate, we incorporate these features into a multi-feature temporal attention mechanism in order to dynamically model the correlation of traffic flow in different time periods. Next, we adopt a spatial-temporal adaptive fusion graph convolutional network to capture the daily cycle similarity and potential spatial-temporal dependence of traffic flow data. Finally, the superiority of the proposed MFSTAPFGCN model over the traditional baseline model is verified through comparative experiments on real Electronic Toll Collection (ETC) gantry transaction data, and the effectiveness of each module is demonstrated through ablation experiments.

Inventarisasi Kepadatan Perlintasan Sebidang Kereta Api Berdasarkan Warna Peta Jalan pada Aplikasi Google Maps di Kota Madiun”

Through this research, it is expected to know the characteristics of the level of traffic density around railway crossings and contribute to improving the safety and efficiency of railway crossings in Indonesia.How is the inventory of vehicle traffic density at railway crossings in Madiun City? Based on the color condition of the highway map in the Google Maps application. The method carried out is to collect historical data on traffic conditions on the google map application at a specified JPL point with a certain period of time, namely during the morning, afternoon and evening rush hours, traffic density condition data is shown with certain color indications. As comparison data, samples of live-traffic data are taken on Google Maps which will be analyzed and identified the level of density of railway crossings. Data analysis was carried out to identify railway crossing points that are prone to congestion in the city of Madiun. Through analysis of railway crossing density data, crossing points that have high, medium and low density levels will be identified. Color condition data shows that the plot crossing on JPL 138 has a frequency percentage of 50.37% and 47.71% of the distance is green, with the level of vehicle traffic density is not dense to rather dense. JPL 138 crossing on the side of Jalan Yos Sudarso – Pahlawan has a higher level of traffic density.

A Missing Traffic Data Imputation Method Based on a Diffusion Convolutional Neural Network–Generative Adversarial Network

Traffic state data are key to the proper operation of intelligent transportation systems (ITS). However, traffic detectors often receive environmental factors that cause missing values in the collected traffic state data. Therefore, aiming at the above problem, a method for imputing missing traffic state data based on a Diffusion Convolutional Neural Network–Generative Adversarial Network (DCNN-GAN) is proposed in this paper. The proposed method uses a graph embedding algorithm to construct a road network structure based on spatial correlation instead of the original road network structure; through the use of a GAN for confrontation training, it is possible to generate missing traffic state data based on the known data of the road network. In the generator, the spatiotemporal features of the reconstructed road network are extracted by the DCNN to realize the imputation. Two real traffic datasets were used to verify the effectiveness of this method, with the results of the proposed model proving better than those of the other models used for comparison.

Anti-circulant dynamic mode decomposition with sparsity-promoting for highway traffic dynamics analysis

Highway traffic state data collected from a network of sensors can be considered as a high-dimensional nonlinear dynamical system. In this paper, we develop a novel data-driven method–anti-circulant dynamic mode decomposition with sparsity-promoting (circDMDsp)–to study the dynamics of highway traffic speed data. Particularly, circDMDsp addresses several issues that hinder the application of existing DMD models: limited spatial dimension, presence of both recurrent and non-recurrent patterns, high level of noise, and known mode stability. The proposed circDMDsp framework allows us to numerically extract spatial–temporal coherent structures with physical meanings/interpretations: the dynamic modes reflect coherent spatial bases, and the corresponding temporal patterns capture the temporal oscillation/evolution of these dynamic modes. Our result based on Seattle highway loop detector data showcases that traffic speed data is governed by a set of periodic components, e.g., mean pattern, daily pattern, and weekly pattern, and each of them has a unique spatial structure. The spatiotemporal patterns can also be used to recover/denoise observed data and predict future values at any timestamp by extrapolating the temporal Vandermonde matrix. Our experiments also demonstrate that the proposed circDMDsp framework is more accurate and robust in data reconstruction and prediction than other DMD-based models. The code for the algorithm and experiment is available at https://github.com/mcgill-smart-transport/circDMDsp.

LibCity-Dataset: a standardized and comprehensive dataset for urban spatial–temporal data mining

Abstract The LibCity-Dataset represents a significant contribution to the field of urban spatial-temporal data mining. This dataset uniquely integrates macro traffic state data with micro trajectory data, providing researchers with comprehensive and diverse urban spatial-temporal data. Specifically, we begin by collecting and processing existing open-source spatial-temporal data. Subsequently, we independently collected Beijing taxi trajectory data through third-party interfaces. This data bridges the gap in the scarcity of current open-source vehicle trajectory data. The distinctive aspect of the LibCity-Dataset lies in its innovative approach of standardizing the storage format, achieved through the implementation of atomic files. By adopting this standardized format, diverse data sources are harmonized, enabling effortless application of spatial-temporal prediction models across various datasets. The uniform storage format not only simplifies experimentation but also expedites the advancement of spatial-temporal prediction research, acting as a catalyst for further innovation. This Data Note provides a comprehensive insight into the creation methodology of the LibCity-Dataset, including data collection and processing methodology, data description, data validation, and usage notes. By facilitating open-source collaboration and setting a benchmark for standardization within the spatial-temporal prediction domain, this dataset aims to foster increased research cooperation and knowledge sharing. The open-source link of our dataset is https://drive.google.com/drive/folders/1g5v2Gq1tkOq8XO0HDCZ9nOTtRpB6-gPe.

P‐2.5: Research on real‐time performance of Road condition display for automatic driving

In view of the problems of multi‐scale, densely distributed and difficult small target detection in real‐time road condition detection, a new improved yolov5 real‐time target detection method was proposed. The activation function in the original spatial pyramid (SPPF) was replaced by ReLu in the backbone network to enhance the expression ability of the model. The bidirectional feature pyramid (BiFPN) is used to replace the original feature pyramid network (FPN) + pixel aggregation network (PAN) in the neck area. The bidirectional feature fusion improves the utilization of multi‐scale semantic features and strengthens the extraction of image deep features. The convolutional attention mechanism (CBAM) is introduced to further improve the feature extraction ability of the algorithm and make the algorithm pay more attention to useful information. The results of self‐made traffic condition data set show that the average accuracy of the improved yolov5 model reaches 81.3%, which is 10.9% higher than that of the original yolov5 model, showing better detection accuracy and real‐time performance. Compared with some mainstream target detection algorithms, this algorithm has certain advantages.

A V2V Identity Authentication and Key Agreement Scheme Based on Identity-Based Cryptograph

Cellular vehicle to everything (C-V2X) is a technology to achieve vehicle networking, which can improve traffic efficiency and traffic safety. As a special network, the C-V2X system faces many security risks. The vehicle to vehicle (V2V) communication transmits traffic condition data, driving path data, user driving habits data, and so on. It is necessary to ensure the opposite equipment is registered C-V2X equipment (installed in the vehicle), and the data transmitted between the equipment is secure. This paper proposes a V2V identity authentication and key agreement scheme based on identity-based cryptograph (IBC). The C-V2X equipment use its vehicle identification (VID) as its public key. The key management center (KMC) generates a private key for the C-V2X equipment according to its VID. The C-V2X equipment transmit secret data encrypted with the opposite equipment public key to the other equipment, they authenticate each other through a challenge response protocol based on identity-based cryptography, and they negotiate the working key used to encrypt the communication data. The scheme can secure the V2V communication with low computational cost and simple architecture and meet the lightweight and efficient communication requirements of the C-V2X system.

Spotted hyena optimizer with deep learning enabled vehicle counting and classification model for intelligent transportation systems

<abstract> <p>Traffic surveillance systems are utilized to collect and monitor the traffic condition data of the road networks. This data plays a crucial role in a variety of applications of the Intelligent Transportation Systems (ITSs). In traffic surveillance, it is challenging to achieve accurate vehicle detection and count the vehicles from traffic videos. The most notable difficulties include real-time system operations for precise classification, identification of the vehicles' location in traffic flows and functioning around total occlusions that hamper the vehicle tracking process. Conventional video-related vehicle detection techniques such as optical flow, background subtraction and frame difference have certain limitations in terms of efficiency or accuracy. Therefore, the current study proposes to design the spotted hyena optimizer with deep learning-enabled vehicle counting and classification (SHODL-VCC) model for the ITSs. The aim of the proposed SHODL-VCC technique lies in accurate counting and classification of the vehicles in traffic surveillance. To achieve this, the proposed SHODL-VCC technique follows a two-stage process that includes vehicle detection and vehicle classification. Primarily, the presented SHODL-VCC technique employs the RetinaNet object detector to identify the vehicles. Next, the detected vehicles are classified into different class labels using the deep wavelet auto-encoder model. To enhance the vehicle detection performance, the spotted hyena optimizer algorithm is exploited as a hyperparameter optimizer, which considerably enhances the vehicle detection rate. The proposed SHODL-VCC technique was experimentally validated using different databases. The comparative outcomes demonstrate the promising vehicle classification performance of the SHODL-VCC technique in comparison with recent deep learning approaches.</p> </abstract>

Taxi travel time prediction based on fusion of traffic condition features

The research on travel time prediction has shown its importance and research significance in rational planning of travel arrangements and alleviating road congestion. As the level of urbanization increases, the number of cars has increased sharply. Traffic congestion has gradually become a norm in many first-tier and medium-sized cities. Existing models lack effective traffic information, especially traffic condition, to predict taxi travel time. The accuracy of the research model in urban areas is low. This will affect passenger travel arrangements. This paper defines urban congestion and taxi flow to represent traffic condition. A method for capturing traffic condition is proposed, and traffic condition and trajectory data are merged. Secondly, this work integrates two indirect factors of departure time and travel date to improve the accuracy of the model. The experimental results show that our model has some advantages over some classical models in travel time prediction.

Du-Bus: A Realtime Bus Waiting Time Estimation System Based On Multi-Source Data

Realtime bus waiting time information is of great importance to the intelligent public transportation system and is beneficial for improving user satisfaction by online map services. While there are limited realtime bus waiting time services in a city, because of the expensive cost of sensor deployment and sophisticated traffic conditions. To address the above problem, we propose Du-Bus, a multi-source data fusion based system, which estimates the realtime bus waiting time based on approximating the realtime locations of buses without GPS sensors, by a variety of urban datasets, including historical bus trip data reported by a limited number of GPS equipped buses, transportation network data, traffic condition data, user mobility data, and temporal data. Du-Bus approximates the realtime locations of buses without GPS sensors by jointly modeling the bus timetable and the bus realtime travel time, which can be estimated by a variety of data sources. Specifically, we first propose a BiLSTM based end-to-end model for each bus route to estimate the bus departure interval and generate the corresponding departure timetable. Then, we estimate the travel time for each individual bus via a deep neural network component by incorporating the traffic conditions, geolocation, and map query information. Finally, we estimate the bus waiting time for arbitrary stations in the city by jointly modeling the estimated bus departure timetable and travel time. We evaluate our system on two real-world datasets, and the results verify the effectiveness of Du-Bus compared with historical average based and headway based methods. Since early 2019, Du-Bus has been deployed on Baidu Maps, one of the world’s largest map services, servicing over 20 major cities in China.

Bayesian Kernelized Matrix Factorization for Spatiotemporal Traffic Data Imputation and Kriging

Missingness and corruption are common problems for real-world traffic data. How to accurately perform imputation and prediction based on incomplete or even sparse traffic data becomes a critical research question in intelligent transportation systems. Low-rank matrix factorization (MF) is a common solution for the general missing value imputation problem. To better characterize and encode the strong spatial and temporal consistency in traffic data, existing work has introduced flexible spatial/temporal Gaussian process (GP) priors to model the latent factors in MF framework, which also allows us to perform kriging for unseen locations and virtual sensors. However, learning the hyperparameters in GP kernels remains a challenging task. In this paper, we present a Bayesian kernelized matrix factorization (BKMF) model with an efficient Markov chain Monte Carlo (MCMC) sampling algorithm for model inference. By learning the kernel hyperparameters from their marginal posteriors through a slice sampling treatment and updating the latent factors alternatively with Gibbs sampling, we achieve a fully Bayesian model for the spatiotemporally kernelized (i.e., GP prior regularized) MF framework. We apply BKMF on both imputation and kriging tasks, and our results demonstrate the superiority of BKMF compared with state-of-the-art spatiotemporal models. In addition, we also explore the effects of different GP kernels in characterizing networked spatiotemporal traffic state data.

From driving behavior to energy consumption: A novel method to predict the energy consumption of electric bus

Accurate real-time energy consumption prediction of electric buses (EBs) is essential for bus operation and management, which can effectively mitigate the driving range anxiety while reducing the operation cost simultaneously. This paper presents a machine learning-based energy consumption prediction method for EB, which combines driving data with road characteristics data (such as road type), traffic condition (such as peak hour), and meteorology data (such as temperature). The importance of driving behavior features affecting energy consumption is quantitatively revealed by the novel Shapley additive explanation (SHAP). Given the road characteristics, traffic condition and meteorology information, a Long Short-Term Memory (LSTM) network is then used to predict driving microscopic parameters, including speed, acceleration, gas pedal position and brake pedal position. Finally, the instantaneous electricity consumption is predicted using an Extreme Gradient Boosting (XGBoost) model based on the predicted values from the LSTM. The results show that the proposed LSTM-XGBoost model with accurate time series prediction and regression is powerful for efficiently fitting the complex volatility of energy consumption. Moreover, the proposed model chain outperforms other model combinations (such as artificial neural networks and conventional regression methods) in terms of root mean squared error (RMSE = 0.079), mean absolute error (MAE = 0.086) and R-square (R2 = 0.814).

Improving performance and efficiency of Graph Neural Networks by injective aggregation

Aggregation functions are regarded as the multiplication between an aggregation matrix and node embeddings, based on which a full rank matrix can enhance representation capacity of Graph Neural Networks (GNNs). In this work, we fill this research gap based on the full rank aggregation matrix and its functional form, i.e., the injective aggregation function, and state that injectivity is necessary to guarantee the rich representation capacity to GNNs. To this end, we conduct theoretical injectivity analysis for the typical feature aggregation methods and provide inspiring solutions on turning the non-injective aggregation functions into injective versions. Based on our injective aggregation functions, we create various GNN structures by combining the aggregation functions with the other ingredient of GNNs, node feature encoding, in different ways. Following these structures, we highlight that by using our injective aggregation function entirely as a pre-processing step before applying independent node feature learning, we can simultaneously achieve satisfactory performance and computational efficiency on the large-scale graph-based traffic data for traffic state prediction tasks. Through comprehensive experiments on standard node classification benchmarks and practical traffic state data (for Chengdu and Xi’an cities), we show that the representation capacity of GNNs can be improved by using our injective aggregation functions just by changing the model in simple operations.

Traffic State Data Imputation: An Efficient Generating Method Based on the Graph Aggregator

Road traffic state estimation is an essential component of intelligent transportation systems (ITSs). However, road traffic state data collected by traffic detectors are often incomplete, which can cause problems across a variety of transportation applications, such as traffic state prediction and pattern recognition. We present GA-GAN (Graph Aggregate Generative Adversarial Network), consisting of graph sample and aggregate (GraphSAGE) and a generative adversarial network (GAN), to impute missing road traffic state data. Instead of using the original road network structure, which presents the spatial information to process a graph operation, we reconstruct the road network according to the correlation coefficients of road historical data. We utilize GraphSAGE to aggregate the temporal-spatial information from the neighbors of each road in the reconstructed road network. GAN is used to generate complete traffic state data from the extracted temporal-spatial information to achieve traffic state data imputation. To illustrate the efficient performance of the model, experiments are conducted on traffic data collected from California and Seattle, Washington, showing that the proposed model outperforms state-of-the-art methods.

Traffic condition estimation and data quality assessment for signalized road networks using massive vehicle trajectories

Traffic condition estimation and data quality assessment for signalized road networks using massive vehicle trajectories

Intelligent Traffic Control System Using Deep Learning

Traffic congestion and regulating traffic in traffic signals are major issues in cities. Nowadays, in most of the cities, traffic management centers installed numerous cameras all over the roads and traffic signals. Such cameras can be effectively used for the automation of traffic signals. The objective is to develop a real time system that can automatically monitor real time traffic and make the system intelligent using artificial intelligence techniques. Specifically, Deep Convolutional Neural Networks are employed to perform the task. From statistical traffic data, it determines count, type of vehicle, average speed, distance between vehicles, etc. Based on traffic, the algorithm instructs to stop vehicle or queue or move. It can also record a wrong-way driver. Using license plate recognition, security applications such as unauthorized vehicles are identified. If there is violation of traffic rules, they are recorded with registration number. It can detect ambulances and give first preference. The proposed algorithm identifies VIP vehicles and clear traffics in automated ways. Ambulances are given priority to pass the road. The entire system have been developed using a standalone-Graphical User Interface (GUI). We have implemented successfully and the proposed framework performs satisfactorily.