Construction Of Intelligent Transportation System Research Articles

Multi-layer feature fusion and attention enhancement for fine-grained vehicle recognition research

Abstract Vehicle recognition technology is widely applied in automatic parking, traffic restrictions, and public security investigations, playing a significant role in the construction of intelligent transportation systems. Fine-grained vehicle recognition seeks to surpass conventional vehicle recognition by concentrating on more detailed sub-classifications. This task is more challenging due to the subtle inter-class differences and significant intra-class variations. Localization-classification subnetworks represent an efficacious approach frequently employed for this task, but previous research has typically relied on CNN deep feature maps for object localization, which suffer from the low resolution, leading to poor localization accuracy. The multi-layer feature fusion localization method proposed by us fuses the high-resolution feature map of the shallow layer of CNN with the deep feature map, and makes full use of the rich spatial information of the shallow feature map to achieve more precise object localization. In addition, traditional methods acquire local attention information through the design of complex models, frequently resulting in regional redundancy or information omission. To address this, we introduce an attention module that adaptively enhances the expressiveness of global features and generates global attention features. These global attention features are then integrated with object-level features and local attention cues to achieve a more comprehensive attention enhancement. Lastly, we devise a multi-branch model and employ the aforementioned object localization and attention enhancement methods for end-to-end training to make the multiple branches collaborate seamlessly to adequately extract fine-grained features. Extensive experiments conducted on the Stanford Cars dataset and the self-built Cars-126 dataset have demonstrated the effectiveness of our method, achieving a leading position among existing methods with 97.7% classification accuracy on the Stanford Cars dataset.

Synthesis and characterization of polyurethane-based self-luminous pavement coatings: a performance evaluation study

Improving the nighttime vision of drivers is essential, given the growing advancements in urban transportation. In this study, polyurethane-based self-luminous pavement coatings (PSCs) were prepared by doping luminous powders (LPs) into the polyurethane materials. The superior optical properties and chemical stabilities of these coatings were ensured by synthesizing the polyurethane-based material. Then, the PSCs were evaluated for their comprehensive performances, such as luminescence, aging resistance, and abrasion resistance, using various characterization methods, including fluorescence spectral analysis, Fourier-transform infrared spectroscopy, fluorescence microscopy, and mechanical property testing. The results show that the 50-mesh LP has the optimal overall performance, with an initial luminescence that exceeds those of the 100 and 400 meshes. The initial brightness of the PSC is mainly influenced by the LP and increases with dosage. The lattice structure and luminescent properties of the luminescent material did not change after coating preparation. The peak excitation wavelength of 420 nm implies that the coating has the best excitation effect under UV light. The primer-marking coating effectively improves the abrasion resistance of the PSC, and the mass loss of the PSC with a coating thickness of 0.4 kg/m2 is 52.9% of that without the primer-marking coating, with the optimal coating thickness being 0.6 kg/m2. This research provides an innovative solution to improve nighttime roadway lighting, which provides useful support for the sustainable development of urban transportation infrastructures and construction of intelligent transportation systems.

Ridesplitting demand prediction via spatiotemporal multi-graph convolutional network

Ridesplitting demand prediction plays an important role in vehicle scheduling and intelligent transportation system construction. Accurate ridesplitting demand prediction is crucial for alleviating supply–demand imbalance and increasing vehicle utilization. Ridesplitting refers to the sharing of a vehicle by multiple passengers with similar routes, thereby achieving a reduction in the adverse effects of increased congestion caused by ride-hailing. However, most existing works mainly address the region-based ride-hailing demand prediction, whereas few works focus on the ridesplitting demand prediction, which takes into account the correlation between shared orders. To address the issue, we develop several intersection-based graphs to character the ridesplitting demand correlations between the intersections. The multi-graph convolutional networks (MGCN) with different graph combinations are constructed to capture the spatial topologies. Furthermore, we introduce the probabilistic model structure to predict the uncertainty of ridesplitting demand. A novel deep learning model, referred to as the Multi-graph Convolutional Gated Recurrent Unit with Probabilistic prediction (MGCGRU-P) is proposed. We conduct extensive numerical experiments on the real-world ride-hailing demand dataset (from Beijing, China). The results demonstrate that the model we propose performs the best against baseline models.

Learning traffic as videos: Short-term traffic flow prediction using mixed-pointwise convolution and channel attention mechanism

In the construction of intelligent transportation systems, short-term traffic flow prediction is of great significance for the advancement of traffic network management. But due to the presence of many complex factors in both spatial and temporal domains, it remains a complex and challenging task. Existing literature usually employs the convolutional neural network (CNN)-based methods in capturing spatiotemporal correlations. These CNN-based methods often use a single-channel data structure to represent different periodic patterns, which makes the model susceptible to over-parameterization when capturing periodic dependencies and prone to information loss after convolution. To overcome these limitations, this paper presents a hybrid deep learning method for short-term traffic flow prediction. In this method, a video-shaped multi-channel data structure is designed to represent different periodic patterns more efficiently. Next, a new mixed-pointwise convolution is introduced for capturing periodic dependencies without the negative impacts mentioned above. Lastly, an improved channel attention mechanism is proposed to learn channel inter-dependencies with controllable parameter usage. The proposed method is lightweight, yet highly effective. Compared to the state-of-the-art baseline method, it reduces the root mean squared error by up to 6.7% on the PeMSD4 dataset and 13.3% on the PeMSD7 dataset, while also achieving substantial improvement in two additional metrics, exhibiting strong robustness and great scalability across various settings.

Short-term traffic flow prediction based on weather factors analysis and neural network

With the progress of urban transportation infrastructure and the construction of intelligent transportation system, sufficiently accurate traffic flow prediction is of increasing importance for urban planning and management. This paper based on traffic flow data in a section of highway in Los Angeles, USA, we combine external qualitative data such as weather and work calendars, analyze and process the factors significantly influencing traffic flow first, then train and test the traffic flow data by building machine learning Support Vector Regression (SVR) model and the Back Propagation neural network (BP neural network). The test results show that the BP neural network traffic flow prediction model incorporating the external environment is more accurate, and that the external environment has a significant impact on the traffic flow prediction problem. If more significantly influencing factors can be taken into account, or if the current algorithm can be optimized, the prediction accuracy will have further improved, thus effectively enhancing the efficiency and safety of traffic systems.

Spatial-temporal hypergraph convolutional network for traffic forecasting.

Accurate traffic forecasting plays a critical role in the construction of intelligent transportation systems. However, due to the across road-network isomorphism in the spatial dimension and the periodic drift in the temporal dimension, existing traffic forecasting methods cannot satisfy the intricate spatial-temporal characteristics well. In this article, a spatial-temporal hypergraph convolutional network for traffic forecasting (ST-HCN) is proposed to tackle the problems mentioned above. Specifically, the proposed framework applies the K-means clustering algorithm and the connection characteristics of the physical road network itself to unify the local correlation and across road-network isomorphism. Then, a dual-channel hypergraph convolution to capture high-order spatial relationships in traffic data is established. Furthermore, the proposed framework utilizes a long short-term memory network with a convolution module (ConvLSTM) to deal with the periodic drift problem. Finally, the experiments in the real world demonstrate that the proposed framework outperforms the state-of-the-art baselines.

Break the Data Barriers While Keeping Privacy: A Graph Differential Privacy Method

The booming development of Internet of Vehicles (IoV) has brought new vitality to the construction of intelligent transportation systems (ITS). At the same time, a huge amount of data has been generated due to the gradual development of IoV toward large scale, complex, and diversified. These data are owned by the companies that vehicles belonging to or service providers, such as taxi companies own taxi data. Due to interest and privacy considerations, data owners are not willing to share data, thus a serious data isolated island problem is created, which is detrimental to the development of ITS. Therefore, this article focuses on how to prevent privacy disclosure of vehicles while sharing vehicle data to improve the service. Considering the amount of interactive data and privacy disclosure during data release, vehicle data are abstracted from text form into a graph-structured data form. At the same time, graph differential privacy (DP) together with anonymity protection is proposed innovatively to firmly protect vehicle privacy. Moreover, to solve the high complexity of big data graph-structure transformation, an accelerated nodes and edges combined graph DP (ACGDP) algorithm is proposed. Based on the simulations of real-world data that combine electric and nonelectric taxies, it is verified that our proposed scheme has a tradeoff between information availability and privacy protection. With the graph DP processed data, our proposed scheme reduces the average wasted mileage for charging by 3.87% and achieves a 44.28% increase in drivers’ income. Drivers’ satisfaction of receiving orders and charging preference reaches 68% after the graph-structured data reuse.

Short-Term Traffic Flow Prediction Based on the Optimization Study of Initial Weights of the Attention Mechanism

Traffic-flow prediction plays an important role in the construction of intelligent transportation systems (ITS). So, in order to improve the accuracy of short-term traffic flow prediction, a prediction model (GWO-attention-LSTM) based on the combination of optimized attention mechanism and long short-term memory (LSTM) is proposed. The model is based on LSTM and uses the attention mechanism to assign individual weight to the feature information extracted via LSTM. This can increase the prediction model’s focus on important information. The initial weight parameters of the attention mechanism are also optimized using the grey wolf optimizer (GWO). By simulating the hunting process of grey wolves, the GWO algorithm calculates the hunting position of the grey wolf and maps it to the initial weight parameters of the attention mechanism. In this way, the short-time traffic flow prediction model is constructed. The traffic flow data of the trunk roads in the center of Qingdao (China) are used as the research object. Multiple sets of comparison models are set up for prediction analysis. The results show that the GWO-attention-LSTM model has obvious advantages over other models. The prediction error MAE values of the GWO-attention-LSTM model decreased by 7.32% and 14.35% on average compared with the attention-LSTM model and LSTM model. It is concluded that the GWO-attention-LSTM model has better model performance and can provide effective help for traffic management control and traffic flow theory research.

A digital decision approach for scheduling process planning of shared bikes under Internet of Things environment

Digital technology plays an important role in the construction of intelligent transportation systems. The digitization of travel and traffic information contributes to the efficiency, equality, and safety of mobility for urban residents. This research aims at improving the imbalance between the supply and demand of bike-sharing system. A scheduling process planning algorithm for shared bikes towards Internet of Things (IoT) environment was proposed in this research. Firstly, the algorithm combined the massive shared bikes data of IoT, Long Short-Term Memory and Gated Recurrent Unit neural networks (LSTM-GRU) hybrid model was employed to predict the shared bike demand towards electronic fence(e-fence). Then, based on the division of scheduling sub-areas, the mathematical model of scheduling path optimization for shared bikes was constructed, in addition to the constraints and costs, the minimum carbon emission was also considered as the objective function. Finally, the algorithm was applied to the bike-sharing system in Yanqing District (Beijing China) as the case study. The results show that: the LSTM-GRU hybrid model proposed in this research has a high prediction accuracy of 6.16 mean square error and 0.86 goodness of fit, the sub-area partition model can reduce the average scheduling demand imbalance degree by 58.90%. Under the same scheduling task, electric vehicles can reduce carbon emissions by about 32% compared with fuel vehicles. The proposed shared bike scheduling planning algorithm can provide a decision-making guidance for related operation departments, as well as realize low-carbon and sustainable development for urban transportation system.

Multiscale Backcast Convolution Neural Network for Traffic Flow Prediction in The Frequency Domain

With the construction of intelligent transportation systems in recent years, intelligent methods for the prediction of traffic flow are becoming more and more important, and accurate prediction plays a key role in enabling downstream scheduling algorithms. However, the accuracy of most current forecasting algorithms remains unsatisfactory. Because traffic depends on the time of the day and varies throughout the week, such as during peak commuting periods as opposed to other times, traffic flow data show evident cyclical patterns. We capitalize on this notion and propose a multiscale convolutional feedback network for frequency prediction based on frequency angle. We combine multiscale convolution (MSC) with dilated convolution, and increase the convolutional receptive field by expanding cavity size while retaining similar parameterization costs, and achieve multiscale convolution with kernels referring to different receptive fields. At the same time, we incorporate an autoencoding module by assigning the same set of hidden features to input reconstruction and output prediction, which results in enhanced stability of features within the hidden layers. When we tested our approach on the Traffic dataset, our model achieved the best performance as assessed via the three indicators measured using mean squared error (MSE), mean absolute error (MAE), and correlation coefficient (CORR), with improvements of 3.818%, 2.472% and, 0.1515%, respectively.

A New Perspective on Traffic Flow Prediction: A Graph Spatial-Temporal Network with Complex Network Information

Traffic flow prediction provides support for travel management, vehicle scheduling, and intelligent transportation system construction. In this work, a graph space–time network (GSTNCNI), incorporating complex network feature information, is proposed to predict future highway traffic flow time series. Firstly, a traffic complex network model using traffic big data is established, the topological features of traffic road networks are then analyzed using complex network theory, and finally, the topological features are combined with graph neural networks to explore the roles played by the topological features of 97 traffic network nodes. Consequently, six complex network properties are discussed, namely, degree centrality, clustering coefficient, closeness centrality, betweenness centrality, point intensity, and shortest average path length. This study improves the graph convolutional neural network based on the above six complex network properties and proposes a graph spatial–temporal network consisting of a combination of several complex network properties. By comparison with existing baselines containing graph convolutional neural networks, it is verified that GSTNCNI possesses high traffic flow prediction accuracy and robustness. In addition, ablation experiments are conducted for six different complex network features to verify the effect of different complex network features on the model’s prediction accuracy. Experimental analysis indicates that the model with combined multiple complex network features has a higher prediction accuracy, and its performance is improved by 31.46% on average, compared with the model containing only one complex network feature.

A Comprehensive Spatio-Temporal Model for Subway Passenger Flow Prediction

Accurate subway passenger flow prediction is crucial to operation management and line scheduling. It can also promote the construction of intelligent transportation systems (ITS). Due to the complex spatial features and time-varying traffic patterns of subway networks, the prediction task is still challenging. Thus, a hybrid neural network model, GCTN (graph convolutional and comprehensive temporal neural network), is proposed. The model combines the Transformer network and long short-term memory (LSTM) network to capture the global and local temporal dependency. Besides, it uses a graph convolutional network (GCN) to capture the spatial features of the subway network. For the sake of the stability and accuracy for long-term passenger flow prediction, we enhance the influence of the station itself and the global station and combine the convolutional neural networks (CNN) and Transformer. The model is verified by the passenger flow data of the Shanghai Subway. Compared with some typical data-driven methods, the results show that the proposed model improves the prediction accuracy in different time intervals and exhibits superiority in prediction stability and robustness. Besides, the model has a better performance in the peak value and the period when passenger flow changes quickly.

A GAN framework-based dynamic multi-graph convolutional network for origin–destination-based ride-hailing demand prediction

Ride-hailing demand prediction plays an important role in ride-hailing vehicle scheduling, traffic condition control and intelligent transportation system construction. Accurate and real-time ride-hailing demand prediction is crucial for improving supply–demand imbalance, vehicle utilization and traffic conditions. However, most existing works mainly address the region-based demand prediction whereas only a few works focus on the origin–destination (OD)-based demand prediction. To address the issue, we develop several dynamic OD graphs to character the ride-hailing demand transactions between the origin and destination. We propose a novel deep learning model, referred to as the Dynamic Multi-Graph Convolutional Network with Generative Adversarial Network structure (DMGC-GAN), to investigate the challenging problem. Different from previous studies, we develop the temporal multi-graph convolutional network (TMGCN) layer with different dynamic OD graphs to capture the spatial topologies contained in the dynamic OD graphs in terms of time, and exploit GAN structure to overcome the high sparsity of OD demand. We conduct extensive numerical experiments on the real-world ride-hailing demand dataset (from Manhattan district, New York City). The results demonstrate that the model we propose performs the best against to nine baseline models.

Time-Evolving Graph Convolutional Recurrent Network for Traffic Prediction

Accurate traffic prediction is crucial to the construction of intelligent transportation systems. This task remains challenging because of the complicated and dynamic spatiotemporal dependency in traffic networks. While various graph-based spatiotemporal networks have been proposed for traffic prediction, most of them rely on predefined graphs from different views or static adaptive matrices. Some implicit dynamics of inter-node dependency may be neglected, which limits the performance of prediction. To address this problem and make more accurate predictions, we propose a traffic prediction model named Time-Evolving Graph Convolution Recurrent Network (TEGCRN), which takes advantage of time-evolving graph convolution to capture the dynamic inter-node dependency adaptively at different time slots. Specifically, we first propose a tensor-composing method to generate adaptive time-evolving adjacency graphs. Based on these time-evolving graphs and a predefined distance-based graph, a graph convolution module with mix-hop operation is applied to extract comprehensive inter-node information. Then the resulting graph convolution module is integrated into the Recurrent Neural Network structure to form an general predicting model. Experiments on two real-world traffic datasets demonstrate the superiority of TEGCRN over multiple competitive baseline models, especially in short-term prediction, which also verifies the effectiveness of time-evolving graph convolution in capturing more comprehensive inter-node dependency.

Threshold Key Management Scheme for Blockchain-Based Intelligent Transportation Systems

Intelligent transportation systems (ITS) have always been an important application of Internet of Things (IoT). Today, big data and cloud computing have further promoted the construction and development of ITS. At the same time, the development of blockchain has also brought new features and convenience to ITS. However, due to the endless emergence of increasingly advanced types of attacks, the security of blockchain-based ITS needs more attention from industry and academia. In this paper, we focus on exploring the primitives in cryptography to guarantee the security of blockchain-based ITS. In particular, the authentication, encryption, and key management schemes in cryptography are discussed. Furthermore, we propose two methods for achieving the threshold key management in blockchain-based ITS. The proposed threshold key management scheme (with threshold t ) enables various stakeholders to recover a secret if the number of participated stakeholders is at least t . It should be noted that the proposed threshold key management scheme is efficient and secure for multiple users in blockchain-based ITS, especially for the data-sharing scenario.

A Multi-Loop Vehicle-Counting Method under Gray Mode and RGB Mode

With the rapid development of road traffic, real-time vehicle counting is very important in the construction of intelligent transportation systems (ITSs). Compared with traditional technologies, the video-based method for vehicle counting shows great importance and huge advantages in its low cost, high efficiency, and flexibility. However, many methods find difficulty in balancing the accuracy and complexity of the algorithm. For example, compared with traditional and simple methods, deep learning methods may achieve higher precision, but they also greatly increase the complexity of the algorithm. In addition to that, most of the methods only work under one mode of color, which is a waste of available information. Considering the above, a multi-loop vehicle-counting method under gray mode and RGB mode was proposed in this paper. Under gray and RGB modes, the moving vehicle can be detected more completely; with the help of multiple loops, vehicle counting could better deal with different influencing factors, such as driving behavior, traffic environment, shooting angle, etc. The experimental results show that the proposed method is able to count vehicles with more than 98.5% accuracy while dealing with different road scenes.

Online Traffic Flow Prediction for Edge Computing-Enhanced Autonomous and Connected Vehicles

The development of edge computing based autonomous and connected vehicles (CAVs) provides a very promising solution for the construction of intelligent transportation system. Unfortunately, the existing methods are difficult to predict traffic flow accurately in such case due to not only the dynamic nature of the CAVs but also the considerable amount of missing traffic flow data. Based on this, we propose an online rolling traffic flow prediction method to provide support for the CAVs can be seen into practice. The new matrix factorization techniques proposed can learn the low-dimensional embeddings in the online setting and impute missing ones simultaneously. Moreover, instead of directly predicting the high-dimensional traffic flow data, a standard vector autoregressive (VAR) process is employed on low-dimensional embeddings to predict future values. Further, a multidimensional Cadzow method is proposed to solve the coefficient matrices of VAR efficiently even if there is noise. The simulation results on two real datasets show the applicability of the proposed method to online traffic flow prediction for edge computing-enhanced CAVs.

A Multifaceted Vigilare System for Intelligent Transportation Services in Smart Cities

The Internet of Things (IoT), information and communication technology, and data mining technologies are three prime pillars of any smart city project. The intelligent urban transportation system is an indispensable part of any smart city and acts as a major contributor to a city's vitality. An extensive amount of vehicular information is being amassed by the wireless sensor networks (WSNs), vehicular ad hoc networks, and radio frequency identification (RFID)-based Intelligent Transportation System (ITS), which can provide an insightful image of various ITS issues concerning safety, security, and management. Merely depending on WSN and RFID predicated technologies for the construction of ITS is not adequate to realize the smart city dream in developing countries due to technological and monetary barriers. Considering this, an intelligent vigilare system for ITS is proposed, which sanctions network implementation without disrupting the current vehicular infrastructure through multifaceted modeling.

The effect of the dataset on evaluating urban traffic prediction

With the continuous development of economic strength and science and technology, the construction of Intelligent Transportation System(ITS) has become a new development direction in many cities. A complete and accurate traffic dataset can improve the accuracy of traffic prediction and promote the construction of ITS in cities. Most of the existing traffic datasets are collected on highways, and they are only one-way road data. There is little analysis of the impact of weather on traffic prediction, and more traffic auxiliary information is lacking at the same time. The use of such datasets for experiments can lead to inaccurate and unconvincing results, which is of little significance for the study of urban road prediction reference. In this paper, we are motivated to develop a new dataset for the evaluation of Metropolitan Traffic Prediction. Our dataset(XiAn Road Traffic) collected 308 urban road data and included two-way road data, weather data, driving angles, and congestion levels. XiAn Road Traffic can provide help for urban road state prediction and intelligent transportation city construction. We use the current more popular machine learning model for experiments. It is also proved by experiments that our dataset is more accurate and persuasive than the prediction results of other datasets.

The impact of intelligent transportation points system based on Elo rating on emergence of cooperation at Y intersection

The construction of intelligent transportation system is of great benefit to the efficiency, safety and fairness of urban residents’ travel. This paper focuses on a passing dilemma at Y intersection. An intelligent transportation points system (ITPS) based on Elo rating system is proposed to attempt to solve this dilemma. The drivers in the simulation system are given reinforcement learning ability based on Q-learning algorithm, by evaluating the benefits of each behavior. The conclusions are summarized as follows. For pure selfish drivers group, the application of ITPS has little impact on cooperation. For heterogeneous drivers group, the cooperation probability and passing efficiency of drivers can be improved by the regulation of the ITPS. Meantime, the fairness between drivers could be also maintained. It means that the application of ITPS can achieve the unity of fairness and efficiency. From a long-term perspective, the establishment of the ITPS will be a strong guarantee for the reciprocity of the travelers’ efficiency and fairness. Therefore, this study is conducive to the future construction of more perfect urban traffic intelligent system.