Development Of Intelligent Transportation Systems Research Articles

Traffic Sign Recognition Using Deep Learning

Abstract: Traffic sign recognition is a crucial component in advanced driver assistance systems and autonomous vehicles, enhancing road safety and overall transportation efficiency. Deep learning, specifically convolutional neural networks (CNNs), has emerged as a powerful tool for image based recognition tasks. The proposed deep learning-based traffic sign recognition system exhibits promising results, providing a foundation for the development of intelligent transportation systems. The trained model demonstrates remarkable accuracy in recognizing a wide range of traffic signs under different scenarios, including challenging lighting conditions and occlusions. The system's real-time performance is evaluated on both simulated and actual road scenarios, showcasing its feasibility for deployment in practical driving environments. The integration of such technology into vehicles holds great potential for enhancing road safety, reducing accidents, and contributing to the evolution of autonomous driving technology.

Precise positioning and prediction system for autonomous driving based on generative artificial intelligence

Self-driving systems collect vast amounts of data through a variety of sensors, including cameras, lidar, millimeter-wave radar, and more. This data needs to be processed in real time to identify obstacles such as roads, vehicles, pedestrians and make decisions accordingly. Therefore, this paper discusses the importance of accurate positioning and prediction system in automatic driving technology, and analyzes the performance of various positioning technologies in automatic driving applications.In addition, the paper explores the application potential of AI technology in autonomous driving and the prospect of combining advanced positioning and prediction systems with generative AI. Overall, this study highlights the importance of algorithm performance improvement and artificial intelligence technology in the development of autonomous driving technology, and provides new ideas and directions for the innovation and development of intelligent transportation systems in the future.

A graph-based approach for traffic prediction using similarity and causal relations between nodes

Accurate traffic prediction is crucial for the development of intelligent transportation systems (ITS) and various smart applications. To achieve this, effectively capturing the complex interplay between spatial and temporal dependencies across traffic nodes is essential. However, existing research often focuses solely on fixed spatial dependencies between neighboring nodes, neglecting the potential influence of distant nodes. This paper addresses these limitations by exploring two key types of relationships among traffic nodes. First, we examine indirect relationships based on similarity, where nodes exhibit similar traffic patterns irrespective of their physical proximity. Second, we investigate direct causal relationships, where traffic conditions at one node are directly influenced by other nodes. Based on these findings, we propose a novel approach named TPSC (Traffic Prediction using nodes Similarity and Causal relations). TPSC incorporates a classifier that utilizes the K-Prototype algorithm to group nodes based on their traffic similarity and nearby points of interest (POIs). Separate models are then trained for each cluster. Our model leverages a spatial module that employs graph convolutional network representation learning alongside transfer entropy to capture causal relationships and dynamic spatial dependencies. Additionally, a temporal module is introduced to capture periodic temporal dependencies across three components: recent patterns, daily patterns, and weekly patterns. Extensive experiments are conducted to evaluate proposed model on four large-scale traffic datasets for multiple traffic characteristics including speed, flow, and travel time. The experimental results demonstrate that TPSC surpasses the performance of the compared baselines, highlighting its superior predictive capabilities in traffic prediction.

Revolutionizing Traffic Management: Advanced Machine Learning Techniques for Accurate Traffic Flow Prediction

In modern urban¬¬¬¬¬ transportation systems, efficient traffic flow prediction is of paramount importance to optimize traffic management, reduce congestion, and improve the overall commuting experience. This research report examines the application of state-of-the-art machine learning algorithms to accurately predict traffic flow patterns. By leveraging historical traffic data, weather conditions, time of day, and various other relevant features, our proposed model exhibits significant predictive capabilities. We study the effectiveness of various machine learning techniques, such as neural networks, decision trees, and ensemble methods, in capturing the complex dynamics of traffic flows. Through extensive experiments and validation using real datasets, we demonstrate the superiority of our approach compared to traditional methods. Ultimately, this research will contribute to the further development of intelligent transportation systems, paving the way for more efficient and sustainable urban mobility solutions

Multi-Source Information Fusion Based DLaaS for Traffic Flow Prediction

Traffic flow prediction is the key to transportation safety and efficiency. The advance in machine learning and deep learning has promoted the development of intelligent transportation systems. For example, the emergence of Deep Learning as a Service (DLaaS) has benefitted researchers a lot in dealing with large scale dataset and complex deep learning algorithms. In traffic forecasting, despite the success of deep learning-based models, there are still shortcomings, such as inadequate use of temporal and spatial traffic information, and indirect modeling of dependencies in traffic data. To address these challenges, we learn the transportation network in the form of a graph, and use graph wavelet as a key component to extract well-positioned features from the graph based on the transportation network. Compared with graph convolution, graph wavelets are very flexible and do not need to specify adjacent regions in the topological graph structure for feature extraction. At the same time, we propose to combine the multi-information fusion traffic control and guidance collaborative neural network and the results obtained are better than the benchmark algorithms. The results by comparison with several baseline methods show that our proposed method can outperform all the baseline methods.

The application of deep learning in autonomous driving

Autonomous driving technology is currently a globally prominent subject, with its relevance and impact readily apparent. Leveraging advanced sensors, sophisticated algorithms, and state-of-the-art computer vision techniques, autonomous vehicles can autonomously navigate, mitigate traffic accidents, and alleviate urban congestion. Furthermore, this technology is poised to accelerate innovation within the automotive sector, drive industrial advancement, and enhance people's convenience and safety in their travel experiences. The importance of autonomous driving technology is not only reflected in its own advantages, but also in its ability to lead the development direction of intelligent transportation in the future, helping to promote the development of intelligent transportation systems, realize the intelligent interconnection between vehicles and vehicles, vehicles and road infrastructure, and further enhance the safety and convenience of traffic travel. Therefore, autonomous driving technology is a significant innovation that will bring a better and more convenient future for mankind. In this study, a method based on sensor internal and external parameter calibration transformation matrix, road target detection algorithm, automatic vehicle detection method, pedestrian intention prediction technology and automatic pedestrian recognition system are analyzed, which are applied to object detection and obstacle avoidance. This article provides a good overview of the field of autonomous driving.

A Dual-Stage Attention-Based Vehicle Speed Prediction Model Considering Driver Heterogeneity with Fuel Consumption and Emissions Analysis

With the development of intelligent transportation systems (ITSs), personalized driving systems are receiving more and more attention, and the development of advanced systems cannot be separated from the practical exploration of drivers’ heterogeneous driving behaviors. An important foundation for subsequent driver-targeted research is how to mine the key influencing factors that characterize drivers through real driving data and how to appropriately classify drivers as a whole. This study took heterogeneous drivers as the object, based on a dual-stage attention-based vehicle speed prediction model, and carried out research on the speed prediction of traffic flow and the impact of fuel consumption and emissions in the car-following state considering the heterogeneity of drivers. Specifically, first, Spearman’s correlation analysis and K-means clustering were used to classify different types of drivers. Then, speed predictions for different types of drivers were separated via the dual-stage attention-based encoder–decoder (DAED) model and the prediction results between models and drivers were compared. Finally, the heterogeneous drivers’ fuel consumption and emissions were further analyzed via the VT-micro model. The results show that the proposed speed prediction model can effectively discriminate the influences of heterogeneous drivers on the prediction model, and the aggressive type presents the best effect. In addition, from the experiments on traffic fuel consumption and emissions, it can be concluded that the timid driver is the friendliest to the environment. By researching individual drivers’ driving characteristics, this study may help sustainable development in traffic management.

Vehicle speed prediction using a convolutional neural network combined with a gated recurrent unit with attention

Vehicle speed prediction can facilitate many applications, such as optimizing vehicle propulsion systems and designing advanced driver assistance control systems. In a complex and variable traffic environment, many dynamic factors affect vehicle speed and make it difficult to predict accurately. The development of intelligent transportation systems and machine learning methods makes it possible to predict short-term vehicle speed accurately. A novel vehicle speed prediction model is proposed in this paper to improve prediction accuracy based on a deep learning method. A practical temporal and channel attention module (TCAM) is designed for convolutional neural networks (CNNs) to strengthen meaningful information and reduce the amount of unnecessary information. A gated recurrent unit (GRU) network with an attention mechanism is constructed to explore significant hidden relationships among time-series data with its memory function. These two subprediction models are fused to enhance the performance of vehicle speed prediction. Simulation experiments using IPG Carmaker software validate that the proposed model provides better predictive accuracy than traditional and existing vehicle speed prediction methods based on deep learning.

A survey of sustainable development of intelligent transportation system based on urban travel demand

<p>This paper provides a comprehensive exploration of urban travel demand forecasting and its implications for intelligent transportation systems, emphasizing the crucial role of intelligent transportation systems in promoting sustainable urban development. With the increasing challenges posed by traffic congestion, environmental pollution, and diverse travel needs, accurate prediction of urban travel demand becomes essential for optimizing transportation systems, fostering sustainable travel methods, and creating opportunities for business development. However, achieving this goal involves overcoming challenges such as data collection and processing, privacy protection, and information security. To address these challenges, the paper proposes a set of strategic measures, including advancing intelligent transportation technology, integrating intelligent transportation systems with urban planning, enforcing policy guidance and market supervision, promoting sustainable travel methods, and adopting intelligent transportation technology and green energy solutions. Additionally, the study highlights the role of intelligent transportation systems in mitigating traffic congestion and environmental impact through intelligent road condition monitoring, prediction, and traffic optimization. Looking ahead, the paper foresees an increasingly pivotal role for intelligent transportation systems in the future, leveraging advancements in deep learning and information technology to more accurately collect and analyze urban travel-related data for better predictive modeling. By combining data analysis, public transportation promotion, shared travel modes, intelligent transportation technology, and green energy adoption, cities can build more efficient, environmentally friendly transportation systems, enhancing residents’ travel experiences while reducing congestion and pollution to promote sustainable urban development. Furthermore, the study anticipates that intelligent transportation systems will be intricately integrated with urban public services and management, facilitating efficient and coordinated urban functions. Ultimately, the paper envisions intelligent transportation systems playing a vital role in supporting urban traffic management and enhancing the overall well-being of urban construction and residents’ lives. In conclusion, this research not only enhances our understanding of urban travel demand forecasting and the evolving landscape of intelligent transportation systems but also provides valuable insights for future research and practical applications in related fields. The study encourages greater attention and investment from scholars and practitioners in the research and practice of intelligent transportation systems to collectively advance the progress of urban transportation and sustainable development.<strong></strong></p>

Predicting Autonomous Driving Behavior through Human Factor Considerations in Safety-Critical Events

This paper investigates the ability of autonomous driving systems to predict outcomes by considering human factors like gender, age, and driving experience, particularly in the context of safety-critical events. The primary objective is to equip autonomous vehicles with the capacity to make plausible deductions, handle conflicting data, and adjust their responses in real-time during safety-critical situations. A foundational dataset, which encompasses various driving scenarios such as lane changes, merging, and navigating complex intersections, is employed to enable vehicles to exhibit appropriate behavior and make sound decisions in critical safety events. The deep learning model incorporates personalized cognitive agents for each driver, considering their distinct preferences, characteristics, and requirements. This personalized approach aims to enhance the safety and efficiency of autonomous driving, contributing to the ongoing development of intelligent transportation systems. The efforts made contribute to advancements in safety, efficiency, and overall performance within autonomous driving systems. To describe the causal relationship between external factors like weather conditions and human factors, and safety-critical driver behaviors, various data mining techniques can be applied. One commonly used method is regression analysis. Additionally, correlation analysis is employed to reveal relationships between different factors, helping to identify the strength and direction of their impact on safety-critical driver behavior.

May the privacy be with us: Correlated differential privacy in location data for ITS

With the development of Intelligent Transportation Systems (ITS), a vast amount of location data is being generated from various IoT devices equipped with location positioning sensors. Preserving the privacy of location data release is a critical concern, as the publication of aggregated data often reveals private information about the users. Differential Privacy (DP) has recently emerged as a robust framework to guarantee privacy in this context. However, conventional DP mechanisms commonly make no assumption about the distribution of the input data, which could lead to unexpected privacy leakage if the data are correlated. In this paper, we investigate the complex simultaneous impact of user correlation, spatial–temporal correlation and prior knowledge of an adversary on the privacy leakage of a DP mechanism, which has not been addressed in prior work. We derive several closed-form expressions that demonstrate and quantify the privacy leakage under correlated location data, followed by the design of efficient algorithms to compute such privacy leakage. Then, we propose a Δ-CDP (Correlated Differential Privacy) to provide a formal privacy guarantee against the additional privacy leakage incurred by these factors. Extensive comparisons, theoretical analysis, and experimental simulations are presented to validate the correctness and efficiency of the proposed work.

Dynamic multi-granularity spatial-temporal graph attention network for traffic forecasting

Traffic forecasting, as the cornerstone of the development of intelligent transportation systems, plays a crucial role in facilitating accurate control and management of urban traffic. By treating sensors as nodes in a road network, recent research on modeling complex spatial-temporal graph structures has achieved notable advancements in traffic forecasting. However, limited by the increasing number of sensors and recorded data points, most of the recent studies on spatial-temporal graph neural network (STGNN) research concentrate on aggregating short-term (e.g. recent one-hour) traffic history to predict future data. Furthermore, almost all previous STGNNs neglect to incorporate the cyclical patterns that appear in the traffic historical data. For example, the cyclical patterns of traffic on the same day or hour of each week can help improve the accuracy of future traffic predictions. In this paper, we propose a novel Dynamic Multi-Granularity Spatial-Temporal Graph Attention Network (DmgSTGAT) framework for traffic forecasting, which leverages multi-granularity spatial-temporal correlations across different time-scales and variables to efficiently consider cyclical patterns in traffic data. We also design effective temporal encoding and transformer encoding layers to produce meaningful multi-granularity sensor-level, day-level, hour-level, and point-level representations. The multi-granularity spatial-temporal graph attention network can use the produced representations to extract useful but sparsely distributed patterns accurately, which also avoids the influence of extra noise from the long-term history. Experimental results on four real-world traffic datasets show that DmgSTGAT can achieve state-of-the-art performance with the help of multi-granularity cyclical patterns compared with various recent baselines.

Highly Discriminative Driver Distraction Detection Method Based on Swin Transformer

Driver distraction detection not only helps to improve road safety and prevent traffic accidents, but also promotes the development of intelligent transportation systems, which is of great significance for creating a safer and more efficient transportation environment. Since deep learning algorithms have very strong feature learning abilities, more and more deep learning-based driver distraction detection methods have emerged in recent years. However, the majority of existing deep learning-based methods are optimized only through the constraint of classification loss, making it difficult to obtain features with high discrimination, so the performance of these methods is very limited. In this paper, to improve the discrimination between features of different classes of samples, we propose a high-discrimination feature learning strategy and design a driver distraction detection model based on Swin Transformer and the highly discriminative feature learning strategy (ST-HDFL). Firstly, the features of input samples are extracted through the powerful feature learning ability of Swin Transformer. Then, the intra-class distance of samples of the same class in the feature space is reduced through the constraint of sample center distance loss (SC loss), and the inter-class distance of samples of different classes is increased through the center vector shift strategy, which can greatly improve the discrimination of different class samples in the feature space. Finally, we have conducted extensive experiments on two publicly available datasets, AUC-DD and State-Farm, to demonstrate the effectiveness of the proposed method. The experimental results show that our method can achieve better performance than many state-of-the-art methods, such as Drive-Net, MobileVGG, Vanilla CNN, and so on.

Edge-enhanced Graph Attention Network for driving decision-making of autonomous vehicles via Deep Reinforcement Learning

Despite the rapid advancement in the field of autonomous driving vehicles, developing a safe and sensible decision-making system remains a challenging problem. The driving decision-making module is one of the most essential sections of the entire autonomous driving system, and the decision generated from it can significantly impinge the lives and property of passengers. Complicated interactions among traffic participants have the most profound impact on the decision-making process, yet the interactions are often simplified or overlooked due to their complexity and implicit nature. To address this issue, this work proposes an Edge-Enhanced Graph Attention Reinforcement Learning (EGARL) framework that aims to make rational driving decisions by comprehensively modeling the interactions among agents. EGARL comprises three core components: a graphical representation of the traffic scenario that covers both topological and interactive information; an Edge-enhanced Graph Attention Network (E-GAT) that utilizes the graphical representation to extract interactive features by comprehensively considering nodes and edges of the graph; and a deep reinforcement learning method that generates driving decisions based on the current state and features extracted from E-GAT. Experimental results demonstrate the satisfying performance of EGARL. Our proposed framework can contribute to the development of intelligent transportation systems, enhancing the safety and efficiency of driving.

Parallel Driving with Big Models and Foundation Intelligence in Cyber-Physical-Social Spaces.

Recent years have witnessed numerous technical breakthroughs in connected and autonomous vehicles (CAVs). On the one hand, these breakthroughs have significantly advanced the development of intelligent transportation systems (ITSs); on the other hand, these new traffic participants introduce more complex and uncertain elements to ITSs from the social space. Digital twins (DTs) provide real-time, data-driven, precise modeling for constructing the digital mapping of physical-world ITSs. Meanwhile, the metaverse integrates emerging technologies such as virtual reality/mixed reality, artificial intelligence, and DTs to model and explore how to realize improved sustainability, increased efficiency, and enhanced safety. More recently, as a leading effort toward general artificial intelligence, the concept of foundation model was proposed and has achieved significant success, showing great potential to lay the cornerstone for diverse artificial intelligence applications across different domains. In this article, we explore the big models embodied foundation intelligence for parallel driving in cyber-physical-social spaces, which integrate metaverse and DTs to construct a parallel training space for CAVs, and present a comprehensive elucidation of the crucial characteristics and operational mechanisms. Beyond providing the infrastructure and foundation intelligence of big models for parallel driving, this article also discusses future trends and potential research directions, and the "6S" goals of parallel driving.

Introducing fine grained energy consumption variables into a public passenger transport simulation in SUMO

Improving energy efficiency in public passenger transport is key to achieving sustainability goals. In many developing countries, public passenger transport relies heavily on fossil fuels, which necessitates a strong focus on reducing emissions from energy consumption. Surprisingly, few studies have addressed this issue in the context of daily operations, with most research focusing on operational and infrastructural changes. This paper aims to fill this gap by introducing detailed energy consumption variables into a public transport simulation model using SUMO, a tool known for its seamless integration with Python. The development of two Python scripts underpins this endeavour. The first script facilitates the automatic generation of scenarios, allowing the manipulation of parameters such as station spacing, line length, passenger capacity and waiting times, among others. The second script is dedicated to estimating energy consumption for each scenario. Together, these tools allow us to calculate average energy consumption for different scenarios and modes of public transport. As a result, they provide valuable insights for the formulation of public policies aimed at saving energy in different public transport environments and lay the foundation for the integration and development of intelligent transport systems and simulation-based digital twins.

Privacy-Preserving Distributed Transfer Learning and its Application in Intelligent Transportation

With the rapid development of intelligent transportation systems (ITS), more and more intelligent applications for ITS have received widespread attention, such as the vehicle detection, inference of typical routes, and traffic forecasting. In these applications, deep learning is widely used as a key artificial intelligence technology. However, most ITS providers fail to collect enough labeled traffic data for model training. As a complement to deep learning, transfer learning is an effective way to solve the scarcity of labeled data, which can transfer knowledge from labeled datasets to unlabeled datasets, thus improving the accuracy of prediction and classification. Nevertheless, when the labeled dataset and the unlabeled dataset are held by different entities, it is still unrealistic for two mutually distrustful entities to cooperate in transfer learning regarding data security and privacy preservation. Although some existing works provide privacy-preserving transfer learning methods, such methods fail to apply to traffic data with high sample dimensions due to their high computational cost and round complexity. To address this problem, we design an efficient privacy-preserving distributed transfer learning protocol, which is appropriate for traffic data. Compared to existing works, our protocol addresses the privacy-preserving problem of transfer learning for traffic data with high sample dimensions. In addition, our protocol has fewer interaction rounds and can be proved in the semi-honest model. Finally, we validate the effectiveness, efficiency and security of the proposed protocol via experiments. Furthermore, we show the application of the proposed protocol in intelligent transportation systems.

Detecting the Background-Similar Objects in Complex Transportation Scenes

With the development of intelligent transportation systems, most human objects can be accurately detected in normal road scenes. However, the detection accuracy usually decreases sharply when the pedestrians are merged into the background with very similar colors or textures. In this paper, a camouflaged object detection method is proposed to detect the pedestrians or vehicles from the highly similar background. Specifically, we design a guide-learning-based multi-scale detection network (GLNet) to distinguish the weak semantic distinction between the pedestrian and its similar background, and output an accurate segmentation map to the autonomous driving system. The proposed GLNet mainly consists of a backbone network for basic feature extraction, a guide-learning module (GLM) to generate the principal prediction map, and a multi-scale feature enhancement module (MFEM) for prediction map refinement. Based on the guide learning and coarse-to-fine strategy, the final prediction map can be obtained with the proposed GLNet which precisely describes the position and contour information of the pedestrians or vehicles. Extensive experiments on four benchmark datasets, e.g., CHAMELEON, CAMO, COD10K, and NC4K, demonstrate the superiority of the proposed GLNet compared with several existing state-of-the-art methods.

Variable optimization domain-based cooperative energy management strategy for connected plug-in hybrid electric vehicles

The design of energy management strategy (EMS) that can be applied in real-time with nearly optimal fuel economy for connected plug-in hybrid electric vehicles (C-PHEVs) is an urgent need at present, especially in the context where the benefits of rapid development of intelligent transportation system are increasingly evident. Equivalent consumption minimization strategy (ECMS) is able to achieve the desired performance, on the premise that the equivalent factor (EF) is adjusted reasonably. To achieve this goal, a variable optimization domain-based cooperative EMS for C-PHEVs is proposed in this paper. First, an offline sub-cycle division method is designed, which is effectively utilized to construct a fitting function to output reference EF based on the latest driving information. Second, the theoretical relationship between EF and operating efficiency of the driving components is explored, and the variable optimization domain of EF is designed to avoid inefficient operation of engine. Third, the EF optimization is then simplified into a quadratic problem within the designed domain, which is rapidly solved online with the golden section search algorithm. Finally, the comparison work is conducted under two real-world driving cycles. The results exhibit that the proposed strategy improves the fuel economy of C-PHEV by 6.440 % and 7.936 % over that using the conventional adaptive ECMS (CA-ECMS), respectively. The average engine fuel consumption rates of the proposed strategy are significantly reduced compared with that of CA-ECMS. Moreover, the effectiveness of the proposed strategy is verified on the experiment platform, demonstrating its application prospects.

Multi-level Graph Memory Network Cluster Convolutional Recurrent Network for traffic forecasting

Traffic forecasting plays a vital role in the management of urban road networks and the development of intelligent transportation systems. To effectively capture spatial and temporal dependencies within traffic data, Graph Neural Networks (GNNs) emerge by combining recurrent neural networks and dynamic graph learning. However, traditional GNNs face challenges in efficiently memorizing patterns at different levels of these dependencies, including long-term shared patterns and short-term specific patterns. We propose a traffic forecasting model, the Multi-level Graph Memory Network Cluster Convolutional Recurrent Network (MMNCCRN). The MMNCCRN consists of four modules: Encoder Module (EM), Attention Module (AM), Memory Network Cluster Module (MNCM), and Decoder Module (DM). To enhance the model’s performance, AM incorporates a concise yet efficient attention mechanism that augments important information in the output of EM. This alleviates the pressure on MNCM to identify patterns at different levels. Meanwhile, in MNCM, we extensively leverage memory networks and introduce the concept of clustering. By storing and memorizing patterns implicit in spatial and temporal dependencies, MNCM assists the model in learning underlying graph structures and discovering new hidden patterns. Experimental results show that our model outperforms others in most metrics on four datasets.