Intelligent Transportation Applications Research Articles

Live Intersection Data Acquisition for Traffic Simulators (LIDATS).

Real-time traffic signal acquisition and network transmission are essential components of intelligent transportation systems, facilitating real-time traffic monitoring, management, and analysis in urban environments. In this paper, we introduce a comprehensive system that incorporates live traffic signal acquisition, real-time data processing, and secure network transmission through a combination of hardware and software modules, called LIDATS. LIDATS stands for Live Intersection Data Acquisition for Traffic Simulators. The design and implementation of our system are detailed, encompassing signal acquisition hardware as well as a software platform that is used specifically for real-time data processing. The performance evaluation of our system was conducted by simulation in the lab, demonstrating its capability to reliably capture and transmit data in real time, and to effectively extract the relevant information from noisy and complex traffic data. Supporting a variety of intelligent transportation applications, such as real-time traffic flow management, intelligent traffic signal control, and predictive traffic analysis, our system enables remote data analysis and decisionmaking, providing valuable insights and enhancing the traffic efficiency while reducing the congestion in urban environments.

Disentanglement-Guided Spatial-Temporal Graph Neural Network for Metro Flow Forecasting (Student Abstract)

In recent intelligent transportation applications, metro flow forecasting has received much attention from researchers. Most prior arts endeavor to explore spatial or temporal dependencies while ignoring the key characteristic patterns underlying historical flows, e.g., trend and periodicity. Although the multiple granularity distillations or spatial dependency correlation can promote the flow estimation. However, the potential noise and spatial dynamics are under-explored. To this end, we propose a novel Disentanglement-Guided Spatial-Temporal Graph Neural Network or DGST to address the above concerns. It contains a Disentanglement Pre-training procedure for characteristic pattern disentanglement learning, a Characteristic Pattern Prediction for different future characteristic explorations, and a Spatial-Temporal Correlation for spatial-temporal dynamic learning. Experiments on a real-world dataset demonstrate the superiority of our DGST.

A high-performance conical-neck helmholtz resonator-based piezoelectric self-powered system for urban transportation

As urbanization accelerates, the issue of traffic noise escalates. Efficiently harnessing this prevalent acoustic energy and facilitating its collection and conversion has emerged as a notable challenge in contemporary research. This paper introduces a piezoelectric self-powered system anchored on a Conical-Neck Helmholtz Resonator-Based Piezoelectric Self-Powered System (CNHR-PSS) which places the piezoelectric device inside a Conical-Neck Helmholtz resonator. This system amalgamates acoustic energy harvesting, traffic noise abatement, and traffic condition discernment. It combines by two parts, including a Piezoelectric Self-Powered Node (PSN) and a machine learning algorithm. The PSN, employing the Conical Neck Helmholtz Resonator and piezoelectric module, seizes noise and transmutes it into electrical energy, showcasing robust scalability. Multiple PSNs coalesce to form a sound barrier for traffic noise mitigation. Concurrently, the voltage signals emanated by the PSN also encapsulate traffic status information. The algorithm extracts feature from the output signal and employs machine learning to decipher traffic conditions. Simulative and theoretical analyses affirm that the system can efficaciously harvest acoustic energy from urban traffic noise and attenuate noise, with a pinnacle output power of 0.52mW and an average noise reduction of 13.16 %. The recognition accuracy of traffic conditions via SVM attained 100 %. The investigative outcomes underscore the exemplary performance of this self-powered system, rendering it a viable solution for applications in traffic noise mitigation and intelligent transportation.

Multibeam Cylindrical Conformal Array in the Presence of Enhanced Mutual Coupling

The limitations of conventional sensors have made array antennas increasingly crucial for gathering information and communication applications in intelligent transportation and communication systems. Compact cylindrical arrays are particularly favored for their ability to achieve azimuth angle scanning. However, the substantial mutual coupling effect between the elements on curved surfaces and its implication for these arrays remain unclear, which is a key factor to consider when such arrays are used for multibeam applications. This study investigates the effect of mutual coupling in a dual-slant-polarized cylindrical array. The results showed that mutual coupling is predominantly observed among the closely located elements, and it is essential for achieving an ultra-wide bandwidth. The study also analyzes the impact of mutual coupling on the scan impedance and radiation characteristics for multibeam applications and reveals that these arrays exhibit robust multibeam capability, hence having great potential for use in sensing and communication applications.

Graph autoencoder with mirror temporal convolutional networks for traffic anomaly detection

Traffic time series anomaly detection has been intensively studied for years because of its potential applications in intelligent transportation. However, classical traffic anomaly detection methods often overlook the evolving dynamic associations between road network nodes, which leads to challenges in capturing the long-term temporal correlations, spatial characteristics, and abnormal node behaviors in datasets with high periodicity and trends, such as morning peak travel periods. In this paper, we propose a mirror temporal graph autoencoder (MTGAE) framework to explore anomalies and capture unseen nodes and the spatiotemporal correlation between nodes in the traffic network. Specifically, we propose the mirror temporal convolutional module to enhance feature extraction capabilities and capture hidden node-to-node features in the traffic network. Morever, we propose the graph convolutional gate recurrent unit cell (GCGRU CELL) module. This module uses Gaussian kernel functions to map data into a high-dimensional space, and enables the identification of anomalous information and potential anomalies within the complex interdependencies of the traffic network, based on prior knowledge and input data. We compared our work with several other advanced deep-learning anomaly detection models. Experimental results on the NYC dataset illustrate that our model works best compared to other models for traffic anomaly detection.

DLOAM: Real-time and Robust LiDAR SLAM System Based on CNN in Dynamic Urban Environments

Dynamic object detection, state estimation, and map-building are crucial for autonomous robot systems and intelligent transportation applications in urban scenarios. Most current LiDAR Simultaneous Localization and Mapping (SLAM) systems operate on the assumption that the observed environment is static. However, the overall accuracy and robustness of a SLAM system can be compromised by dynamic objects in the environment. Aiming at the problem of inaccurate odometry estimation and wrong mapping caused by the existing LiDAR SLAM method which cannot detect the dynamic objects, we study the SLAM problem of robots and unmanned vehicles equipped with LiDAR traveling in the dynamic urban scenes. We propose a fast LiDAR-only model-free dynamic objects detection method, which uses the spatial and temporal information of point cloud through a convolutional neural network (CNN), and the detection accuracy is improved by 35 use spatial information. We further integrate it into a state-of-the-art LiDAR SLAM framework to improve the SLAM performance. Firstly, the range image constructed by LiDAR point cloud is used for ground extraction and non-ground point clustering. Then, the motion of objects in the scene is estimated by the difference between adjacent frames, and the segmented objects are further divided into dynamic objects and static objects by their motion features. After that, the stable feature points are extracted from the static objects. Finally, the pose transformation of adjacent frames is solved by matching feature point pairs. We evaluated the accuracy and robustness of our system on datasets with different challenging dynamic environments, and the results show our system has significant improvements in accuracy and robustness of odometry and mapping, while still maintain real-time performance, which is sufficient for autonomous robot systems and intelligent transportation applications in urban scenarios.

Survey of intelligent transportation applications based on cloud computing technology

China is a large transportation country, and in addition to the huge demand for public transportation such as rail transit, private cars on city streets and highways are also a major force, followed by safety issues, and cloud computing plays an important role in today's society, and in some areas where transportation wisdom has been applied, transportation wisdom has become the general trend. As a result, this article will examine and describe the use of cloud computing in urban rail transit information security issues as well as urban and highway traffic safety early warning.

Enhancing Road Safety with Convolutional Neural Network Traffic Sign Classification

Recent computer vision and deep learning breakthroughs have improved road safety by automatically classifying traffic signs. This research uses CNNs to classify traffic signs to improve road safety. Autonomous vehicles and intelligent driver assistance systems require accurate traffic sign detection and classification. Using deep learning, we created a CNN model that can recognize and classify road traffic signs. This research uses a massive dataset of labeled traffic sign photos for training and validation. These CNN algorithms evaluate images and produce real-time predictions to assist drivers and driverless cars in understanding traffic signs. Advanced driver assistance systems, navigation systems, and driverless vehicles can use this technology to give drivers more precise information, improving their decision-making and road safety. Researcher optimized CNN model design, training, and evaluation metrics during development. The model was rigorously tested and validated for robustness and classification accuracy. The research also solves real-world driving obstacles like illumination, weather, and traffic signal obstructions. This research shows deep learning-based traffic sign classification can dramatically improve road safety. This technology can prevent accidents and enhance traffic management by accurately recognizing and interpreting traffic signs. It is also a potential step toward a safer, more efficient transportation system with several automotive and intelligent transportation applications. Road safety is a global issue, and CNN-based traffic sign classification can reduce accidents and improve driving. On filter 3, Convolutional Neural Network training accuracy reached 98.9%, while validation accuracy reached 88.23%.

Multi-objectives reinforcement federated learning blockchain enabled Internet of things and Fog-Cloud infrastructure for transport data

For the past decade, there has been a significant increase in customer usage of public transport applications in smart cities. These applications rely on various services, such as communication and computation, provided by additional nodes within the smart city environment. However, these services are delivered by a diverse range of cloud computing-based servers that are widely spread and heterogeneous, leading to cybersecurity becoming a crucial challenge among these servers. Numerous machine-learning approaches have been proposed in the literature to address the cybersecurity challenges in heterogeneous transport applications within smart cities. However, the centralized security and scheduling strategies suggested so far have yet to produce optimal results for transport applications. This work aims to present a secure decentralized infrastructure for transporting data in fog cloud networks. This paper introduces Multi-Objectives Reinforcement Federated Learning Blockchain (MORFLB) for Transport Infrastructure. MORFLB aims to minimize processing and transfer delays while maximizing long-term rewards by identifying known and unknown attacks on remote sensing data in-vehicle applications. MORFLB incorporates multi-agent policies, proof-of-work hashing validation, and decentralized deep neural network training to achieve minimal processing and transfer delays. It comprises vehicle applications, decentralized fog, and cloud nodes based on blockchain reinforcement federated learning, which improves rewards through trial and error. The study formulates a combinatorial problem that minimizes and maximizes various factors for vehicle applications. The experimental results demonstrate that MORFLB effectively reduces processing and transfer delays while maximizing rewards compared to existing studies. It provides a promising solution to address the cybersecurity challenges in intelligent transport applications within smart cities. In conclusion, this paper presents MORFLB, a combination of different schemes that ensure the execution of transport data under their constraints and achieve optimal results with the suggested decentralized infrastructure based on blockchain technology.

MDP-based connectivity and availability models for Internet of Vehicles

Smart and connected vehicles have enabled a series of services and applications in intelligent transportation. Such vehicles introduce a new paradigm that supports the Internet of Vehicles, where content and resource sharing happens dynamically through Vehicle to Everything (V2X) communication. Communication technologies, such as vehicular and cellular networks, are expected to reliably support connections and mobile computing. However, due to challenges related to highly dynamic topologies in urban environments, the feasibility and reliability of vehicular communications in real urban environments have been discussed in recent works. In light of solving the issues that originated from unstable connectivity, we propose an MDP-based connectivity model which estimates link stability for data delivery. Moreover, from analyses, it was evident that the predictability of individual vehicle connectivity directly depends on the repeatability of its connection patterns. Consequently, we propose an availability model which identifies the suitability of connectivity status to determine the vehicles that provide high availability conditioned on their mobility.

Monitoring and analyzing as a service (MAaaS) through cloud edge based on intelligent transportation applications

Monitoring and analyzing as a service (MAaaS) through cloud edge based on intelligent transportation applications

Protecting Data and Privacy: Cloud-based Solutions for Intelligent Transportation Applications

The interaction between transportation networks and intelligent transportation systems has been revolutionized by cloud computing. However, the reliance on cloud-based solutions raises security and privacy concerns. This article examines the challenges of safeguarding data and privacy in intelligent transportation applications and emphasizes the potential of cloud-based solutions to resolve these issues. Organizations can protect sensitive data and user privacy by employing encryption, access controls, threat detection mechanisms, and privacy protection measures. Adopting these cloud-based solutions will encourage the extensive adoption of intelligent transportation applications while infusing users and stakeholders with confidence.

Digitalization of Traffic Scenes in Support of Intelligent Transportation Applications

Digitalization of real-world traffic scenes is a fundamental task in development of digital twins of road transportation. However, the existing digitalization approaches are either expensive in equipment costs or inapplicable to collect granular level data of traffic scenes. This study proposed a vision-based method for real-time digitalization of traffic scenes through modeling and merging the road infrastructure (static components) and road users (dynamic components) progressively. Specifically, the former is reconstructed by leveraging unmanned aerial vehicles (UAVs) and structure from motion; and the latter is digitized via using roadside surveillance videos and a new reconstruction process through applying deep learning and view geometry. Last, the digital model of the traffic scene is built by merging the digital models of static and dynamic components. A field experiment was performed to evaluate the performance of the proposed method. The results showed that the traffic scene can be successfully digitalized by the proposed method with promising accuracy, thus signifying the method’s potential for the development of the digital twins of road transportation in support of intelligent transportation applications.

Research on an Adaptive Method for the Angle Calibration of Roadside LiDAR Point Clouds.

Light Detection and Ranging (LiDAR), a laser-based technology for environmental perception, finds extensive applications in intelligent transportation. Deployed on roadsides, it provides real-time global traffic data, supporting road safety and research. To overcome accuracy issues arising from sensor misalignment and to facilitate multi-sensor fusion, this paper proposes an adaptive calibration method. The method defines an ideal coordinate system with the road's forward direction as the X-axis and the intersection line between the vertical plane of the X-axis and the road surface plane as the Y-axis. This method utilizes the Kalman filter (KF) for trajectory smoothing and employs the random sample consensus (RANSAC) algorithm for ground fitting, obtaining the projection of the ideal coordinate system within the LiDAR system coordinate system. By comparing the two coordinate systems and calculating Euler angles, the point cloud is angle-calibrated using rotation matrices. Based on measured data from roadside LiDAR, this paper validates the calibration method. The experimental results demonstrate that the proposed method achieves high precision, with calculated Euler angle errors consistently below 1.7%.

Highly accurate map construction and deep Q-network for autonomous driving and smart transportation

With the advancement of artificial intelligence and positioning technologies, high precision maps are crucial for autonomous driving and intelligent transportation. Our paper proposes a lucid structure for intelligent high precision map data, examining the role of each data layer in autonomous driving. Leveraging a centralized training and distributed execution reinforcement learning framework, our approach achieves an average deviation of 0.1023 m, 0.0200 m, and 0.0560 m in x, y, and z directions, respectively, and a 0.5191° average deviation in the heading angle. Results demonstrate the effectiveness and accuracy of our approach, confirming its potential in autonomous driving and intelligent transportation applications.

A brief survey on cooperative intelligent transportation systems and applications

Cooperative Intelligent Transport Systems (C-ITS) have emerged to provide a range of intel-ligent transport services that optimize traffic management, improve the travel experience of road users, increase road safety and security, and reduce the negative environmental impacts of transport. C-ITS, which aim to ensure that intelligent transport services function effec-tively and efficiently, communicate and exchange data with vehicles, road users, traffic con-trol centers, and road infrastructure as well. In this study, an overview of C-ITS related ac-tivities in the world and in Türkiye are discussed. C-ITS studies in literature and the objec-tives and benefits of C-ITS, its stakeholders, its relationship with ITS, its components and services are examined. After summarizing C-ITS studies in the world, policies and strategies in Europe, USA and Asian countries, and the current situation in Türkiye is provided. In addition, since there are limited studies on C-ITS in Türkiye, where ITS is still in its devel-opment stage, it is aimed to contribute to the literature by presenting recommendations for Türkiye to support the dissemination of C-ITS.

Knowledge Expansion and Consolidation for Continual Traffic Prediction With Expanding Graphs

Accurate traffic prediction plays a vital role in intelligent transport managements and applications. However, in the vast majority of existing works, the focus is mainly on modeling spatiotemporal correlations in static traffic networks. Thus, the continuous expansion and evolution of traffic networks are ignored. In this work, we study the problem of traffic prediction with expanding road network structures under the continual learning paradigm. Considering the model prediction performance, efficiency, and data accessibility, a SpatioTemporal Knowledge Expansion and Consolidation (STKEC) framework is proposed. This framework contains an influence-based knowledge expansion strategy to help the spatiotemporal learning model integrate new spatiotemporal traffic patterns and a memory-augmented knowledge consolidation mechanism to preserve the learned spatiotemporal patterns without accessing the data in previous graphs. Extensive experiments are conducted on a large-scale dataset and verify the superior performance of STKEC in continual traffic prediction.

6G Connected Vehicle Framework to Support Intelligent Road Maintenance Using Deep Learning Data Fusion

The growth of IoT, edge and mobile Artificial Intelligence (AI) is supporting urban authorities exploit the wealth of information collected by Connected and Autonomous Vehicles (CAV), to drive the development of transformative intelligent transport applications for addressing smart city challenges. A critical challenge is timely and efficient road infrastructure maintenance. This paper proposes an intelligent hierarchical framework for road infrastructure maintenance that exploits the latest developments in 6G communication technologies, deep learning techniques, and mobile edge AI training approaches. The proposed framework abides with the stringent requirements of training efficient machine learning applications for CAV, and is able to exploit the vast numbers of CAVs forecasted to be present on future road networks. At the core of our framework is a novel Convolution Neural Networks (CNN) model which fuses imagery and sensory data to perform pothole detection. Experiments show the proposed model can achieve state of the art performance in comparison to existing approaches while being simple, cost-effective and computationally efficient to deploy. The proposed system can form part of a federated learning framework for facilitating large scale real-time road surface condition monitoring and support adaptive resource allocation for road infrastructure maintenance.

Fault-Tolerant Cooperative Positioning Based on Hybrid Robust Gaussian Belief Propagation

This paper proposes a hybrid robust Gaussian belief propagation (HRGBP) as a fault-tolerant cooperative positioning (CP) system that can be used to support cooperative intelligent transportation applications. For fault-tolerant state estimation, it is well known that fault detection and exclusion (FDE) based methods and Huber’s M-estimation based methods have their own drawbacks when facing different forms of observation outliers, or faults. To solve this problem, our proposed HRGBP uses an interactive multiple model (IMM) framework to fuse these two strategies, which combines the advantages of both methods without their drawbacks. HRGBP can fully exploit the message passing process to mitigate the biased estimates, which further improves the system’s fault-tolerant robustness. HRGBP can be further adapted to fuse more fault-tolerant strategies to improve the robustness of the CP system, and be extended to other factor graph-based methods. Here, we evaluate HRGBP for observations from visual landmark range and bearing, neighboring vehicle range and bearing, and odometer. Our evaluations show that HRGBP outperforms other state-of-the-art CP methods.

$\mathcal {R}$-Tracing: Consortium Blockchain-Based Vehicle Reputation Management for Resistance to Malicious Attacks and Selfish Behaviors

Empowered by 5G communication technology, high-speed information exchange can be realized on the Internet of Vehicles (IoV) for future intelligent transportation applications. Since most applications require vehicles to report perceived information to nearby base stations, how to defend against malicious attacks and selfish behaviors of vehicles in reporting activities has become an essential security issue. Some researchers have attempted to encourage vehicles to actively report truthful information by establishing reputations for them, but these efforts have some shortcomings. In model design, they neither verify the basis and process of reputation evaluation nor pay attention to the diversity and intelligence of vehicle behaviors. In system construction, they not only fail to meet the management needs of multi-party participation but also fail to provide verifiable reputation management services. In this paper, we propose <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\mathcal{R}$</tex-math></inline-formula> -tracing, a consortium blockchain-based vehicle reputation management scheme. The main contribution of our work lies in three points. First, a vehicle reputation model is designed with a reward and punishment mechanism and a regular tax mechanism. Second, a vehicle reputation management system is constructed by using Hyperledger Fabric, in which all tasks of reputation value update are abstracted into three types of transactions. Finally, the effectiveness of <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\mathcal{R}$</tex-math></inline-formula> -tracing is verified by extensive simulations running on a large-scale traffic scenario and performance evaluation on a prototype system. Compared with the typical linear reputation model, our model not only resists the usual malicious attack and selfish behavior but also effectively deals with the on-off attack and rational selfish behavior improved by intelligent vehicles. In the test of throughput, <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\mathcal{R}$</tex-math></inline-formula> -tracing achieves 600/textittps, outperforming two state-of-the-art blockchain-based schemes.