Intelligent Transportation Research Articles

Optimization of the age of correlated information in V2X networks with edge computing

Vehicle-to-Everything (V2X) communication has the potential to revolutionize the travel experience in intelligent transportation, which has received the great attention recently. However, ensuring the freshness of information from multiple sources is critical for the real-time and reliable communication in vehicular networks, especially for timely updates of service centers. To address this issue, we use a promising metric called Age of Correlated Information (AoCI), which can characterize the freshness of multi-source information. Therefore, we propose a novel model that can dynamically regulate the channel activation matching and edge computing collaboration strategy to minimize AoCI in V2X vehicular networks. Firstly, we describe the system model of a V2X network with edge computing, including definitions and assumptions for freshness of information, edge co-computing, etc. Secondly, we formulate the joint optimization problem as a source-related age minimization (SRAM) problem, which is NP-complete. A heuristic algorithm is proposed to solve it under fast-fading channel. Finally, since traditional graph models cannot capture the changing correlation between nodes in dynamic networks, we use graph convolutional networks(GCN) to extract the features of multi-source correlation. The features extracted by GCN include relevant attributes of the sources and its communication links. The features are provided as input to a double deep Q network (DDQN) for training the model that can adapt to a dynamic network environment. Extensive simulation experiments in different network scenarios validate that our proposed method can effectively and efficiently reduce the average AoCI and the computational resources.

Multimodal Dataset Construction and Validation for Driving-Related Anger: A Wearable Physiological Conduction and Vehicle Driving Data Approach

Anger impairs a driver’s control and risk assessment abilities, heightening traffic accident risks. Constructing a multimodal dataset during driving tasks is crucial for accurate anger recognition. This study developed a multimodal physiological -vehicle driving dataset (DPV-MFD) based on drivers’ self-reported anger during simulated driving tasks. In Experiment 1, responses from 624 participants to anger-inducing videos and driving scenarios were collected via questionnaires to select appropriate materials. In Experiments 2 and 3, multimodal dynamic data and self-reported SAM emotion ratings were collected during simulated and real-vehicle tasks, capturing physiological and vehicle responses in neutral and anger states. Spearman’s correlation coefficient analysis validated the DPV-MFD’s effectiveness and explored the relationships between multimodal data and emotional dimensions. The CNN-LSTM deep learning network was used to assess the emotion recognition performance of the DPV-MFD across different time windows, and its applicability in real-world driving scenarios was validated. Compared to using EEG data alone, integrating multimodal data significantly improved anger recognition accuracy, with accuracy and F1 scores rising by 4.49% and 9.14%, respectively. Additionally, real-vehicle data closely matched simulated data, confirming the dataset’s effectiveness for real-world applications. This research is pivotal for advancing emotion-aware human–machine- interaction and intelligent transportation systems.

PV-LaP: Multi-sensor fusion for 3D Scene Understanding in intelligent transportation systems

Intelligent transportation systems are pivotal in modern urban development, aiming to enhance traffic management efficiency, safety, and sustainability. However, existing 3D Visual Scene Understanding methods often face challenges of robustness and high computational complexity in complex traffic environments. This paper proposes a Multi-Sensor Signal Fusion method based on PV-RCNN and LapDepth (PV-LaP) to improve 3D Visual Scene Understanding. By integrating camera and LiDAR data, the PV-LaP method enhances environmental perception accuracy. Evaluated on the KITTI and WHU-TLS datasets, the PV-LaP framework demonstrated superior performance. On the KITTI dataset, our method achieved an Absolute Relative Error (Abs Rel) of 0.079 and a Root Mean Squared Error (RMSE) of 3.014, outperforming state-of-the-art methods. On the WHU-TLS dataset, the method improved 3D reconstruction precision with a PSNR of 19.15 and an LPIPS of 0.299. Despite its high computational demands, PV-LaP offers significant improvements in accuracy and robustness, providing valuable insights for the future development of intelligent transportation systems.

Local Differential Privacy for correlated location data release in ITS

The ubiquity of location positioning devices has facilitated the implementation of various Intelligent Transportation System (ITS) applications that generate an enormous volume of location data. Recently, Local Differential Privacy (LDP) has been proposed as a rigorous privacy framework that permits the continuous release of aggregate location statistics without relying on a trusted data curator. However, the conventional LDP was built upon the assumption of independent data, which may not be suitable for inherently correlated location data. This paper investigates the quantification of potential privacy leakage in a correlated location data release scenario under a local setting, which has not been addressed in the literature. Our analysis shows that the privacy guarantee of LDP could be degraded in the presence of spatial–temporal and user correlations, albeit the perturbation is performed locally and independently by the users. This privacy guarantee is bounded by a privacy barrier that is affected by the intensity of correlations. We derive several important closed-form expressions and design efficient algorithms to compute such privacy leakage in a correlated location data. We subsequently propose a Δ-CLDP model that enhances the conventional LDP by incorporating the data correlations, and design a generic LDP data release framework that renders adaptive personalization of privacy preservation. Extensive theoretical analyses and simulations on scalable real datasets validate the security and performance efficiency of our work.

Self-adaptive equation embedded neural networks for traffic flow state estimation with sparse data

The data-driven approach in intelligent traffic systems has achieved successive breakthroughs, thanks to the ever-increasing volume of traffic data. Nonetheless, in practical scenarios, the collected data often contain some issues, e.g., missing values, significantly impacting the accuracy and efficiency of the algorithms. To enhance the precision of traffic estimation utilizing the sparse data, we have developed a physics-informed neural network (PINN) based algorithm in the line with the traffic flow theory and deep learning principles. In contrast to the conventional PINNs, our approach uniquely incorporates a self-adaptive macro model for mixed flow into the network's architecture, serving as an embedded source of physics information. With this algorithm, we can capture the dynamic behavior of an entire traffic flow including its spatiotemporal evolution with sparse traffic data such as initial and boundary value information. To realize the model's adaptability, we have revised the macro model by inverting its parameters and incorporating a data-driven nonlinear element, which simplifies the intricate macro model structure. The network's effectiveness has been validated through the experiments conducted on a mixed traffic flow system experiencing local agglomeration and real-world data, demonstrating its capability for precise traffic simulation, efficient traffic flow prediction, and interpretability. Our study offers a novel insight for data-driven traffic flow state estimation.

Isolation enhancement of a capacitively-fed MIMO antenna using a quasi-fractal parasitic element and defected ground structure

Vehicular Internet of Things (IoT) is facilitated by efficient RF front ends with suppressed mutual coupling for enhanced spatial diversity and increased channel capacity. This paper presents a mutual coupling suppressed MIMO antenna with a hybrid decoupling technique for Vehicle-to-Everything (V2X) communications, enabling IoT in automotive systems. The single elements consist of a radiating patch with a cleaving circular slot to introduce a capacitive effect on the radiating structure. Afterwards, the single-unit design is further extrapolated to a 2 × 2 MIMO antenna. The mutual coupling is suppressed between antenna elements by introducing a quasi-fractal parasitic element and a defected ground structure (DGS). The MIMO antenna is designed to conform to the requirements posed by V2X systems in Dedicated Short-Range Communications (DSRC) and Intelligent transportation system (ITS) scenarios. The proposed MIMO antenna offers measured |S11| < −10 dB of 200 MHz, ranging from 5.77 GHz to 5.97 GHz, fully covering the spectrum guided by the IEEE 802.11p standard. A physical prototype is fabricated and placed on a car roof to assess the congruency between measured and simulated results. The MIMO antenna exhibits exceptional diversity properties, such as enhanced isolation (>28 dB) between its individual elements, a diversity gain (DG) close to the ideal value of 10 dB (9.99 dB), peak realized gain of 6.5 dBi, an ECC below 0.001, and a beam coverage area of 180° in azimuthal and elevation plane by dynamic port switching. Thus, the proposed MIMO antenna module is a considerable candidate for future V2X communication paradigms.

Security-enabled optimal placement of drone-assisted Intelligent Transportation Systems in mission-critical zones

A massive increase in highly dynamic vehicular nodes has resulted in network instability. Owing to the heterogeneous vehicular environment requires a multi-objective solution using a meta-heuristic optimization algorithm in the event of mission-critical zones with poor signal and secured quick decision-making system. Developed a security-enabled optimal placement of Drones or unmanned aerial vehicles (UAV) in mission-critical zones aims to achieve two primary objectives: 1) Maximizing the effectiveness of the intelligent transportation system (ITS) for traffic management and ubiquitous connectivity in mission-critical zones. 2) Ensuring robust security measures to protect sensitive data and infrastructure. This approach represents a cutting-edge solution for optimizing transportation systems in high-risk environments while safeguarding against potential security threats. The pre-deployment of drones and vehicles (VOBU) parameter occurs during the registration phase, and then the mission-critical zone (MCZ) is identified and stored. The optimal position for drones in MCZs is determined by mathematically modeling a golden eagle optimization (GEO), which is inspired by varying the speed at different stages along their spiral trajectory for cruising and hunting. Furthermore, the robustness of the sensitive data and the real identity is ensured by using a biometric-based AKA algorithm utilizing the prevalent real-or-random (ROR) model and the formal security analysis. Based on a comparison of the simulation results, the proposed SDV-GEOAKA scheme outperforms the existing system- STPTC-A2G, IoDAV, and IMOC with 99.36% of PDR approximately, whereas, SDV-GEOAKA has maintained a load balancing factor with 0.01 to 0.1 when the transmission range between 0-60. When it comes to network coverage, proposed work outperforms with 99.95% during the transmission range of 50mW means it uses a minimum number of drones with maximum connectivity within the coverage range and also has significantly reduced the computation overhead and an increase in anomaly detection rate.

Harmonizing Maritime Innovation: Enhancing International and National Standardization in Intelligent Ship Transport Systems

Abstract The rapid advancement of maritime technologies, particularly in the domain of autonomous ships and maritime intelligent transport systems (MITS), necessitates a robust framework for digital interoperability at both national and international levels. This paper presents an in-depth analysis of the current state of standardization within MITS. It emphasizes the importance of harmonizing efforts to facilitate the integration of innovative technologies into the maritime sector, ensuring safety, efficiency, and environmental sustainability. To gain broader insights, standardization practices from other industries are examined. In conclusion, the paper argues that enhancing collaboration and standardization in MITS is essential for the successful implementation of maritime innovations. It calls for a collective effort from national and international stakeholders to develop a unified framework that supports the growth of autonomous ship technology and the evolution of intelligent maritime transport systems.

CLLS: Efficient certificateless lattice-based signature in VANETs

The rapid development of Vehicular Ad-hoc Network (VANETs) has improved road safety and traffic management, and brought great convenience to intelligent transportation system (ITS). However, the transmission of data over open channels caused many security issues. Certificateless cryptography solves the certificate management and key escrow problems, which makes it the primary method for message authentication in VANETs. However, with the emergence of quantum computing, traditional cryptography faces a significant challenge. Lattice-based cryptography are regarded as effective post-quantum ciphers. Nevertheless, nearly all existing lattice-based certificateless signature schemes rely on Gaussian sampling or trapdoor techniques, resulting in computational inefficiencies and large key and signature sizes that are impractical for VANETs. To address these issues, we proposed the first efficient algebraic lattice-based certificateless signature scheme in VANETs based on the Dilithium signature algorithm. The security of our certificateless lattice-based signature(CLLS) scheme is based on the MSIS and MLWE hardness assumption, which makes the scheme resistant to quantum attacks and easy to implement. Our scheme did not use Gaussian sampling or trapdoor techniques, which improve the computational and storage efficiency. As a result, the public key of our scheme is 1X smaller than the previous scheme and the size of signature is 2X smaller than the previous efficient algebraic lattice scheme. In addition, compared to the most efficient existing CLLS scheme, the signing and verification computation cost of our scheme are reduced by 20% and 55% respectively and our proposed CLLS scheme has low power consumption. Furthermore, the security of our scheme achieves strong unforgeability against chosen-message attacks(SUF-CMA) in the random oracle model(ROM), which surpasses that of existing lattice-based certificateless signature schemes.

SCVAN- BKM: Swarm clustering for vehicular ad hoc network with a secure blockchain-based key management scheme

The advancements in telematics and communication technology for automobiles have contributed to the development of Vehicular ad Hoc Networks (VANETs). These networks serve as the foundation for Intelligent Transportation Systems (ITS). Communication across various VANET entities is challenging due to the open communication environment and the highly dynamic nature of VANETs. One of the major challenges in VANETs is ensuring stable and secure transmission. To address these factors, several studies have been conducted. The article discusses a clustering algorithm for VANETs that leverages SCVAN-DPSO to create stable clusters and provide secure communication for mitigating malicious nodes. Additionally, Hyperelliptic Curve Cryptography (HECC) with signcryption in blockchain is proposed. This algorithm is designed to identify and mitigate malicious nodes, ensuring robust and secure communication within the network. To verify vehicles in VANETs, this study also suggests a safe and reliable key management method that generates and stores cryptographic keys using blockchain’s distributed ledger technology. By doing so, the risk of rogue nodes is reduced, and a safe, stable connection between vehicles is guaranteed. This work has been implemented using NS 3.34 simulation with the SUMO real-time traffic mobility simulator, and its performance has been evaluated. The proposed algorithm SCVAN-BKM provides a 99.6 % packet delivery ratio for 20 nodes, 0.4 % packet loss, end-to-end delay of 32.65 ms, throughput of 9.522 Mbps, and a cluster lifetime of 105 s. As the number of nodes increases in the communication zone, stable communication is maintained due to the clustering algorithm used in the proposed approach, as cluster formation supports stability in the high-mobility nature of vehicles, while secure communication is ensured using blockchain technology. The findings demonstrate that our approach is more effective and yields better outcomes than existing systems.

Creative artificial intelligence and narrative transportation.

Creative artificial intelligence and narrative transportation.

Efficient license plate recognition in unconstrained scenarios

Automatic license plate recognition (ALPR) is a critical technology for intelligent transportation systems. Most existing ALPR methods are focused on specific application scenarios. Although there are a few methods that focus on unconstrained scenarios, they are very time-consuming. In this work, we propose an efficient ALPR (EALPR) framework, where we can handle distorted license plates (LP) caused by perspective problems with high efficiency. We design a light LPD structure based on efficient object detection methods and use anchor-free strategies for LPD to alleviate the problem of expensive costs. Benefitting from these optimizations and a united framework structure, the proposed EALPR has real-time efficiency. We evaluate our method on five datasets and the results show that our method achieves state-of-the-art accuracy: 98.15% on OpenALPR(EU), 95.61% on OpenALPR(BR), 99.51% on AOLP(RP), 88.81% on SSIG, 79.41% on CD-HARD. Additionally, our method achieves an impressive speed of 74.9 FPS (Frames Per Second), outperforming existing approaches and demonstrating its efficiency. Our source code can be accessed at https://github.com/wechao18/Efficient-alpr-unconstrained.

Intelligent Traffic Control Decision-Making Based on Type-2 Fuzzy and Reinforcement Learning

Intelligent traffic control decision-making has long been a crucial issue for improving the efficiency and safety of the intelligent transportation system. The deficiencies of the Type-1 fuzzy traffic control system in dealing with uncertainty have led to a reduced ability to address traffic congestion. Therefore, this paper proposes a Type-2 fuzzy controller for a single intersection. Based on real-time traffic flow information, the green timing of each phase is dynamically determined to achieve the minimum average vehicle delay. Additionally, in traffic light control, various factors (such as vehicle delay and queue length) need to be balanced to define the appropriate reward. Improper reward design may fail to guide the Deep Q-Network algorithm to learn the optimal strategy. To address these issues, this paper proposes a deep reinforcement learning traffic control strategy combined with Type-2 fuzzy control. The output action of the Type-2 fuzzy control system replaces the action of selecting the maximum output Q-value of the target network in the DQN algorithm, reducing the error caused by the use of the max operation of the target network. This approach improves the online learning rate of the agent and increases the reward value of the signal control action. The simulation results using the Simulation of Urban MObility platform show that the traffic signal optimization control proposed in this paper has achieved significant improvement in traffic flow optimization and congestion alleviation, which can effectively improve the traffic efficiency in front of the signal light and improve the overall operation level of traffic flow.

Disentangled traffic forecasting via efficient graph neural network

Abstract Traffic prediction is important to intelligent transportation systems, but it poses significant challenges due to the complex spatio-temporal correlation of traffic data. To address these challenges, we decompose complex traffic time series into events and trends using discrete wavelet transform. However, the high-frequency information decomposed by wavelet transform contains noise, so we designed a module to denoise the high-frequency events. We model the spatio-temporal correlations of trends and events separately using two mutually independent spatio-temporal networks. We use causal dilation convolution with local receptive fields and attention with global receptive fields to capture the correlation of fluctuating time series and the correlation of stable time series, respectively. We capture spatial correlation using a GNN optimized by an attention mechanism. Finally, we merge useful information from volatile events into predictable trends using adaptive event fusion. Our model significantly outperforms nine existing traffic prediction methods across four real datasets.

Joint Energy and Completion Time Difference Minimization for UAV-Enabled Intelligent Transportation Systems: A Constrained Multi-Objective Optimization Approach

Joint Energy and Completion Time Difference Minimization for UAV-Enabled Intelligent Transportation Systems: A Constrained Multi-Objective Optimization Approach

Geometric Constraints and Rough-Fine Registration-Based Localization Method for Social Intelligent Transportation Systems

Geometric Constraints and Rough-Fine Registration-Based Localization Method for Social Intelligent Transportation Systems

Advances in vehicle re-identification techniques: A survey

The development of vehicle re-identification technology has significantly enhanced the operational efficiency of intelligent transport systems and smart cities, attributed to the advancement of artificial intelligence technologies such as deep learning and transformer models. By accurately tracking and identify the same vehicle under different cameras, the technology not only greatly enhances the ability of urban safety monitoring, traffic management and accident investigation, but also provides powerful technical support for the development of intelligent transportation. This paper explores the shift from traditional to deep learning approaches in vehicle re-identification, highlighting the rise of Transformer models. We assess both non-visual and vision-based re-identification technologies, with a special focus on the deep feature-based methods across supervised, unsupervised, and semi-supervised learning. And we summarize the performance of supervised and unsupervised methods on the VeRi-776 and VehicleID datasets. Finally, this paper outlines six directions for the future development of vehicle Re-ID technology, highlighting its potential applications in various areas such as smart city traffic management.

EPAKA: An efficient and privacy-preserving authenticated key agreement scheme based on physical security for VANET

Vehicular ad hoc network (VANET) has been a promising technology in smart transportation system, which can enable information exchange between vehicles and roadside units (RSUs). However, the privacy of vehicles and RSUs is a critical challenge in VANET, as they may expose sensitive information to malicious attackers or unauthorized parties. Many existing authenticated key agreement (AKA) schemes aim to protect the privacy of vehicles and RSUs, but they often neglect the physical security of the devices involved in the communication. Therefore, we propose an efficient and privacy-preserving AKA scheme in VANET, which embeds physical unclonable function (PUF) and fuzzy extraction (FE) technology. PUF is a physical device that generates random strings based on their intrinsic characteristics and external inputs, which can protect the secrets in the devices from being stolen by attackers. FE can compensate for the drawbacks of PUF affected by environmental factors. Our scheme preserves the identity privacy of legitimate RSUs and vehicles, as well as intercepts and traces the identity of malicious attackers. In addition, we eliminate the involvement of the third party (TP) in the AKA phase to better meet the high-speed driving of vehicles. Finally, we conduct formal and informal security analyses in random oracle model (ROM), which prove that our scheme can resist various attacks. We also show in the performance analysis that our scheme has the lowest computational cost, communication overhead, and total energy consumption.

Logistics Performance Index-driven in operational planning for logistics companies: A smart transportation approach

The responsibility of Logistics Companies (LCs) extends beyond simply handling logistical processes and choosing transportation routes; they focus on being competitive and efficient in their operations. In multiple origins and destinations networks, LCs attempt to select the most optimal routes from each point. To address this challenge and reduce the time needed to identify potential routes, a novel method has been developed in this research for LCs. In operational planning, additional factors need to be considered to increase efficiency, customer satisfaction, and competitiveness. To confront this issue, the study proposes a novel model and contributions, inspired by the LPI, to apply the transformative impact of smart ports, the integration of smart containers, the choices of clearing and forwarding agents and port operators, and time uncertainty in the multi-objective framework. Specifically, the mathematical model's objectives include cost, time, customer satisfaction, and environmental impact in the periodic multimodal network. An innovative customer satisfaction function is introduced by integrating the selection of smart containers and smart ports, emphasizing their impact on enhancing customer satisfaction, while addressing time uncertainty through a chance-constrained approach and coefficients of variation. The model is solved using goal programming, and the results show that smart ports and smart containers can majorly affect transportation time and customer satisfaction. Furthermore, comparing the results to other studies demonstrates its superiority in decision-making for LCs, particularly by including time uncertainty and the role of clearing and forwarding agents and port operators. Therefore, the model holds practical significance in lowering costs, enhancing customer satisfaction, and facilitating smart international logistics. This research offers insights that are not only useful for the LCs but also for other stakeholders in the transport industry.

Adaptive Mobility and Reliability-based Routing Protocol for Smart Healthcare Management Systems in Vehicular Ad‐hoc Networks

Ambulances enable digital and widespread remote care for older people in the healthcare sector. The Vehicular Ad Hoc Network (VANET) is critical for allowing the digital and Intelligent Transportation System (ITS) for the smart healthcare world. Enhancing the dependability and flexibility of an adaptive routing algorithm improves vehicular communications' Quality of Service (QoS) effectiveness. An essential concern in vehicular technology is enabling drivers to make reliable judgments. Developing an effective routing system that ensures a suitable QoS takes time and effort. The vehicular network ecosystem is characterized by limited mobility, fast vehicle speeds, and constantly changing configurations. This study makes four distinct contributions. Initially, it presents adaptive routing protocols, capable of recognizing changes in the network environment, aware of the mobility of nodes, and dependable in delivering data packets. The experimental configuration is implemented inside a discrete Network Simulator (NS-3) scenario to enhance the QoS. Mobility-aware routing algorithms can provide ITS with satisfactory mobility, vital dependability, high Packet Delivery Ratio (PDR), high throughput, and low End-to-End (E2E) Delay. The proposed method has an average throughput of 664.3 kbps, a delay of 151.3 ms, and a packet delivery ratio (PDR) of 94.23%.