Intelligent Transportation Systems Services Research Articles

Pothole detection in bituminous road using convolutional neural network with transfer learning

<p>The challenges of road maintenance, particularly in detecting potholes and cracks, and the proposed method using transfer learning and convolutional neural networks (CNNs) are significant advancements in this domain. Transfer learning is particularly beneficial, as it allows leverage pre-trained models to enhance the performance of the pothole detection system. CNNs, with their ability to capture spatial hierarchies in data, are well-suited for image-based tasks like pothole detection. The potential applications of the suggested method for intelligent transportation systems (ITS) services, such as alerting drivers about real-time potholes, demonstrate we research’s practical implications. This contributes to road safety and aligns with the broader goals of innovative city initiatives and infrastructure management. Achieving a 96% accuracy rate is a significant result, indicating the robustness of the proposed approach. Using this information to assess initial maintenance needs in a road management system is forward-thinking. Overall, we work is a valuable contribution to intelligent transportation and infrastructure management, showcasing the potential of advanced machine-learning techniques for addressing critical issues in road maintenance.</p>

Enhanced Federated Learning for Edge Data Security in Intelligent Transportation Systems

Federated learning (FL) provides a promising solution to meet the requirements of data privacy and security in intelligent transportation systems (ITS), which enables edge devices and road side units (RSUs) to collaboratively train learning models without exposing the raw data. However, the deep leakage from gradients (DLG) still leads to the risk of divulging the original data. Meanwhile, the existing gradient protection methods based on secure multi-party computation (SMC) result in huge communication overheads and latency, which are difficult to satisfy the real-time demands of both FL and the diverse services in ITS. Focusing on improving edge data security in ITS, this paper proposes an enhanced federated learning (FL) model (SemBroc-RF) with reinforcement learning, which considers the advantages of both end-to-end homomorphic encryption (HE) and SMC. To reduce communication overheads and strengthen data security in RSUs and end devices simultaneously, a partially encrypted secure multi-party broadcast computation algorithm (SemBroc) is designed, which achieves the time complexity O(n) by constructing the decoding function and sharing the gradients among the local models. To improve the model accuracy by gradients aggregation, a FL algorithm (GreFLa) with reinforcement learning is proposed based on the adaptive assigned weight of the local gradients. Theoretical analysis and detailed simulation results verify that SemBroc-RF can effectively prevent gradient leakage. On the MNIST and CIFAR-10 datasets, compared with the benchmark, the accuracy of SemBroc-RF is increased by 3.63% and 1.35%, and the training round of SemBroc-RF is reduced by 70.8% and 45.6%, respectively.

Spatial–temporal uncertainty-aware graph networks for promoting accuracy and reliability of traffic forecasting

Providing both point estimation and uncertainty quantification for traffic forecasting is crucial for supporting accurate and reliable services in intelligent transportation systems. However, the majority of existing traffic forecasting works mainly focus on point estimation without quantifying the uncertainty of predictions. Meanwhile, existing uncertainty quantification (UQ) methods fail to capture the inherent static characteristics of traffic uncertainty along both the spatial and temporal dimensions. Directly equipping the traffic forecasting works with uncertainty quantification techniques may even damage the prediction accuracy. In this paper, we propose a novel traffic forecasting model aiming at providing point estimation and uncertainty quantification simultaneously, called STUP. Compared to the traditional graph convolution networks (GCNs), our framework is able to incorporate uncertainty quantification into traffic forecasting to further improve forecasting performance. Specifically, we first develop an adaptive strategy to initialize uncertainty distribution. Then a kind of spatial–temporal uncertainty layer is carefully designed to model the evolution process of both the traffic state and its corresponding uncertainty, along with a gated adjusting unit to avoid error information propagation. Finally, we propose a novel constraint loss to further help improve the forecasting accuracy and to alleviate the training difficulty caused by the lack of uncertainty labels. Experiments on five real-world traffic datasets demonstrate that STUP outperforms the state-of-the-art baselines on both the traffic prediction task and uncertainty quantification task.

Privacy and Accuracy for Cloud-Fog-Edge Collaborative Driver-Vehicle-Road Relation Graphs

There are three key roles in Intelligent Transportation Systems (ITS): driver, vehicle and road. However, existing static interactions among Driver-Vehicle-Road (DVR) are too passive to reflect the change of driver preferences, vehicle conditions, road conditions, etc. Therefore, we provide a data-driven Cloud-Fog-Edge Collaborative Driver-Vehicle-Road (CFEC-DVR) framework. The framework could self-adaptively evolves through continuous iteration to provide better ITS services for humans. The collaboration among DVR creates a lot of relation data that construct our relation graphs. Cloud brings some privacy risks. Relation graphs have great analytic value. As DVR collaboration, privacy quality and analytic accuracy are three key issues in the framework, we propose a Relation Graph Privacy-Preserving scheme with High Accuracy in our framework, which is named as RGPP-HA. Based on machine learning, our method nearly maximizes the difficulty for attackers to know exactly how many other roles are connected to the attacked role, which enhances the privacy quality. Meanwhile, we find as much valuable information as possible from roles’ encrypted relations for more accurately analytic performance. Based on the experiments, we compare the proposed scheme RGPP-HA with existing classic and relevant schemes. The experimental results show that our scheme has the best privacy quality and analytic accuracy. This further verifies the feasibility of CFEC-DVR framework.

FOXS-GSC—Fast Offset Xpath Service with HexagonS Communication

Congestion in large cities is widely recognized as a problem that impacts various aspects of society, including the economy and public health. To support the urban traffic system and to mitigate traffic congestion and the damage it causes, in this article we propose an assistant Intelligent Transport Systems (ITS) service for traffic management in Vehicular Networks (VANET), which we name FOXS-GSC, for Fast Offset Xpath Service with hexaGonS Communication. FOXS-GSC uses a VANET communication and fog computing paradigm to detect and recommend an alternative vehicle route to avoid traffic jams. Unlike the previous solutions in the literature, the proposed service offers a versatile approach in which traffic road classification and route suggestions can be made by infrastructure or by the vehicle itself without compromising the quality of the route service. To achieve this, the service operates in a decentralized way, and the components of the service (vehicles/infrastructure) exchange messages containing vehicle information and regional traffic information. For communication, the proposed approach uses a new dedicated multi-hop protocol that has been specifically designed based on the characteristics and requirements of a vehicle routing service. Therefore, by adapting to the inherent characteristics of a vehicle routing service, such as the density of regions, the proposed communication protocol both enhances reliability and improves the overall efficiency of the vehicle routing service. Simulation results comparing FOXS-GSC with baseline solutions and other proposals from the literature demonstrate its significant impact, reducing network congestion by up to 95% while maintaining a coverage of 97% across various scenery characteristics. Concerning road traffic efficiency, the traffic quality is increasing by 29%, for a reduction in carbon emissions of 10%.

A three-stage framework for efficient deployment of intelligent transportation systems in urban areas

Rapid urbanization in big cities worldwide leads to severe traffic congestion and damages the urban living environment. Intelligent Transportation Systems (ITS) play a crucial role in addressing the growing challenges of urban transportation, such as congestion, pollution, and safety concerns. However, there is a lack of studies to present an overall framework to deploy ITS efficiently in urban areas considering each city's unique conditions. Therefore, this paper develops a three-stage framework to simplify the process of efficient deployment of ITS application services in a specific city. Three stages include identifying potential ITS services, evaluating and ranking the priority of ITS application services, and analyzing legal requirements as well identifying any gaps or areas where the current legal framework may fall short in accommodating ITS technologies. The three-stage framework considers the specific transportation challenges and requirements of each urban area/city, taking into account factors such as traffic patterns, infrastructure limitations, environmental considerations, and future development plans. A case study in Hai Phong city was presented where expert surveys were conducted to assess the current transport situation, evaluate satisfaction and expectation regarding applying ITS services. By providing a comprehensive framework for the efficient deployment of ITS in urban areas, this paper offers valuable insights and guidance to policymakers, transportation planners, and researchers. The framework can be as reference for other similar cities grappling with transportation challenges, facilitating the implementation of effective ITS solutions to transform advanced and sustainable urban transportation systems.

A Data Reporting Protocol With Revocable Anonymous Authentication for Edge-Assisted Intelligent Transport Systems

Intelligent Transport Systems (ITS) have received growing attention recently driven by technical advances in Industrial Internet of Vehicles (IIoV). In IIoV, vehicles report traffic data to management infrastructures so as to achieve better ITS services. To ensure both security and privacy, many anonymous authentication-enabled data reporting protocols have been proposed. However, these protocols usually require a large number of preloaded pseudonyms or involve a costly and irrevocable group signature. Thus, they are not ready for realistic deployment due to large storage overhead, expensive computation costs, or absence of malicious users' revocation. To address these issues, we present a novel data reporting protocol for edge-assisted ITS in this paper, where the traffic data is sent to the distributed edge nodes for local processing. In particular, we propose a new anonymous authentication scheme fine-tuned to fulfill the needs of vehicular data reporting, which allows the authenticated vehicles to report unlimited unlinkable messages to edge nodes without huge pseudonyms download and storage costs. Moreover, we designed an efficient certificate update scheme based on a bivariate polynomial function. In this way, the malicious vehicles can be revoked with time complexity O(1). The security analysis demonstrates that our protocol satisfies source authentication, anonymity, unlinkability, traceability, revocability, non-frameability, and non-repudiation. Further, extensive simulation results show that the efficiency and performance of our protocol are greatly improved since the signature size is reduced by at least 8%, the computation costs in message signing and verification are reduced by at least 56% and 67%, respectively, and the packet loss rate is reduced by at least 14%.

Pothole Detection and Prevention using YOLOv5 in ITS (Intelligent Transportation System)

Potholes on roads can cause serious damage to vehicles and accidents, so it is essential to detect them quickly and accurately. Determining appropriate strategies for ITS (Intelligent Transportation System) service is critical. In this study, the proposed solution employs YOLOv5 to perform real-time detection of potholes in images and videos. The dataset of annotated images and videos containing potholes, were used to train and fine-tune the algorithm. The proposed approach exhibits exceptional accuracy in detecting potholes, highlighting its capacity to boost road maintenance efforts while reducing the occurrence of accidents related to potholes.

Vehicular Relative Positioning With Measurement Outliers and GNSS Outages

Relative positioning among vehicles finds many applications regarding location-based services in intelligent transportation systems (ITSs). This article introduces a hybrid relative positioning strategy integrating global navigation satellite system (GNSS), inertial navigation system (INS), and ultrawideband (UWB) observations, which addresses measurement outliers and GNSS outages simultaneously. An improved extended Kalman filter (IEKF) based on tracking an appropriately weighted window of past innovations is developed to deal with measurement outliers. To perform relative positioning during GNSS outages, a nonlinear autoregressive network with exogenous inputs (NARX) is developed to predict GNSS measurements increments, with the least-squares support vector machine (LSSVM) algorithm identifying the NARX model. The NARX-LSSVM module learns the relationship between GNSS pseudorange and Doppler shift increments of a target vehicle and its local and neighbors’ dynamics. Whereas during GNSS outages, the increments of GNSS measurements are generated by this prediction algorithm. The feasibility of the proposed methodology is evaluated on empirical road data, and improved positioning accuracy is achieved in cooperative positioning (CP) systems.

Design of Secure and Lightweight Authentication Scheme for UAV-Enabled Intelligent Transportation Systems Using Blockchain and PUF

Unmanned-aerial-vehicle (UAV)-enabled intelligent transportation system (ITS) is an advanced technology that can provide various services including autonomous driving, real-time creation of high-definition maps, and car sharing. In particular, a UAV-enabled ITS can be realized through the combination of traditional vehicular ad hoc networks (VANETs) and UAVs that can act as flying roadside units (RSUs) at the outskirts and monitor road conditions from predefined locations to spot car accidents and any law violations. Notably, to realize these services, real-time communication between UAVs and RSUs must be guaranteed. However, UAVs have limited computing powers, and if extensive computation is required during communication, the provision of real-time ITS services may be hindered. Furthermore, UAVs and RSUs communicate via public channels that are prone to various attacks, such as replay, impersonation, trace, and session key disclosure attacks. Thus, in this article, a secure and lightweight authentication scheme is proposed for UAVs and RSUs using the blockchain technology. The proposed scheme is analyzed using informal and formal methods including Burrows–Abadi–Nikoogadam (BAN) logic, automated validation of internet security protocols and applications (AVISPA) simulation tool, and real–or–random (RoR) model, and its performance is compared with that of related schemes. The results reveal that the proposed scheme is more efficient and secure as compared to the other competing schemes.

Data Security Enhancement in 4G Vehicular Networks Based on Reinforcement Learning for Satellite Edge Computing

The vehicular network provides the dedicated short-range communication (DSRC) with IEEE 802.11p standard. The VANET model comprises of cellular vehicle-to-everything communication with wireless communication technology. Vehicular Edge Computing exhibits the promising technology to provide promising Intelligent Transport System Services. Smart application and urban computing. Satellite edge computing model is adopted in vehicular networks to provide services to the VANET communication for the management of computational resources for the end-users to provide access to low latency services for maximal execution of service. The satellite edge computing model implemented with the 4G vehicular communication network model subjected to data security issues. This paper presented a Route Computation Deep Learning Model (RCDL) to improve security in VANET communication with 4G technology. The RCDL model uses the route establishment model with the optimal route selection. The compute route is transmitted with the cryptographic scheme model for the selection of optimal route identified from the satellite edge computing model. The proposed RCDL scheme uses the deep learning-based reinforcement learning scheme for the attack prevention in the VANET environment employed with the 4G technology communication model. The simulation results expressed that proposed RCDL model achieves the higher PDR value of 98% which is ~6% higher than the existing model. The estimation of end-to-end delay is minimal for the RCDL scheme and improves the VANET communication.

Performance Analysis of Existing ITS Technologies: Evaluation and Coexistence

The performance of vehicular communication technologies changes dynamically according to the application requirements considering data rate, communication ranges, latency, etc. These applications are evolving rapidly and should enhance intelligent transport systems (ITS) such as road safety and automated driving. However, to reach the required quality, these applications need many radio resources to carry the potential traffic load resulting from the environmental perception and data exchanged between the different entities. Therefore, an assessment of vehicular communication technologies' reliability and resilience under these conditions is required to address the multiple challenges of the ITS services. The paper's main contribution is to propose a comprehensive analysis model able to evaluate and compare the performances of ITS technologies according to different constraints related to environment-changing situations. This analysis examines the channel occupancy and provides simulation results which allow the identification of the suitable configurations and the most appropriate technology for a given use case. We also propose a coexistence solution between these technologies based on density-sharing according to the use case requirements and the availability of the technology. Finally, we present the challenge of adaptive configuration in vehicular networks, which helps to provide the optimal structure through road profiles and environment variability (infrastructure, data, etc.). Results show different trade offs and limitations between the considered ITS technologies, which are essential to understand their behaviour in a realistic environment.

Service-Oriented Architecture for Providing ITS Services in Vehicular Ad Hoc Networks

Vehicular Ad hoc Network (VANET) is the cutting edge technology for smart transportation. VANET becomes an important aspect of the Intelligent Transport System (ITS). Different safety and non-safety applications have been developed for VANET. The inspiration behind VANET is to provide safe, and pleasant journeys to the drivers and passengers. Although the quality of software depends upon its architecture, most of them do not give proper attention to the consideration of Software-Oriented Architecture (SOA) for providing safety and non-safety ITS services in VANET. To address this issue, we proposed an efficient software architecture by highlighting the important operations and services of the system. The performance of the proposed architecture is evaluated by several design metrics and the results are compared with a state-of-the-art solution. The results showed that our proposed architecture has low coupling and high cohesion factors. Furthermore, the results reveal that our architecture is less complex and more reusable. From the results, we conclude that the proposed architecture is suitable for providing safety and non-safety ITS services and will pave the way for the implementation of the futuristic vision of the ITS.

Impact of High Resolution Radar-Obtained Weather Data on Spatio-Temporal Prediction of Freeway Speed

Inclement weather and environmental factors impact traffic operations resulting in travel delays and a reduction in travel time reliability. Precipitation is an example of an environmental factor that affects travel conditions, including traffic speed. While Intelligent Transportation Systems services aim to proactively mitigate congestion on roadways, these services are often not sensitive to weather conditions. This paper investigates the application of high-resolution weather data in improving the performance of proactive transportation management models and proposes short-term speed prediction models that fuse real-time high-resolution weather surveillance radar data with traffic stream data to conduct spatial and temporal prediction of the speed of roadway segments. Extreme gradient boosting weather-aware speed prediction models were developed for a 7-km segment of Interstate 270 in St. Louis, MO, USA. The performance of the weather-aware models was compared with the performance of weather-insensitive speed prediction models that did not take precipitation into account. The results indicated that in the majority of instances, the weather-aware models outperformed the weather-insensitive models. The extreme gradient boosting models were compared with the K-nearest neighbors algorithm and feed-forward neural network models. The extreme gradient boosting model consistently outperformed the other two methods. In addition to speed prediction models, van Aerde speed-flow traffic stream models were developed for rain and no-rain conditions to study the impact of precipitation on the traffic stream across the corridor. Results indicated that the impact of precipitation is not identical across the corridor, which was mirrored in the results obtained from weather-aware speed prediction models.

Secure, Privacy Preserving, and Verifiable Federating Learning Using Blockchain for Internet of Vehicles

Internet of Vehicles (IoV) has been sought as a solution to realize an Intelligent Transportation System (ITS) for efficient traffic management. Data driven ITS requires learning from vehicular data and provide vehicles with timely information to support a wide range of safety and infotainment ITS applications. IoV is vulnerable to multitude of cyber-attacks and privacy concerns. Federated learning (FL) is on the verge of delivering the collaborative learning by exchanging learning model parameters instead of actual data, which is expected to provide privacy in IoV. However, despite featuring an inherently secure and privacy-preserving framework, FL is still vulnerable to poisoning and reverse engineering attacks. Blockchain technology (BC) has already demonstrated a zero-trust, fully secure, distributed, and auditable information recording and sharing paradigm. In this article, we present a practical prospect of blockchain empowered federated learning to realize fully secure, privacy preserving, and verifiable FL for the IoV that is capable of providing secure and trustworthy ITS services.

CNN-Based Automatic Helmet Violation Detection of Motorcyclists for an Intelligent Transportation System

An intelligent transportation system (ITS) is an advanced application that supports multiple transport and traffic management modes. ITS services include calling for emergency rescue and monitoring traffic laws with the help of roadside units. It is observed that many people lose their lives in motorbike accidents mainly due to not wearing helmets. Automatic helmet violation detection of motorcyclists from real-time videos is a demanding application in ITS. It enables one to spot and penalize bikers without a helmet. So, there is a need to develop a system that automatically detects and captures motorbikers without a helmet in real time. This work proposes a system to detect helmet violations automatically from surveillance videos captured by roadside-mounted cameras. The proposed technique is based on faster region-based convolutional neural network (R-CNN) deep learning model that takes video as an input and performs helmet violation detection to take necessary actions against traffic rule violators. Experimental analysis shows that the proposed system gives an accuracy of 97.69% and supersedes its competitors.

Fleet management and control system for developing countries implemented with Intelligent Transportation Systems (ITS) services

Fleet Management Control Systems (FMCS) monitor vehicles in real-time and help assessing schedule compliance. Transit services in developing countries must improve in aspects such as information about routes, schedules and users; and compliance with traffic regulations, to achieve an increase in their demand. Although a FMCS can deal with these issues, currently implemented systems have some limitations related to communications technology, associated costs, interoperability and standardization. This paper includes the following: 1) The Intelligent Transportation System (ITS) architecture designed for the FMCS; 2) The development of a FMCS prototype for developing countries, considering the proposed architecture, using the Long Range communication technology and Intelligent Transportation Systems services; 3) A validation and testing of the FMCS prototype, using transit vehicles in a city. The developed prototype was successfully tested. The ideal operating parameters of the FMCS in terms of communications technology were identified in one of the four routes used in the tests. The results in such route were validated with additional tests, using the same parameters, and reaching similar operating values. A data set with the information of the performed tests was generated. With the results obtained in the FMCS, a better control of the transit service can be achieved, helping to improve upon the problems identified for developing countries (especially in medium-sized cities) related to route and schedule compliance, speeding, safety, standardization and helpful information for users. Additionally, service operation costs are reduced by using cutting-edge communications technology and promoting interoperability with other mobility services created for these cities.

HAPS-ITS: Enabling Future ITS Services in Trans-Continental Highways

With the advent of rapid globalization and the inter-border supply chain network, the reliability and efficiency of transportation systems have become even more critical. Indeed, trans-continental highways need particular attention due to their important role in sustaining globalization. In this context, intelligent transportation systems (ITS) can actively enhance the safety, mobility, productivity, and comfort of trans-continental highways. However, ITS efficiency depends greatly on the roads where they are deployed, on the availability of power and connectivity, and on the integration of future connected and autonomous vehicles. To this end, high altitude platform station (HAPS) systems, due to their mobility, sustainability, payload capacity, and communication/caching/computing capabilities, are seen as a key enabler of future ITS services for trans-continental highways; this paradigm is referred to as HAPS-ITS. The latter is envisioned as an active component of ITS systems to support a plethora of transportation applications, such as traffic monitoring, accident reporting, and platooning. This article discusses how HAPS systems can enable advanced ITS services for trans-continental highways, presenting the main requirements of HAPS-ITS and a detailed case study of the Trans-Sahara highway.

A method for predicting ITS cooperative applications performances

Vehicular cooperation taking place in Intelligent Transportation Systems (ITS) aims to solve traffic issues or to improve road safety for vehicles and vulnerable road users. Such cooperation is achieved through distributed applications running in the vehicular network (VANET), composed of communicating units in vehicles and infrastructure. For safety and legal reasons, it is expected that ITS services reach a satisfactory level of efficiency in the context they are deployed. However, predicting the behavior of distributed applications running in dynamic topologies remains a complex problem, which limits their deployment. In this paper, we propose a method able to predict the performances of cooperative ITS (C-ITS) applications in dynamic vehicular networks. It concerns applications relying on messages exchanges between close vehicles or between vehicles and infrastructure. The proposed method is based on an analysis of the application with respect to the vehicular traffic for determining the conditions ensuring the success of its underlying distributed algorithms and protocols. This is formalized as performances properties depending on the network dynamic. It becomes then easy to check whether these conditions are fulfilled or not in a given road traffic, either captured (and anonymized) for an existing road or expected for a new one. Thanks to an appropriate modeling, the conditions are sought and the performances of the C-ITS applications are predicted. We believe that our approach fills a gap between formal studies, VANET simulations and road tests. It will be of particular interest for the deployment of C-ITS applications. This is illustrated by several use-cases studied in realistic conditions.

Potential of Cooperative Intelligent Transport System Services to Mitigate Risk Factors Associated With Emergency Vehicle Accidents

Emergency vehicles (EVs) are at high risk of accidents during emergency driving. To make use of countermeasures to mitigate these risks, it is important to understand under what circumstances EV-related accidents occur. The common risk factors for EV-related accidents were examined through a systematic literature review. A total of 22 articles were examined for risk factors associated with EV-related accidents. The most reported risk factors were, in order of frequency, intersections, daytime, dry roads, clear weather, urban roads, traffic signals, and angular collisions. The articles were also reviewed for suggested countermeasures to mitigate the risk factors. The most commonly suggested countermeasures were driver training for EV operators, educating the public, exercising caution at intersections, wearing a seatbelt, and intelligent vehicle technologies. Cooperative intelligent transport systems (C-ITSs) have the potential to mitigate the risks of EV-related accidents. Therefore, three C-ITS services were investigated: EV approaching, EV preemption, and geofencing. They could all be used to inform, warn, or control aspects of driving. Each suggested service has the potential to decrease risk factors for EV-related accidents. The current literature review provides guidance on under what circumstance and in what form C-ITSs could be beneficial to prevent EV-related accidents. Further research is needed to examine behavior when drivers are introduced to C-ITSs.