Smart Transportation Networks Research Articles

Car Accident Detection and Alert System Leveraging Deep Learning

This paper presents a novel approach to address the critical issue of car accidents through an advanced Accident Detection and Alerting System (ADAS) empowered by cutting-edge technologies in deep learning, computer vision, and communication APIs. With road safety being a paramount concern worldwide, timely detection of car accidents followed by swift alerting mechanisms can significantly reduce the severity of accidents and save lives. The proposed system architecture incorporates the Ultralytics framework, Convolutional Neural Networks (CNN), You Only Look Once version 8 (YOLOv8), OpenCV, and Twilio API. Initially, YOLOv8 is employed to perform real-time detection of vehicles and potential accident scenarios from live video feeds obtained from roadside cameras or vehicle-mounted cameras. Subsequently, CNN models are utilized for comprehensive analysis of detected objects to discern potential accidents based on predetermined criteria, including sudden deceleration, collision patterns, and anomalous vehicle movements. Upon successful detection of an accident, the system triggers an alert mechanism via the Twilio API, which delivers instantaneous notifications to emergency services, nearby medical facilities, and designated contacts of the involved parties. These alerts are enriched with crucial details such as the accident location, vehicle types involved, and severity assessments derived from CNN analyses. Furthermore, the integration of OpenCV facilitates preprocessing tasks such as noise reduction, image enhancement, and object tracking, thereby enhancing the system's robustness and accuracy in diverse environmental conditions and lighting scenarios. The proposed ADAS offers numerous benefits, including real-time accident detection, automated alerting of emergency services, and minimized response times, ultimately contributing to mitigating the severity of accidents and preserving lives. By harnessing the power of deep learning algorithms, advanced computer vision techniques, and seamless communication APIs, this system represents a significant step towards fostering safer road environments within smart cities and transportation networks.

IoT-based parking surveillance scheme: Emerging a smart, effective, and secured solution for urban parking management and performance improvement

Parking spots have become a prevalent concern in urban growth. The number of automobiles is increasing faster than accessible parking spaces. This problem is addressed by implementing an Internet of Things (IoT)-based Parking Surveillance Scheme (IoT-PSS) for the smart campus. The system aims to efficiently match vehicles with available parking spaces, resulting in time savings, improved parking space usage, reduced management expenses, and decreased traffic congestion. Edge computing provides a new answer to data processing in monitoring systems by using advancements in IoT, artificial intelligence, and transmission technologies to analyze data regionally at the edge. This research explores the viability of using edge computing for smart parking monitoring, focusing on detecting parking occupancy via a real-time video stream. The structure operating pipeline to prioritize adaptability, online surveillance, data transfer, detection precision, and system dependability. The experimental findings show that the final detection approach achieves more than 95% accuracy in real-world situations with outstanding effectiveness and reliability. The IoT-PSS system is essential for smart cities and is a strong basis for future use in smart transportation networks.

The 5G revolution: Tackling challenges in smart cities and intelligent transportation systems

<div><p>The use of cutting-edge technology and data systems to increase the effectiveness, safety, and environmental responsibility of transport networks is known as intelligent transportation systems (ITS). In order to improve many elements of transportation, ITS incorporates a wide range of technologies, including sensors, communication networks, data analytics, and robots. By addressing the shortcomings of the current 4G network, the next mobile technology, 5G, challenges the electronic communication environment as it stands. By allowing a large number of concurrent connections and networks ubiquitous, even in high mobility scenarios or densely inhabited places, such Smart trains and smart cities (SC) are made possible by cutting-edge technology a new approach of becoming fully integrated. According to this strategy; 5G will enable the true Internet of Things (IoT) and its related automobiles on the World Wide Web (WWW). This conversation attempts to thoroughly explain how 5G wireless networks will impact urban smart transport networks, including semi-autonomous or self-driving cars, and automotive communication over the coming years, as well as any technical, economical, and regulatory issues.</p></div>

Cognitive-Radio-Based Resource Management for Smart Transportation: A Sliding Mode Control Approach

Smart transportation is one of the key components of the smart city. A significant amount of data is produced by the numerous vehicles connected via wireless networks. This demands smart spectrum management for efficient data communication. The optimal bandwidth usage can be obtained by opportunistically sharing the spectrum among high-priority class primary and low-priority class secondary users’ vehicles. In this study, we develop a mathematical model to ensure effective resource allocation in Cognitive Radio based Smart Transportation Networks (CR-STN) considering the mobility, bandwidth constraint and interference models. Robust sliding mode control is synthesized using an exponential reaching law to avoid data packet congestion in CR-STN to ensure smart spectrum management. In addition, a dynamic event-triggered mechanism is incorporated with the sliding mode controller to reduce computational complexity and energy expenses. The effectiveness of the suggested controller has been validated by simulation results.

Optimal allocation of FCSs and PV units in smart grids considering traffic and generation dispatch

Worldwide, transportation electrification and photovoltaics (PVs) have become vital components of modern and future planning problems. Therefore, the large-scale deployment of electric vehicles (EVs) requires reliable fast-charging stations (FCSs). However, random allocation of FCSs and PV adversely impacts the performance and operation of the traffic flow and power networks. Thus, this paper proposes a new planning approach for the optimal allocation of FCSs and PVs in large-scale smart grids and transportation networks. Unlike existing approaches, the well-known Dynamic Network Assignment Simulation for Road Telematics (DYNASMART) is updated and employed in the proposed planning approach to accurately simulate the EVs within the traffic stream. The average waiting time of the EVs at the charging stations (including charging time) and the total annual costs are utilized as conflicting objective functions to be minimized. To effectively solve this comprehensive model with conflicting objectives, a bi-layer multiobjective optimization based on metaheuristic (NSGA-II) and deterministic (GAMS) algorithms is established. The outer layer optimizes the allocation of FCSs and PV accurately, while the inner one optimally dispatches the generated power of the conventional generation units. The proposed planning approach is tested on a 26-bus electrical transmission network and 92-node transportation system. The simulation results demonstrate the efficiency of the proposed approach. The optimal allocation of FCSs and PVs with 80% EVs penetration increases the net profit by 85.36% while maintaining a maximum of 30 minutes for both charging and waiting time.

Smart Transportation: An Overview of Technologies and Applications.

As technology continues to evolve, our society is becoming enriched with more intelligent devices that help us perform our daily activities more efficiently and effectively. One of the most significant technological advancements of our time is the Internet of Things (IoT), which interconnects various smart devices (such as smart mobiles, intelligent refrigerators, smartwatches, smart fire alarms, smart door locks, and many more) allowing them to communicate with each other and exchange data seamlessly. We now use IoT technology to carry out our daily activities, for example, transportation. In particular, the field of smart transportation has intrigued researchers due to its potential to revolutionize the way we move people and goods. IoT provides drivers in a smart city with many benefits, including traffic management, improved logistics, efficient parking systems, and enhanced safety measures. Smart transportation is the integration of all these benefits into applications for transportation systems. However, as a way of further improving the benefits provided by smart transportation, other technologies have been explored, such as machine learning, big data, and distributed ledgers. Some examples of their application are the optimization of routes, parking, street lighting, accident prevention, detection of abnormal traffic conditions, and maintenance of roads. In this paper, we aim to provide a detailed understanding of the developments in the applications mentioned earlier and examine current researches that base their applications on these sectors. We aim to conduct a self-contained review of the different technologies used in smart transportation today and their respective challenges. Our methodology encompassed identifying and screening articles on smart transportation technologies and its applications. To identify articles addressing our topic of review, we searched for articles in the four significant databases: IEEE Xplore, ACM Digital Library, Science Direct, and Springer. Consequently, we examined the communication mechanisms, architectures, and frameworks that enable these smart transportation applications and systems. We also explored the communication protocols enabling smart transportation, including Wi-Fi, Bluetooth, and cellular networks, and how they contribute to seamless data exchange. We delved into the different architectures and frameworks used in smart transportation, including cloud computing, edge computing, and fog computing. Lastly, we outlined current challenges in the smart transportation field and suggested potential future research directions. We will examine data privacy and security issues, network scalability, and interoperability between different IoT devices.

A Synthetic Data Generation Technique for Enhancement of Prediction Accuracy of Electric Vehicles Demand

In terms of electric vehicles (EVs), electric kickboards are crucial elements of smart transportation networks for short-distance travel that is risk-free, economical, and environmentally friendly. Forecasting the daily demand can improve the local service provider's access to information and help them manage their short-term supply more effectively. This study developed the forecasting model using real-time data and weather information from Jeju Island, South Korea. Cluster analysis under the rental pattern of the electric kickboard is a component of the forecasting processes. We cannot achieve noticeable results at first because of the low amount of training data. We require a lot of data to produce a solid prediction result. For the sake of the subsequent experimental procedure, we created synthetic time-series data using a generative adversarial networks (GAN) approach and combined the synthetic data with the original data. The outcomes have shown how the GAN-based synthetic data generation approach has the potential to enhance prediction accuracy. We employ an ensemble model to improve prediction results that cannot be achieved using a single regressor model. It is a weighted combination of several base regression models to one meta-regressor. To anticipate the daily demand in this study, we create an ensemble model by merging three separate base machine learning algorithms, namely CatBoost, Random Forest (RF), and Extreme Gradient Boosting (XGBoost). The effectiveness of the suggested strategies was assessed using some evaluation indicators. The forecasting outcomes demonstrate that mixing synthetic data with original data improves the robustness of daily demand forecasting and outperforms other models by generating more agreeable values for suggested assessment measures. The outcomes further show that applying ensemble techniques can reasonably increase the forecasting model's accuracy for daily electric kickboard demand.

Garbage Management System using Internet of Things

Any city can be considered to as a “smart city” Because of its orderly and tidy surroundings. Numerous challenges, including those related to smart grids, smart environments, smart living, and smart transport networks, are currently plaguing many modern cities. Today, cities and urban areas’ top priority is proper waste management. Traditional waste management techniques are too simplistic to produce an effective and reliable waste management system. Any smart city must priorities smart waste management because it has a direct impact on people’s way of life, health, and environment. This article deliberates a thorough analysis of various proposed methods for smart bin systems, such as smart waste collection, smart waste monitoring, and smart waste segregation. We also suggest a framework for a smart waste management system in addition to this survey. The decline in the cleanliness of the environment due to garbage management is one of the issues that most cities and towns are facing. The improper management of garbage collection is to blame for this. This poor management causes garbage to spread throughout the neighborhood, which in turn leads to unhealthy conditions in the immediate area. Additionally, it degrades the area’s beauty and encourages the development of a number of serious diseases in those living nearby. The Garbage Monitoring System is designed to prevent improper garbage management and to enhance societal cleanliness.

Vehicle-to-roadside-unit-to-vehicle communication system under different amplify-and-forward relaying schemes

A vehicular Rayleigh fading communication system in which a vehicular transmitter (VT) is communicating with a vehicular receiver (VR) only through a dedicated stationary amplify-and-forward (AF) relaying roadside unit (RSU) is proposed in this paper (i.e., V2RSU2V system). To capture the effect of VT and VR motion, system's fading channels from VT to RSU and from RSU to VR are modeled to be time-varying in accordance with the first order autoregressive model. For the sake of performance comparison, the three common AF relaying sub-schemes are adopted at the RSU relay in separate scenarios; namely, the optimal channel-state-information-and-noise-assisted variable-gain (CSIN-VG) sub-scheme, the blind fixed-gain (B-FG) sub-scheme, and the semi-blind fixed-gain (SB-FG) sub-scheme. Under these AF relaying sub-schemes, closed-form expressions for outage probabilities are derived. The derived expressions are given in terms of variant vehicular system and channel parameters and can be directly considered for the special scenario of stationary VT and VR. Numerical and simulation results are reported to validate the analytical work and to reveal new insightful guidelines into vehicular systems outage performance. For example, results reveal that, for low average signal-to-noise-ratio (SNR) per symbol values, the SB-FG sub-scheme is superior in terms of outage performance for all vehicular scenarios and all threshold SNR values. As well, at high per-symbol average SNR values, results illustrate that the CSIN-VG sub-scheme is superior for high threshold SNR values, while the SB-FG is superior for low threshold SNR values. The study in this paper is timely due to the rapid advancements towards autonomous vehicles and smart transportation networks.

Big Geospatial Data Analytics, Connected Vehicle Technologies, and Visual Perception and Sensor Fusion Algorithms in Smart Transportation Networks

Big Geospatial Data Analytics, Connected Vehicle Technologies, and Visual Perception and Sensor Fusion Algorithms in Smart Transportation Networks

Algorithm-driven Sensing Devices and Connected Vehicle Data in Smart Transportation Networks

Algorithm-driven Sensing Devices and Connected Vehicle Data in Smart Transportation Networks

Autonomous Driving Algorithms and Behaviors, Sensing and Computing Technologies, and Connected Vehicle Data in Smart Transportation Networks

Autonomous Driving Algorithms and Behaviors, Sensing and Computing Technologies, and Connected Vehicle Data in Smart Transportation Networks

Cloud Computing Vs Fog Computing: A Comparative Study

Fog computing (or fogging) is extending cloud computing to the edge of the network. It describes a decentralized computing structure located between the cloud and devices that produce data. Operations like computing, storing and networking between end devices and data centers of cloud computing are facilitated by Fog computing. Decentralization and flexibility are the main difference between Fog computing and Cloud computing. Advantages of Fog computing include, minimize latency, conserve network bandwidth, reduce operating costs, enhance security, improve reliability, deepen insights and boost business agility. Various applications of Fog computing are, smart cities and smart electric grids, smart transportation networks, connected cars, real-time analytics etc. Here, this paper presents a comparative study of Cloud computing and Fog computing.

Smart Car Parking System (SPS) with the applications of Intelligent Transportation System

Intelligent Transportation Systems (ITS) is a modern approach in transportation engineering and management strategies of computer science, electronics and communication as it aims to provide advanced services in various methods of transport and traffic management systems. This helps the users to make safe, smart and efficient transport networks. Intelligent Transportation Systems (ITS) has a very wide application starting from traffic management to driver operation and vehicle control systems. Due to increase in vehicle production and world population leads to demand for more parking spaces and parking facilities. This problem is arising due to gap between demand and supply of parking spaces. The basic focus of this study is how to identify the exact location for parking the vehicle with the help of Arduino IDE software program. It will address the problems effectively associated with identification of parking slots and reaching parking places in urban areas. It informs and guide drivers to find limited number of parking spaces including their price in parking zones with in a shorter duration. Infrared sensors are also used to detect car parking slot occupancy. Smart Parking System (SPS) deals with identification of empty parking space, improper parking of vehicles and show the direction towards vacant parking slots. It also deals with digital payment facility. The ultimate focus of this is to identify the availability or non-availability of parking space.

UAV-Aided Data Delivery Scheme Based on Opportunistic Virtual Intersections for Smart Transportation Networks

Smart transportation networks, featured by high mobility and intermittent connectivity, are facing critical challenges in data delivery especially when the network is sparse and with less or no support from any infrastructure, such as in disaster and military environments. Unmanned aerial vehicles (UAVs), due to their flexible mobility, can be envisioned to enhance the connectivity of ground vehicular networks. In this paper, incorporating UAVs into vehicular networks, a novel data delivery scheme, named UAV-assisted data delivery (UADD), is proposed for smart transportation networks. We introduce a novel concept called “opportunistic virtual intersections”, at which UAVs can communicate with ground vehicles, and assist to deliver data packets. Specifically, at an opportunistic virtual intersection, UAVs may act as a relay, which can relay data packets between two vehicles as an intermediate hop, or deliver data packets in a store-carry-and-forward manner. The data forwarding rules are devised based on expected delivery delay and delivery probability of data packets. The performance evaluation demonstrates that the proposed UAV-assisted data delivery scheme can achieve a significant improvement of data delivery performance in terms of delivery delay and delivery ratio.

Machine Learning for Severity Classification of Accidents Involving Powered Two Wheelers

Road traffic safety is one of the major challenges for the future of smart cities and transportation networks. Despite several solutions exist to reduce the number of fatalities and severe accidents happening daily in our roads, this reduction is smaller than expected and new methods and intelligent systems are needed. The emergency Call is an initiative of the European Commission aimed at providing rapid assistance to motorists thanks to the implementation of a unique emergency number. In this work, we study the problem of classifying the severity of accidents involving Powered Two Wheelers, by exploiting machine learning systems based on features that could be reasonably collected at the moment of the accident. An extended study on the set of features allows to identify the most important factors that enable to distinguish accident severity. The system we develop achieves around 90% of precision and recall on a large, publicly available corpus, using only a set of eleven features.

Fog Services and Enabling Technologies

The articles in this special section examine fog computing which has received considerable attention in various application domains, especially those including time-sensitive transactions such as intelligent manufacturing, smart transportation, and cellular networks. Fog computing derives benefi ts from the increasingly smarter and more capable devices that reside not only at the network perimeter but also along the cloud-to-things continuum, which means fog-enabled services can be deployed anywhere within a network. Such continuous service provisioning and management have great potential to elevate the intelligence within multi-tier computing networks to realize context awareness, timely response, and task offloading. As a comprehensive and effective way of delivering customized new services, cloud, fog, and edge computing would be able to jointly reshape the landscape and the ecosystem of information and communication technology (ICT) and create tremendous business opportunities for future customers and various things. Realizing the challenges of providing diff erent fog services to satisfy high customer requirements, the articles in this section aim to give a timely overview of fog services and enabling technologies.

Vehicular Ad Hoc Networks and Security Issues: Survey

Vehicular ad hoc network (VANET) technologies are evolving networked communications advances that incorporate mobile-based routing protocol sets for inter-vehicular exchanges of information in support of smart transportation networks. Privacy and security difficulties are primary concerns in VANET research as a result of the repeated vehicular movements, time-critical responses, and hybrid VANET architectures that differentiate these from other ad hoc networking types. Therefore, the design of secure mechanisms for authenticating and validating message transmissions between vehicles and eliminating adversarial elements from networks are of considerable importance in VANET research. This report offers a review of VANET features and security difficulties. The paper also summarizes certain chief threats to the authentication, confidentiality, and availability of secure services.

Stealthy Attacks in Dynamical Systems: Tradeoffs Between Utility and Detectability With Application in Anonymous Systems

Cyber physical systems which integrate physical system dynamics with digital cyber infrastructure are envisioned to transform our core infrastructural frameworks, such as the smart electricity grid, transportation networks, and advanced manufacturing. This integration, however, exposes the physical system functioning to the security vulnerabilities of cyber communication. Both scientific studies and real-world examples have demonstrated the impact of data injection attacks on complex systems, including the Internet, the smart electricity grid, and air traffic systems. In this paper, an abstract theoretical framework is proposed to study data injection/modification attacks on Markov modeled dynamical systems from the perspective of an adversary. Typical data injection attacks focus on one shot attacks by adversary and the non-detectability of such attacks under static assumptions. In this paper, we study dynamic data injection attacks where the adversary is capable of modifying a temporal sequence of data and the physical controller is equipped with prior statistical knowledge about the data arrival process to detect the presence of an adversary. The goal of the adversary is to modify the arrivals to minimize a utility function of the controller while minimizing the detectability of his presence as measured by the K–L divergence between the prior and posterior distribution of the arriving data. The tradeoff between these two metrics—controller utility and the detectability cost—is studied analytically for different underlying dynamics. The proposed framework is then applied to a practical problem in data networks where a router tries to hide the path of traffic flow from timing analysis by an active adversary who can modify the timing of an incoming packet stream. This problem is studied from the adversary perspective wherein the goal is to balance two costs—the adversary’s detectability cost measured by the K–L divergence and the network privacy cost measured by the maximum length of the packet stream whose paths can be hidden by a memory limited router.

VEHICLE-TO-GRID NETWORKS

The articles in this special section focus on the growing market for electric vehicles, with an emphasis on vehicle-to-grid network (V2G) development. These articles explore the state of the art in research and development on V2G networks. From the perspective of the power-sector, V2G networks necessitate a careful management of charging/discharging services for a large population of EVs, with the objectives of guaranteeing grid stability, improving energy utilization, and reaping potential arbitrage value. In addition, as indispensable bridges for managing the large number of EVs connected to the power grid and their associated bi-directional energy-flows, new sophisticated designs for communication infrastructures and protocols will play a crucial role. The objective here is to realize an efficient and effective information-flow, in addition to the energy-flow, which enables real-time monitoring, signaling and information-dissemination in V2G networks, regardless of the location, time, and the physical conditions/types of EVs. Such designs require the integration of emerging advances in information, computing, and communications technologies. Therefore, V2G networks involve the multidisciplinary study of smart grids, communication networks, and transportation networks, and they will lead to a wide range of interesting studies of practical importance and theoretical impact.