Skip to main content
Fachgebiete
Automobil + Motoren Bauwesen + Immobilien Business IT + Informatik Elektrotechnik + Elektronik Energie + Nachhaltigkeit Finance + Banking Management + Führung Marketing + Vertrieb Maschinenbau + Werkstoffe Versicherung + Risiko
DE
EN
Bücher
Zeitschriften
Kongresse
Themenseiten
Organisationspsychologie Projektmanagement Marketing Smart Manufacturing
Weitere Formate
Podcasts Webinare Technik Webinare Wirtschaft Veranstaltungskalender Awards MyNewsletter Firmensuche
Kunden Login
Über Einzelzugang informieren
Über Unternehmenszugang informieren
Referenzkunden
Heavy-Duty Engines 2025 | 18. + 19. November 2025

Nutzfahrzeuge | Land- und Baumaschinen | Marine

Nehmen Sie als Referent an der 20. Internationalen MTZ-Fachtagung für Erfahrungsaustausch zu Industrie- und Nfz-Motoren teil. Reichen Sie online einen Themenvorschlag ein!
Erweiterte Suche
Anmelden
nach oben

2025 | Buch

Kapitel lesen Erstes Kapitel lesen

Smart Cities, Green Technologies, and Intelligent Transport Systems

12th International Conference, SMARTGREENS 2023, and 9th International Conference, VEHITS 2023, Prague, Czech Republic, April 26-28, 2023, Revised Selected Papers

herausgegeben von: Cornel Klein, Matthias Jarke, Jeroen Ploeg, Karsten Berns, Alexey Vinel, Oleg Gusikhin

Verlag: Springer Nature Switzerland

Buchreihe : Communications in Computer and Information Science

Enthalten in: Springer Professional "Wirtschaft+Technik" , Springer Professional "Technik" , Springer Professional "Wirtschaft"

Inhaltsverzeichnis
insite
SUCHEN

Über dieses Buch

This book includes extended and revised selected papers from the 12th International Conference on Smart Cities and Green ICT Systems, SMARTGREENS 2023, and 9th International Conference on Vehicle Technology and Intelligent Transport Systems, VEHITS 2023, held in Prague, Czech Republic, in April 2023.

The 10 full papers presented in this book were carefully reviewed and selected from 80 submissions. These papers contribute to our understanding of relevant trends currently underway in research on Smart Cities and Green ICT Systems, & Vehicle Technology and Intelligent Transport Systems.

Inhaltsverzeichnis

Frontmatter

Smart Cities and Green ICT Systems

Frontmatter
Calculation of Modes and Electromagnetic Influences of a Long-Distance Ultra-high Voltage Power Transmission to Pipeline Based on Digital Models
Abstract
The task of determining the voltages induced on a pipeline by the electromagnetic field of power lines is significantly complex and requires taking into account a number of factors, such as: operating mode of the influencing line; approach trajectory; the nature of the grounding of the metal structure; the length of the approach area and the conductivity of soils on it. The goal of the research presented in this article was to develop computer models of long-distance ultra-high voltage (UHV) power transmission lines to provide comprehensive modeling of power flows and calculating electromagnetic interference effects on extended steel structures. In developing the models, we employed the methods based on the use of the phase frame of reference and equivalent lattice circuits with a fully connected topology. The simulations were carried out for a 1,150 kV UHV transmission line with a length of 900 km, each phase of which was formed by eight AC-330 wires. Simulations were performed using the software package Fazonord. Along with power flow calculations and determination of the voltages created by the 1,150 kV long-distance transmission line on the pipeline, we simulated electromagnetic fields, taking into account the impact exerted by the grounded steel structure. The following modes were considered: normal with loads at the receiving end of 300 + j200 MVA per phase; emergency, caused by single-phase and two-phase short circuits; single-phase with loads 80 + j50 MVA per phase. The results of modeling a long-distance 1,150 kV transmission line with receiving end loads of 300 + j 200 MVA per phase led to the following conclusions: in the case of a normal power flow with balanced loads at individual points of the structure the levels of induced voltages did not exceed the allowable limit of 60 V; in the case of two-phase and single-phase short-circuit power flows the maximum induced voltages also did not exceed the 1,000 V limit set by the regulatory document. When phase B is disconnected at the starting end of the power line, the induced voltages on the pipeline increase 3…12 times and at the point with coordinate x = 50 km exceed the permissible value; in this case, the currents flowing through the pipe increase more than three times, which can lead to malfunctions in the pipeline protection system against electrochemical corrosion.The models presented in the paper can be put into practice when planning the measures to ensure the electrical safety of technicians working at the pipeline sections located in the areas that are subject to electromagnetic interference effects of transmission lines. Based on them, it is possible to reasonably select measures to ensure the safety of personnel servicing the structure, as well as to develop methods and means of protection against corrosion. The application scope of the technique developed covers the cases where a transmission line and a pipeline run in close proximity following a complex trajectory that includes parallel and oblique segments. Based on the presented digital models, it is possible to reasonably select measures to ensure the safety of personnel servicing the structure, as well as develop methods and means of protection against corrosion.
Andrey Kryukov, Konstantin Suslov, Alexandr Kryukov
Decentralised Vehicle Allocation for Community-Based Ride-Sharing Services
Abstract
This paper presents the design, implementation and evaluation of the vehicle fleet allocation in a community-based ride-sharing service. Independent communities of a city compete for the allocation of vehicle resources, which use to handle the transport requests of its own neighbours via ride-sharing. This vehicle allocation problem (VAP) is formulated as a decentralised, iterative negotiation process among independent communities with the underlying ride-sharing service operated by each community is formulated as a vehicle routing problem with both dynamic resources and requests. Two separate solution designs are evaluated: on the one hand, a Multi-Objective and Multi-Agent Reinforcement Learning algorithm, involving Deep Q-Learning with Graph Convolutional Networks, is applied to compute the vehicle allocation; on the other hand, a reactive-based simulation on top of a greedy decision-making process is applied to compute the underlying ride-sharing problem of each community. Existing benchmarks (e.g. Google HashCode) and public datasets (e.g. NYC taxis) are aligned to the proposed problem formulation, evaluating the solution approach under different community connectivity-levels and transport request distributions. Ride-sharing services have demonstrated scalable efficiency. This efficiency is achieved through a centralised Mixed-Integer Programming formulation, which optimally addresses the vehicle allocation problem.
Avinash Nagarajan, Alan McGibney, Pio Fenton, Ignacio Castiñeiras

Vehicle Technology and Intelligent Transport Systems

Frontmatter
Towards Better Modeling of Bicycle Lateral Motion: Model Development, Naturalistic Data Acquisition, and Model Validation
Abstract
This research effort starts by developing a descriptive model that is capable of capturing the inherent non-lane-based traffic behavior characteristics of bicycles. In that regard, the research team extends the Fadhloun-Rakha bicycle-following longitudinal motion model through complementing it with a lateral motion strategy; thus allowing for overtaking maneuvers and lateral bicycle movements. For the most part, the following strategy of the FR model remains valid for modeling the longitudinal motion of bicycles except for the activation conditions of the collision avoidance strategy, which are modified in order to allow for overtaking when possible. The proposed methodology is innovative in that it makes use of the intersection of certain pre-defined regions around the bicycles to decide on the feasibility of angular motion along with its direction and magnitude. The resulting model is the first point-mass dynamics-based model for the description of the longitudinal and lateral behavior of bicycles in both constrained and unconstrained conditions. In fact, by having the FR bicycle-following model as the governing module of longitudinal behavior and a dynamic lateral module, the proposed model is found to be both robust and able to model bicyclist behavior variability. Furthermore, it is the only existing model that is sensitive to the bicyclist physical characteristics and the bicycle and roadway surface conditions given that the used longitudinal logic was previously validated against experimental cycling data.
Next, this study describes a new framework for the collection of naturalistic cycling data. In that process, a new naturalistic cycling dataset is collected for the purpose of validating the developed bicycle lateral motion model. Given that the collection of naturalistic cycling data is not achievable in the traditional vehicle approach, machine learning and computer vision techniques were used to construct the naturalistic dataset from existing video feeds. The used videos come from a dataset collected in a previous Virginia Tech Transportation Institute study in collaboration with SPIN in which continuous video data at a non-signalized intersection on the Virginia Tech campus was recorded. The research team applied existing computer vision and machine learning techniques to develop a comprehensive framework for the extraction of naturalistic cycling trajectories. In total, the proposed methodology resulted in the collection of 619 bicycle trajectories at a high level of precision in relation to extracting the locations, speeds, and accelerations of the bicycles. Besides providing preliminary insights into the naturalistic acceleration and speed behavior of bicyclists around motorists, the collected dataset is used to further confirm the validity and robustness of the proposed model for bicycle lateral motion behavior modeling. That is achieved by verifying the model’s ability to generate simulated trajectories that are consistent with the naturalistically observed lateral behavior.
Fahd Alazemi, Karim Fadhloun, Hesham Rakha
Small Vehicle Damage Detection with Acceleration Spectrograms: An Autoencoder-Based Anomaly Detection Approach
Abstract
This paper presents a Machine Learning (ML) based methodology for a real-time small-vehicle damage detection system. While dents and scratches may seem trivial for individual car owners, they hold significant implications for insurance companies and car-rental/taxi service providers. In addition to these interested parties, car manufacturers and car service providers are also keen to obtain accurate vehicle damage information for vehicle behaviour analysis. Therefore, vehicle damage detection remains a key and challenging problem in the automotive research community. Our novel approach mainly uses spectrograms of inertial sensors like accelerometers which measure accurate vehicle acceleration. Inertial sensors are cost-effective and tailored for real-time data capture which makes them a competitive candidate for our choice. The designed system employs auto-encoders as automatic feature extractors from input acceleration spectrograms. These feature representations derived from sensor data are then classified into damage or non-damage categories using an anomaly detection approach. We achieved an impressive approximately 90% F1-score. The outcomes of this work contribute to the progress of intelligent damage detection systems. Furthermore, it assists in understanding the relationships between auto-encoders and signal data in this context. Our approach can be used in many applications in the automotive sector, such as automated vehicle inspection, enhanced airbag response systems, and improving the safety of autonomous driving.
Sara Khan, Bruno Faria, Andre Ferreira
Modeling the Traffic Scene in Intelligent Transport Systems for Cooperative Connected Automated Mobility
Abstract
Cooperative, connected and automated mobility (CCAM) is a step further compared to the driving solutions of the past decade. The possibility of sharing up-to-date information about the state of the traffic infrastructure, or about any agent on the road, makes it possible to generate more complex decision systems in connected and automated vehicles. In that sense, the notion of what is happening around the vehicle, as well as the representation of relevant traffic events, becomes of vital importance for decision making processes in complex traffic situations. Before starting its journey, the vehicle systems need to have a robust and clear notion of the traffic scene, i.e. all those static and dynamic elements the vehicle can come up with while driving. Thus, this information, when processed, would provide sufficient semantics of the surroundings to find out what needs to be done next depending on the context. This chapter proposes the development and design of an information system that aims to generate the necessary data structures to represent the traffic scene information. This representation will serve, once integrated in an automated software ecosystem, to understand the traffic context and act accordingly to the semantics of the scene.
David Yagüe-Cuevas, Pablo Marín-Plaza, María-Paz Sesmero, Araceli Sanchis
A Technique for Authentic Fatigue Driving Detection Using Nighttime Infrared Images
Abstract
Traffic accidents are one of the top ten causes of death, with driver fatigue accounting for a significant proportion. Fatigue can lead to reduced attention and slower reaction times. Many professions require frequent nighttime driving, such as truck and taxi drivers, making them particularly a high risk group. Therefore, preventing accidents caused by driver fatigue, especially during nighttime, is a crucial task. Currently, there is limited research and datasets focused on fatigue driving in nighttime scenes. To address this gap we collect nighttime fatigue driving data using an infrared (IR) camera, and propose Unbalanced LocalCNNs for fatigue driving detection in this work. The network architecture can effectively direct the network’s attention to different regions based on specific actions caused by fatigue, and result in a 1.6% improvement in accuracy compared to the original models. Furthermore, an adversarial learning mechanism is introduced to enhance the network’s robustness, ensuring effective feature extraction in both day and night scenarios. Compared to models without adversarial learning, the overall accuracy is improved by 1.5%. The code is available at https://​github.​com/​KaiChun-Tu/​slow fastDrowsyDriver.
Huei-Yung Lin, Kai-Chun Tu
Identifying Challenges in Remote Driving
Abstract
Since the first demonstration of remote driving in 2013, the technological possibilities have advanced enormously. This includes increases in computational hardware as well as in mobile communications technology (Long Term Evolution (LTE) and, nowadays, 5G). In this paper, we investigate challenges in remote driving using our own implementation as well as comparisons with trials by two commercial providers.
Michael Klöppel-Gersdorf, Adrien Bellanger, Thomas Otto
Decision Tree Based Incident Detection for Distributed Progressive Signal System in an Organic Traffic Control System
Abstract
Today’s world-wide traffic congestion significantly contributes to wastage of time and fuel in addition to environmental stress, such as air pollution due to \(CO_2\) emissions. To address these concerns, traffic management systems are continually developed and improved to become intelligent and adaptable. For instance, self-organizing strategies like the Organic Traffic Control (OTC) system present benefits such as enhanced efficiency, resilience, and scalability. Beyond the de-centralised and traffic-responsive manipulation of traffic signals, synchronised adjustment of traffic lights through Progressive Signal Systems (“Green Waves”) plays an important role. As previous work we presented an approach for creating decentralised PSS, taking recognised incidents into account to steer the traffic flows. In this paper we further propose a decision-tree based incident detection mechanism.
Ingo Thomsen, Sven Tomforde
Monitoring Traffic Congestion Using Trust-Based Smart Road Signs
Abstract
The evolution of Intelligent Transportation Systems (ITSs) enabled the emergence of traffic management applications, with the aim to enhance the traffic flow and ease the congestion by monitoring the traffic. However, the efficiency of these applications resides on the accuracy of the shared traffic information. Accordingly, trust management models are applied to secure the Vehicular Ad-hoc NETwork (VANET) and to assess the reliability of the data shared within the vehicular network. In this paper, we propose a proof-of-concept of the trust framework proposed in [2]. The main objective is to observe the utility of applying trust management models to the intelligent transportation systems. The simulation results show that deploying trust-based Smart Road Signs (SRSs) helps to alleviate the traffic congestion around junctions by displaying the traffic state to users and offering them the opportunity to take alternative roads.
Rihab Abidi, Nabil Sahli, Nadia Ben Azzouna, Wassim Trojet, Ghaleb Hoblos
Infrastructure-Assisted Collective Perception Service with Emphasis on Vulnerable Road User Perception
Abstract
The safety of Vulnerable Road Users (VRUs) is a pivotal element in assistance-supported and autonomous driving systems, necessitating heightened awareness of pedestrians and cyclists among road users. While Intelligent Transport Systems (ITS) employ on-board sensors to identify VRUs, they are insufficient in complex traffic environments, i.e. urban city scenarios, where not all relevant entities are captured. To address this, the Collective Perception Service (CPS) offers supplementary Vehicle-to-Everything (V2X) communication for sharing information about these entities with nearby ITS stations (ITS-Ss). Additional deployment of Road Side Units (RSUs) can further enhance the performance in terms of environmental awareness.
Our earlier research established that utilizing a relay and aggregation mechanism for Collective Perception Messages (CPMs) implemented in RSUs enhances ITS-Ss’ perception of VRUs. However, it is essential to optimize the use of network resources given the limited bandwidth of the V2X channel. Unlike our prior work, which did not specify Road-Side Unit (RSU)-specific CPM rules and had a constant CPM dissemination rate, the current study incorporates the Value of Information (VoI) to prioritize more relevant objects for surrounding ITS-Ss. Our simulation results according to ETSI standards show that this enhanced approach effectively reduces network channel load while maintaining high VRU awareness among vehicles.
Vincent Albert Wolff
Backmatter
Metadaten
Titel
Smart Cities, Green Technologies, and Intelligent Transport Systems
herausgegeben von
Cornel Klein
Matthias Jarke
Jeroen Ploeg
Karsten Berns
Alexey Vinel
Oleg Gusikhin
Copyright-Jahr
2025
Electronic ISBN
978-3-031-70966-1
Print ISBN
978-3-031-70965-4
DOI
https://doi.org/10.1007/978-3-031-70966-1

Premium Partner

    Bildnachweise