Ebook: Emerging Cutting-Edge Applied Research and Development in Intelligent Traffic and Transportation Systems

The International Conference on Intelligent Traffic and Transportation (ICITT) is a major event for academics, researchers, and industrialists engaged in intelligent traffic and transportation research. Initiated as a national Intelligent Traffic and Transportation workshop by ICITT (a consortium of key university professors of intelligent traffic and transportation applied research) and held annually since it became an international conference in 2016, ICITT is renowned as a friendly and inclusive platform that brings together a broad community of researchers who share the common goal of developing and managing the engineering and technology revolution in transportation systems, and the operations key to sustaining the success of the intelligent traffic and transportation industries. For more than a decade, ICITT has been the main research conference worldwide for intelligent traffic and transportation, successfully bringing researchers, academics, and industrialists together to share their knowledge, expertise and experience.

The ICITT Consortium is an independent body established in 2010 and led by Professor Mahmoud Shafik. Its main aim is to promote engineering and technology education, training, research and knowledge transfer, and exchange in the area of intelligent traffic and transportation. To achieve this, conference chairman, together with consortium, and committee members, maintains a close association with international bodies concerned with the training and continuing development of professional engineers and technologists, while responding to appropriate consultative and discussion documents and other initiatives. The conference also plans major industrial visits to small, medium and large industrial enterprises (SMEs and LEs) to enhance conference participants’ knowledge and experience of the existing and future industrial revolution (digital transformation, industry 4.0 and beyond, autonomous technology, industrial automation, and 2D and 3D data streaming) and its impact on the intelligent traffic and transportation market.

In 2016, the ICITT conference was given the title International (ICITT) to reflect current trends in intelligent traffic and transportation engineering and technology and to promote the exchange of research, engineering, and the application of technological experience internationally. The ICITT has taken place in previous years in the following countries:

ICITT 2016 China

ICITT 2017 France

ICITT 2018 Sweden

ICITT 2019 Netherlands

ICITT 2020 VR Online

ICITT 2021 VR Online

ICITT 2022 France

ICITT 2023 Spain

ICITT 2024 Italy

The ICITT 2024 conference embraces a plenary speech presented by conference founder and chairman Professor Dr Mahmoud Shafik, University of Derby, UK, and three keynote speeches, given by Professor Dr Alexey Vinel, Institute of Technology (KIT), Germany; Dr Stephen Robert Pearson, CEO of Smart Technology Group, UK; and Professor Dr Stefano Barberis, University of Genoa, Italy.

This conference proceedings is SCOPUS indexed and the third iteration of the conference-wider publication to ensure that international scholars are able to make the best use of the conference. This year, the selected peer reviewed papers focus on: intelligent traffic and transportation; autonomous technology; industrial automation; artificial intelligence; machine, deep and cognitive learning; distributed networking; transportation in future smart cities; hybrid-vehicle technology; mobility; cyber-physical systems; design and cost engineering; enterprise information management; product design; intelligent automation; ICT-enabled collaborative global manufacturing; knowledge management; product-service systems; optimisation; product lifecycle management; sustainable systems; machine vision; industry 4.0; and navigation systems.

The proceedings presents 37 selected papers, representing an acceptance rate of 60%.

We look forward to welcoming you at ICITT2024 - http://www.icitt.org/index.html and hope that every delegate will enjoy the conference.

Mahmoud Shafik

Editor & ICITT Conference Chairman

Acknowledgements

On behalf of the ICITT organising consortium and committee, we would first and foremost like to take this opportunity to thank all the contributing authors for the high-quality papers they have submitted, the reviewers for their time and constructive comments, the keynote speakers for sharing their research with the delegates, and the local organizing committee for their meticulous preparation of the conference. Our thanks also go to the Programme Committee members who helped to review papers and ensure the high quality of the conference.

We would also like to acknowledge ICITT consortium members and industrial partners for their support for this conference. The conference theme of ICITT2024, 2D and 3D Data Streaming, is one of the critical safety factors for traffic and transportation. Within this context, ICITT2024 will bring researchers, academics, and industrialists together to share their vision, knowledge, and experience, and to discuss emerging trends and new challenges in the field.

The article describes how to effectively dispatch hundreds of thousands of ride requests per hour, with thousands of cabs. Not only which cab should pick up which passenger, but which passengers should share a ride and what is the best pick-up and drop-off order. An automatic dispatching process has been implemented to verify feasibility of such cab sharing solution, simulation was used to check quality of routes. Performance of different programming tools and frameworks has been tested. Thousands of passengers per minute could be dispatched with basic algorithms and simple hardware and they can be dispatched in a cab sharing scheme very effectively, at least 11 passengers per cab per hour. The spotlight is on practical aspects, not well-known theory. The goal is to verify feasibility of a large-scale dispatcher and to give its benchmark. Implementation of algorithms including a dispatcher and simulation environment is available as open source on GitHub.

Traffic environment carrying capacity is a key index to measure the sustainable development of urban traffic, and the coupling coordination between traffic environment carrying capacity and urbanization is an important embodiment of high-quality urban development. Taking Xi’an as the object, this paper constructs a dual-system evaluation framework of traffic environment carrying capacity and urbanization, which is composed of 32 indexes, and studies the coupling coordination relationship and obstacle factors between traffic environment carrying capacity and urbanization by using entropy weight method-coefficient of variation combination weighting method, coupling coordination degree model, relative development degree model and obstacle degree model. The research findings are as follows: (1) During the study period, the overall traffic environment carrying capacity of Xi’an showed are current changing trend of “rising-falling”, and the urbanization “steadily rising”. (2) The degree of coupling coordination between traffic environment carrying capacity and urbanization shows a trend of “steady increase”, and type of the coupling coordination realizes an obvious change of “antagonism-running in-coordination”. (3) The leading obstacle factors of traffic environment carrying capacity are the average of urban road traffic noise, the number of vehicles per mileage operated by the bus unit, and the density of urban road network. The leading obstacle factors of urbanization are population density, Engel coefficient of urban residents and the proportion of employees in the tertiary industry. In addition, the average of urban road traffic noise, the density of rail transit network and the proportion of transportation financial expenditure are the key indexes which hinder the further improvement of traffic environment carrying capacity in Xi’an.

Roads are considered the artery of countries that feed cities and regions and have great importance in achieving high levels of services for its users in facilitating their transportation and their goods from one place to another. Governments attach increasing importance to road conditions to achieve sustainability in the services provided to roadway users and thus increase users’ satisfaction with government services. Perhaps one of the things that governments aim to monitor the road surface conditions. Where, Keeping the pavement in high-quality conditions can achieve the highest levels of comfort while driving, reducing vehicle maintenance costs, reducing traffic accidents, and thus increasing traffic safety. Monitoring the pavement condition is considered one of the significant applications to evaluate the pavement condition by determining the type and severity of defects on the pavement surfaces. In this study, a vibration-based method is used to measure the level of comfort riding a passenger car at a speed of 40 km/hr on local roads in Melbourne. The vibration signals are measured using an accelerometer sensor fixed on the front dashboard of a sedan car. The vibration signals then are smoothed and filtered to be used for the detection of the pavement defect locations according to the fluctuations in signals. Besides, the filtered vibration data was then divided into training and testing databases to develop an artificial neural network model named Long-Short-term memory LSTM. The LSTM is used to automatically detect and classify the quantity and quality of pavement defects according to the conducted vibration data.

A bibliometric analysis of 1000 publications were obtained from the Publish and Perish application from 2000-2023, which is then processed in VOSviewer to display the connection and relevance between publications. This research produced 826 journal articles, 128 proceedings articles, 29 book chapters, 6 posted content, 3 datasets, 3 others, 2 components, 2 reports, and 1 book. In addition, the most frequently used keyword is driver, and 2019 was the year with the most publications, 109. In conclusion, research on driver’s behavior on signalized intersections is still relevant and can be used for research discussion.

Trains are a popular mode of transportation in Indonesia. People from higher and lower socioeconomic brackets are increasing interest in the industry as it gets more well-known. Some safety equipment is available, but mishaps can still occur. People attempting to determine where a problem originated often use such as the Ishikawa model for assistance. The Poisson model is well-suited for crash simulation, and this work provides a valuable method for doing so. A root cause analysis allows for identifying and eliminating the accident’s most significant contributing factors. From 1999 to 2014, data was gathered through a variety of intermediaries. According to Ishikawa’s research, ten primary factors influence the frequency of accidents. There are issues with the route, the train, the signals, the upkeep, the communication, the processes, the personnel, the climate, and the machinery. Next, we use the Dispersion and Vuong tests to see which of the regression models provides the most accurate forecasts. Using the Vuong test, the Zero-inflated model has the best predictive power for accidents and events, with p-values of 0.19695481, 0.1301056, and 0.0689108. Train derailments, collisions, and SPAD are the most common causes of accidents.

The increase in mobility in Poland is one of the most visible manifestations of the country’s dynamic socio-economic development since joining the European Union in 2004. This phenomenon reflects both technological advances and the changing needs and expectations of citizens. The increasing number of vehicles, and thus traffic participants, poses numerous challenges to society and authorities in particular in the context of ensuring traffic safety. The publication conducted a study of the impact of calendar-related factors (day of the week, month) on the number of accidents in Poland. The purpose of the article was to assess, whether these are significantly influential factors and to present the issue of road accidents in the context of the current state of road safety in Poland as measured by the number of victims and injuries. The number of accidents was shown to be significantly dependent on the month, as well as the day of the week. Attention was also paid to the issue of the severity of accidents in Poland compared to other EU countries, in view of which recommendations aimed at minimizing the number of victims were indicated.

Traffic congestion has been a major concern in urban areas due to its strong impact on various social, economic, and human safety sectors. Understanding the relationship and analyzing the trends and patterns between congestion and accidents can strengthen the strategy for reducing traffic congestion. Research on causes of accidents and their impact on congestion has recently been explored on a greater scale, but there is still a lot of scope for vast areas of improvement. To tackle this issue, we built a Bayesian Network (BN) model for analyzing and predicting congestion probability that can occur due to accidents. In this work, the complexity of handling real data obtained from Darmstadt city is described in detail. The accidents and congestion are correlated by introducing a novel threshold-based approach, which identifies congestion based on the change in vehicle density immediately following an accident. Different thresholds are explored to determine the most reliable measure of congestion, with the T₄ threshold emerging as the optimal choice. Moreover, the proposed BN model is evaluated against several machine learning models, demonstrating competitive performance and its ability to understand the root cause of traffic congestion.

This study aims to investigate the chaotic characteristics of subway passenger flow during the COVID pandemic in order to improve the prediction accuracy of passenger flow. The research focuses on the daily traffic and passenger flow growth at Chengdu subway stations, using the maximum Lyapunov index to determine the temporal characteristics of chaos. Additionally, the study compares the prediction accuracy of passenger flow growth using an ARIMA model and a Volterra model. Furthermore, a Granger causality test is conducted to examine the relationship between chaos and the prediction results. The findings reveal that chaos accounts for 96.85% of the time series of daily passenger flow growth during COVID, and the overall prediction error of the Volterra model is 23.37% lower than that of the ARIMA model. Causal analysis demonstrates that chaos is an important factor impacting prediction accuracy.

This research paper examines the influence of Saudi Vision 2030 on the advancement of sustainable transportation and intelligent infrastructure in Saudi Arabia, specifically emphasizing the incorporation of renewable energy sources. The study evaluates the existing condition of transportation and infrastructure within the country, identifies the primary obstacles and prospects encountered by the sector, and assesses the efficacy of Saudi Vision 2030 in tackling these challenges. Furthermore, the research explores the potential of renewable energy sources, including solar and wind power, to facilitate the progression of sustainable transportation and intelligent infrastructure in Saudi Arabia. Through a quantitative research approach, this study sheds light on the impact of Saudi Vision 2030 and provides insights into the future prospects of sustainable transportation and intelligent infrastructure development in Saudi Arabia.

The process of urbanization on a global scale has generated a significant increase in metropolitan populations, which in turn brings with it a series of challenges for the management of transport infrastructure. In this context, the importance of accurate traffic flow prediction in urban traffic management systems stands out, with the city of Catania being used as the focus of this study. However, predicting traffic flow faces challenges, such as the high costs associated with acquiring extensive real traffic data, particularly when installing sensors on every road is not feasible. To address the issue of missing traffic flow data on roads without sensors, this study proposes an innovative approach based on machine learning, using the Long Short-Term Memory architecture and incorporating both sensor and floating car data. The results obtained are thoroughly analyzed and discussed, highlighting the ability of the LSTM model to provide accurate predictions of urban traffic, even with a limited amount of data available. These findings highlight the relevance of employing advanced machine learning techniques in the efficient management of urban mobility, aiming to improve the quality of life in cities and deal more effectively with the challenges of contemporary urban traffic.

Road markings have always been vital for driver safety, but with the rise of intelligent and autonomous vehicles, Advanced Driver Assistance Systems (ADAS) are taking on the task of perceiving and interpreting these markings. Road markings can be irregular and vary in color from one country to another, making them even more difficult to detect in adverse weather conditions such as rain or fog. To meet these challenges, the detection of road markings was evaluated in adverse weather conditions in an indoor fog & rain platform. The night performance of a car equipped with a camera using a road marking detection algorithm was evaluated on several road markings, with different headlights illumination conditions, and within several fog and rain conditions. A luminancemeter camera was also used to measure contrast level on the road markings and surrounding pavement surface.

The study showed a link but not a direct correlation between contrast and detection: when contrast is below a given threshold, the marking is never detected, when contrast is above another threshold, the marking is always detected. Moreover, between these two thresholds values, nothing can be concluded. Weather conditions had a significant impact, with heavy rain causing no detections and dense fog allowing only structured markings to be detected when headlights were on low or high beam. The impact of markings and headlight illumination mode was particularly significant in intermediate weather conditions.

This work tackles the problem of building trustworthy AI for the automotive industry in a context in which generic guidelines have already been proposed yet their instantiation is far from straightforward. The following work presents a first iteration of a methodology for developing trustworthy AI in CCAM (Connected, Cooperative Autonomous Mobility) applications as a meet-in-the-middle approach integrating generic European ethics guidelines (top-down) as well as leveraging the scenario approach (bottom-up) as a well-known practice in the automotive field. The result is a first version of application of the trustworthiness criteria into a use case of AI-enhanced ADAS and a related scenario subset. The premise is that in order to truly develop trustworthy AI, trustworthiness criteria are necessary but must be coupled with solid practices in the field and systems of reference in order to ensure integration of ongoing and proven engineering processes to the new challenges and opportunities linked to the development cycle of AI-based systems.

As Unmanned Aerial Vehicles (UAVs) become integral to urban infrastructure, their ability to communicate effectively with human operators and adapt to dynamic environments is crucial. This paper presents an innovative approach to enhancing UAV performance in transportation and traffic monitoring by integrating emotional intelligence through the PAD (Pleasure, Arousal, Dominance) model. The proposed system architecture includes a comprehensive data collection layer that gathers diverse inputs from sensors and contextual information, a perception analysis layer that processes these inputs to generate emotional states using the PAD model, and a response layer that translates these emotional states into specific behaviors through behavioral mapping and adaptation modules. Detailed methodologies, including pseudocode and flowcharts for key modules such as data normalization, PAD calculation, mood updating, and mood octant determination, are provided for clarity and reusability. The system’s effectiveness is validated through practical scenarios such as routine surveillance, heavy traffic monitoring, and incident detection, demonstrating significant improvements in UAV adaptability and interaction. Key contributions include the development of a multi-dimensional emotional model for UAVs, a dynamic mood updater module, and the successful application of the PAD model in complex traffic monitoring scenarios. This approach significantly enhances UAV performance, ensuring more natural interactions with human operators and better adaptability to real-time traffic conditions. It paves the way for future exploration into emotionally intelligent autonomous UAV systems.

The study investigates the equity of public transportation systems in two Mediterranean tourist cities, Palma and Málaga, using open GTFS data, GIS analysis, and socio-economic variables. It aims to compare the distribution of public transport services, focusing on horizontal equity and vertical equity. The methodology involves calculating service levels for each stop and section, considering walking catchment areas, and assessing potential public transport needs using the Public Transport Need Index. The findings reveal significant disparities in transport service distribution in both cities, with Palma showing a high concentration of services in the city centre and specific vertical axes, leaving peripheral areas with insufficient coverage. In contrast, Málaga demonstrates a more evenly distributed transport network, benefiting both residents and tourists. The study concludes that Palma exhibits considerable horizontal inequity, particularly affecting low-income residents in suburban areas, while Málaga offers a more equitable service distribution. However, both cities face challenges in meeting the transport needs of socially disadvantaged groups, underscoring the necessity for more inclusive and demand-responsive transport planning.

Subway systems serve as vital components of urban transportation infrastructure. Due to the critical concern for transportation safety, research on the resilience and recovery capabilities of subway systems is therefore of great significance. This paper proposes a recovery model for cascading failures in subway systems and the recovery measures and cascading failures are addressed simultaneously. The recovery measures in the model include both station repairs with resource allocation and passenger evacuation. The recovery model incorporates five key factors: the maximum number of stations in repair, the sequence of station repairs, the total amount of repair resources, the allocation of repair resources, and the speed of passenger evacuation. The model is applied to different subway networks, simulating the deliberate attack on the station with the highest load. Simulation results demonstrate the superiority of the proposed capacity-based resource allocation method. Moreover, the effectiveness and importance of passenger evacuation in halting the propagation of cascading failures and improving network recovery are examined. Finally, the impact of station capacity on the recovery outcome is explored, We reveal an optimal station capacity setting that could minimize network resilience loss during attacks. This study holds significant implications for the development of resilient and sustainable subway systems.

This paper presents the results of intelligent traffic light management (TLM) which improves the traffic efficiency via optimally controlling the green lights’ time interval and selecting the traffic phases. As the control problem is stochastic and difficult to be modeled accurately, model-free reinforcement learning (RL) is applied in this work. To stabilize the training process and mitigate the overestimation issue of conventional deep Q-learning based RL methods, we developed an RL algorithm with double deep Q-network (DQN) and a clipping function for the TLM problem with a discrete action space. The advantage of this clipped version of double DQN over other Q-learning-based algorithms is demonstrated in this work. Furthermore, the performance of RL-based TLM is compared with both fixed-time and adaptive rule-based TLM by using PTV Vissim which is a multi-modal traffic simulation software as the testing platform in this work.

The rapid expansion of anthropogenic infrastructure has increased commuting distances and patterns, particularly in countries like Qatar where personal vehicles dominate transportation. This trend has contributed to traffic congestion. This study introduces a Doha Driving Cycle (DC) to facilitate a tool that can be used to analyze various aspects of vehicle performance, including tailpipe emissions. The DC is developed using real-world data collected from vehicles equipped with on-board diagnostics devices. This data was meticulously processed and filtered before employing the microtrip approach to construct the driving cycle. Two distinct driving cycles were created to reflect seasonal variations in Doha’s driving patterns: one for the summer, characterized by greater variability in speed and acceleration, and one for the winter, marked by speeds with low variance. The resulting driving cycles reveal significant deviations from the Worldwide Harmonized Light Vehicles Test Cycle (WLTC), underscoring the necessity of creating site-specific driving cycles for accurate environmental and performance assessments in Doha.

The goal is to bring together an in-depth analysis of physics-based deep learning approaches in transportation domains and classify them according to their applicability. To carry out the systematic literature search, a Preferred Reporting Items for Systematic Reviews and Meta-Analysis flowchart is used with certain inclusion and exclusion criteria. Different keyword searches are carried out in the Scopus and Web of Science databases, followed by relevant references and citation analyses to find eligible papers subject to a full-text peer review. Finally, the classification and analysis of these papers take place based on their applicability. 141 and 39 records were found by the initial database search and referencing and citation analysis respectively. A total of 65 documents were selected to carry out full-text reviews, and finally, 35 documents were included in the study. Based on the applications of physics-informed deep learning in transportation engineering, the authors classified the literature into three major categories: 1) safety assessment and safety analysis, 2) model preparation, and 3) prediction and estimation. Finally, this research also provides the challenges and future directions in this emerging field.

Analyzing the articulation mechanism of urban multi-modal transportation network and mastering the operation of the road network to meet the travel demand of tourists between different scenic spots within the city. Firstly, the hypernetwork theory is used to construct a super network model of urban multi-modal transportation system. Secondly, considering that the main factor affecting travelers’ route selection is time volatility, and based on this, the evaluation index system of the road network operation status is improved, and the improved index system considers the influence of unblocked reliability on route selection. Subsequently, the frequency of occurrence of different road network traffic states is transformed into the state transfer probability of the Markov decision process, and a minimum generalized cost travel decision model considering tourists’ economic, time, and comfort costs is developed, and an algorithm was designed to solve the frequency of different road network traffic states is transformed into the state transition probability of Markov decision process, and the minimum generalized cost travel decision model considering tourist economic cost, time cost and comfort cost is established, and the algorithm is designed to solve it. Finally, the road network between scenic spots in Yanta District of Xi’an is taken as an example to verify the validity of the model. The results of the study show that there are differences in the travel modes or routes chosen by tourists of different ages under different road network traffic states, proving the validity of the model.

The current scarcity of viable simulation solutions for cooperative and connected driving research is one of the main reasons to start dedicating efforts to generate robust validation environments. Most current simulators focus on the egocentric perspective of the automated vehicle, with cooperative information being either non-existent or difficult to access. If soon the industry migrates towards connectivity and cooperation paradigms, it will then be necessary to build simulation environments to validate the cooperative behaviors that arise from the interactions between traffic agents. This work focuses on the possibilities offered by Carla simulator integrated with ROS framework for multi-agent simulation and arbitration capabilities between intelligent infrastructure and automated connected vehicles. By combining a wide variety of methodologies, the solution proposed in this work allows generating an effective validation framework for coordinated and autonomous cooperative driving.

To be effective in lane positioning, automated vehicle cameras must be able to detect the road making lines, even if the road marking is very old. Several studies have attempted to define detection threshold for various physical indicators characterizing markings, but the results are not unanimous. A specific instrumentation was carried out on a test track to generate several types of road marking lines (from very good to extremely worn). Experiments were conducted by day and night to study the detection performance of a Machine Vision (MV) system on a dry road. The road markings lines were characterized by physical indicators expressing their state of wear and their contrast with the surrounding road. The MV system was always able to detect the marking lines, including the most severe case of wear. This result raises the question of the relevance of the threshold values to be ensured for good detection by automated vehicles.