Next Article in Journal
Navigating Environmental Tax Challenges: Business Strategies for Chinese Firms Sustainable Growth
Previous Article in Journal
Toward Greener Supply Chains by Decarbonizing City Logistics: A Systematic Literature Review and Research Pathways
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
Sustainability
Volume 16
Issue 17
10.3390/su16177514
sustainability-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite question_answer Discuss in SciProfiles thumb_up
...
Endorse textsms
...
Comment
first_page
settings
Order Article Reprints
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
Review

4IR Applications in the Transport Industry: Systematic Review of the State of the Art with Respect to Data Collection and Processing Mechanisms

by
Olusola O. Ajayi
1,*,
Anish M. Kurien
1,
Kareem Djouani
1,2 and
Lamine Dieng
1,3
1
F’SATI, Faculty of Engineering and the Built Environment, Tshwane University of Technology, Pretoria 0001, South Africa
2
LISSI Laboratory, Université Paris-Est Créteil, 94000 Créteil, France
3
MAST Laboratory, Université Gustave Eiffel, All. Des Ponts et Chaussees, 44340 Bouguenais, France
*
Author to whom correspondence should be addressed.
Sustainability 2024, 16(17), 7514; https://doi.org/10.3390/su16177514
Submission received: 20 May 2024 / Revised: 13 August 2024 / Accepted: 27 August 2024 / Published: 30 August 2024
Browse Figures
Review Reports Versions Notes

Abstract

:
Transportation systems through the ages have seen drastic evolutions in terms of transportation methods, speed of transport, infrastructure, technology, connectivity, influence on the environment, and accessibility. The massive transformation seen in the transportation sector has been fueled by the Industrial Revolutions, which have continued expansion and progress into the fourth Industrial Revolution. However, the methodologies of data collection and processing used by the many drivers of this progress differ. In order to achieve a better understanding of the impact of these technologies, in this study, we methodically reviewed the literature on the subject of the data collection and processing mechanisms of 4IR technologies in the context of transport. Gaps in present practices are identified in the study, especially with regard to the integration and scalability of these technologies in transportation networks. In order to fully reap the rewards of 4IR technologies, it is also necessary to apply standardized methods for data gathering and processing. In this report, we offer insights into current obstacles and make recommendations for future research to solve these concerns through a comprehensive evaluation of the literature, with the goal of promoting the development of intelligent and sustainable transportation systems.

1. Introduction

The word “transport” can be considered to be a partition-able word (trans-port), where trans is a prefix that emanates from Latin, referring to movement or carrying from one place to another. The suffix, “port”, on the other hand, implies a place (city, town or land) with access to water, through which loads can be conveyed from one end to the other. Transportation systems could therefore be described as a means of moving items, goods, people, and objects from one point to another. Transport can also be described as a passage, conveying things from one location to another in a safe mode. The authors of [1] highlighted that a sustainable transport system must provide mobility and accessibility to all urban residents in a safe and environment friendly mode of transport.
Transportation systems are intricately interwoven with nearly every facet of human activity, from work and production to leisure and consumption, supporting a worldwide flow of goods, and linking societies. It is little wonder that the authors of [2] described it as the backbone of any economic, cultural, social and industrial development. As these large technical systems become pervasive and integral constituents of modern society, the manner in which human forces perceive, analyze, and attempt to shape the development of these systems becomes increasingly complex, and increasingly important [3].
Mobility in the olden age can be considered undoubtedly different from modern-day transportation, since transportation was achieved through the use of animals (horse-riding, donkey-riding, oxen-riding) and wheeled vehicles (wagons and carts). Today, transportation systems have witnessed significant evolution, which has been driven largely by changes and developments in digital technologies, which include artificial intelligence, big data, machine learning, blockchain, cloud computing, the IoT, fog computing, etc. The level of impact of these technologies in easing mobility cannot be over-emphasized. The revolution that started in the 18th century undoubtedly had huge impacts on the growth recorded in the transport sector and gave birth to a modern transportation structure that is today described as the Intelligent Transportation System (ITS).
Figure 1 provides an overview of the various Industrial Revolutions. The integration and deployment of these innovations led to a sustainable global economy. The cyber physical system (CPS) was key in the birth of the fourth revolution, in 2016, which was first defined after the World Economic Forum (WEF) [4]. The revolution saw the adoption of artificial intelligence, the internet of things (IoT), big data, machine learning, virtual and augmented reality, and blockchain, and emerging digital transformation approaches are contributing to the great transformative experience currently being witnessed in the evolution of the industrial space.
The use of 4IR technologies in the transportation sector is transforming the way in which transportation systems function, improving efficiency, safety, and sustainability. This is especially true regarding data collection and processing. Although the 4IR technologies have demonstrated great prowess in transforming the transportation industry and are aiding in the fulfilment of a smart transportation network, these technologies rely heavily on data. Modern transportation systems rely heavily on data, since they allow for real-time analysis, monitoring, and decision-making. The process of creating effective, safe, and sustainable mobility systems might be hampered by data collection techniques that are not optimal or efficient for the transportation industry. By revisiting and evaluating earlier studies in these fields and offering pertinent recommendations for the future, in this study, we seek to carefully dissect the data collecting and processing methods of these technologies in order to address these difficulties.
The remaining parts of the structure of this research study are as follows: The methodology is presented in Section 2; related works (general literature review and specific literature review) are explained in Section 3; the identified gaps are in Section 4; Section 5 is a discussion of the findings; and the conclusion and recommendations are presented in Section 6.

2. Methodology

To identify and evaluate existing related research works in this domain, in this study, we adopted systematic literature review method. As part of the steps for achieving the purpose of this study, an S3-Triangular procedure was used for the execution of the systematic review considered in the study. The first part of the procedure is the search key approach; the second is source selection; and the last is the selection of closely related papers.

2.1. Search Key/String Approach

Table 1 displays the number of articles retrieved under each group, as well as the search terms used to retrieve the articles used for this investigation. Two clusters were created out of the search results: the first focused on “4IR technologies”, and the second used the term “Data Collection and Data Processing” to find additional relevant papers. The search was limited to papers published between 2014 and 2024 in order to include research articles that were not older than 10 years, as there were not many publications on 4IR during that time frame, according to our search (104 papers were found to be referenceable during the chosen period). We additionally employed keywords in serial numbers 3 through 10 to enable a more thorough search that would provide access to more papers on this subject (a total of 61 were found to be citable).

2.2. Source/Database Selection

Essential studies that addressed the subject under investigation were accessed (relevant articles published between 2014 and 2024) from recognized publishing outlets and repositories. The selected database sources (IEEE Xplore, Elsevier Science Direct, ACM, Taylor and Francis, Springer, and Google Scholar) were based on the premise of accessibility/subscription, as well as their vast collections of peer-reviewed journals with high density/repository of Engineering-, Computing Science-, and Technology-related articles. The source selection, presented in Table 2, shows the number of papers retrieved from the various chosen publishing outfits using the search strings presented in Section 2.1 (Table 1).

2.3. Selection of Closely Related Articles (Inclusion and Exclusion Criteria)

Upon initiating this study, we located and downloaded 203 journal articles as part of our comprehensive review of the literature on “4IR Applications in the Transport Industry: Systematic Review of the State of the Art with respect to Data Collection and Processing Mechanisms”. Applying preset inclusion and exclusion criteria to guarantee relevance, quality, and applicability led to the deletion of 79 articles and the admission of 124 articles. Articles from peer-reviewed publications published in English between January 2014 and December 2023 met the inclusion criteria. These articles included empirical investigations, randomized controlled trials, systematic reviews, and meta-analyses.
Included in the list of exclusion criteria were articles that were published outside of the specified time range, in languages other than English, from non-peer-reviewed sources, and that contained opinion pieces, book reviews, letters to the editor, or editorials. Articles lacking full-text availability and failing to directly tackle the research problem were likewise excluded. However, following rounds of expert assessment/review by reviewers of this paper, the included papers were found to be inadequate. As a result, the authors accessed and downloaded seventy (70) additional articles with fresher, more sensible and logical keywords. The searched year range was also extended to cover articles published in 2024. By using the same filtering technique, 29 journal articles were eliminated and 41 were deemed worthy of inclusion. In total, 165 journals were used, making up 60.4%, while 108 journals were discarded, making up 39.6% (Figure 2). Table 3 and Figure 3 present further information on the number of articles used and not used in this study.

3. Related Works

3.1. General Literature Review

4IR has a vast number of advantages that demonstrate critical services’ benefits. The fourth Industrial Revolution has brought forth several benefits for the health sector, including better healthcare outcomes and more precise diagnoses, thanks to machine learning and artificial intelligence. The authors of [5] highlighted that Internet of Things, cloud and fog computing, and big data technologies are revolutionizing eHealth and its whole ecosystem, moving it towards Healthcare 4.0. In [6], the authors investigated the need for the transition of Industry 4.0 to Pharmacy 4.0. The authors identified and argued for the elimination of the barriers to the full implementation of Industry 4.0 for the pharmaceutical arm of the health sector in developing nations. Agriculture and food products are further essential services to which 4IR has greatly contributed. A further study [7] demonstrated the deployment of ML and IoT in the automatic prediction of crop water requirements. The authors of this article implemented a 4IR-enabled Smart Irrigation System that minimizes water usage within the agriculture sector to assist farmers in obtaining live data on soil moisture, weather API, the water capacities of different crops, and plugging sensors to predict when farmers can irrigate. The technologies of the fourth Industrial Revolution (4IR/Industry 4.0) have been catalysts for all fields of human endeavor, permeating the water, energy, and food (WEF) nexus. The application of 4IR to the WEF nexus will lead to economic sustainability, social sustainability, and environmental sustainability [8].
Apart from these and a few other essential services, transportation is a notable and essential service whose important features cannot be over-emphasized. A critical look at the transportation ecosystem shows that these technologies are enhancing safety and efficiency, streamlining operations, and enabling data-driven decision-making. Several systematic literature review research works have been carried out on the general influence and impact of 4IR technologies on the transportation sector. The authors of [9] developed a simulation model to evaluate various traffic scenarios involving truck platoons. The authors reviewed the issue of the safety of mixed traffic flows involving truck platoons, human-driven cars, and human-driven trucks, with a focus on the stochastic behavior of human drivers. The authors extended their work in [10] to assess the changing conditions of the transportation system due to political and technological shifts and discussed the issue of the sustainability of the system. The work reviewed in [11] highlighted the history of IRs and established the relationship between 4IR and the previous IRs. The paper presented the enhancement and improvement 4IR brought to the transportation sector in developing countries. Another study [12] reviewed the transformative impact of 4IR on transport systems in low-income, high-growth countries. The combination of IoT and RFID technology provided a more responsive and efficient public transport system that reduced congestion and waiting times [13]. The authors of [14] gave a comprehensive review on the impact of 4IR emerging technologies on freight transportation. In [15], the authors divulged and discussed five 4IR technologies that brought transformation to the transportation system. The authors of [16] emphasized the increasing importance of smart technologies (AI, ML, IoT etc.) in enhancing higher service levels and ensuring lower operating costs in logistics and transportation systems. The authors of [17] assessed the effects of 4IR technologies on the effective management of road transport assets, while [18] demonstrated the deployment of 4IR technologies in reducing traffic jams.
The work presented by the authors of [19] discussed the disruptive changes 4IR brought to the maritime sector, as well as its neglect of human elements in its transition, thereby advocating for the full adoption and implementation of Industry 5.0. The focus of [20] was the application of an Intelligent Transportation System in the context of 4IR. The authors examined path computation algorithms for determining optimal routes in Advanced Traveler Information Systems. The authors of [21] discussed the influence and applications of 4IR technologies in optimizing transportation systems in smart cities, with an emphasis on how they can minimize traffic problems and increase infrastructure usage. Similarly, the authors of [22] reviewed the roles and impact of AI and ML in solving real-time transportation challenges. The authors of [23] highlighted the transformative capabilities of 4IR in achieving smart and sustainable logistics. The systematic review paper examined how 4IR enhances economic efficiency and environmental performance. The authors of [24] provided an in-depth review on the 4IR technologies used in developing smart transportation systems, highlighting their capabilities and the communication protocols used. The work presented by the authors of [25] presented the Intelligent Transportation System as the solution to transportation challenges, through its leveraging of 4IR technologies like AI, ML, cloud computing, and the Internet of Vehicles to enhance efficiency, address and avert congestion, pollution and accidents in smart cities. Furthermore, the authors of [26] emphasized the exploration of an Intelligent Transportation System in tackling traffic challenges in urban India, involving the leveraging of the transformative effects of 4IR. The research work presented in [27,28,29] emphasizes how a big data analytics framework can be integrated to enhance Intelligent Transportation Systems’ design and application, making transportation systems safer, more efficient, and profitable in the era of 4IR, whereas [30] prioritizes data-driven models in enhancing transportation efficiency in the era of 4IR. The authors of [31,32] underscore the important roles of 4IR in advancing the field of Intelligent Transport Systems by leveraging natural language processing and modern sensor technologies to ensure further advancement in Intelligent Transportation Systems’ reliability, security, scalability, and sustainability, whereas the emphasis of the authors in [33,34] was on its roles in road safety. The authors of a further study [35] recognized and reviewed the transformative effects 4IR has brought to the data collection mechanism in the transportation sector. The authors of [36] addressed the transformative effects of 4IR on the workforce landscape.
Table 4 provides a summary of the impact of IR technologies on the Transport System, while Figure 4 and Figure 5 provide an overview of the trends in the evolutionary impacts and the relationship between the technological revolutions, respectively.

3.2. Specific Literature Review

The technologies of the fourth Industrial Revolution (4IR) are changing many industries, and the transportation industry is no exception. The confluence of technologies such as artificial intelligence (AI), the Internet of Things (IoT), big data, and cloud computing is revolutionizing the transportation sector at a rate never seen before (Table 5; Figure 6 is the corresponding chart). The merger of digital, biological, and physical technology has given rise to previously unheard-of degrees of automation, connectedness, and intelligence, defining this new era. The transportation ecosystem as a whole is becoming safer and more efficient thanks to these technologies, which are also enabling data-driven decision-making and the optimization of operations.
These research works highlight how important it is to comprehend and adjust to continuous changes in the transportation sector, especially in light of emerging technologies and shifting social demands. The papers emphasize how urgently the transportation system needs to change in order to become more efficient, sustainable, and future-proof. They emphasize how crucial it is to make strategic decisions and create all-encompassing frameworks in order to handle the opportunities and complex challenges that come with these changes.
The transportation industry is undergoing a transformation in its operations with the deployment of 4IR technologies, especially in data collecting and processing, improving sustainability, safety, and efficiency. Because of their heavy reliance on data, these technologies cannot function properly without efficient data collection and processing. Hence, the main objective of this review work is to assess this topic. The paragraphs that follow provide an overview of the writers whose writings have addressed 4IR technologies’ data collection and processing techniques in particular. Figure 7 illustrates the recentness of the publications used, Figure 8 shows the articles and corresponding 4IR technologies, and Table 6 provides a summary of the review of these relevant studies.
An Internet of Things (IoT)-based intelligent transport system prototype was created by the authors of [111]. It uses GPS, NFC, and environmental sensors to track vehicles, facilitate ticket sales, assess crowd and bus ambience, and display information. With its successful demonstration of real-time data display, precise bus tracking, crowd analysis, and environmental monitoring, the system raises the possibility of enhanced passenger experiences and more effective transportation. Subsequent investigations may tackle problems such as misplaced stations, misplaced cards, and air quality monitoring.
To enhance urban mobility, the authors of [112] created an IoT-based smart transportation system. The system included wireless sensors, RFID, and GPS for real-time data collecting and processing. This lowered CO2 emissions, controlled traffic congestion, provided parking recommendations, and improved transportation efficiency. The Ooty parking support and traffic monitoring system demonstrated efficacy, indicating potential enhancements in traffic safety and management. Future studies should concentrate on improving system scalability, security, and privacy, as well as efficiency.
Using 20 million GPS traces from Maryland, the authors of [113] reviewed the literature on the use of trajectory data in road transportation. They demonstrated both new and established uses of trajectory data by utilizing V-Analytics software for data exploration and applying a density-based grouping technique. However, problems with population bias, device identification, trip division, the sample rate, and spatial precision were brought to light. Subsequent investigations should tackle these data concerns and foster cooperation between the transportation and visual analytics domains.
An Internet of Things (IoT)-based Intelligent Transportation System (ITS) was created by the authors in [114] to offer real-time bus location and seating information. The Arduino Uno, GPS, touch sensors, and Internet of Things are used by the system to gather and present data on an Android app. The technology increases the dependability and effectiveness of public transportation while assisting users in making wiser travel selections. Subsequent studies should improve the precision of arrival times and provide bus position displays based on maps.
The authors of [115] corrected missing temporal and spatial data from Gangnam-gu (November 2018) using LSTM in order to predict traffic congestion. In comparison to previous models, the accuracy of the model was higher in suburban regions. This method can be used elsewhere and improves the accuracy of traffic congestion forecasts. Subsequent studies should enhance user efficiency, make more precise predictions in low-speed zones, and verify the system in alternative locations. In order to shorten passenger wait times, the authors of [116] created an Internet of Things-based real-time public transit monitoring system. The system uses GPS, an ESP32 Wi-Fi microcontroller, and the Blynk IoT platform to calculate arrival times and distances using the Haversine formula. By effectively providing real-time bus information, it raises the standard and ease of use of public transportation. Subsequent research endeavors may augment the system with functionalities such as passenger counts and ticket booking, and evaluate its efficacy across several urban areas. The authors of [12] explored the creation of a smart transportation system with big data analytics, Hadoop, and Spark to analyze real-time transportation data efficiently, enhancing road safety and traffic flow. The aim of the authors of [117] was to enhance smart city transportation by developing a sophisticated traffic control system using VANET and connected car technology, focusing on efficient data collection, traffic flow standardization, safety improvement, and congestion management.
Ref. [118] presented an enhanced intelligent transport system with IoT-based RSUs using Raspberry Pi for real-time data transmission to drivers, improving traffic safety and supporting smart cities with accurate information and vehicle detection. In [100], an IoT-based smart transportation security system architecture was examined to address geospatial, cyber-physical, and urban security concerns in Beijing, China. The authors incorporated public infrastructure data, geographic factors, metro convenience indices, national standards, and 5G base station coverage into their modeling and simulation of the system using GIS technology. The outcomes demonstrate how security challenges are handled well and highlight how crucial it is to integrate cyber physical security, 5G networks, and public infrastructure. Developing universal standards, improving IoT-geospatial integration, and testing in diverse urban environments should be the main goals of future research. The authors of [119] discussed the issues with smart transportation that developing nations face because of their quickening population growth. Using information from roadside units (RSUs) and Internet of Vehicles (IoV) technologies, the authors suggested an IoT architecture for congested intersections. Game theory and Nash equilibrium were used to determine the best route. In addition to highlighting the advantages of smart transportation for the environment, economy, public health, and quality of life, the study also draws attention to the problems with infrastructure, governance, education, and expenses. Future work should concentrate on sophisticated IoT frameworks, useful evaluations, and the combination of AI and machine learning while taking the effects on society and the economy into account.
The authors of [120] examined three parking garages and predicted the parking occupancy and traffic assignment for a mid-size institution. The authors sought to create an application that will guide drivers and provide insights for upcoming garages by utilizing forecasts derived from statistical and machine learning approaches. Utilizing Autoregressive LSTM, ANN, and LSTM models, the pressure sensor data obtained at garage entrances and exits were processed and saved in a MySQL database. An ensemble model was created by combining these forecasts. The peak demand was seen during class hours based on the data gathered at one-minute intervals over a two-week period. Because the ensemble model predicts parking availability with accuracy, less time is spent searching, which enhances traffic flow. Subsequent studies should employ deep learning methodologies, gather data in real-time, and juxtapose outcomes with those of bigger cities. The authors of [121] looked at how emerging technologies (ETs) are chosen for intelligent cars. They also identified important variables that affect ET choice and suggested a draft PTM framework. A qualitative examination of these variables emphasizes the necessity of developing corporate internal skills and more specific PTM standards.
In order to enhance incident management and response times, the authors of [122] suggest an Internet of Things (IoT)-based emergency vehicle service system within intelligent transportation networks. To reduce traffic delays and assist emergency vehicles in navigating intersections, the system incorporates a UAV-guided priority system. Through the use of real-time traffic data and incident records, the system optimizes traffic signal phases, resulting in 12% faster incident clearance times and 8% faster emergency vehicle response times. Subsequent studies should concentrate on improving the integration of UAVs, tackling problems related to battery life and communication latency, and broadening the operating scope of the system.
Through an analysis of technological novelty and breadth, the authors of [123] focused on the digital revolution in the automotive industry. They used topic modeling to discover 26 digital technology issues, classified as enhancing, spanning, transforming, and disrupting technologies, using 455 autonomous car technology patents from Swedish automakers. The findings reveal that these technologies can both exhibit gradual advancement and drastically alter the sector. The study highlights the benefits of combining multiple digital technology categories and urges more research into how these technologies affect different industries. In order to fuel the Industrial Revolution, the authors also advise investigating new technology classifications and how businesses may create them.
The authors of [124] explored the real-time implementation of machine-learning-based data collection protocols for intelligent transport systems using Dublin’s M50 as a case study. The authors proposed ML-TDG, a lightweight methodology utilizing Apache Spark for efficient data management, reduced network load, and optimized resource use. The results show that ML-TDG outperforms baseline methods with higher efficiency and lower resource consumption. Future research should focus on cost-effectiveness, integration with existing traffic systems, and further machine learning applications in intelligent transport systems.
In order to examine urban mobility patterns and enhance public transportation, the authors of [125] made use of smart card data from a public transit system. The study was intended to improve the understanding of travel patterns and related socioeconomic variables by generating temporal passenger profiles and clustering passengers and stations based on utilization. Rebuilding trip chains and estimating alighting locations from more than 5 million journey transactions were part of the data processing procedure. In [126], a Mobility-as-a-Service (MaaS) solution featuring modular autonomous vehicles (MAVs) is proposed to improve energy efficiency and reduce emissions in airport-related transportation. The study evaluates MAVs using virtual models based on shuttle bus characteristics and incorporates advanced scheduling and optimization techniques. The results indicate that MAVs can reduce energy consumption, improve passenger comfort and safety, and integrate well with existing transportation networks. Future work should focus on developing MAV virtual models, integrating them with IT systems for GPS tracking and ticketing, and deploying MAVs for further evaluation.
The system in [127] minimizes control efforts, maximizes safety, and imitates human behavior to improve autonomous driving at uncontrolled junctions. Using information from actual intersections, it makes use of motion planning, driving mode selection, and goal state prediction. Testing and a simulation confirmed its efficacy, and further study is advised to enhance prediction and incorporate V2X communication.
In order to enhance vehicle trajectory data from video cameras, the authors of [128] created a postprocessing pipeline that addresses noise, outliers, and fragmentation. The pipeline enhances trajectory length and precision by merging fragments using online data association and convex optimization for outlier removal. Up to 500,000 pieces can be processed in an hour, which helps with traffic analysis and management. Subsequent research should improve the parameters and include interactions with vehicles. In [129], taxi trajectory data are used to evaluate the efficacy of on-board sensor networks in smart cities. Strong network coverage and connectivity are found in the study, facilitating a range of applications for smart cities. Subsequent investigations must concentrate on network capacity and practical applications. Using AIS data, the authors of [130] assessed five machine learning and seven deep learning techniques for forecasting ship trajectories. The comparison offers new guidelines for trajectory prediction and insights for improving marine safety and autonomous navigation.
In [131], model-free measures such as the Procrustes distance are used to examine vehicle interactions through the development of unsupervised learning techniques. These techniques increase the stability and effectiveness of clustering in vehicle-to-vehicle data. Trajectory prediction and anomaly detection in traffic are two examples of applications; the handling of complicated interactions and noise is recommended for future research. The authors of [132] examined developments in mapping, sensing, and localization for autonomous vehicles. Better sensor systems, real-time mapping, and the incorporation of autonomous functions in consumer cars were all emphasized, along with the significance of safety evaluations and real-world testing.
The goal of the authors of [133] was to lower wait times at the maritime terminal in Messina–Tremestieri by incorporating automated and linked vehicles into daily operations. The authors discovered that the new framework efficiently controls vehicle flow and shortens wait times using simulations and data from smart systems, and they proposed enhancements like autonomous reservation systems and priority freight processing. The YOLOv3 algorithm is used in [134] for vehicle identification and classification in toll systems. Compared to earlier techniques, YOLOv3 exhibits great accuracy and better precision, increasing the effectiveness of toll collecting. Future studies ought to investigate broader applicability and multi-scale identification methods.
A method for tracking vehicle trajectories and fuel rates using 360-degree cameras and OBD-II scanners is presented in [135]. This approach offers highly accurate data for phantom traffic wave and fuel efficiency analysis, indicating areas for further research on real-time scenarios and the effects of autonomous vehicles. The adoption of connected and autonomous cars (CAVs) is reviewed in [136], emphasizing how they might enhance traffic flow and energy efficiency. Integration problems and infrastructural requirements are challenges. Future studies should concentrate on the effects of CAVs in diverse contexts, optimized traffic management, and dedicated lanes for CAVs.
Through the integration of autonomous vehicles (AVs) and a multi-agent reinforcement learning (MARL) methodology, the research presented in [137] is designed to improve urban transportation. Through the optimization of AV collaboration and the simulation of human-driven vehicle behavior, the methodology enhances environmental effects, traffic flow, and lane-changing judgments. The paper emphasizes the use of AI in creating sustainable urban transportation and makes recommendations for further studies on multi-agent systems and environments with varying scalability. According to the evaluation of multi-AGV scheduling approaches in [138], the Co-SLMAB approach outperforms the others, with MAB-based solutions outperforming CPLEX in terms of speed. The authors recommend more investigations on enhancing robustness and application across many sectors. The authors of [139] introduce a hybrid algorithm for optimizing multidepot vehicle routing with shared resources and recycling. The model, using 3D k-means clustering and SGA-PSO, effectively improves routing, resource use, and recycling efficiency. Future research should explore diverse settings, pricing strategies, and environmental impacts.
The Dec-CTDSP technique for routing optimization in congested networks of connected and autonomous vehicles (CAVs) is presented in [140]. In high-density CAV situations, the Dec-CTDSP technique performs better than conventional techniques like Dijkstra, and the authors recommend additional validations and enhancements. According to the authors of [141], DSR is generally the most successful routing system for data distribution in autonomous cars, particularly in grid and metropolitan environments, when AODV, DSR, and DSDV are compared. Subsequent investigations should examine protocol performance in other circumstances. By merging deep reinforcement learning (DRL) with model predictive control (MPC), the authors of [142] created a regional route guiding system. They concluded that the use of multi-agent techniques is more successful in easing traffic congestion and enhancing traffic efficiency, and they recommended further research on the integration of connected cars and hybrid systems. The authors of [143] examined the advantages and moral dilemmas of artificial intelligence (AI)-enabled urban routing for unmanned aerial vehicles (CAVs). They emphasized how AI may enhance sustainability and traffic management while tackling moral concerns like safety and justice. They demanded methods for striking a balance between ethical and sustainable issues.
“Intersense”, a method for identifying and classifying traffic regulators using GPS data gathered from the public, is described [144]. It makes use of XGBoost, obtaining 97.06% accuracy and exhibiting strong performance in many cities. The technology enhances digital maps for autonomous vehicles and demonstrates how machine learning works well for traffic control. Subsequent investigations should concentrate on incorporating supplementary data sources and on real-time execution.
Outperforming conventional techniques and providing insights for advanced driving systems, a multi-agent Transformer-based deep reinforcement learning model (MA-TDDPG) for simulating lane change behaviors in connected automobiles is presented in [145]. In order to improve prediction accuracy and make recommendations for future research in real-time co-driving systems, the authors of [146] introduced a dynamic graph convolution network model to anticipate driver intentions to change lanes based on head motions and traffic circumstances. According to the research in [147], roundabout geometry and vehicle precision were found to be critical factors that influence autonomous vehicle performance at roundabouts when evaluating how design features and safety regulations affect it. The integration of intelligent transportation systems and the optimization of roundabout designs should be the main areas of future research.
With an emphasis on electric vehicles (EVs) in South Tyrol, the authors of [148] employed SWOT and AHP analyses to assess issues affecting Italy’s road transport industry. The authors list the advantages, disadvantages, opportunities, and threats associated with EV technology and make recommendations for further studies on the financial implications, infrastructure for charging, and policy implications.
In order to improve road safety, the authors of [125] used sensor data and video footage analysis to identify accidents and minimize false alarms in order to improve road safety by combining IoT and deep learning. To improve the sustainability of urban transportation systems, the authors of [149] argued for improved traffic management to increase safety and sustainability by researching the effects of gridlock and chaos on accident rates. The goal of the authors of [150] was to use fuzzy algorithms and dynamic programming to create a decision model for autonomous vehicles that takes safety and social ethics into consideration. The authors of [151] examined how biometric data might improve the effectiveness, security, and caliber of service provided by public transit, while the authors of [152] built a framework for sustainable urban mobility utilizing IoT and ITS, with a focus on pollution management, traffic forecasting, and traffic reduction.
A blockchain-based system for multi-UAV task processing is proposed in [153], with the goal of improving situation awareness, decision-making, and task-scheduling effectiveness. The system makes use of a Pointer Network for optimal path planning and blockchain technology for safe, unchangeable task management. The efficiency and security of the system have increased, and future research will concentrate on testing practical applications and refining algorithms.
In order to improve urban mobility services, the authors of [154] present the Future Mobility Sensing Advisor (FMSA), a federated platform that blends IoT, big data, AI, and cloud, fog, and edge computing. Enhancing performance and sustainability, the FMSA facilitates multi-modal data management and standardized interfaces. The report suggests more investigations into new technologies, data integration, and platform capabilities. In order to address concerns over data privacy and integration, the research in [155] suggests Federated Learning for big data analytics in IoT-enabled Urban ITSs. With the use of a modified Federated Averaging technique, Federating Learning achieves superior scalability and great accuracy. Algorithm advancements and real-time adaptation should be the main topics of future research. In order to provide safe, distributed deep learning model services and improve security and efficiency in transportation systems, the authors of [156] integrated blockchain technology with IPFS. They recommended more investigations into developing the answer and looking into other technologies. In order to estimate passenger flow and increase operational efficiency, the authors of [157] built JP-DAP, an intelligent big data platform for metro rail systems. They achieved this by employing machine learning. The study draws attention to the necessity of sophisticated data analytics and the authors suggest incorporating new technologies and enhancing JP-DAP’s functionality.
The authors of [158] examined a number of train delay prediction methods, such as deep learning, machine learning, and statistical regression. They discovered that accuracy is increased by accounting for outside variables, like weather and maintenance. Noisy and missing data are challenges, and advanced and hybrid machine learning models are becoming more popular in order to improve prediction and real-time adaptability.
Through the use of non-model-based techniques and roadside 3D LiDAR data, the authors of [159] increased the accuracy of vehicle tracking. For accurate trajectory extraction, the method makes use of sophisticated clustering algorithms and spatiotemporal stacks. The accuracy of real-time tracking, scalability, and resistance to occlusions are highlighted by the results. The authors’ suggestions for future study include expanding sensor coverage, integrating with other technologies, and testing in real-world settings. The trends indicate an increase in the use of LiDAR and sensor fusion.
Using real-time data from stationary sensors, the authors of [160] created an analytical framework for identifying cyberattacks on transportation networks. They validated the framework using city-scale traffic simulations, optimized sensor location, and compared LSTM-autoencoder and Gaussian process models for anomaly detection. Both models exhibit good scalability and accuracy (F1 scores 84–96%), with the best location for the sensors improving resource distribution and detection. Future research should concentrate on data source integration, multi-city testing, and practical implementation.
Using the extended STIRPAT model and ridge regression, the authors of [161] estimated and projected CO2 emissions from Beijing’s transportation sector, emphasizing the effects of efficiency, affluence, population, and technology. They made recommendations for efficiency enhancements, population control, and technology advancement. Using group-based and network-wide models, the authors of [162] assessed the impact of speed harmonization on emissions and traffic flow and found decreases in fuel consumption and emissions. Future research should concentrate on more extensive applicability and computing efficiency. According to the authors of [163], carbon pricing and technical improvements successfully cut emissions. The authors examined the effects of energy use and technological innovations on GHG emissions in 38 OECD nations. They suggested promoting carbon price, renewable energy, technology, and sector-specific emission-reduction strategies.
Deep reinforcement learning (DRL) is a technique that is explored in [164] to increase the energy efficiency of plug-in hybrid electric vehicles (PHEVs). The authors find that DRL-based systems offer significant energy savings compared with conventional techniques. In comparing spaceplanes to maglev trains for Mars colonization, the authors in [165] pointed out that while maglev trains are energy-efficient but require expensive infrastructure, spaceplanes are initially more versatile and cost-effective. The two studies demonstrate current developments in technology for exploration and sustainability.

4. Identified Gaps

Numerous studies highlight the necessity of enhancing systems’ scalability, integrating them with current technology, and broadening their applicability to additional metropolitan contexts. Improvements in data precision are also essential, especially for boosting the quality of traffic forecasts, trajectory data, and bus arrival times. The literature consistently emphasizes the significance of tackling issues related to data security and privacy, together with guaranteeing the resilience of IoT systems, particularly in urban settings and public infrastructure. Furthermore, numerous studies emphasize how emerging technologies like blockchain, AI, machine learning, and deep learning must be used in order to improve the efficacy and precision of current systems.

5. Discussion of Findings

The majority of the research focuses on creating and deploying different intelligent transportation systems (ITS) that make use of machine learning, artificial intelligence, IoT, and other cutting-edge technologies. The objectives of these systems are to improve energy efficiency, road safety, public transportation, and traffic management.
The following are the major technologies/tools deployed in the review papers:
i.
IoT-based transportation systems: research on IoT applications in real-time data collecting, traffic management, and public transportation systems is the focus of studies like [111,112,114,116] (in Table 7).
ii.
Machine learning and AI in transportation: studies [124,128,135,164] (in Table 7) examine how machine learning and AI can be used to improve energy efficiency, vehicle behavior, and traffic prediction.
iii.
Data security and privacy: the difficulties with integrating IoT with public infrastructure while maintaining data security and privacy are covered in articles like [100,155] (in Table 7)
iv.
Sustainability and environmental impact: studies such as [126,161,162] (in Table 7) look at how transportation systems affect the environment and offer solutions to cut emissions and increase energy efficiency.
Successful system demonstrations, increased traffic control and safety, and improved data gathering and processing capabilities are among the common findings in these research works. Nevertheless, there are certain drawbacks, including the requirement for improved integration, scalability, security, and privacy of data.
Despite tremendous advancements in the field of intelligent transportation systems development, there are still issues with making these systems secure, scalable, and ecologically sustainable. The systems have shown the potential to increase transportation safety and efficiency when cutting-edge technologies like AI, IoT, and machine learning are integrated, but further study is required to improve these systems and close the gaps that have been found. The significance of a comprehensive strategy for the future of transportation networks is underscored by these findings. Policies that guarantee security, privacy, and environmental sustainability must be created in a way that facilitates the use of cutting-edge technologies. The integration of AI and IoT in transportation, as well as the gaps in scalability and accuracy, require ongoing research. Making sure these sophisticated technologies are safe and scalable requires urban planners to concentrate on developing the infrastructure that supports them. Further, in line with the goals of global sustainability, the transportation industry should keep innovating to lower emissions and boost energy efficiency.

6. Conclusions and Recommendation

In this study, we conducted a thorough analysis of the implications and applications of fourth Industrial Revolution (4IR) technologies in the transportation industry, with an emphasis on data processing and gathering methods. It is clear that the transportation sector has changed dramatically over the course of the several Industrial Revolutions, and 4IR technologies like AI, IoT, big data, and machine learning have been essential to this progress. Because these technologies allow for real-time data analysis, monitoring, and decision-making, they have improved the sustainability, safety, and efficiency of transportation networks.
However, this review also brought to light a number of difficulties. There are several obstacles, including the variety of data collection techniques and the absence of data processing standardization. These difficulties may prevent 4IR technologies from being implemented effectively, which would restrict their ability to completely revolutionize the transportation sector. In this systematic study, we identified gaps in the literature, especially with regard to the harmonization of data gathering techniques and the well-coordinated integration of diverse 4IR technologies.
A number of crucial recommendations need to be given top priority if the transportation industry is to fully benefit from fourth Industrial Revolution (4IR) technologies. First, in order to guarantee industry-wide interoperability and the efficient use of various technologies, standardizing data gathering standards is crucial. The difficulties presented by a variety of data types can also be addressed by implementing cutting-edge computational techniques like artificial intelligence (AI) and machine learning, which can lead to more effective data processing and useful insights. In order to align technological capabilities with industrial needs and promote integrated systems, cooperation amongst technology developers, transportation authorities, and policymakers is also essential. In addition to governments and regulatory organizations establishing clear regulations that support the safe, effective, and sustainable deployment of 4IR technologies, ongoing research and development are required to keep up with the difficulties involved, which are consistently changing.
Some relevant models to this study could not be presented or analyzed due to data and ethical challenges. However, it is envisaged that during the course of our upcoming research project, this obstacle will be removed.

Author Contributions

Conceptualization, A.M.K., K.D. and L.D.; methodology, O.O.A.; software, O.O.A.; formal analysis, O.O.A.; investigation, O.O.A.; resources, O.O.A.; data curation, O.O.A.; writing—original draft preparation, O.O.A.; writing—review and editing, A.M.K., K.D., L.D. and O.O.A.; visualization, O.O.A.; supervision, A.M.K. and L.D. All authors have read and agreed to the published version of the manuscript.

Funding

This project was made possible through funding received from The Transport and Education Training Authority (TETA), project number: TETA22/R&K/PR0011.

Institutional Review Board Statement

Not applicable.

Informed Consent Statement

Not applicable.

Data Availability Statement

Not applicable.

Acknowledgments

The authors appreciate the funding provided by The Transport and Education Training Authority (TETA) for the execution of this research project. The encouragement and enabling environment from Tshwane University of Technology (TUT) is appreciated herewith.

Conflicts of Interest

The authors declare no conflicts of interest.

References

  1. Mohan, D.; Tiwari, G. Sustainable Transport Systems: Linkages between environmental issues, public transport, non-motorised transport and safety. Econ. Political Wkly. 2000, 34, 1589–1596. [Google Scholar]
  2. Choudhary, A.K.; Rao, S. History of rail Transportation and Importance of Indian Railways (IR) Transportation. Int. J. Eng. Dev. Res. 2018, 6, 73–77. [Google Scholar]
  3. Dodder, R. The Evolving Systems View of Transportation: Implications for Policy; Massachusetts Institute of Technology: Cambridge, MA, USA, 2000. [Google Scholar]
  4. Schwab, K. The Fourth Industrial Revolution: What it means, how to respond. Foreign Aff. 2017, 96, 20–27. [Google Scholar]
  5. Aceto, G.; Persico, V.; Pescape, A. Industry 4.0 and Health: Internet of Things, Big Data, and Cloud Computing for Health 4.0. J. Ind. Inf. Integr. 2020, 18, 100129. [Google Scholar] [CrossRef]
  6. Zaman, A.; Jerin, I.; Ghosh, P.; Akther, A.; Shrity, S.S. A hierarchical multi-criteria model for analyzing the barriers to Pharma 4.0 implementation in developing countries. Healthc. Anal. 2024, 5, 100334. [Google Scholar] [CrossRef]
  7. Lephondo, I.; Telukdarie, A.; Munien, I.; Onkonkwo, U.; Vermeulen, A. The outcomes of smart irrigation system using machine learning to minimize water usage within the agriculture sector. In Proceedings of the International Conference on Industry Sciences and Computer Science Innovation, Porto, Portugal, 29–31 October 2024. [Google Scholar]
  8. David, O.; Nwulu, N.I.; Aigbavboa, C.O.; Adepoju, O.O. Integrating fourth industrial revolution (4IR) technologies into water, energy and food nexus for sustainable security: A bibliometric analysis. J. Clean. Prod. 2022, 363, 132522. [Google Scholar] [CrossRef]
  9. Chen, W.; Chen, L.; Chen, Z.; Tu, S.W. A wireless sensor network for intelligent transportation system. In Proceedings of the First International Multi-Symposiums on Computer and Computational Sciences (IMSCCS’06), Hangzhou, China, 20–24 June 2006. [Google Scholar]
  10. Hull, B.; Bychkovsky, V.; Zhang, Y.; Chen, K.; Goraczko, M.; Miu, A.; Shih, E.; Balakrishnan, H.; Madden, S.C. A distributed mobile sensor computing system. In Proceedings of the 4th International Conference on Embedded networked Sensor Systems, Boulder, CO, USA, 31 October–3 November 2006. [Google Scholar]
  11. Pham, T.; Tsai, M.; Nguyen, D.; Dow, C.; Deng, D. A cloud-based smart-parking system based on Internet-of-Things technologies. IEEE Access 2015, 3, 1581–1591. [Google Scholar] [CrossRef]
  12. Jan, B.; Farman, H.; Khan, M.; Talha, M.; Din, I. Designing a smart transportation system: An internet of things and big data approach. IEEE Wirel. Commun. 2019, 26, 73–79. [Google Scholar] [CrossRef]
  13. Niture, D.; Dhakane, V.; Jawalkar, P.; Bamnote, A. Smart transportation system using IOT. Int. J. Eng. Adv. Technol. 2021, 10, 434–438. [Google Scholar] [CrossRef]
  14. Soltanmohammadi, E.; Ghavami, K.; Naraghi-Pour, M. A survey of traffic issues in machine-to-machine communications over LTE. IEEE Internet Things J. 2016, 3, 865–884. [Google Scholar] [CrossRef]
  15. Dogra, A.; Kaur, J. Moving towards smart transportation with machine learning and Internet of Things (IoT): A review. J. Smart Environ. Green Comput. 2022, 2, 3–18. [Google Scholar] [CrossRef]
  16. Zhu, F.; Li, Z.; Chen, S.; Xiong, G. Parallel Transportation Management and Control System and Its Applications in Building Smart Cities. IEEE Trans. Intell. Transp. Syst. 2016, 17, 1576–1585. [Google Scholar] [CrossRef]
  17. Diderot, C.D.; Bernice, N.; Tchappi, I.; Muala, Y.; Najjar, A.; Galland, S. Intelligent Transportation Systems in Developing Countries: Challenges and Prospects. In Proceedings of the 20th International Conference on Mobile Systems and Pervasive Computing (MobileSPC), Halifax, NS, Canada, 14–16 August 2023. [Google Scholar]
  18. Kim, H.; Yoon, S.; Kim, M.; Ji, Y. Deriving future user experiences in autonomous vehicle. In Proceedings of the 7th International Conference on Automotive User Interfaces and Interactive Vehicular Applications, Nottingham, UK, 1–3 September 2015. [Google Scholar]
  19. Li, L.; Liu, Y.; Wang, J.; Deng, W.; Oh, H. Human dynamics based driver model for autonomous car. IET Intell. Transp. Syst. 2016, 10, 545–554. [Google Scholar] [CrossRef]
  20. Galambos, K.J.; Palomino-Hernandez, A.B.; Hemmelmayr, V.C.; Turan, B. Sustainability initiatives in urban freight transportation in Europe. Transp. Res. Interdiscip. Perspect. 2024, 23, 101013. [Google Scholar] [CrossRef]
  21. Miner, P.; Smith, B.M.; Jani, A.; McNeil, G.; Gathonie-Hardy, A. Car harm: A global review of automobility’s harm to people and the environment. J. Transp. Geogr. 2024, 115, 103817. [Google Scholar] [CrossRef]
  22. Gupta, A.; Anpalagan, A.; Guan, L.; Khwaja, A.S. Deep learning for object detection and scene perception in self-driving cars: Survey, challenges and open issues. Array 2021, 10, 100057. [Google Scholar] [CrossRef]
  23. Jiang, C.; Yin, S.; Yao, Z.; He, J.; Jiang, R. Safety evaluation of mixed traffic flow with truck platoons equipped with (cooperative) adaptive cruise control, stochastive human-driven cars and trucks on port freeways. Phys. A Stat. Mech. Its Appl. 2024, 643, 129802. [Google Scholar] [CrossRef]
  24. Olayode, I.O.; Du, B.; Severino, A.; Campisi, T.; Alex, F.J. Systematic literature review on the applications, impacts, and public perceptions of autnomous vehicles in road transportation system. J. Traffic Transp. Eng. 2023, 10, 1037–1060. [Google Scholar]
  25. Wang, Y.; Ram, S.; Currim, F.; Dantas, E.; Sabóia, L. A big data approach for smart transportation management on bus network. In Proceedings of the 2016 IEEE International Smart Cities Conference (ISC2), Trento, Italy, 12–15 September 2016. [Google Scholar]
  26. Ozbayoglu, M.; Kucukayan, G.; Dogdu, E. A real-time autonomous highway accident detection model based on big data processing and computational intelligence. In Proceedings of the 2016 IEEE International Conference on Big Data (Big Data), Washington, DC, USA, 5–8 December 2016. [Google Scholar]
  27. Khazaei, H.; Zareian, S.; Veleda, R.; Litoiu, M.S. A big data analytic platform for smart transportation. In Smart City 360°; Springer: Berlin/Heidelberg, Germany, 2016; pp. 419–430. [Google Scholar]
  28. Zhang, J.; Shen, D.; Tu, L.; Zhang, F.; Xu, C.; Wang, Y.; Tian, C.; Li, X.; Huang, B.; Li, Z. A real-time passenger flow estimation and prediction method for urban bus transit systems. IEEE Trans. Intell. Transp. Syst. 2017, 18, 3168–3178. [Google Scholar] [CrossRef]
  29. Lu, Y.; Misra, A.; Wu, H. Smartphone sensing meets transport data: A collaborative framework for transportation service analytics. IEEE Trans. Mob. Comput. 2017, 17, 945–960. [Google Scholar] [CrossRef]
  30. Trueblood, F.; Rodriguez, D.; Hernandez, J.; Salomon, M.; Soundarajan, S.; Pirouz, M. Demystifying Transportation Using Big Data Analytics. In Proceedings of the 2019 IEEE International Conference on Computational Science and Computational Intelligence (CSCI), Las Vegas, NV, USA, 5–7 December 2019; IEEE: Piscataway, NJ, USA, 2019. [Google Scholar]
  31. Al Najada, H.; Mahgoub, I. Anticipation and alert system of congestion and accidents in VANET using Big Data analysis for Intelligent Transportation Systems. In Proceedings of the 2016 IEEE Symposium Series on Computational Intelligence (SSCI), Athens, Greece, 6–9 December 2016; IEEE: Piscataway, NJ, USA, 2016. [Google Scholar]
  32. Puiu, D.; Bischof, S.; Serbanescu, B.; Nechifor, S.; Parreira, J.; Schreiner, H. A public transportation journey planner enabled by IoT data analytics. In Proceedings of the 2017 20th IEEE Conference on Innovations in Clouds, Internet and Networks (ICIN), Paris, France, 7–9 March 2017; IEEE: Piscataway, NJ, USA, 2017. [Google Scholar]
  33. Nelson, Q.; Steffensmeier, D.; Pawaskar, S. A simple approach for sustainable transportation systems in smart cities: A graph theory model. In Proceedings of the 2018 IEEE Conference on Technologies for Sustainability (SusTech), Long Beach, CA, USA, 11–13 November 2018; IEEE: Piscataway, NJ, USA, 2018. [Google Scholar]
  34. Rathore, M.; Ahmad, A.; Paul, A.; Jeon, G. Efficient graph-oriented smart transportation using internet of things generated big data. In Proceedings of the 2015 11th IEEE International Conference on Signal-Image Technology & Internet-Based Systems (SITIS), Bangkok, Thailand, 23–27 November 2015; IEEE: Piscataway, NJ, USA, 2015. [Google Scholar]
  35. Guo, Y.; Wang, S.; Zheng, L.; Lu, M. Trajectory Data Driven Transit-Transportation Planning. In Proceedings of the 2017 5th IEEE International Conference on Advanced Cloud and Big Data (CBD), Shanghai, China, 13–16 August 2017; IEEE: Piscataway, NJ, USA, 2017. [Google Scholar]
  36. Van Oort, N.; Cats, O. Improving public transport decision making, planning and operations by using big data: Cases from Sweden and the Netherlands. In Proceedings of the 2015 18th IEEE International Conference on Intelligent Transportation Systems, Gran Canaria, Spain, 15–18 September 2015; IEEE: Piscataway, NJ, USA, 2015. [Google Scholar]
  37. Shi, Q.; Abdel-Aty, M. Big data applications in real-time traffic operation and safety monitoring and improvement on urban expressways. Transp. Res. Part C Emerg. Technol. 2015, 58, 380–394. [Google Scholar] [CrossRef]
  38. Wang, Y.; Zhang, W.; Zhang, F.; Yin, L.; Zhang, J.; Tian, C.; Jiang, W. Analysis of subway passenger flow based on smart card data. In Proceedings of the 2020 6th IEEE International Conference on Big Data Computing and Communications (BIGCOM), Deqing, China, 24–25 July 2020; IEEE: Piscataway, NJ, USA, 2020. [Google Scholar]
  39. Kumar, N.; Rahman, S.; Dhakad, N. Fuzzy inference enabled deep reinforcement learning-based traffic light control for intelligent transportation system. IEEE Trans. Intell. Transp. Syst. 2020, 22, 4919–4928. [Google Scholar] [CrossRef]
  40. Lv, Z.; Lou, R.; Singh, A. AI Empowered Communication Systems for Intelligent Transportation Systems. IEEE Trans. Intell. Transp. Syst. 2021, 22, 4579–4587. [Google Scholar] [CrossRef]
  41. Hossain, M.; Sinha, H.; Mustafa, R. A belief rule based expert system to control traffic signals under uncertainty. In Proceedings of the 2015 International Conference on Computer and Information Engineering (ICCIE), Rajshahi, Bangladesh, 26–27 November 2015; IEEE: Piscataway, NJ, USA, 2015. [Google Scholar]
  42. Olwan, M.; Mostafa, A.; AbdELAty, Y.; Mahfouz, D.; Shehata, O.; Morgan, E. Behavior Evaluation of Vehicle Platoon via Different Fuzzy-X Tuned Controllers. In Proceedings of the 2020 8th EEE International Conference on Control, Mechatronics Andand Automation (ICCMA), Moscow, Russia, 6–8 November 2020; IEEE: Piscataway, NJ, USA, 2020. [Google Scholar]
  43. Wang, W.; Tai, C.; Wu, S.; Liu, Z. A hybrid genetic algorithm with fuzzy logic controller for wireless power transmission system of electric vehicles. In Proceedings of the 2015 IEEE International Conference on Industrial Technology (ICIT), Seville, Spain, 17–19 March 2015; IEEE: Piscataway, NJ, USA, 2015. [Google Scholar]
  44. Yeh, Y.; Tsai, M. Development of a genetic algorithm based electric vehicle charging coordination on distribution networks. In Proceedings of the 2015 IEEE Congress on Evolutionary Computation (CEC), Sendai, Japan, 25–28 May 2015; IEEE: Piscataway, NJ, USA, 2015. [Google Scholar]
  45. Alaguvelu, R.; Curry, D.; Dagli, C. Fuzzy—Genetic algorithm approach to generate an optimal meta-architecture for a smart, safe & efficient city transportation system of systems. In Proceedings of the 2016 11th IEEE System of Systems Engineering Conference (SoSE), Kongsberg, Norway, 12–16 June 2016; IEEE: Piscataway, NJ, USA, 2016. [Google Scholar]
  46. Nayeem, M.; Islam, M.; Yao, X. Solving transit network design problem using many-objective evolutionary approach. IEEE Trans. Intell. Transp. Syst. 2019, 20, 3952–3963. [Google Scholar] [CrossRef]
  47. Tang, J.; Liu, F.; Zou, Y.; Zhang, W.; Wang, Y. An improved fuzzy neural network for traffic speed prediction considering periodic characteristic. IEEE Trans. Intell. Transp. Syst. 2017, 18, 2340–2350. [Google Scholar] [CrossRef]
  48. Bao, D. A multi-index fusion clustering strategy for traffic flow state identification. IEEE Access 2019, 7, 166404–166409. [Google Scholar] [CrossRef]
  49. Leung, C.; Elias, J.; Minuk, S.; de Jesus, A.; Cuzzocrea, A. An Innovative Fuzzy Logic-Based Machine Learning Algorithm for Supporting Predictive Analytics on Big Transportation Data. In Proceedings of the 2020 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE), Glasgow, UK, 19–24 July 2020. [Google Scholar]
  50. Ai, C.; Jia, L.; Hong, M.; Zhang, C. Short-term road speed forecasting based on hybrid RBF neural network with the aid of fuzzy system-based techniques in urban traffic flow. IEEE Access 2020, 8, 69461–69470. [Google Scholar] [CrossRef]
  51. Schmidhuber, J. Deep learning in neural networks: An overview. Neural Netw. 2015, 61, 85–117. [Google Scholar] [CrossRef]
  52. Zheng, J.A. Vehicle Routing Problem ModelWith Multiple FuzzyWindows Based on Time-Varying Traffic Flow. IEEE Access 2020, 8, 39439–39444. [Google Scholar] [CrossRef]
  53. Sun, F.; Wang, X.; Zhang, Y.; Liu, W.; Zhang, R. Analysis of bus trip characteristic analysis and demand forecasting based on GA-NARX neural network model. IEEE Access 2020, 8, 8812–8820. [Google Scholar] [CrossRef]
  54. Thiranjaya, C.; Rushan, R.; Udayanga, P.; Kaushalya, U.; Rankothge, W. Towards a Smart City: Application of Optimization for a Smart Transportation Management System. In Proceedings of the 2018 IEEE International Conference on Information and Automation for Sustainability (ICIAfS), Colombo, Sri Lanka, 21–22 December 2018. [Google Scholar]
  55. Yang, H.; Hu, X. Wavelet neural network with improved genetic algorithm for traffic flow time series prediction. Optik 2016, 127, 8103–8110. [Google Scholar] [CrossRef]
  56. Qu, Y.; Lin, Z.; Li, H.; Zhang, X. Feature recognition of urban road traffic accidents based on GA-XGBoost in the context of big data. IEEE Access 2019, 7, 170106–170115. [Google Scholar] [CrossRef]
  57. Zhang, Q.; Liu, S.; Gong, D.; Zhang, H.; Tu, Q. An improved multi-objective quantum-behaved particle swarm optimization for railway freight transportation routing design. IEEE Access 2019, 7, 157353–157362. [Google Scholar] [CrossRef]
  58. Wang, R.; Zhang, Z.; Wang, L.; Zhang, H. Resource-Expandable Railway Freight Transportation Routing Optimization. IEEE Access 2019, 7, 161607–161620. [Google Scholar] [CrossRef]
  59. Liu, W. Route optimization for last-mile distribution of rural E-commerce logistics based on ant colony optimization. IEEE Access 2020, 8, 12179–12187. [Google Scholar] [CrossRef]
  60. Olayode, O.I.; Tartibu, L.K.; Okwu, O.M. Application of Artificial Intelligence in Traffic Control System of Non-autonomous Vehicles at Signalized Road Intersection. In Proceedings of the 30th CIRP Design 2020 (CIRP Design 2020), Pretoria, South Africa, 5–8 May 2020. [Google Scholar]
  61. Kusic, K.; Schumann, R.; Ivanjko, E. A digital twin in transportation: Real-time synergy of traffic data streams and simulation for virtualizing motorway dynamics. Adv. Eng. Inform. 2023, 55, 101858. [Google Scholar] [CrossRef]
  62. Rauf, M.; Kumar, L.; Zulkifli, S.A.; Jamil, A. Aspects of artificial intelligence in future electric vehicle technology for sustainable environmental impact. Environ. Chall. 2024, 14, 100854. [Google Scholar] [CrossRef]
  63. Low, R.; Cheah, L.; You, L. Commercial vehicle activity prediction with imbalanced class distribution using a hybrid sampling and gradient boosting approach. IEEE Trans. Intell. Transp. Syst. 2020, 22, 1401–1410. [Google Scholar] [CrossRef]
  64. Li, P.; Abdel-Aty, M.; Cai, Q.; Islam, Z. A deep learning approach to detect real-time vehicle maneuvers based on smartphone sensors. IEEE Trans. Intell. Transp. Syst. 2020, 23, 3148–3157. [Google Scholar] [CrossRef]
  65. Keller, M.; Haß, C.; Seewald, A.; Bertram, T. A model predictive approach to emergency maneuvers in critical traffic situations. In Proceedings of the 2015 IEEE 18th International Conference on Intelligent Transportation Systems, Gran Canaria, Spain, 15–18 September 2015. [Google Scholar]
  66. Jiang, Y.; Liu, Y.; Liu, D.; Song, H. Applying Machine Learning to Aviation Big Data for Flight Delay Prediction. In Proceedings of the 2020 IEEE International Conference on Dependable, Autonomic and Secure Computing, International Conference on Pervasive Intelligence and Computing, International Conference on Cloud and Big Data Computing, International Conference on Cyber Science and Tec, Calgary, AB, Canada, 17–22 August 2020; IEEE: Piscataway, NJ, USA, 2020. [Google Scholar]
  67. Diao, Z.; Zhang, D.; Wang, X.; Xie, K.; He, S.; Lu, X.; Li, Y. A hybrid model for short-term traffic volume prediction in massive transportation systems. IEEE Trans. Intell. Transp. Syst. 2018, 20, 935–946. [Google Scholar] [CrossRef]
  68. Castro-Neto, M.; Jeong, Y.; Jeong, M.; Han, L. Online-SVR for short-term traffic flow prediction under typical and atypical traffic conditions. Exp. Syst. Appl. 2009, 36, 6164–6173. [Google Scholar] [CrossRef]
  69. Ke, R.; Li, Z.; Tang, J.; Pan, Z.; Wang, Y. Real-time traffic flow parameter estimation from UAV video based on ensemble classifier and optical flow. IEEE Trans. Intell. Transp. Syst. 2018, 20, 54–64. [Google Scholar] [CrossRef]
  70. Feng, W.; Chen, H.; Zhang, Z. Short-term traffic flow prediction based on wavelet function and extreme learning machine. In Proceedings of the 2017 8th IEEE International Conference on Software Engineering and Service Science (ICSESS), Beijing, China, 24–26 November 2017. [Google Scholar]
  71. Wang, D.; Xiong, J.; Xiao, Z.; Li, X. Short-term traffic flow prediction based on ensemble real-time sequential extreme learning machine under non-stationary condition. In Proceedings of the 2016 IEEE 83rd Vehicular Technology Conference (VTC Spring), Nanjing, China, 15–18 May 2016. [Google Scholar]
  72. Liu, R.; Wang, Y.; Zhou, H.; Qian, Z. Short-term passenger flow prediction based on wavelet transform and kernel extreme learning machine. IEEE Access 2019, 7, 158025–158034. [Google Scholar] [CrossRef]
  73. Said, A.; Abd-Elrahman, E.; Afifi, H. A comparative study on machine learning algorithms for green context-aware intelligent transportation systems. In Proceedings of the 2017 International Conference on Electrical and Computing Technologies and Applications (ICECTA), Ras AI Khaimah, United Arab Emirates, 21–23 November 2017. [Google Scholar]
  74. Panovski, D.; Scurtu, V.; Zaharia, T. A neural network-based approach for public transportation prediction with traffic density matrix. In Proceedings of the 2018 7th European Workshop on Visual Information Processing (EUVIP), Tampere, Finland, 26–28 November 2018. [Google Scholar]
  75. Liu, Y.; Liu, C.; Yuan, N.; Duan, L.; Fu, Y.; Xiong, H.; Xu, S.; Wu, J. Intelligent bus routing with heterogeneous human mobility patterns. Knowl. Inf. Syst. 2017, 50, 383–415. [Google Scholar] [CrossRef]
  76. Abedalla, A.; Fadel, A.; Tuffaha, I.; Al-Omari, H.; Omari, M.; Abdullah, M.; Al-Ayyoub, M. MTRecS-DLT: Multi-modal transport recommender system using deep learning and tree models. In Proceedings of the 2019 Sixth International Conference on Social Networks Analysis, Management and Security (SNAMS), Granada, Spain, 22–25 October 2019. [Google Scholar]
  77. Ma, Y.; Zhang, Z. Travel Mode Choice Prediction Using Deep Neural Networks with Entity Embeddings. IEEE Access 2020, 8, 64959–64970. [Google Scholar] [CrossRef]
  78. Zhou, F.; Yang, Q.; Zhong, T.; Chen, D.; Zhang, N. Variational Graph Neural Networks for Road Traffic Prediction in Intelligent Transportation Systems. IEEE Trans. Ind. Inform. 2020, 17, 2802–2812. [Google Scholar] [CrossRef]
  79. Zheng, Z.; Yang, Y.; Liu, J.; Dai, H.; Zhang, Y. Deep and embedded learning approach for traffic flow prediction in urban informatics. IEEE Trans. Intell. Transp. Syst. 2019, 20, 3927–3939. [Google Scholar] [CrossRef]
  80. Zhang, J.; Zheng, Y.; Qi, D. Deep spatio-temporal residual networks for citywide crowd flows prediction. In Proceedings of the AAAI Conference on Artificial Intelligence, San Francisco, CA, USA, 4–9 February 2017. [Google Scholar]
  81. Guo, S.; Lin, Y.; Li, S.; Chen, Z.; Wan, H. Deep spatial–temporal 3D convolutional neural networks for traffic data forecasting. IEEE Trans. Intell. Transp. Syst. 2019, 20, 3913–3926. [Google Scholar] [CrossRef]
  82. Dai, G.; Ma, C.; Xu, X. Short-term traffic flow prediction method for urban road sections based on space–time analysis and GRU. IEEE Access 2019, 7, 143025–143035. [Google Scholar] [CrossRef]
  83. Zheng, G.; Chai, W.; Katos, V. An Ensemble Model for Short-Term Traffic Prediction in Smart City Transportation System. In Proceedings of the 2019 IEEE Global Communications Conference (GLOBECOM), Waikoloa, HI, USA, 9–13 December 2019. [Google Scholar]
  84. Shukla, A.; Bhattacharya, P.; Tanwar, S.; Kumar, N.; Guizani, M.D. A deep learning-based dynamic toll pricing scheme for intelligent transportation systems. IEEE Trans. Veh. Technol. 2020, 69, 12510–12520. [Google Scholar] [CrossRef]
  85. Zhang, J.; Chen, F.; Shen, Q. Cluster-based LSTM network for short-term passenger flow forecasting in urban rail transit. IEEE Access 2019, 7, 147653–147671. [Google Scholar] [CrossRef]
  86. Zhu, K.; Xun, P.; Li, W.; Li, Z.; Zhou, R. Prediction of passenger flow in urban rail transit based on big data analysis and deep learning. IEEE Access 2019, 7, 142272–142279. [Google Scholar] [CrossRef]
  87. Sha, S.; Li, J.; Zhang, K.; Yang, Z.; Wei, Z.; Li, X.; Zhu, X. RNN-based subway passenger flow rolling prediction. IEEE Access 2020, 8, 15232–15240. [Google Scholar] [CrossRef]
  88. Li, J.; Peng, H.; Liu, L.; Xiong, G.; Du, B.; Ma, H.; Wang, L.; Bhuiyan, M. Graph CNNs for urban traffic passenger flows prediction. In Proceedings of the 2018 IEEE SmartWorld, Ubiquitous Intelligence & Computing, Advanced & Trusted Computing, Scalable Computing & Communications, Cloud & Big Data Computing, Internet of People and Smart City Innovation (SmartWorld/SCALCOM/UIC/ATC/CBDCom/IOP/SCI), Guangzhou, China, 8–12 October 2018. [Google Scholar]
  89. Li, D.; Cao, J.; Li, R.; Wu, L. A Spatio-Temporal Structured LSTM Model for Short-Term Prediction of Origin-Destination Matrix in Rail Transit with Multisource Data. IEEE Access 2020, 8, 84000–84019. [Google Scholar] [CrossRef]
  90. Toqué, F.; Côme, E.; El Mahrsi, M.; Oukhellou, L. Forecasting dynamic public transport origin-destination matrices with long-short term memory recurrent neural networks. In Proceedings of the 2016 IEEE 19th International Conference on Intelligent Transportation Systems (ITSC), Rio de Janeiro, Brazil, 1–4 November 2016. [Google Scholar]
  91. Hong, K.; Lillethun, D.; Ramachandran, U.; Ottenwälder, B.; Koldehofe, B. Mobile fog: A programming model for large-scale applications on the internet of things. In Proceedings of the Second ACM SIGCOMM Workshop on Mobile Cloud Computing, Hong Kong, China, 16 August 2013. [Google Scholar]
  92. Tao, X.; Jiang, C.; Han, Y. Applying SOA to intelligent transportation system. In Proceedings of the 2005 IEEE International Conference on Services Computing (SCC’05), Orlando, FL, USA, 11–15 July 2005. [Google Scholar]
  93. Lin, J.; Yu, W.; Yang, X.; Zhao, P.; Zhang, H.; Zhao, W. An edge computing based public vehicle system for smart transportation. IEEE Trans. Veh. Technol. 2020, 69, 12635–12651. [Google Scholar] [CrossRef]
  94. Cai, W.; Sun, T.C. The new generation intelligent transportation system. In Proceedings of the 2011 Second International Conference on Innovations in Bio-inspired Computing and Applications, Shenzhen, China, 16–18 December 2011. [Google Scholar]
  95. Jaworski, P.; Edwards, T.; Moore, J.; Burnham, K. Cloud computing concept for intelligent transportation systems. In Proceedings of the 2011 14th International IEEE Conference on Intelligent Transportation Systems (ITSC), Washington, DC, USA, 5–7 October 2011. [Google Scholar]
  96. Tsubouchi, K.; Yamato, H.; Hiekata, K. Innovative on-demand bus system in Japan. IET Intell. Transp. Syst. 2010, 4, 270–279. [Google Scholar] [CrossRef]
  97. Ji, Z.; Ganchev, I.; O’Droma, M.; Zhang, X. A cloud-based intelligent car parking services for smart cities. In Proceedings of the 2014 31st URSI General Assembly and Scientific Symposium (URSI GASS), Beijing, China, 16–23 August 2014. [Google Scholar]
  98. Sergiy, B.; Inna, L.; Alla, B.; Alexander, L.; Khusainova, M. Creating urban transportation networks grounded in the principles of the smart port-city paradigm. In Proceedings of the International Workshop Digital Society: In the Eve of the 6th Information Revolution (DS 2023), Almaty, Kazakhstan, 7–9 November 2024. [Google Scholar]
  99. Lu, X. Research on architecture for web services based uniform GIS transportation information platform. In Proceedings of the 2006 International Conference on Machine Learning and Cybernetics, Dalian, China, 13–16 August 2006. [Google Scholar]
  100. Zhang, J.; Wang, Y.; Li, S.; Shi, S. An architecture for IoT-enabled smart transportation security system: A geospatial approach. IEEE Internet Things J. 2021, 8, 6205–6213. [Google Scholar] [CrossRef]
  101. Vakula, D.; Raviteja, B. Smart public transport for smart cities. In Proceedings of the 2017 International Conference on Intelligent Sustainable Systems (ICISS), Thirupur, India, 12–13 December 2017; IEEE: New York, NY, USA, 2017. [Google Scholar]
  102. Htay, T.; Komapov, V.; Glushenkov, V. Creation of an interactive geo-information model of the multifunctional magneticlevitation transport system ELTRO in Naypyidaw, Republic of Myanmar. In Proceedings of the 2021 3rd International Youth Conference on Radio Electronics, Electrical and Power Engineering (REEPE), Moscow, Russia, 12–14 March 2021. [Google Scholar]
  103. Timofeev, V.; Teselkina, K.; Veselova, A. Development and Research of Transport Speed Models Using the Methods of Geo-Statistical Data Analysis. In Proceedings of the 2018 XIV International Scientific-Technical Conference on Actual Problems of Electronics Instrument Engineering (APEIE), Novosibirsk, Russia, 2–6 October 2018. [Google Scholar]
  104. Gokasar, I.; Cetinel, Y.; Baydogan, M. Estimation of Influence Distance of Bus Stops Using Bus GPS Data and Bus Stop Properties. IEEE Trans. Intell. Transp. Syst. 2019, 20, 4635–4642. [Google Scholar] [CrossRef]
  105. Olawuni, O.A.; Sadare, O.O.; Moothi, K. The adsorption routes of 4IR technologies for effective desulphurization using cellulose nanocrystals: Current trends, challenges and future perspectives. Heliyon 2024, 10, e24732. [Google Scholar] [CrossRef]
  106. Elassy, M.; Al-Hattab, M.; Takruri, M.; Badawi, S. Intelligent Transportation Systems for Sustainable Smart Cities. Transp. Eng. 2024, 16, 100252. [Google Scholar] [CrossRef]
  107. Gicha, B.B.; Tufa, L.T.; Lee, J. The electric vehicle resolution in Sub-Saharan Africa: Trends, Challenges and Opportunities. Energy Strategy Rev. 2024, 53, 101384. [Google Scholar] [CrossRef]
  108. Rouhana, F.; Zhu, J.; Chacou-Hurtado, D.; Hertel, S.; Bagtzoglou, A.C. Ensuring a just transition: The electric vehicle resolution from a human rights perspective. J. Clean. Prod. 2024, 462, 142667. [Google Scholar] [CrossRef]
  109. Xiao, G.; Xiao, Y.; Shu, Y.; Ni, A.; Jiang, Z. Technical and economic analysis of battery electric buses with different charging rates. Transp. Res. Part D 2024, 132, 104254. [Google Scholar] [CrossRef]
  110. Kartasan, P.; Mavrin, S. The Digital Revolution of the Transportation Industry. In Proceedings of the XIII International Conference on Transport Infrastructure: Territory Development and Sustainability, Irkutsk-Krasnoyarsk, Russia, 26–28 October 2022. [Google Scholar]
  111. Bojan, T.M.; Kumar, U.R.; Bojan, V.M. An Internet of Things based Intelligent Transport System. In Proceedings of the 2014 IEEE International Conference on Vehicular Electronics and Safety (ICVES), Hyderabad, India, 16–17 December 2014. [Google Scholar]
  112. Sherly, J.; Somasundareswari, D. Internet of Things based Smart Transportation Systems. Int. Res. J. Eng. Technol. 2015, 2, 1207–1210. [Google Scholar]
  113. Markovic, N.; Sekula, P.; Vander-Laan, Z.; Andrienko, G.; Andrienko, N. Applications of Trajectory Data From the Perspective of a Road Transportation Agency: Literature Review and Maryland Case Study. In IEEE Transactions on Intelligent Transportation Systems; IEEE: Piscataway, NJ, USA, 2018; pp. 1–12. [Google Scholar]
  114. Sachin, K.S.; Santhiya, V.; Mohan, J. Intelligent Transportation System using IoT. Int. Res. J. Eng. Technol. 2020, 17, 2048–2052. [Google Scholar]
  115. Shin, D.-H.; Chung, K.; Park, R.C. Prediction of Traffic Congestion Based on LSTM Through Correction of Missing Temporal and Spatial Data. IEEE Access 2020, 8, 150784–150796. [Google Scholar] [CrossRef]
  116. Salih, T.A.; Younis, N.K. Designing an Intelligent Real-Time Public Transportation Monitoring System based on IoT. Open Access Libr. J. 2021, 8, 1–14. [Google Scholar] [CrossRef]
  117. Singh, P.; Vimal, V. An Intelligent Transportation System for Traffic Management over the IoT. Webology 2021, 18, 3295–3302. [Google Scholar]
  118. Morkhandikar, D.; Vargantwar, M.; Ardhapurkar, S.; Joshi, M. IoT Based Road Side Unit for Intelligent Transportation System. Int. Res. J. Mod. Eng. Technol. Sci. 2021, 3, 357–364. [Google Scholar]
  119. Farman, H.; Khan, Z.; Jan, B.; Boulila, W.; Habib, S.; Koubaa, A. Smart Transportation in Developing Countries: An Internet-of-Things-based Conceptual Framework for Traffic Control. Hindawi Wirel. Commun. Mob. Comput. 2022, 2022, 11. [Google Scholar] [CrossRef]
  120. Farag, M.; Hilal, A.; El-Tawab, S. Parking Occupancy Prediction and Traffic Assignment in a University Environment. In Proceedings of the 10th International Japan-Africa Conference on Electronics, Communications and Computations (JAC-ECC), Alexandria, Egypt, 19–20 December 2022. [Google Scholar]
  121. Zhao, F.; Kuang, X.; Hao, H.; Liu, Z. Selection of Emerging Technologies: A Case Study in Technology Strategies of Intelligent Vehicles. Eng. Manag. J. 2022, 34, 37–49. [Google Scholar] [CrossRef]
  122. Chowdhurry, A.; Kaisar, S.; Khoda, M.E.; Naha, R.; Khoshkholghi, M.A.; Aiash, M. IoT-Based Emergency Vehicle Services in Intelligent Transportation System. Sensors 2023, 23, 5324. [Google Scholar] [CrossRef] [PubMed]
  123. Lopez-Vega, H.; Moodysson, J. Digital Transformation of the Automotive Industry: An Integrating Framework to Analyse Technological Novelty and Breadth. Ind. Innov. 2023, 30, 67–102. [Google Scholar] [CrossRef]
  124. Gillani, M.; Niaz, H.A. Machine Learning Based Data Collection Protocol for Intelligent Transport Systems: A Real-Time Implementation on Dublin M50 Ireland. Complex Intell. Syst. 2023, 2023, 19. [Google Scholar] [CrossRef]
  125. Pathik, N.; Gupta, R.K.; Sahu, Y.; Sharma, A.; Masud, M.; Baz, M. AI Enabled Accident Detection and Alert System using IoT and Deep Learning for Smart Cities. Sustainability 2022, 14, 7701. [Google Scholar] [CrossRef]
  126. Oarga, I.T.; Varga, B.O.; Moldovanu, D.; Carausan, H.; Prunean, G. Modular Autonomous Vehicles’ Application in Public Transport Networks: Conceptual Analysis on Airport Connection. Sustainability 2024, 16, 1512. [Google Scholar] [CrossRef]
  127. Jeong, Y.; Yi, K. Target Vehicle Motion Prediction-Based Motion Planning Framework for Autonomous Driving in Uncontrolled Intersections. IEEE Trans. Intell. Transp. Syst. 2021, 22, 168–177. [Google Scholar] [CrossRef]
  128. Wang, Y.; Gloudemans, D.; Ji, J.; Teoh, Z.N.; Liu, L.; Zachar, G.; Barbour, W.; Work, D. Automatic Vehicle Trajectory Data Reconstruction at Scale. Transp. Res. C 2024, 160, 104520. [Google Scholar] [CrossRef]
  129. Naseer, S.; Liu, W.; Sarkar, N.I.; Shafiq, M.; Choi, J.G. Smart City Taxi Trajectory Coverage and Capacity Evaluation Model for Vehicular Sensor Networks. Sustainability 2021, 13, 10907. [Google Scholar] [CrossRef]
  130. Li, H.; Jiao, H.; Yang, Z. AIS data-driven ship trajectory prediction modelling and analysis based on machine learning and deep learning methods. Transp. Res. Part E 2023, 175, 103152. [Google Scholar] [CrossRef]
  131. Guha, A.; Lei, R.; Zhu, J.; Nguyen, X.; Zhao, D. Robust unsupervised learning of temporal dynamic vehicle-to-vehicle interactions. Transp. Res. Part C 2022, 142, 103768. [Google Scholar] [CrossRef]
  132. Van Brummelen, J.; O’Brien, M.; Gruyer, D.; Najjaran, H. Autonomous Vehicle Perception: The Technology of Today and Tomorrow. Transp. Res. Part C 2018, 89, 384–406. [Google Scholar] [CrossRef]
  133. Belcore, O.M.; Di Gangi, M.; Polimeni, A. Connected Vehicles and Digital Infrastructures: A Framework for Assessing the Port Efficiency. Sustainability 2023, 15, 8168. [Google Scholar] [CrossRef]
  134. Rajput, S.K.; Patni, J.C.; Alshamrani, S.S.; Chaudhari, V.; Dumka, A.; Singh, R.; Rashid, M.; Gehlot, A.; AlGhamdi, A.S. Automatic Vehicle Identification and Classification Model using the YOLOV3 Algorithm for a Toll Management System. Sustainability 2022, 14, 9163. [Google Scholar] [CrossRef]
  135. Wu, F.; Stern, R.E.; Cui, S.; Monache, M.L.D.; Bhadani, R.; Bunting, M.; Churchill, M.; Hamilton, N.; Haulcy, R.; Piccoli, B.; et al. Tracking vehicle trajectories and fuel rates in phantom traffic jams: Methodology and data. Transp. Res. Part C 2019, 99, 82–109. [Google Scholar] [CrossRef]
  136. Luo, Q.; Du, R.; Jia, H.; Yang, L. Research on the deployment of joint dedicated lanes for CAVs and Buses. Sustainability 2022, 14, 8686. [Google Scholar] [CrossRef]
  137. Louati, A.; Louati, H.; Kariri, E.; Neifar, W.; Hassan, M.K.; Khairi, M.; Farahat, M.; El-Hoseny, H. Sustainable Smart Cities through Multi-Agent Reinforcement Learning-Based Cooperative Autonomous Vehicles. Sustainability 2024, 16, 1779. [Google Scholar] [CrossRef]
  138. Li, K.; Liu, T.; Kumar, P.N.R.; Han, X. A reinforcement learning-based hyper-heuristic for AGV task assignment and route planning in parts-to-picker warehouses. Transp. Res. Part E 2024, 105, 103518. [Google Scholar] [CrossRef]
  139. Wang, Y.; Luo, S.; Fan, J.; Zhen, L. The multidepot vehicle routing problem with intelligent recycling prices and transportation resource sharing. Transp. Res. Part E 2024, 185, 103503. [Google Scholar] [CrossRef]
  140. Mostafizi, A.; Koll, C.; Wang, H. A decentralized and coordinated routing algorithm for connected and autonomous vehicles. IEEE Trans. Intell. Syst. 2022, 23, 11505–11517. [Google Scholar] [CrossRef]
  141. Malik, F.; Khattak, H.A.; Almogren, A.; Bouachir, O.; Din, I.U.; Altameem, A. Performance Evaluation of Data Dissemination Protocols for Connected Autonomous Vehicles. IEEE Access 2020, 8, 126896–126906. [Google Scholar] [CrossRef]
  142. Jiang, S.; Tran, C.Q.; Keyvan-Ekbatani, M. Regional route guidance with realistic compliance patterns: Application of deep reinforcement learning and MPC. Transp. Res. Part C 2024, 158, 104440. [Google Scholar] [CrossRef]
  143. Guo, R.; Vallati, M.; Wang, Y.; Zhang, H.; Chen, Y.; Wang, F. Sustainability Opportunities and Ethical Challenges of AI-Enabled Connected Autonomous Vehicles Routing in Urban Areas. IEEE Trans. Intell. Transp. Syst. 2024, 9, 55–58. [Google Scholar] [CrossRef]
  144. Vlachogiannis, D.M.; Moura, S.; Macfarlane, J. Intersense: An XGBoost Model for Traffic Regulator Identification at Intersections through Crowdsourced GPS Data. Transp. Res. Part C 2023, 151, 104112. [Google Scholar] [CrossRef]
  145. Guo, H.; Keyvan-Ekbatani, M.; Xie, K. Modeling coupled driving behaviour during lane change: A multi-agent transformer reinfrocement learning approach. Transp. Res. Part C 2024, 165, 104703. [Google Scholar] [CrossRef]
  146. Huang, T.; Fu, R.; Sun, Q.; Deng, Z.; Liu, Z.; Jin, L.; Khajepour, A. Driver lane change intention prediction based on topological graph constructed by driver behaviours and traffic context for human-machine co-driving system. Transp. Res. Part C 2024, 160, 104497. [Google Scholar] [CrossRef]
  147. ElGanaoui-Mourlan, O.; Camp, S.; Verhas, C.; Pollet, N.; Ortega, B.; Robic, B. Traffic Manager Development for a Roundabout Crossed by Autonomous and Connected Vehicles using V21 Architecture. Sustainability 2023, 15, 9247. [Google Scholar] [CrossRef]
  148. Ben-Ali, M.; Rauch, E. Sustainable Mobility Transition: A SWOT-AHP Analysis of the Case Study of Italy. Sustainability 2024, 16, 4861. [Google Scholar] [CrossRef]
  149. Morozov, V.; Petrov, A.I.; Shepelev, V.; Balfaqih, M. Ideology of urban road transport chaos and accident risk management for sustainable transport systems. Sustainability 2024, 16, 2596. [Google Scholar] [CrossRef]
  150. Wang, L.; Jing, H.; Zhong, G.; Wang, J.; Wang, T. Research on Autonomous Vehicle Obstacle Avoidance Path Planning with Consideration of Social Ethics. Sustainability 2024, 16, 4763. [Google Scholar] [CrossRef]
  151. Ciziuniene, K.; Prokopovic, M.; Zaranka, J.; Matijosius, J. Biometric Breakthrough for Sustainable Travel: Transforming Public Transportation through Secure Identifications. Sustainability 2024, 16, 5071. [Google Scholar] [CrossRef]
  152. Musa, A.A.; Malami, S.I.; Alanazi, F.; Ounaies, W.; Alshammari, M.; Haruna, S.I. Sustainable Traffic Management for Smart Cities using Internet-of-Things-Oriented Intelligent Transportation Systems (ITS): Challenges and Recommendations. Sustainability 2023, 15, 9859. [Google Scholar] [CrossRef]
  153. Chen, Z.; Xiong, X.; Wang, W.; Xiao, Y.; Alfarraj, O. A Blockchain-Based Multi-Unmmaned Aerial Vehicle Task Processing System for Situation Awareness and Real-Time Decision. Sustainability 2023, 15, 13790. [Google Scholar] [CrossRef]
  154. You, L.; Danaf, M.; Zhao, F.; Guan, J.; Azevedo, C.L.; Atasoy, B.; Ben-Akwa, M. A federated Platform Enabling a Systematic Collaboration Among Devices, Data, and Functions for Smart Mobility. IEEE Trans. Intell. Transp. Syst. 2023, 24, 4060–4074. [Google Scholar] [CrossRef]
  155. Kaleem, S.; Sohail, A.; Tariq, M.U.; Asim, M. An Improved Big Data Analytics Architecture using Federated Learning for IoT-Enabled Urban Intelligent Transportation Systems. Sustainability 2023, 15, 15333. [Google Scholar] [CrossRef]
  156. Jiang, R.; Li, J.; Bu, W.; Chen, C. Towards Sustainable Model Services for Deep Learning: A Sub-Network-Based Solution Integrating Blockchain with IPFS and a Use-Case in Intelligent Transportation. Sustainability 2023, 15, 15435. [Google Scholar] [CrossRef]
  157. Mulerikkal, J.; Thandassery, S.; Dixon, K.; Rejathalal, V.; Ayyappan, B. JP-DAP: An Intelligent Data Analytics Platform for Metro Rail Transport Systems. IEEE Trans. Intell. Transp. Syst. 2022, 23, 9146–9156. [Google Scholar] [CrossRef]
  158. Tiong, K.Y.; Ma, Z.; Palmqvist, C. A review of data-driven approaches to predict train delays. Transp. Res. Part C 2023, 148, 104027. [Google Scholar] [CrossRef]
  159. Chang, Y.; Xiao, W. Coifman. Using spatiotemporal stacks for precise vehicle tracking from raodside 3D LiDAR data. Transp. Res. Part C 2023, 154, 104280. [Google Scholar] [CrossRef]
  160. Sun, R.; Luo, Q.; Chen, Y. Online transportation network cyber-attack detection based on stationary sensor data. Transp. Res. Part C 2023, 149, 104058. [Google Scholar] [CrossRef]
  161. Yang, Y.; Dong, R.; Ren, X.; Fu, M. Exploring sustainable planning strategies for carbon emission reduction in Beijing’s transportation sector: A multi-scenario carbon peak analysis using the extended STIRPAT model. Sustainability 2024, 16, 4670. [Google Scholar] [CrossRef]
  162. Nguyen, C.; Hoang, N.H.; Lee, S.; Vu, H.L. A system optimal speed advisory framework for a network of connected and autonomous vehicles. IEEE Trans. Intell. Transp. Syst. 2022, 23, 5727–5738. [Google Scholar] [CrossRef]
  163. Khurshid, A.; Khan, K.; Chen, Y.; Cifuentes-Faura, J. Do green transport and mitigation technologies drives OECD Countries to sustainable path? Transp. Res. Part D 2023, 118, 103669. [Google Scholar] [CrossRef]
  164. Qi, X.; Luo, Y.; Wu, G.; Boriboonsomsin, K.; Barth, M. Deep reinforcement learning enabled self-learning control for energy efficient driving. Transp. Res. Part C 2019, 99, 67–81. [Google Scholar] [CrossRef]
  165. de Curto, J.; de Zarza, I. Analysis of Transportation Systems for Colonies on Mars. Sustainability 2024, 16, 3041. [Google Scholar] [CrossRef]
Sustainability 16 07514 g001
Figure 1. The Industrial Revolution (authors).
Figure 1. The Industrial Revolution (authors).
Sustainability 16 07514 g001
Sustainability 16 07514 g002
Figure 2. Article selection criteria.
Figure 2. Article selection criteria.
Sustainability 16 07514 g002
Sustainability 16 07514 g003
Figure 3. Articles accessed.
Figure 3. Articles accessed.
Sustainability 16 07514 g003
Sustainability 16 07514 g004
Figure 4. Trends in revolutionary impact on transportation.
Figure 4. Trends in revolutionary impact on transportation.
Sustainability 16 07514 g004
Sustainability 16 07514 g005
Figure 5. Relationship among the technologies (authors).
Figure 5. Relationship among the technologies (authors).
Sustainability 16 07514 g005
Sustainability 16 07514 g006
Figure 6. References/citations on the influences/impacts of 4IR technologies (authors).
Figure 6. References/citations on the influences/impacts of 4IR technologies (authors).
Sustainability 16 07514 g006
Sustainability 16 07514 g007
Figure 7. Recentness of articles used on 4IR data collection and processing mechanisms (authors).
Figure 7. Recentness of articles used on 4IR data collection and processing mechanisms (authors).
Sustainability 16 07514 g007
Sustainability 16 07514 g008
Figure 8. Articles and corresponding 4IR technologies.
Figure 8. Articles and corresponding 4IR technologies.
Sustainability 16 07514 g008
Table 1. Search keywords/strings and number of articles retrieved.
Table 1. Search keywords/strings and number of articles retrieved.
S/NSearch Keywords/StringsNumber of Papers Retrieved
1.4IR technologies and the transportation system (4IR + technologies + transportation system)88
Impact of 4IR technologies on transportation system
Application of 4IR technologies on transportation system
4IR and the transportation system
2.Data collection and processing approaches in the application of 4IR technologies
(data collection + processing approach + 4IR application)		16
3.Research work on transportation system and 4IR
(transportation + 4IR)		2
4.Sustainable cities and urban transportation
(sustainable + cities + urban + transportation)		3
5.Traffic, human driven-and electric cars, buses and trucks
(traffic + human driver + electric cars)		8
6.Research articles on revolutions in the transport industry
(revolutions + transport industry)		3
7.4IR and essential services
(4IR + essential services)		4
8.Sustainable transportation technologies
(sustainable + transportation + technologies)		8
9.Smart and Intelligent Transportation Systems
(smart + intelligent + transportation + system)		17
10.Connected Transport and Autonomous Vehicles
(connected + transport + autonomous + vehicle)		16
Total 165
Table 2. Publishing companies/search engines and the number of papers retrieved.
Table 2. Publishing companies/search engines and the number of papers retrieved.
S/NPublishing Outfit/Search EngineNumber of Papers Retrieved
1.IEEE85
2.Elsevier Science Direct36
3.ACM1
4.Taylor and Francis1
5.Springer 2
6.Google Scholar40
Total 165
Table 3. Articles accessed.
Table 3. Articles accessed.
S/NArticles AccessedNumber of Papers%
1.Used 16560.4 (60)
2.Unused 10839.6 (40)
Total Accessed273100
Table 4. Technologies that made a revolutionary impact on transportation systems (authors).
Table 4. Technologies that made a revolutionary impact on transportation systems (authors).
S/NMajor Technology1st Revolution (1IR)2nd Revolution (2IR)3rd Revolution (3IR)4th Revolution (4IR)
1.Artificial Intelligencen/an/an/a✓
2.Big Datan/an/an/a✓
3.Machine Learningn/an/an/a✓
4.IoTn/an/an/a✓
5.Blockchain n/an/an/a✓
6.Smart Gridn/an/a✓✓
7.Cloud Computingn/an/a✓✓
8.Roboticsn/an/a✓✓
9.Virtual and Augmented Realitiesn/an/an/a✓
10.3D Printingn/an/an/a✓
11.Dronesn/an/an/a✓
12.Fog Computingn/an/an/a✓
13.Internet Technologyn/an/a✓✓
14.Communication Technologyn/a✓✓✓
15.Autonomous Systemn/an/an/a✓
16.Quantum Computingn/an/an/a✓
17.Electrical Technologyn/a✓✓✓
18.Energy/Power Technology✓✓✓✓
Key: n/a: not applicable; ✓: available.
Table 5. Influence and impact of 4IR technologies (authors).
Table 5. Influence and impact of 4IR technologies (authors).
S/NTypes of 4IR TechnologiesInfluence and ImpactReferences No of Ref.
1.IoT/SensorThe interconnection of vehicles, infrastructure, and users through a network of sensors and smart devices.[9,10,11,12,13,14,15,16,17]9
2.Autonomous SystemImprovements in autonomous vehicle performance, safety, and efficiency.[18,19,20,21,22,23,24]7
3.Big DataNovel techniques and methodologies that pave the way for smarter, more efficient, and user-friendly transportation systems.[12,25,26,27,28,29,30,31,32,33,34,35,36,37,38]15
4.Artificial IntelligenceContributes to the development and implementation of intelligent systems and control algorithms, which have revolutionized urban transportation and led to the creation of smarter and safer transportation systems.[39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62]24
5.Machine Learning/Deep LearningAchieve predictive data analysis, optimization and decision support. Revolutionized urban transportation systems and contribute to the creation of smarter and more efficient cities. [15,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90]29
6.Computing Paradigms Introduces innovative technologies that enhance the safety and sustainability of smart and intelligent transportation systems.[11,16,91,92,93,94,95,96,97,98]10
7.Geographic Information SystemEnhances precision, safety, security, and satisfaction.[28,99,100,101,102,103,104]7
8.Energy/Power TechnologyEnhances environmental protection by reducing carbon emission.[105]1
9.Communication TechnologyEnables connectivity through faster and more reliable networks.[106]1
10.Electrical TechnologyImproves energy efficiency, and enables industrial automation and the development of electric vehicles.[107,108,109]3
11.Internet TechnologyRevolutionizes connectivity, and gives access to information and online services and interactions.[110]1
Table 6. Summary of reviewed specific studies.
Table 6. Summary of reviewed specific studies.
S/NArticle Ref NoArticle YearAim ApproachArticle Contribution Article Limitation
1. [111]2014To develop a prototype ITS that tracks vehicles, enables payment tickets, and analyzes crowds and ambience inside buses.Prototype model approach using sensor, monitoring, and display systems.Successfully developed a system that tracks/detects vehicle location, commuter information, and the ambience.Measures implemented to safeguard the CIA of data and information were not discussed.
2. [112]2015The study’s main objective was to deploy IoT technologies to build ITS in improving an urban transportation systemThe authors used wireless sensors to obtain real-time traffic information.The authors successfully developed a real-time traffic controlling and monitoring system that reduced traffic congestion in the urban area.The authors did not approach the issues of RFID’s data reading range and data security privacy.
3. [113]2018The purpose of the study is to support transportation agencies in determining the usefulness of trajectory data for their particular requirements and decision-making procedures.ML and GPS trajectory data using V-Analytic software for visual data exploration, analysis and modelling.The study contributed to advancing the understanding and utilization of trajectory data in road transportation systems analysis.Factors to take into account prior to acquiring trajectory data were not considered.
4. [114]2020The authors’ goal was to create a smart information system that offers all pertinent, connected information on buses, with a focus on seating arrangements.A framework based on IoT using a touch sensor, which detects occupied and empty seats.The authors successfully implemented a system that provides real-time information about the exact location, arrival time, and seat availability of a bus.Waiting times and traffic congestion were not taken into consideration. The data privacy of the passenger’s location information was also an issue.
5. [115]2020The aim of the study was to predict traffic congestion. Adopts LSTM-based traffic congestion prediction approach based on the correction of missing temporal and spatial values.The model achieved higher prediction accuracy for suburban areas, and in comparison with other relevant models.Urban areas and low-speed zones need to be predicted in order to validate the model.
6. [116]2021The authors aimed at designing a system that reduces passengers’ waiting times.The system was implemented based on IoT technology using GPS and a microcontroller.The implemented system was able to compute real-time information about buses (e.g., current location, arrival time, speed, etc.). The authors were unable to implement passenger count and e-ticketing. Data privacy was also an issue.
7. [12]2019To offer a framework for using big data analytics and Internet of Things (IoT) technology to design a smart transportation system. The four layers of the system that the authors designed were data processing, the application, the network, and data gathering and acquisition. Each of these was designed to handle and process data efficiently. In the data processing layer, the authors made effective use of Spark and Hadoop to manage real-time traffic data.A model that integrates IoT, big data analytics, and named data networking for smart transportation systems was proposed. The proposed model offers solutions to challenges such as processing big data in real time and disseminating information to citizens efficiently.Challenges relating to data privacy and security concerns were not discussed.
8. [117]2021Ton develop a model for traffic monitoring and control was the study’s goal.The STMS model was adopted.The study achieved superior results in the modelling of traffic congestion.Challenges involved in implementing the model on a large scale was not discussed (e.g., data integration).
9. [118]2021To present an enhanced Intelligent Transport System with roadside unit (RSU) using IoT.The authors used Raspberry Pi Board as the main component for real-time data/information collection, while ZigBee wireless technology was used for communication.Implemented IoT-based roadside unit for ITS with the aid of OpenCV library.A precise vehicle count for the overlapping of vehicles was not achieved.
10. [100]2021To address several IoT challenges with relative to cyber physical security, etc.Applied geospatial modelling approach.The authors simulated a set of geospatial indicators that support the master planning of IoT networks in facilitating the running of a Smart Transportation Security System.Availability and quality of data.
In addition, the work is limited in its generalization and may also face integration challenges.
11.[119]2022The study highlights the challenges and consequences of an existing transportation system in Peshawar, in Pakistan, in response to the rapid growth in population.IoT-based framework for busy traffic junction.The implemented framework was able to successfully reduce travelling times, fuel consumption, and environmental pollution.The framework was limited in the number of actors used, which could have possible effects on the effectiveness of the system in a scenario involving highly congested traffic.
12.[120]2022Investigation of traffic assignment based on parking prediction.Ensemble machine learning models were deployed to predict parking spaces after data were collected from an accumulated copy of the parking availability posted on digital signs at garages’ entrances.Successful applicability of ensemble machine learning models in the accurate and precise prediction of ITS.Deployment of deep learning models for a more accurate and precise prediction of ITS.
13.[121]2022The article emphasizes the importance of technology selection in corporate ET strategies.PTM framework for emerging technology selection.A structured approach to guide engineering managers in making strategic decisions about ET adoption.Non-establishment of more detailed criteria for PTM factors and corporate internal capabilities.
14.[122]2023To obtain better clearance times and lower response times for emergency vehicles.Adoption of unmanned aerial vehicle (UAV)-guided priority-based incident management model.The proposed system has the potential to significantly enhance emergency response capabilities within urban transportation systems while minimizing disruption to other road users.Real-life implementation challenge, and lack of scalability to handle larger datasets.
15.[123]2023The study was designed to identify digital technology topics that are transforming the automotive industry.Use of integrating frameworks to illustrate the value of digital technologies.The result of the study’s use of pyLDAvis library to visualize shows that digital technologies in the automotive industry have the incremental characteristics to achieve potential in transforming the industry.The call for a combinatorial radical (hybrid) application for implementing automotive control systems, such as collision prevention assistance technology.
16.[124]2023Proposal of a lightweight machine-learning-based data collection protocol called ML-TDG.Lightweight ML-based data collection procedure.Presents ML-TDG as an innovative solution to address challenges in data collection and communication in urban traffic environments.A better machine learning framework is needed to improve time, storage, energy, and communication efficiency, with possible security features incorporated.
17.[125]2022To create temporal passenger profiles and to examine travel patterns.Generative-model-based approach.Enhanced public transportation systems.Security of smart card data.
18.[126]2024To improve energy efficiency and lower pollutant emission.MAV virtual model.Minimizes energy consumption.Need to certify MAV virtual models.
19.[127]2021To anticipate other vehicles’ movement and adjust driving maneuvers.Motion-planning framework.Guarantees the safety and replicates the actions of real drivers at junctions.Need for more prediction accuracy.
20.[128]2024To design a postprocessing pipeline to solve problems.Simulation. High-resolution trajectory data.Refinement of parameters.
21.[129]2021To analyze the effectiveness of on-board sensor networks.Model for collecting delay-tolerance data for smart sensors.Strong network coverage and connectivity.Robust network to connect diverse smart city applications.
22.[130]2023To tackle increasingly complicated traffic situations.DL + ML.Advancement of autonomous navigation technology.Prediction accuracy issue.
23.[131]2022To develop a reliable unsupervised learning technique for examining temporal dynamic interactions between vehicles.Deployment of metrics on Safety Pilot DB.Clustering efficiency. Geometric approach.
24.[132]2023Discussion of the difficulties with and development of autonomous vehicles.Localization and mapping techniques.Emphasizes the implication of presumptive knowledge. Need for more reliable sensor systems.
25.[133]2023To reduce wait times at terminals.Simulation. Increased port productivity and overall performance.Automation and connectivity in maritime terminals.
26.[134]2022To achieve vehicle detection and classification for toll management system.Prediction with YOLOv3 algorithm.High degree of accuracy of the deployed DL approach (YOLOv3).Investigation of multi-scale vehicle identification.
27.[135]2019To investigate free flow traffic and phantom traffic waves.A novel technique for tracking vehicle trajectories and fuel rates.Understanding of the effects of phantom traffic waves on fuel.Need to corroborate results with empirical data.
28.[136]2022To analyze the prospects and impacts of and difficulties in adopting autonomous vehicles.Data retrieved from previous studies.Enhanced energy efficiency and traffic flow.Infrastructure and integration issues.
29.[137]2024To improve the efficiency and sustainability of urban transportation.Multi-agent reinforcement learning (MARL).Safe, effective and sustainable transportation system.Multi-agent lane switching.
30.[138]2024To examine the effectiveness and efficiency of multi-AGV scheduling issues in warehouse picking.Simulation. Improved scheduling. Needs to enhance DMAB and MAB methodologies’ resilience.
31.[139]2024To create a hybrid algorithm that combines 3D k-means clustering and self-adapting genetic algorithm–particle swarm optimization.Mixed-integer programming model.Optimized routing problem.The use and validation of the model in diverse settings.
32.[140]2022To improve mobility and efficiency in a crowded transportation network.Dec-CTDSP routing algorithm.Higher performance in CAV networks.Validation in a real-world scenario.
33.[141]2020To implement routing strategies in autonomous cars.Simulation.High performance result.More investigation into protocols.
34.[142]2024To offer a regional route guiding system.MPC + DRL.Dynamic route guidance and improvement in traffic management.Integration of real-time predictive data.
35.[143]2024To examine the sustainability and moral dilemmas posed by AI-enabled urban routing for CAVs.Review of the literature.Support sustainable urban mobility with reduced emissions, accidents, and traffic.Moral issues.
36.[144]2023To improve the quality of digital maps for self-driving cars.GPS + XGBoost.Better mapping, traffic control, and scalability.Integration of more data sources and real-time implementation.
37.[145]2024To analyze observatory-action memory and learn the sequential decision-making process during lane changes.MA-TDDPG.Realistic lane changes and improvements in driving techniques and safety.Multi-agent and recurrent reinforcement learning methodologies.
38.[146]2023To forecast driver lane change intention.Simulation. Achieved higher safety and prediction accuracy.Application of DL model.
39.[147]2023To examine how different design elements and safety standards affect the operation of autonomous cars at junction.Performance measurements + simulation model.Improved the effectiveness and safety of roundabouts for autonomous vehicles.Investigation of the effects of extra parameters.
40.[148]2024To evaluate the variables impacting Italy’s road transport industry.Literature review.Offers support and opportunities to EV technology in Italy.EV charging infrastructure.
41.[149]2024To improve the sustainability of urban transportation systems.Data from previous research.Improved sustainability is achieved, as well as reduced accident and traffic chaos.Environmental entropy features.
42.[150]2024To create a decision-planning model for autonomous vehicles.Fuzzy algorithm + dynamic programming.More sustainable and safe transportation achieved.Moral decision-making model.
43.[151]2024To evaluate how biometric data affect a public transportation system.Expert-data collection approach.Use of model is positively correlated. Improvement in the implementation of biometric techniques.
44.[152]2023To address traffic-related issues in smart cities.Sustainable framework, uses ITS devices and AI sensors to capture data.Improved smart city sustainability.Consideration of cutting-edge technologies.
45.[153]2023To improve situation awareness and in-the-moment decision-making in a sustainable transportation scenario.Distributed task-processing network + Pointer Network structure.Improved collaborative processing and efficiency.Algorithm optimization.
46.[154]2023To improve smart mobility services.Future mobility sensing advisor.Enhanced urban livability and sustainability. Newer techniques for more intelligent urban mobility solutions.
47.[155]2023To improve big data analytics architecture for IoT-enabled urban ITS.Federated Learning.Better scalability.Real-time adaptability.
48.[156]2023To achieve a sustainable model service in deep learning.Blockchain + IPFS.Balanced security + system efficiency.Investigation of supplementary technologies.
49.[157]2022To guarantee seamless operation and enable effective management.Real-time and historical data.Improved customer experience.Investigate additional technologies.
50.[158]2023To examine and predict the causes of train delays.GTFS data + NSW’s open data center.Increased prediction accuracy.Hybrid or sophisticated machine learning models.
51.[159]2023To improve the accuracy of vehicle tracking.Data collection from sensor.Scalability and good accuracy.Real-world circumstances.
52.[160]2023To employ real-time sensory data to identify cyber-attacks on transportation networks.Gaussian process model + LSTM-autoencoder model.Better predictive performance.Investigation of intricate assault scenario.
53.[161]2024To estimate and forecast emissions.Extended STIRPAT Model.Efficiency enhancement.Examination of supplementary impacting elements.
54.[162]2022To handle the speed advisory problem in a network.Microscopic and macroscopic methods.Speed harmonization and emission reduction.Computational efficiency.
55.[163]2023To examine data from OECD and IEA sources and check for correlation.Correlation analysis.Reduced emissions.Wider range of mitigation techniques.
56.[164]2019To increase the energy efficiency of plug-in hybrid electric vehicles.DRL.Increased energy efficiency. Process optimization.
57.[165]2024To access energy efficiency. Comparative analysis. Energy-efficient surface transportation.Enhancement of Mars exploration tactics.
Table 7. Data collection and processing mechanisms used in the reviewed studies.
Table 7. Data collection and processing mechanisms used in the reviewed studies.
S/NArticle Ref. No4IR TechnologyData Collection Method/Means/TypeProcessing Mechanism
1.[111]IoTNFC reader, GPS receiver, environmental sensorsInformation Processing System (IPS)
2.[112]IoTWireless sensor, RFID, GPSMobile Agents & GPRS
3.[113]GPSTrajectory dataV-Analytics Software
4.[114]IoTArduino Uno, GPS, sensor, IoTIoT Module, Android App
5.[115]ML/DLTraffic dataLong-Short Term memory (LSTM) Model
6.[116]IoTGPS dataGPS, ESP32, Microcontroller + Wifi, Blynk IoT Platform
7.[12]IoTSensor data on parking lots and roadwaysHadoop and Spark
8.[117]IoTReal-time sensor dataData Analysis Search Engine (Simulation)
9.[118]IoTRaspberry Pi and Zigbee serial connectionOpenCV Library
10.[100]IoTPublic infrastructure, geographic variables, metro convenience indices, national standards, 5G basic station coverageSimulation
11.[119]IoTRoadside unit (RSU) and IoV dataGame Theory and Nash Equilibrium
12.[120]ML/DLPressure sensor dataLSTM, ANN, MySQL
13.[121]Emerging technologies (ETs)Data on ET selection criteria Qualitative analysis
14.[122]IoTReal-time traffic data + incident recordUAV-guided priority system
15.[123]Autonomous Patent data on autonomous car technologyTopic modelling
16.[124]MLML-TDGApache Spark
17.[125]Autonomous Journey transaction data collected through automated fare collection systemMaaS (Mobility-as-a-Service)
18.{126}Autonomous Data on population, traveler routes, bus stop and busesSophisticated scheduling and optimization techniques
19.[127]Autonomous Data from uncontrolled crossings in Midan cityIntelligent Driver Model (IDM) and K-means clustering
20.[128]Autonomous Simulated and real-world dataOptimization
21.[129]Smart gridT-Drive dataset for taxi trajectories Grid clustering algorithm, SQL, visualization
22.[130]ML/DLAutomatic identification system (AIS) data7 DL Models + 5 ML models
23.[131]MLSafety pilot datasetClustering model
24.[132]Autonomous Research paper data + automotive companies‘ dataComparative analysis
25.[133]Autonomous Data from smart edge cloud systemAutomated vehicle reservation systems and advisory-based arrival system
26.[134]DLVideo photo datasetYOLOv3 algorithm
27.[135]DLVideo dataComputer vision algorithm
28.[136]Autonomous Traffic dataQualitative analysis
29.[137]Autonomous Data on vehicle placements, speed, traffic signals, and environmental factorsMARL (multi-agent reinforcement learning) algorithm
30.[138]Autonomous Syntetic dataSimulation and comparative analysis
31.[139]Autonomous Data from recycling center location, quantities of goods returned, recycling costs, and transportation resourcesSGA-PSO (Self-adapting genetic algorithm–particle swam optimization)
32.[140]Autonomous Data from journey time and dependabilityDec-CTDSP (Decentralized and Collaborative Time-Dependent Shortest Path)
33.[141]Autonomous Data from traffic patterns and car countsOMNET++ and SUMO (throughput and latency were evaluated)
34.[142]Autonomous Real-time traffic dataMPC (model predictive control) and DRL (deep reinforcement learning)
35.[143]Artificial intelligence Data from previous studiesQualitative analysis
36.[144]Autonomous GPS dataXGBoost
37.[145]Electrical technologyLarge-scale real-world connected vehicle dataMulti-agent Transformer-based deep deterministic policy gradient (MA-TDDPG) model
38.[146]Autonomous Simulated and design dataSimulation and predictive model
39.[147]Electrical technologyData gathered from literature review, official announcements, and local lawsSWOT-AHP
40.[149]Electrical technologyData from previous research, traffic incidents, road accidents, and real-time videosRegression analysis
41.[150]Autonomous Data from traffic safety, self-driving cars, and moral decision-makingFuzzy algorithms + dynamic programming
42.[151]IoTData collected from domain expertsExpert analysis + statistical analysis and computations
43.[152]IoTAutomobile data from ITS devices and AI sensorsML + cloud computing
44.[153]Blockchain Smart contractsDistributed task-processing network + Pointer Network structure
45.[154]IoT, big data, AI, clouds, fog, and edge computingFine-grained data from cloud and edgeFMSA (Future Mobility Sensing Advisor)
46.[155]IoT and Big dataUdacity self-driving car datasetFederated Learning technique/Federated Averaging algorithm
47.[156]DL and blockchainSmart contractIPFS sub-networks
48.[157]Big dataReal-time and historical data (KMRL and AFC data)ML technique
49.[158]MLPublic and open dataset (GTFS data and NSW’s Open Data Centre)Machine model and statistical regression analysis
50.[159]IoT3D LiDAR data from sensorClustering analysis
51.[160]IoTReal-time sensory dataGaussian process model and LSTM-autoencoder model
52.[161]Energy technologyData from multiple statistics year-booksExtended STIRPAT model, scenario analysis, and ridge regression
53.[162]Autonomous Data on network speedMicroscopic and macroscopic models
54.[163]Energy technologyData from OECD and IEA sourcesStatistical and econometric techniques
55.[164]Electricity technology Real-world data on driving circumstances, power demand, and battery state of changeDeep reinforcement learning (DRI) model
56.[165]Senergy technologySimulated and real-world Mars exploration missions and theoretical modelsComparative analysis, using simulation and Monte Carlos
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content.

Share and Cite

MDPI and ACS Style

Ajayi, O.O.; Kurien, A.M.; Djouani, K.; Dieng, L. 4IR Applications in the Transport Industry: Systematic Review of the State of the Art with Respect to Data Collection and Processing Mechanisms. Sustainability 2024, 16, 7514. https://doi.org/10.3390/su16177514

AMA Style

Ajayi OO, Kurien AM, Djouani K, Dieng L. 4IR Applications in the Transport Industry: Systematic Review of the State of the Art with Respect to Data Collection and Processing Mechanisms. Sustainability. 2024; 16(17):7514. https://doi.org/10.3390/su16177514

Chicago/Turabian Style

Ajayi, Olusola O., Anish M. Kurien, Kareem Djouani, and Lamine Dieng. 2024. "4IR Applications in the Transport Industry: Systematic Review of the State of the Art with Respect to Data Collection and Processing Mechanisms" Sustainability 16, no. 17: 7514. https://doi.org/10.3390/su16177514

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop