Building trust for traffic flow forecasting components in intelligent transportation systems via interpretable ensemble learning

Traffic flow forecasting constitutes a crucial component of intelligent transportation systems(ITSs).Numerous studies have been conducted for traffic flow forecasting during the past decades.However,most existing studies have concentrated on developing advanced algorithms or models to attain state-of-the-art forecasting accuracy.For real-world ITS applications,the interpretability of the developed models is extremely important but has largely been ignored.This study presents an interpretable traffic flow forecasting framework based on popular tree-ensemble algorithms.The framework comprises multiple key components integrated into a highly flexible and customizable multi-stage pipeline,enabling the seamless incorporation of various algorithms and tools.To evaluate the effectiveness of the framework,the developed tree-ensemble models and another three typical categories of baseline models,including statistical time series,shallow learning,and deep learning,were compared on three datasets collected from different types of roads(i.e.,arterial,expressway,and freeway).Further,the study delves into an in-depth interpretability analysis of the most competitive tree-ensemble models using six categories of interpretable machine learning methods.Experimental results highlight the potential of the proposed framework.The tree-ensemble models developed within this framework achieve competitive accuracy while maintaining high inference efficiency similar to statistical time series and shallow learning models.Meanwhile,these tree-ensemble models offer interpretability from multiple perspectives via interpretable machine-learning techniques.The proposed framework is anticipated to provide reliable and trustworthy decision support across various ITS applications.

Internet of Things Based Solutions for Transport Network Vulnerability Assessment in Intelligent Transportation Systems

Intelligent Transportation System(ITS)is essential for effective identification of vulnerable units in the transport network and its stable operation.Also,it is necessary to establish an urban transport network vulnerability assessment model with solutions based on Internet of Things(IoT).Previous research on vulnerability has no congestion effect on the peak time of urban road network.The cascading failure of links or nodes is presented by IoT monitoring system,which can collect data from a wireless sensor network in the transport environment.The IoT monitoring system collects wireless data via Vehicle-to-Infrastructure(V2I)channels to simulate key segments and their failure probability.Finally,the topological structure vulnerability index and the traffic function vulnerability index of road network are extracted from the vulnerability factors.The two indices are standardized by calculating the relative change rate,and the comprehensive index of the consequence after road network unit is in a failure state.Therefore,by calculating the failure probability of road network unit and comprehensive index of road network unit in failure state,the comprehensive vulnerability of road network can be evaluated by a risk calculation formula.In short,the IoT-based solutions to the new vulnerability assessment can help road network planning and traffic management departments to achieve the ITS goals.

End-to-End Joint Multi-Object Detection and Tracking for Intelligent Transportation Systems

Environment perception is one of the most critical technology of intelligent transportation systems(ITS).Motion interaction between multiple vehicles in ITS makes it important to perform multi-object tracking(MOT).However,most existing MOT algorithms follow the tracking-by-detection framework,which separates detection and tracking into two independent segments and limit the global efciency.Recently,a few algorithms have combined feature extraction into one network;however,the tracking portion continues to rely on data association,and requires com‑plex post-processing for life cycle management.Those methods do not combine detection and tracking efciently.This paper presents a novel network to realize joint multi-object detection and tracking in an end-to-end manner for ITS,named as global correlation network(GCNet).Unlike most object detection methods,GCNet introduces a global correlation layer for regression of absolute size and coordinates of bounding boxes,instead of ofsetting predictions.The pipeline of detection and tracking in GCNet is conceptually simple,and does not require compli‑cated tracking strategies such as non-maximum suppression and data association.GCNet was evaluated on a multivehicle tracking dataset,UA-DETRAC,demonstrating promising performance compared to state-of-the-art detectors and trackers.

A deep learning based misbehavior classification scheme for intrusion detection in cooperative intelligent transportation systems

With the rise of the Internet of Vehicles(IoV)and the number of connected vehicles increasing on the roads,Cooperative Intelligent Transportation Systems(C-ITSs)have become an important area of research.As the number of Vehicle to Vehicle(V2V)and Vehicle to Interface(V2I)communication links increases,the amount of data received and processed in the network also increases.In addition,networking interfaces need to be made more secure for which existing cryptography-based security schemes may not be sufficient.Thus,there is a need to augment them with intelligent network intrusion detection techniques.Some machine learning-based intrusion detection and anomaly detection techniques for vehicular networks have been proposed in recent times.However,given the expected large network size,there is a necessity for extensive data processing for use in such anomaly detection methods.Deep learning solutions are lucrative options as they remove the necessity for feature selection.Therefore,with the amount of vehicular network traffic increasing at an unprecedented rate in the C-ITS scenario,the need for deep learning-based techniques is all the more heightened.This work presents three deep learning-based misbehavior classification schemes for intrusion detection in IoV networks using Long Short Term Memory(LSTM)and Convolutional Neural Networks(CNNs).The proposed Deep Learning Classification Engines(DCLE)comprise of single or multi-step classification done by deep learning models that are deployed on the vehicular edge servers.Vehicular data received by the Road Side Units(RSUs)is pre-processed and forwarded to the edge server for classifications following the three classification schemes proposed in this paper.The proposed classifiers identify 18 different vehicular behavior types,the F1-scores ranging from 95.58%to 96.75%,much higher than the existing works.By running the classifiers on testbeds emulating edge servers,the prediction performance and prediction time comparison of the proposed scheme is compared with those of the existing studies.

A Nationwide Evaluation of the State of Practice of Performance Measurements for Intelligent Transportation Systems

State departments of transportation’s (DOTs) decisions to invest resources to expand or implement intelligent transportation systems (ITS) programs or even retire existing infrastructure need to be based on performance evaluations. Nonetheless, an apparent gap exists between the need for ITS performance measurements and the actual implementation. The evidence available points to challenges in the ITS performance measurement processes. This paper evaluated the state of practice of performance measurement for ITS across the US and provided insights. A comprehensive literature review assessed the use of performance measures by DOTs for monitoring implemented ITS programs. Based on the gaps identified through the literature review, a nationwide qualitative survey was used to gather insights from key stakeholders on the subject matter and presented in this paper. From the data gathered, performance measurement of ITS is fairly integrated into ITS programs by DOTs, with most agencies considering the process beneficial. There, however, exist reasons that prevent agencies from measuring ITS performance to greater detail and quality. These include lack of data, fragmented or incomparable data formats, the complexity of the endeavor, lack of data scientists, and difficulty assigning responsibilities when inter-agency collaboration is required. Additionally, DOTs do not benchmark or compare their ITS performance with others for reasons that include lack of data, lack of guidance or best practices, and incomparable data formats. This paper is relevant as it provides insights expected to guide DOTs and other agencies in developing or reevaluating their ITS performance measurement processes.

An Optimal Deep Learning for Cooperative Intelligent Transportation System

Cooperative Intelligent Transport System(C-ITS)plays a vital role in the future road traffic management system.A vital element of C-ITS comprises vehicles,road side units,and traffic command centers,which produce a massive quantity of data comprising both mobility and service-related data.For the extraction of meaningful and related details out of the generated data,data science acts as an essential part of the upcoming C-ITS applications.At the same time,prediction of short-term traffic flow is highly essential to manage the traffic accurately.Due to the rapid increase in the amount of traffic data,deep learning(DL)models are widely employed,which uses a non-parametric approach for dealing with traffic flow forecasting.This paper focuses on the design of intelligent deep learning based short-termtraffic flow prediction(IDL-STFLP)model for C-ITS that assists the people in various ways,namely optimization of signal timing by traffic signal controllers,travelers being able to adapt and alter their routes,and so on.The presented IDLSTFLP model operates on two main stages namely vehicle counting and traffic flow prediction.The IDL-STFLP model employs the Fully Convolutional Redundant Counting(FCRC)based vehicle count process.In addition,deep belief network(DBN)model is applied for the prediction of short-term traffic flow.To further improve the performance of the DBN in traffic flow prediction,it will be optimized by Quantum-behaved bat algorithm(QBA)which optimizes the tunable parameters of DBN.Experimental results based on benchmark dataset show that the presented method can count vehicles and predict traffic flowin real-time with amaximumperformance under dissimilar environmental situations.

Optimal control and energy storage for DC electric train systems using evolutionary algorithms

Electrified railways are becoming a popular transport medium and these consume a large amount of electrical energy.Environmental concerns demand reduction in energy use and peak power demand of railway systems.Furthermore,high transmission losses in DC railway systems make local storage of energy an increasingly attractive option.An optimisation framework based on genetic algorithms is developed to optimise a DC electric rail network in terms of a comprehensive set of decision variables including storage size,charge/discharge power limits,timetable and train driving style/trajectory to maximise benefits of energy storage in reducing railway peak power and energy consumption.Experimental results for the considered real-world networks show a reduction of energy consumption in the range 15%–30%depending on the train driving style,and reduced power peaks.

Key Technology Analysis for Driver Support Systems in Japan

This paper presents the technical survey and the trend analysis of the driver support technologies such as a pre-crush braking system in Japan. In the first part, Vehicle Intelligence to assist drivers is defined by two objective functions which are both TGA （Target Generation Agent） and TAA （Target Accomplishment Agent）. TAA is mainly based on the conventional technologies that are braking smoothly, or driving with lower fuel consumption. On the other hand, TGA has the intelligent function instead of human drivers. The actual TGA are explained using some concrete driver support systems. After that, Japanese market introduction date and evolution of driver support systems are discussed with clarifying cognitive aspects which are the perception support, the judgment support and the execution support. And Key technologies underlying evolution of driver support systems are explained. Finally the author concludes that the knowledge and insights needed for intelligent driver support systems will be much more complex than in the case of autonomous vehicles that drive themselves.

Optimized Convolutional Neural Networks with Multi-Scale Pyramid Feature Integration for Efficient Traffic Light Detection in Intelligent Transportation Systems

Transportation systems are experiencing a significant transformation due to the integration of advanced technologies, including artificial intelligence and machine learning. In the context of intelligent transportation systems (ITS) and Advanced Driver Assistance Systems (ADAS), the development of efficient and reliable traffic light detection mechanisms is crucial for enhancing road safety and traffic management. This paper presents an optimized convolutional neural network (CNN) framework designed to detect traffic lights in real-time within complex urban environments. Leveraging multi-scale pyramid feature maps, the proposed model addresses key challenges such as the detection of small, occluded, and low-resolution traffic lights amidst complex backgrounds. The integration of dilated convolutions, Region of Interest (ROI) alignment, and Soft Non-Maximum Suppression (Soft-NMS) further improves detection accuracy and reduces false positives. By optimizing computational efficiency and parameter complexity, the framework is designed to operate seamlessly on embedded systems, ensuring robust performance in real-world applications. Extensive experiments using real-world datasets demonstrate that our model significantly outperforms existing methods, providing a scalable solution for ITS and ADAS applications. This research contributes to the advancement of Artificial Intelligence-driven (AI-driven) pattern recognition in transportation systems and offers a mathematical approach to improving efficiency and safety in logistics and transportation networks.

Context-Aware Feature Extraction Network for High-Precision UAV-Based Vehicle Detection in Urban Environments

The integration of Unmanned Aerial Vehicles(UAVs)into Intelligent Transportation Systems(ITS)holds trans-formative potential for real-time traffic monitoring,a critical component of emerging smart city infrastructure.UAVs offer unique advantages over stationary traffic cameras,including greater flexibility in monitoring large and dynamic urban areas.However,detecting small,densely packed vehicles in UAV imagery remains a significant challenge due to occlusion,variations in lighting,and the complexity of urban landscapes.Conventional models often struggle with these issues,leading to inaccurate detections and reduced performance in practical applications.To address these challenges,this paper introduces CFEMNet,an advanced deep learning model specifically designed for high-precision vehicle detection in complex urban environments.CFEMNet is built on the High-Resolution Network(HRNet)architecture and integrates a Context-aware Feature Extraction Module(CFEM),which combines multi-scale feature learning with a novel Self-Attention and Convolution layer setup within a Multi-scale Feature Block(MFB).This combination allows CFEMNet to accurately capture fine-grained details across varying scales,crucial for detecting small or partially occluded vehicles.Furthermore,the model incorporates an Equivalent Feed-Forward Network(EFFN)Block to ensure robust extraction of both spatial and semantic features,enhancing its ability to distinguish vehicles from similar objects.To optimize computational efficiency,CFEMNet employs a local window adaptation of Multi-head Self-Attention(MSA),which reduces memory overhead without sacrificing detection accuracy.Extensive experimental evaluations on the UAVDT and VisDrone-DET2018 datasets confirm CFEMNet’s superior performance in vehicle detection compared to existing models.This new architecture establishes CFEMNet as a benchmark for UAV-enabled traffic management,offering enhanced precision,reduced computational demands,and scalability for deployment in smart city applications.The advancements presented in CFEMNet contribute significantly to the evolution of smart city technologies,providing a foundation for intelligent and responsive traffic management systems that can adapt to the dynamic demands of urban environments.

Telematics as a Transformative Agent for the Zimbabwean Auto Insurance Ecosystem

Zimbabwe has witnessed the evolution of Information Communication Technology (ICT). The vehicle population soared to above 1.2 million hence rendering the Transport and Insurance domains complex. Therefore, there is a need to look at ways that can augment conventional Vehicular Management Information Systems (VMIS) in transforming business processes through Telematics. This paper aims to contextualise the role that telematics can play in transforming the Insurance Ecosystem in Zimbabwe. The main objective was to investigate the integration of Usage-Based Insurance (UBI) with vehicle tracking solutions provided by technology companies like Econet Wireless in Zimbabwe, aiming to align customer billing with individual risk profiles and enhance the synergy between technology and insurance service providers in the motor insurance ecosystem. A triangulation through structured interviews, questionnaires, and literature review, supported by Information Systems Analysis and Design techniques was conducted. The study adopted a case study approach, qualitatively analyzing the complexities of the Telematics insurance ecosystem in Zimbabwe, informed by the TOGAF framework. A case-study approach was applied to derive themes whilst applying within and cross-case analysis. Data was collected using questionnaires, and interviews. The findings of the research clearly show the importance of Telematics in modern-day insurance and the positive relationship between technology and insurance business performance. The study, therefore revealed how UBI can incentivize positive driver behavior, potentially reducing insurance premiums for safe drivers and lowering the incidence of claims against insurance companies. Future work can be done on studying the role of Telematics in combating highway crime and corruption.

Steering the future:Redefining intelligent transportation systems with foundation models

At the intersection of artificial intelligence and urban development,this paper unveils the pivotal role of Foundation Models(FMs)in revolutionizing Intelligent Transportation Systems(ITS).Against the backdrop of escalating urbanization and environmental concerns,we rigorously assess how FMs-spanning large language models,vision-language models,large multimodal models,etc.-can redefine urban mobility paradigms.Our discussion extends to the potential of modular,scalable models and strategic public-private partnerships in facilitating seamless integration.Through a comprehensive literature review and theoretical framework,this paper underscores the significant role of FMs in steering the future of transportation towards unprecedented levels of intelligence and responsiveness.The insights offered aim to guide policymakers,engineers,and researchers in the ethical and effective adoption of FMs,paving the way for a new era in transportation systems.

Quantum computing in intelligent transportation systems:A survey

Quantum computing,a field utilizing the principles of quantum mechanics,promises great advancements across various industries.This survey paper is focused on the burgeoning intersection of quantum computing and intelligent transportation systems,exploring its potential to transform areas such as traffic optimization,logistics,routing,and autonomous vehicles.By examining current research efforts,challenges,and future directions,this survey aims to provide a comprehensive overview of how quantum computing could affect the future of transportation.

Application of cluster analysis and stepwise regression in predicting the traffic volume of lanes

Because of the difficulty to obtain the traffic flow information of lanes at non-detector intersections in most metropolises of the world,based on the relationships between the lanes of signal-controlled intersections,cluster analysis and stepwise regression are integrated to predict the traffic volume of lanes at non-detector isolated controlled intersections.First cluster analysis is used to cluster the lanes of non-detector isolated signal-controlled intersections and the lanes of all signal-controlled intersections with detectors.Then, by the results of cluster analysis,the traffic volume samples are selected randomly and stepwise regression is used to predict the traffic volume of lanes at non-detector isolated signal-controlled intersections.The method is tested by the traffic volume data of lanes of the road network of Nanjing city.The problem of predicting the traffic volume of lanes at non-detector isolated signal-controlled intersections was resolved and can be widely used in urban traffic flow guidance and urban traffic control in cities without enough intersections equipped with detectors.

A Dynamic Road Incident Information Delivery Strategy to Reduce Urban Traffic Congestion

Advanced information and communication technolo-gies can be used to facilitate traffic incident management.If an incident is detected and blocks a road link,in order to reduce the incident-induced traffic congestion,a dynamic strategy to deliver incident information to selected drivers and help them make detours in urban areas is proposed by this work.Time-dependent shortest path algorithms are used to generate a subnetwork where vehicles should receive such information.A simulation approach based on an extended cell transmission model is used to describe traffic flow in urban networks where path information and traffic flow at downstream road links are well modeled.Simulation results reveal the influences of some major parameters of an incident-induced congestion dissipation process such as the ratio of route-changing vehicles to the total vehicles,operation time interval of the proposed strategy,traffic density in the traffic network,and the scope of the area where traffic incident information is delivered.The results can be used to improve the state of the art in preventing urban road traffic congestion caused by incidents.

On the Connectivity of One-dimensional Vehicular Ad Hoc Networks

In this paper we analyze connectivity of one-dimensional Vehicular Ad Hoc Networks where vehicle gap distribution can be approximat- ed by an exponential distribution. The probabilities of Vehicular Ad Hoc Network connectivity for difference cases are derived. Furthermore we proof that the nodes in a sub-interval [z1, z1 ＋ △z] of interval [0,z],z 〉 0 where all the nodes are independently uniform distributed is a Poisson process and the relationship of Vehicle Ad hoc Networks and one-dimensional Ad Hoc networks where nodes independently uniform distributed in [zl, z1 ＋ △z] is explained. The analysis is validated by computing the probability of network connectivity and comparing it with the Mont Carlo simu- lation results.

Multi-Vehicle Cooperative Positioning Based on Edge-Computed Multidimensional Scaling

As the basis of location-based services(LBS),positioning is one of the most essential parts in intelligent transportation systems(ITS).Although global positioning system(GPS)has been widely used in vehicle positioning,it can not achieve lane level positioning accuracy.Motivated by the mature ranging technologies such as radar and ultra-wideband(UWB),several cooperative positioning(CP)methods have been proposed to enhance the accuracy and robustness of GPS.In this paper,we proposed a twostage CP algorithm that combines multidimensional scaling(MDS)and Procrustes analysis for vehicles with GPS information.Specifically,the optimized MDS based on the scaling by majorizing a complicated function(SMACOF)algorithm is first proposed to get the relative coordinates of vehicles which can tackle measurements of different error distributions,then Procrustes analysis is carried out to transform the relative coordinates of vehicles to their absolute coordinates based on GPS information.All the computations are performed at the mobile edge computing node(MECN)for the request of ultra-reliable and low latency communications(URLLC).Simulation results validate that the proposed algorithm can greatly improve the positioning accuracy and robustness for vehicles.

Intelligent DoS Attack Detection with Congestion Control Technique for VANETs

VehicularAd hoc Network(VANET)has become an integral part of Intelligent Transportation Systems(ITS)in today’s life.VANET is a network that can be heavily scaled up with a number of vehicles and road side units that keep fluctuating in real world.VANET is susceptible to security issues,particularly DoS attacks,owing to maximum unpredictability in location.So,effective identification and the classification of attacks have become the major requirements for secure data transmission in VANET.At the same time,congestion control is also one of the key research problems in VANET which aims at minimizing the time expended on roads and calculating travel time as well as waiting time at intersections,for a traveler.With this motivation,the current research paper presents an intelligent DoS attack detection with Congestion Control(IDoS-CC)technique for VANET.The presented IDoSCC technique involves two-stage processes namely,Teaching and Learning Based Optimization(TLBO)-based Congestion Control(TLBO-CC)and Gated Recurrent Unit(GRU)-based DoS detection(GRU-DoSD).The goal of IDoS-CC technique is to reduce the level of congestion and detect the attacks that exist in the network.TLBO algorithm is also involved in IDoS-CC technique for optimization of the routes taken by vehicles via traffic signals and to minimize the congestion on a particular route instantaneously so as to assure minimal fuel utilization.TLBO is applied to avoid congestion on roadways.Besides,GRU-DoSD model is employed as a classification model to effectively discriminate the compromised and genuine vehicles in the network.The outcomes from a series of simulation analyses highlight the supremacy of the proposed IDoS-CC technique as it reduced the congestion and successfully identified the DoS attacks in network.

Roadroid： Continuous Road Condition Monitoring with Smart Phones

Road condition is an important variable to measure in order to decrease road and vehicle operating/maintenance costs, but also to increase ride comfort and traffic safety. By using the built-in vibration sensor in smart phones, it is possible to collect road roughness data which can be an indicator of road condition up to a level of Class 2 or 3 in a simple and cost efficient way. Since data collection therefore is possible to be done more frequently, one can better monitor roughness changes over time. The continuous data collection can also give early warnings of changes and damage, enable new ways to work in the operational road maintenance management, and can serve as a guide for more accurate surveys for strategic asset management and pavement planning. Collected measurement data are wirelessly transferred by the operator when needed via a web service to an internet mapping server with spatial filtering functions. The measured data can be aggregated in preferred sections, as well as exported to other GlS （geographical information systems） or road management systems. Our conclusion is that measuring roads with smart phones can provide an efficient, scalable, and cost-effective way for road organizations to deliver road condition data.

Hybrid Deep Learning Enabled Air Pollution Monitoring in ITS Environment

Intelligent Transportation Systems(ITS)have become a vital part in improving human lives and modern economy.It aims at enhancing road safety and environmental quality.There is a tremendous increase observed in the number of vehicles in recent years,owing to increasing population.Each vehicle has its own individual emission rate;however,the issue arises when the emission rate crosses a standard value.Owing to the technological advances made in Artificial Intelligence(AI)techniques,it is easy to leverage it to develop prediction approaches so as to monitor and control air pollution.The current research paper presents Oppositional Shark Shell Optimization with Hybrid Deep Learning Model for Air Pollution Monitoring(OSSOHDLAPM)in ITS environment.The proposed OSSO-HDLAPM technique includes a set of sensors embedded in vehicles to measure the level of pollutants.In addition,hybridized Convolution Neural Network with Long Short-Term Memory(HCNN-LSTM)model is used to predict pollutant level based on the data attained earlier by the sensors.In HCNN-LSTM model,the hyperparameters are selected and optimized using OSSO algorithm.In order to validate the performance of the proposed OSSO-HDLAPM technique,a series of experiments was conducted and the obtained results showcase the superior performance of OSSO-HDLAPM technique under different evaluation parameters.