Improving the efficiency of transport systems using simulation

The article describes the possibilities of application of simulation modeling for the analysis of infrastructure and technology of transport services of enterprises. The main technological and possible economic effects for the enterprises arising at performance of modeling of a transport component of their work are resulted.

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.

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.

A Study on Optimizing the Double-Spine Type Flow Path Design for the Overhead Transportation System Using Tabu Search Algorithm

Optimizing Flow Path Design(FPD)is a popular research area in transportation system design,but its application to Overhead Transportation Systems(OTSs)has been limited.This study focuses on optimizing a double-spine flow path design for OTSs with 10 stations by minimizing the total travel distance for both loaded and empty flows.We employ transportation methods,specifically the North-West Corner and Stepping-Stone methods,to determine empty vehicle travel flows.Additionally,the Tabu Search(TS)algorithm is applied to branch the 10 stations into two main layout branches.The results obtained from our proposed method demonstrate a reduction in the objective function value compared to the initial feasible solution.Furthermore,we explore howchanges in the parameters of the TS algorithm affect the optimal result.We validate the feasibility of our approach by comparing it with relevant literature and conducting additional tests on layouts with 20 and 30 stations.

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.

Simulating Transport Capacity, Delivery Speed, and Routing Efficiency to Predict Economic Growth

This study uses a simulation-based approach to investigate the impact of delivery delays due to constraints on transport capacity, transit speed, and routing efficiencies on an economy with various levels of interdependency among firms. The simulation uses object-oriented programming to create specialized production, consumption, and transportation classes. A set of objects from each class is distributed randomly on a 2D plane. A road network is then established between fixed objects using Prim’s MST (Minimum Spanning Tree) algorithm, followed by construction of an all-pair shortest path matrix using the Floyd Warshall algorithm. A genetic algorithm-based vehicle routing problem solver employs the all-pair shortest path matrix to best plan multiple pickup and delivery orders. Production units utilize economic order quantities (EOQ) and reorder points (ROP) to manage inventory levels. Hicksian and Marshallian demand functions are utilized by consumption units to maximize personal utility. The transport capacity, transit speed, routing efficiency, and level of interdependence serve as 4 factors in the simulation, each assigned 3 distinct levels. Federov’s exchange algorithm is used to generate an orthogonal array to reduce the number of combination replays from 34 to just 9. The simulation results of a 9-run orthogonal array on an economy with 6 mining facilities, 12 industries, 8 market centers, and 8 transport hubs show that the level of firm interdependence, followed by transit speed, has the most significant impact on economic productivity. The principal component analysis (PCA) indicates that interdependence and transit speed can explain 90.27% of the variance in the data. According to the findings of this research, a dependable and efficient regional transportation network among various types of industries is critical for regional economic development.

Combining Geographic Information Systems for Transportation and Mixed Integer Linear Programming in Facility Location-Allocation Problems

In this study, we aimed to assess the solution quality for location-allocation problems from facilities generated by the software TransCAD®?, a Geographic Information System for Transportation (GIS-T). Such facilities were obtained after using two routines together: Facility Location and Transportation Problem, when compared with optimal solutions from exact mathematical models, based on Mixed Integer Linear Programming (MILP), developed externally for the GIS. The models were applied to three simulations: the first one proposes opening factories and customer allocation in the state of Sao Paulo, Brazil;the second involves a wholesaler and a study of location and allocation of distribution centres for retail customers;and the third one involves the location of day-care centers and allocation of demand (0 - 3 years old children). The results showed that when considering facility capacity, the MILP optimising model presents results up to 37% better than the GIS and proposes different locations to open new facilities.

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.

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.

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.

How Do V2V and V2I Messages Affect the Performance of Driving Smart Vehicles?

Intelligent transportation systems(ITSs)are becoming increasingly popular as they support efficient coordinated transport.ITSs aim to improve the safety,efficiency and reliability of road transportation through integrated approaches to the exchange of relevant information.Mobile adhoc networks(MANETs)and vehicle ad-hoc networks(VANETs)are integral components of ITS.The VANET is composed of interconnected vehicles with sensitivity capabilities to exchange traffic,positioning,weather and emergency information.One of the main challenges in VANET is the reliable and timely dissemination of information between vehicular nodes to improve decision-making processes.This paper illustrates challenges in VANET and reviews possible solutions to improve road safety control and management using V2V and V2I communications.This paper also summarizes existing rules-based and optimized-based solutions,including reducing the effect of mixed environments,obstacles,malfunctions and short wireless ranges on transportation efficiency and reducing false messages that cause unintended vehicle actions and unreliable transportation systems.Additionally,an event simulation algorithm was designed to maximize the benefits of exchangeable messages among vehicles.Furthermore,simulated VANET environments were developed to demonstrate how the algorithm can be used for transformable messages.Experimental results show that coupling of both V2V and V2I messages yielded better results in terms of end-to-end delay and average time.Future research directions were highlighted to be taken into account in the development of ITS and intelligent routing mechanisms.

Parameter Tuned Deep Learning Based Traffic Critical Prediction Model on Remote Sensing Imaging

Remote sensing(RS)presents laser scanning measurements,aerial photos,and high-resolution satellite images,which are utilized for extracting a range of traffic-related and road-related features.RS has a weakness,such as traffic fluctuations on small time scales that could distort the accuracy of predicted road and traffic features.This article introduces an Optimal Deep Learning for Traffic Critical Prediction Model on High-Resolution Remote Sensing Images(ODLTCP-HRRSI)to resolve these issues.The presented ODLTCP-HRRSI technique majorly aims to forecast the critical traffic in smart cities.To attain this,the presented ODLTCP-HRRSI model performs two major processes.At the initial stage,the ODLTCP-HRRSI technique employs a convolutional neural network with an auto-encoder(CNN-AE)model for productive and accurate traffic flow.Next,the hyperparameter adjustment of the CNN-AE model is performed via the Bayesian adaptive direct search optimization(BADSO)algorithm.The experimental outcomes demonstrate the enhanced performance of the ODLTCP-HRRSI technique over recent approaches with maximum accuracy of 98.23%.

A Nonlinear Spatiotemporal Optimization Method of Hypergraph Convolution Networks for Traffic Prediction

Traffic prediction is a necessary function in intelligent transporta-tion systems to alleviate traffic congestion.Graph learning methods mainly focus on the spatiotemporal dimension,but ignore the nonlinear movement of traffic prediction and the high-order relationships among various kinds of road segments.There exist two issues:1)deep integration of the spatiotempo-ral information and 2)global spatial dependencies for structural properties.To address these issues,we propose a nonlinear spatiotemporal optimization method,which introduces hypergraph convolution networks(HGCN).The method utilizes the higher-order spatial features of the road network captured by HGCN,and dynamically integrates them with the historical data to weigh the influence of spatiotemporal dependencies.On this basis,an extended Kalman filter is used to improve the accuracy of traffic prediction.In this study,a set of experiments were conducted on the real-world dataset in Chengdu,China.The result showed that the proposed method is feasible and accurate by two different time steps.Especially at the 15-minute time step,compared with the second-best method,the proposed method achieved 3.0%,11.7%,and 9.0%improvements in RMSE,MAE,and MAPE,respectively.