Real-time Traffic Management Systems Research Articles

Short-term Traffic Flow Prediction Based on KELM Optimized By Improved Slime Mould Algorithm

Traffic flow prediction plays a crucial role in improving transportation efficiency and enhancing Intelligent Transportation Systems (ITS). However, the temporal, spatial, and nonlinear nature of traffic flow data presents challenges for accurate short-term prediction. We propose a short-term traffic flow prediction model based on Kernel Extreme Learning Machine (KELM) optimized by the improved Slime Mould Algorithm (SMA). KELM is an improved version of Extreme Learning Machine (ELM) that incorporates kernel functions for improved generalization and stability. SMA is a meta-heuristic algorithm inspired by the behavior of slime mould in foraging, known for its strong global searching ability. For better performance, three strategies are introduced: the Good Point Set method for optimizing the initial population, the combination of Opposition Based Learning (OBL) and Differential Evolution (DE) to improve the slime mould generation mechanism, and the use of adaptive t distribution mutation to enhance convergence speed. After comparing the performance of these improved SMAs on twelve test functions, the ISMA improved by integrating three strategies as mentioned above is best. Then the ISMA is applied to search for the optimal parameters of KELM model. Finally, the optimized KELM with optimal parameters is applied to predict the short-term traffic flow on given traffic data set. Experimental results demonstrate that the proposed model, KELM optimized by ISMA namely ISMA-KELM, outperforms existing models such as Random Forest (RF), Least Squares Support Vector Machine (LSSVM), KELM optimized by Tuna Swarm Optimization Algorithm (TSO-KELM), and KELM optimized by SMA (SMA-KELM) in terms of traffic flow prediction accuracy. The proposed model ISMA-KELM provides a promising approach for addressing the challenges of traffic flow prediction, offering improved accuracy and efficiency in real-time traffic management systems.

Using Machine Learning to Predict Pedestrian Compliance at Crosswalks in Jordan

This study employs machine learning (ML) techniques to predict pedestrian compliance at crosswalks in urban settings in Jordan, aiming to enhance pedestrian safety and traffic management. Utilizing data from 2437 pedestrians at signalized intersections in Amman, Irbid, and Zarqa, four models based on different ML algorithms were developed: an artificial neural network (ANN), a support vector machine (SVM), a decision tree (ID3), and a random forest (RF). The results have shown that local infrastructure and traffic conditions influence pedestrian behavior. The RF model, with its excellent accuracy and precision, has proven to be an excellent choice for accurately predicting pedestrian behavior. This research provides valuable insights into the demographic and spatial aspects that influence pedestrian compliance with laws and regulations in the local environment. Additionally, this work highlights the ability of ML algorithms to improve urban traffic dynamics. Policymakers and urban planners, particularly with the rise of theories and trends toward the humanization of urban roads, should firmly establish this understanding among themselves to create environments that make pedestrians safer. This strategy could be a measurable solution for international urban situations if future research focuses on integrating these prediction models with real-time traffic management systems to improve pedestrian safety dynamically.

Wrong Way Vehicle Detection in Single and Double Lane

Wrong-way driving is one of the primary causes of traffic jams and accidents globally. It is possible to identify vehicles going the wrong direction, which lessens accidents and traffic congestion. Surveillance footage has become an important source of data due to the accessibility of less priced cameras and the expanding use of real-time traffic management systems. In this paper, we propose a technique for automatically identifying automobiles moving against traffic. Our system uses the You Only Look Once (CNN) algorithm to recognize and track vehicles from video inputs and the centroid tracking method to determine each vehicle's orientation inside a given region of interest (ROI) in order to identify vehicles traveling in the wrong direction. It functions in three steps. The Deep sort tracking method is particularly good in detecting and tracking objects, and the centroid tracking technique can effectively monitor the direction of travel. Experiments with a variety of traffic films show that the suggested method can detect and identify wrong-way moving vehicles in a variety of lighting and weather scenarios. The interface of the system is quite simple and easy to use.

Combinative distance-based assessment method for decision-making with $ 2 $-tuple linguistic $ q $-rung picture fuzzy sets

<abstract><p>Multi-criteria group decision-making (MCGDM) approaches have a substantial effect on decision-making in a range of critical sectors, including science, business, and real-life research. These strategies also efficiently assist researchers in resolving challenges that may arise throughout their study activity. The current work's major purpose is to research and develop the combinative distance-based assessment (CODAS) approach by employing $ 2 $-tuple linguistic $ q $-rung picture fuzzy sets ($ 2 $TL$ q $-RPFSs) as a background. The CODAS technique computes the distances from the negative ideal solutions and ranks the alternatives in increasing order. To compute the normal weights of attributes, the entropy weighting information process is used. Furthermore, two aggregation operators, namely the $ 2 $-tuple linguistic $ q $-rung picture fuzzy Einstein weighted average and the $ 2 $-tuple linguistic $ q $-rung picture fuzzy Einstein order weighted average, are introduced. Our inspiration for employing the notion of $ 2 $TL$ q $-RPFSs is the ability of $ q $-RPFSs to support a wide range of information and the significant qualities of $ 2 $-tuple linguistic term sets to handle qualitative data. Congested transportation networks may be made more efficient by leveraging digital transformation. Real-time traffic management is one solution to the problem of road congestion. As a result of connected autonomous vehicle (CAV) advances, the benefits of real-time traffic management systems have grown dramatically. CAVs can help manage traffic by acting as enforcers. To complement the extended approach, the proposed technique is used to select the best alternative for a real-time traffic management system. The performance of the suggested technique is validated using scenario analysis. The results show that the suggested strategy is efficient and relevant to real-world situations.</p></abstract>

Analysis of Automobile Wheel Counting using Novel adaboosting Algorithm with Accuracy Compared to Logistic Regression Algorithm

Aim: In order to determine the accuracy of a realtime traffic management system, this work compares novel adaboosting and logistic regression methods to forecast the AutoMobile Wheel Movement Counting. Materials and Methods: The dataset utilized in this article contains 12 columns or attributes and a total of 10,684 rows. The columns in the dataset are named Car Wheels, Bicycle Wheels, Motorcycle Wheels, and Truck Wheels. The data source link provided a sample size of 1,340 records. A Novel adaboosting algorithm (N=20) and Logistic regression (N=20) iterations are simulated by various parameters and automate vehicle monitoring systems to optimize the pH. The 40 iterations were calculated using CilnCal with G power 80% and CI of 95%. Results: Based on obtained results Novel adaboosting Algorithm has significantly better accuracy (84.71%) compared to Logistic regression Algorithm accuracy (80.60%). Statistical significance difference between Novel adaboosting and Logistic regression algorithm was found to be p=0.013 (Independent Sample T Test p<0.05). Conclusion: Novel adaboosting algorithms provide better results in Finding Road Traffic counting than Logistic regression algorithms.

A novel rough numbers based extended MACBETH method for the prioritization of the connected autonomous vehicles in real-time traffic management

Digital transformation can help to make better use of existing transportation networks that are congested. One solution to the road congestion problem is real-time traffic management, which focuses on enhancing traffic flow conditions. The advantages of real-time traffic management systems have developed significantly as a result of connected autonomous vehicle (CAV) innovations. CAVs can act as enforcers for managing the traffic. This study aims to propose a novel rough numbers-based extended Measuring Attractiveness by a Categorical Based Evaluation Technique (MACBETH) method for prioritizing real-time traffic management systems. Furthermore, a new approach for defining rough numbers is proposed, based on an improved methodology for defining rough numbers' lower and upper limits. This allows consideration of mutual relations between a set of objects and flexible representation of rough boundary interval depending on the dynamic environmental conditions. In this study, three main alternatives are defined for real-time traffic management systems: real-time traffic management, real-time traffic management integrated with CAVs, and real-time traffic management by using CAVs. For these alternatives, 5 main criteria and 18 sub-criteria are defined and then prioritized using the fuzzy multi-criteria decision-making (MCDM) approach. The proposed method's performance is validated through scenario analysis. The findings demonstrate that the proposed method is effective and applicable to real-world conditions. According to the study's findings, real-time traffic management with CAVs is the most advantageous alternative, while real-time traffic management integrated with CAVs is the least advantageous

Data-driven models for train control dynamics in high-speed railways: LAG-LSTM for train trajectory prediction

The construction of an accurate train control model (TCM) is crucial to the design of automatic train operation and real-time traffic management systems in high-speed railways. Traditional physical-driven models usually fail to reflect the “true” dynamics of high-speed trains (HSTs) because of the strong nonlinearity and uncertainty due to air resistance, frequently switching working conditions, and variations in external influencing factors such as weather and temperature. Although some data-driven deep learning models have recently been proposed for environmental adaptation, they are all “black-box” models, which cannot explain how the input of the models affects the HST output. To overcome these issues, this study constructs a novel long short-term memory with lagged information (LAG-LSTM) model by combining the physical-driven HST model and an “interpretable” deep learning model. Specifically, our LAG-LSTM model contains three modules: a time-delay variable module to model the transform delay of control variables, state variable enhancement module to extract the key features among high-dimensional input data, and Pre-LSTM module to predict the future train trajectory with given control variables. We collected field data from the Beijing-Shanghai high-speed railway and developed a data filter method and a normalization procedure to overcome the positioning errors of HSTs and construct a standard data set. Finally, we tested the effectiveness of our LAG-LSTM by comparing it with six deep learning structures, including fully connected neural network, recursive neural network, standard LSTM, and LSTM with convolutional layers. The results show that LAG-LSTM can accurately predict the trajectories of HSTs and outperforms other deep learning models. Regarding prediction accuracy, LAG-LSTM improved the performance of the traditional LSTM by 13.5% to 23.3%.

Real-Time Traffic Controlling System Using Multi-Agent Technology

With the development, almost all the sectors, countries tend to grow adapting to latest technologies. The transport sector also has a huge impact on this development sphere. When it comes to traffic, it is a huge problem in the world. In Sri Lanka traffic is a problem that exists for a long period. Annually there is a loss of Rs. 400 billion due to traffic congestions. Over the past years various solutions have been proposed using different methods for traffic control. These solutions are based on different trending technologies such as machine learning, image processing, fuzzy logic and the Internet of Things. However, those systems are not able to handle traffic congestions problems in complex environments. Therefore, a real-time traffic controlling system with the ability to handle traffic congestions in dynamic environment is highly valued. This study aims to design and build a real-time traffic management system using Multi Agent technology. Simulations for both existing system and Agent-Based system are implemented using NetLogo simulation tool and compared for various traffic situations. According to the results obtained from the two simulations, Agent-Based systems provide more accuracy and efficiency than the existing fixed scheduling systems.

Fuzzy Power Heronian function based CoCoSo method for the advantage prioritization of autonomous vehicles in real-time traffic management

One of the key solutions to resolving the traffic congestion problem is the traffic management systems, aiming to increase the efficiency of the road networks so that the traffic flow condition on the road segment is improved. Integration of the advancements in communication and autonomous vehicle technologies might increase the benefits of the existing real-time traffic management systems. Hence, in this study, the advantages of six different real-time traffic management methods, which are dynamic speed limits, lane control systems, variable message signs, ramp metering, traffic diversion, and integrating autonomous vehicles into other traffic management systems, with four main criteria, namely economic, public and political, environmental, and traffic safety, and 13 sub-criteria using fuzzy multi-criteria decision making (MCDM) are prioritized. For this purpose, we propose novel extensions of the combined compromise solution (CoCoSo) methodology, including the logarithmic method and the Power Heronian function. The validation of the results is presented to verify the flexibility of the proposed methodology. Finally, these results of the effect of parameters p and q on decision outcome show that the ranking results were not influenced.

Privacy-Preserving Traffic Management: A Blockchain and Zero-Knowledge Proof Inspired Approach

Incorporation of connected vehicle (CV) data into real-time traffic management systems presents a host of new challenges resulting from the current lack of data integrity and data privacy in traffic networks. Over the past few years, blockchain technologies have been inspiring extensive innovations in the transportation field. However, due to the transparency property, sensitive data stored on the blockchain would be accessible to anyone, resulting in a lack of privacy. In this paper, we propose a decentralized and location-aware architecture to address the data integrity along with the privacy-preserving issues in blockchain-based traffic management systems. Our proposed architecture integrates with permissioned and modular blockchain network and non-interactive zero-knowledge range proof (ZKRP) protocol. We develop the prototype system on the Hyperledger Fabric platform and Hyperledger Ursa cryptographic library. The performance results show that our approach is effective and feasible for real-time traffic management while preserving the data privacy requirements.

Modeling Ant Colony Optimization for Multi-Agent based Intelligent Transportation System

This paper focuses on Sumo Urban Mobility Simulation (SUMO) and real-time Traffic Management System (TMS) simulation for evaluation, management, and design of Intelligent Transportation Systems (ITS). Such simulations are expected to offer the prediction and on-the-fly feedback for better decision-making. In these regards, a new Intelligent Traffic Management System (ITMS) was proposed and implemented - where a path from source to destination was selected by Dijkstra algorithm, and the road segment weights were calculated using real-time analyses (Deep-Neuro-Fuzzy framework) of data collected from infrastructure systems, mobile, distributed technologies, and socially-build systems. We aim to simulate the ITMS in pragmatic style with micro traffic, open-source traffic simulation model (SUMO), and discuss the challenges related to modeling and simulation for ITMS. Also, we expose a new model- Ant Colony Optimization (ACO) in SUMO tool to support a multi-agent-based collaborative decision-making environment for ITMS. Beside we evaluate ACO model performance with exiting built-in optimum route-finding SUMO models (Contraction Hierarchies Wrapper) -CHWrapper, A-star (A*), and Dijkstra) for optimum route choice. The results highlight that ACO performs better than other algorithms.

Real-Time Traffic Network State Prediction for Proactive Traffic Management

Real-time traffic management systems with integrated proactive decision support capabilities are expected to operate with ( a) limited prediction accuracy ( b) decision-making latency, and ( c) partial coverage of the managed area. Such deficiencies are difficult to avoid in most real-world traffic network management applications, and there is a need to quantify the effect of these deficiencies on the performance of traffic network management systems. This paper studies the effectiveness of a proactive traffic management system. Various levels of prediction accuracy of the traffic network state, decision-making latency, and partial area coverage are considered. A traffic management system that emulates real-time operations is developed. The system adopts a closed-loop rolling horizon framework, which integrates network state estimation and prediction modules as well as decision support capabilities. A set of simulation experiments considers a hypothetical highway network. The results show that the effectiveness of the traffic management system can be affected by the deficiencies. However, the impact could be smaller if these deficiencies are kept under certain levels.

Train Rescheduling With Stochastic Recovery Time: A New Track-Backup Approach

Train rescheduling is an important decision process in railway management. It aims to minimize the negative effects arising from the disturbances via real-time traffic management. Two main challenges are how to formulate the dynamic and complex rescheduling problem as an optimization model, and how to obtain a good solution within a short time limit. Focusing on the stochastic capacity recovery times of blocked tracks, we propose a new track-backup rescheduling (TBR) approach which optimally assigns each affected train a backup track, based on the estimation of recovery time, the original timetable, and track changing cost. Then, we formulate a mixed integer programming (MIP) model to obtain a conflict-free timetable which minimizes the delay cost and the expected track changing cost. A greedy algorithm is designed to reorder trains and reschedule the arrival and departure times, and then we use an MIP algorithm to solve the optimal track backup strategy. Based on the Beijing-Shanghai high-speed railway line, we conduct extensive experimental studies which show that the TBR approach can reduce the rescheduling cost by an average of 10.17% compared with traditional approaches. More important, the greedy-based algorithm is shown to be able to obtain good solutions (with an average error of only 2.85%) within 1.5 s, which implies the high potential of our approach in a real-time traffic management system where fast response is critical.

Real Time Traffic Models, Decision Support for Traffic Management

Reliable and accurate short-term traffic state prediction can improve the performance of real-time traffic management systems significantly. Using this short-time prediction based on current measurements delivered by advanced surveillance systems will support decision-making processes on various control strategies and enhance the performance of the overall network. By taking proactive action deploying traffic management measures, congestion may be prevented or its effects limited. An approach of short-term traffic state prediction is presented and implemented in a real life case for the city of Assen in the Netherlands. This prediction is based on connecting online traffic measurements with a real time traffic model using the macroscopic dynamic traffic assignment model StreamLine in a rolling horizon implementation. Different monitoring data sources consisting of both fixed-point and floating car data are used. The advantage of the rolling horizon approach is that no warming-up period is needed for the dynamic traffic assignment taking less computation time while keeping results consistent. Further, the current traffic state estimation is done by combining model estimates of previous predictions and current measurements. The results of predictions made in the real life case are presented as well as several tested methods for improving the current state estimations showing promising results.

K 최대근접이웃 방법을 이용한 통행시간 예측에 대한 연구

Travel-time is considered the most typical and preferred traffic information for intelligent transportation systems(ITS). This paper proposes a real-time travel-time prediction method for a national highway. In this paper, the K-nearest neighbor(KNN) method is used for travel time prediction. The KNN method (a nonparametric method) is appropriate for a real-time traffic management system because the method needs no additional assumptions or parameter calibration. The performances of various models are compared based on mean absolute percentage error(MAPE) and coefficient of variation(CV). In real application, the analysis of real traffic data collected from Korean national highways indicates that the proposed model outperforms other prediction models such as the historical average model and the Kalman filter model. It is expected to improve travel-time reliability by flexibly using travel-time from the proposed model with travel-time from the interval detectors.

A tabu search algorithm for rerouting trains during rail operations

This paper addresses the problem of train conflict detection and resolution, which is dealt every day by traffic controllers to adapt the timetable to delays and other unpredictable events occurring in real-time. We describe a number of algorithmic improvements implemented in the real-time traffic management system ROMA (Railway traffic Optimization by Means of Alternative graphs), achieved by incorporating effective rescheduling algorithms and local rerouting strategies in a tabu search scheme. We alternate a fast heuristic and a truncated branch and bound algorithm for computing train schedules within a short computation time, and investigate the effectiveness of using different neighborhood structures for train rerouting. The computational experiments are based on practical size instances from a dispatching area of the Dutch railway network and include complex disturbances with multiple late trains and blocked tracks. Several small instances are solved to optimality in order to compare the heuristic solutions with the optimum. For small instances, the new tabu search algorithms find optimal solutions. For large instances, the solutions generated by the new algorithms after 20 s of computation are up to more than 15% better than those achieved within 180 s by the previous version of ROMA.

Reordering and Local Rerouting Strategies to Manage Train Traffic in Real Time

Traffic controllers regulate railway traffic by sequencing train movements and setting routes with the aim of ensuring smooth train behaviour and limiting, as much as possible, train delays. In this paper, we describe the implementation of a real-time traffic management system, called ROMA (Railway traffic Optimization by Means of Alternative graphs), to support controllers in the everyday task of managing disturbances. We make use of a branch-and-bound algorithm for sequencing train movements, while a local search algorithm is developed for rerouting optimization purposes. The compound problem of routing and sequencing trains is approached iteratively, computing an optimal train sequencing for given train routes and then improving this solution by locally rerouting some trains. An extensive computational study is carried out, based on a dispatching area of the Dutch railway network. We study practical size instances, and include in the model important operational constraints, including rolling stock and passenger connections. Different types of disturbances are analysed, including train delays and blocked tracks. Comparison with common dispatching practice shows the high potential of the system as an effective support tool to improve punctuality.

Identification and Correction of Dual-Loop Sensitivity Problems

Freeway traffic speed and bin volumes for different vehicle categories are typically collected by dual-loop detectors. Good quality dual-loop detector data are crucial for effective real-time traffic management systems and traveler information systems. However, loop detectors are subject to various malfunctions that can result in erroneous measurements. Previous studies indicated that loop sensitivity-level discrepancies between two single loops forming a dual-loop detector and unsuitable sensitivity levels of the single loops are two major causes of quality degradation in dual-loop data. This paper presents an algorithm and its implementation for identifying and correcting such loop sensitivity problems. The algorithm identifies dual-loop sensitivity problems using individual vehicle data extracted from loop event data and corrects dual-loop sensitivities through a two-step procedure: (a) remove the sensitivity discrepancy between the two single loops and (b) adjust their sensitivities to the appropriate level. Elimination of dual-loop sensitivity problems significantly enhances the reliability of dual-loop detectors and improves the quality of traffic speed and bin volume data.

Identification and Correction of Dual-Loop Sensitivity Problems

Freeway traffic speed and bin volumes for different vehicle categories are typically collected by dual-loop detectors. Good quality dual-loop detector data are crucial for effective real-time traffic management systems and traveler information systems. However, loop detectors are subject to various malfunctions that can result in erroneous measurements. Previous studies indicated that loop sensitivity-level discrepancies between two single loops forming a dual-loop detector and unsuitable sensitivity levels of the single loops are two major causes of quality degradation in dual-loop data. This paper presents an algorithm and its implementation for identifying and correcting such loop sensitivity problems. The algorithm identifies dual-loop sensitivity problems using individual vehicle data extracted from loop event data and corrects dual-loop sensitivities through a two-step procedure: (a) remove the sensitivity discrepancy between the two single loops and (b) adjust their sensitivities to the appropriate...

An Heuristic Algorithm for Dynamic Network Loading

This paper describes an heuristic procedure for the problem of determining the time evolution of traffic flows and routes on a road net work with the key requirement that its computational costs must be appealing so as to include it as part of a real time Traffic Management System.