首页期刊导航|International journal of intelligent transportation systems research
期刊信息/Journal information
International journal of intelligent transportation systems research
Springer
International journal of intelligent transportation systems research

Springer

年3期

1348-8503

International journal of intelligent transportation systems research/Journal International journal of intelligent transportation systems research
正式出版
收录年代

    Clustering Approach to Identifying and Analyzing the Traffic Conditions: A Novel Hybrid Cloud Density and Fuzzy Clustering Algorithm

    Mahdi Banihosseini1Vahid Baradaran1Mohammad Hadi Doroudyan
    1-15页
    查看更多>>摘要：Traffic flow analysis and management are among the most effective ways to improving traffic and mitigating its unfortunate consequences. In the field of traffic engineering, traffic and its various aspects are defined by analyzing variables such as quantity, velocity, and density. This article addresses the challenge of appropriately dealing with the uncertainty of traffic variables and converting traffic data into understandable verbal expressions for drivers and urban planners. The study utilizes a clustering approach to analyzing traffic variables and determining the traffic condition. A new fuzzy clustering method has been developed to enhance the performance of clustering methods, which is then used to detect abnormal traffic conditions on a route based on the value of traffic variables. The algorithm and proposed method have been evaluated on the traffic dataset of a high-traffic route in Tehran, the capital of Iran. The implementation results demonstrate the traffic conditions on the selected route can be shown in six clusters or states.
      原文链接:
    • NETL
    • NSTL
    • Springer Nature

    Mathematical Model to Evaluate the Impact of Power Supply Constraint for Electric Vehicles on Transportation Network

    Yuki NakajimaHiroshi Shimamoto
    16-28页
    查看更多>>摘要：This paper proposes the UE-based mathematical model to evaluate driver's choice of vehicle types and paths, explicitly considering the supply power constraint in addition to the charging station capacity constraints. Because the flows of EVs in the proposed model are represented in a path-based manner, we apply a column generation-based algorithm to avoid enumerating all of the possible paths. The contributions of this study are that 1) we consider both pre-trip charging and charging during a trip, and that 2) we focus on the difference in the impact of power supply constraints on vehicles that need to charge during a trip and those that do not. The proposed model is applied to a hypothetical network. As a result, we confirmed that 1) while the share of EVs in the middle distance tends to be higher, the share of EVs in the short and long distances tends to be lower, and that 2) in case of inadequate power supply, the share of EVs in the short and middle distances decreases significantly, whereas the share of EVs remains almost unchanged in long OD.
      原文链接:
    • NETL
    • NSTL
    • Springer Nature

    Designing and Developing a Model for Detecting Unusual Condition in Urban Street Network

    Mani HazeghiMahmoud SaffarzadehBabak Mirbaha
    29-46页
    查看更多>>摘要：This study introduces a novel model aimed at identifying traffic congestion, accidents, and other irregularities within transportation networks by leveraging a combination of unsupervised machine learning techniques and statistical models applied to speed time series data. The detection of congestion and accidents is a critical aspect of traffic management, yet previous research has seldom focused solely on speed data. This investigation utilizes mobile data sourced from the Neshan application, which operates on the Global Navigation Satellite System (GNSS) and provides 10-min averaged speed metrics. Additionally, data regarding accidents and congestion from the Mashhad traffic control center has been employed to assess and validate the performance of the trained models. The findings of this research yield two distinct methodologies for dissimilarity detection: one that utilizes time series clustering and deviation distribution-based techniques to identify various patterns, and another that employs outlier detection methods, including density-based clustering and predictive confidence bounds, to uncover anomalies. The ensemble model developed demonstrates commendable performance, achieving an accuracy exceeding 80 percent and a robust anomaly detection rate based on the 10-min averaged speed time series. Consequently, the proposed model holds significant potential for the development of real-time anomaly detection applications within urban transportation systems in the future.
      原文链接:
    • NETL
    • NSTL
    • Springer Nature

    Multi Path Real-time Semantic Segmentation Network in Road Scenarios

    Gao PengfeiTian XiaolongLiu CuihongYang Chenfei...
    47-60页
    查看更多>>摘要：Semantic segmentation is a critical task in computer vision. Existing methods often struggle to balance accuracy and computational efficiency when processing high-resolution images, limiting their application scenarios. To address these limitations, we introduce RepMPSeg, a novel re-parameterization-based multi-path real-time semantic segmentation network. RepMPSeg improves upon traditional dual-branch architectures. It features two independent yet interconnected branches: a high-resolution branch for detailed feature capture and a low-resolution branch for global semantic information extraction. By employing re-parameterization techniques, the basic convolutional blocks are optimized to enhance feature capture and local context information. During training, parallel convolution structures are utilized, which are then streamlined into a single kernel during inference to maintain performance while reducing computational complexity. The high-resolution branch leverages sub-pixel sampling and 1×1 convolutions to improve the receptive field and minimize computational load, while the low-resolution branch uses 4× downsampling to enhance semantic information extraction. Features from both branches are fused through the re-parameterization-based Hybrid Downsampling Module (RepHDM), which aligns and combines features effectively. Our experiments on the Cityscapes and CamVid datasets demonstrate that RepMPSeg achieves a balance between speed and accuracy, outperforming state-of-the-art methods. Specifically, RepMPSeg achieves an mIoU of 77.4 and an FPS of 91.4 on the Cityscapes dataset, and an mIoU of 78.6 and an FPS of 117.33 on the CamVid dataset, making it a highly efficient solution for real-time semantic segmentation in road scenarios.
      原文链接:
    • NETL
    • NSTL
    • Springer Nature

    A LIDAR-based Traffic Data Classification Framework for Indian Urban Traffic

    Prajwal Shettigar JArun K TangiralaLelitha Devi Vanajakshi
    61-75页
    查看更多>>摘要：With recent advances in autonomous vehicles and traffic monitoring systems, the use of light detection and ranging (LIDAR) is becoming more popular. One of the essential components of these systems is a LIDAR point-cloud classifier. This work introduces a generalized classification framework based on traditional 3D point cloud processing algorithms, together with a classification model with interpretable inputs. The framework consists of three stages, wherein the first two stages involve the development of input features of the classification model through preprocessing and feature generation algorithms. In the final stage, the multiclass machine learning (ML) model predicts the vehicle class. The study also presents the refining of data from off-line techniques to improve the performance of the ML model. The framework is validated using real-world LIDAR data that represent heterogeneous laneless traffic. A comparison of a range of point-cloud ground segmentation and clustering algorithms is conducted on this data set, and it is shown that density-based spatial clustering of applications with noise (DBSCAN) and ground segmentation by m-estimator sample consensus (MSAC) give the best clustering output. Seven features representing the dimension, distribution, and density of the clusters were extracted using bounding-box fitting and line-fitting algorithms. After training with various classification models using these features, the adaptive boosting algorithm (AdaBoost) was determined to have the highest accuracy (0.922 F1 score) for five output classes. Furthermore, it is demonstrated that this accuracy can be enhanced by data-refining techniques such as skewness reduction and region-ofinterest boundary selection. The final model obtained has an accuracy of 98.4% (0.969 F1 score). The results show that the framework is well-suited for applications that employ multiclass classifiers for heterogeneous and laneless traffic.
      原文链接:
    • NETL
    • NSTL
    • Springer Nature

    Sustainable Smart Parking Site Selection with Charging Stations for Electric and Hybrid Vehicles

    Onur Derse
    76-90页
    查看更多>>摘要：In this study, in order to solve the parking problem in metropolitan cities, save time and fuel, and reduce the damage to the environment, research is conducted on the problem of smart parking site selection integrated with the charging stations of electric vehicles and hybrid vehicles. Considering the Marmara region, the most populated region of Turkey, the population, number of vehicles, the potential of renewable energy sources, and air quality index value are evaluated. The Entropy method is used to weight the evaluation criteria, and the TOPSIS method is used to rank the alternative provinces in the Marmara Region. According to the results of the MCDM methods, when the provinces are examined, it is seen that the city of Istanbul needs smart parking systems the most. When areas of Istanbul are evaluated with different scenarios and the results are examined, different results are obtained according to the results of the Center of Gravity method, while deciding to establish a smart parking lot in the Esenyurt region in all mathematical programming model results. The research, which is integrated with sustainability (use of renewable energy), environmental awareness (air quality index and use of renewable energy), and developing technology (electric vehicles and hybrid vehicles), reveals effective results. It is thought that the study will adapt to developing technology and smart transportation systems and will be effective and contribute to the decision of location selection of smart parking systems and integrated electric charging stations for the increasing number of electric vehicles.
      原文链接:
    • NETL
    • NSTL
    • Springer Nature

    A Traffic Anomaly Detection Method Using Traffic Flow Vectors During Heavy Rainfall

    Kensuke HirataYosuke KawasakiTakahiro Yoshida
    91-103页
    查看更多>>摘要：In torrential rain disasters, affected areas are identified through reporting and patrolling; however, traffic monitoring remains a challenge. This study establishes a traffic anomaly detection method during heavy rain disasters. Using probe trajectory data collected during such events, the proposed method captures traffic flow characteristics using directional vectors of road inflow and outflow. The effectiveness of the proposed method was evaluated through comparisons with previously proposed methods. The results confirmed that compared with existing methods, the proposed method could more accurately detect traffic anomalies, such as U-turns and detours, and can be used to detect other traffic anomalies. Moreover, the proposed model necessitates minimal calibration effort because it requires only two parameters—time step and rate of change. The proposed method can detect various traffic anomalies that occur during a heavy rain disaster and will contribute to the early restoration of damaged areas by providing a detailed understanding of the damage situation.
      原文链接:
    • NETL
    • NSTL
    • Springer Nature

    Predicting the Duration of Traffic Incidents for Sydney Greater Metropolitan Area using Machine Learning Methods

    Artur GrigorevSajjad ShafieiHanna GrzybowskaAdriana-Simona Mihaita...
    104-125页
    查看更多>>摘要：This research presents a comprehensive machine learning approach to predicting the duration of traffic incidents, classifying them as short-term or long-term, and understanding what are the factors that affect the duration the most. Our modelling methodology is using a dataset from the Sydney Metropolitan Area that includes detailed records of traffic incidents, road network characteristics, and socio-economic indicators, we train and evaluate a variety of advanced machine learning models including Gradient Boosted Decision Trees (GBDT), Random Forest, LightGBM, and XGBoost. The models are assessed using Root Mean Square Error (RMSE) for regression tasks and F1 score for classification tasks. Our experimental results demonstrate that XGBoost and LightGBM outperform conventional models with XGBoost achieving the lowest RMSE of 33.7 for predicting incident duration and highest classification F1 score of 0.62 for a 30-minute duration threshold. For classification, the 30-minute threshold balances performance with 70.84% short-term duration classification accuracy and 62.72% long-term duration classification accuracy. Feature importance analysis, employing both tree split counts and SHAP values, identifies the number of affected lanes, traffic volume, and types of primary and secondary vehicles as the most influential features. The proposed methodology not only achieves high predictive accuracy but also provides stakeholders with vital insights into local area factors contributing to incident durations. These insights enable more informed decisionmaking for trafficmanagement and response strategies.
      原文链接:
    • NETL
    • NSTL
    • Springer Nature

    Driving towards Sustainability: Understanding Drivers and Barriers in Adoption of Green Mobility

    Rakesh JhaMukesh Kumar Singh
    126-145页
    查看更多>>摘要：Moving towards sustainable transportation is essential in mitigating environmental effects and achieving worldwide sustainability targets. Explore the impact of green mobility and sustainable transportation. This study investigates how the barriers (institutional, infrastructure, financial, and social) and drivers (Perceived benefits, technology benefits, environmental concerns, and government policies) impact green mobility among stakeholders in Jharkhand, India, highlighting a significant gap in understanding how these factors affect adoption in developing urban areas. Using a sample size of 334 participants, selected through convenience sampling, data was collected via an online questionnaire distributed through Google Forms. The study utilizes Partial Least Squares Structural Equation Modeling (PLS-SEM) to examine the data and pinpoint important factors influencing the acceptance of sustainable transportation. The study's findings show that several factors influence the adoption of green mobility (GMA). Key factors include Infrastructure Barriers (IF) (p = 0.015), Institutional Barriers (IB) (p = 0.000), Perceived Benefits (PB) (p = 0.000), Environmental Concerns (EC) (p = 0.023), and Government Concerns (GC) (0.029). Furthermore, green mobility adoption has a significant impact on sustainable transportation (ST) (p = 0.000). However, Financial Barriers (FB) (p = 0.424), Social Barriers (SB) (p = 0.202), and Technological Benefits (TB) (p = 0.077) had no significant effect on the adoption process. The results show that barriers like institutional and infrastructure impact the adoption of green mobility. Also, the drivers like Perceived benefits environmental concerns, and government policies impact the adoption of green mobility. By understanding these dynamics, the research provides practical insights for policymakers, manufacturers, and stakeholders to encourage the broad use of green mobility solutions, thus aiding in creating a more sustainable urban environment. Compared to previous studies, our work highlights the importance of infrastructure and institutional challenges while offering different perspectives on financial and social barriers.
      原文链接:
    • NETL
    • NSTL
    • Springer Nature

    Counting Mixed Traffic Volumes at Motorcycle-Dominated Intersections by Using Computer Vision

    Tam VuHong Nam ThaiViet Ngoc PhamHuy Tuan Vu...
    146-164页
    查看更多>>摘要：This study addresses the lack of computer vision techniques for counting traffic at motorcycle-dominated intersections by developing an integrated framework. Three models are proposed: a detection model with a large visual dataset, a tracking model with a proposed reference point of bounding box and a suggested algorithm for cases of vehicle identity switches, and a counting model with algorithms for different junction movements. These models were applied to the case study of Vietnam. A large dataset comprising 52 footages recorded in daytime and nighttime conditions yields 1,195,691 labelled vehicles. The tracking model accurately reflects vehicle trajectories on road surface, while the counting model improves performance with a triple double-line method. The counting model achieve over 90% accuracy compared to manual counting in terms of total volume and each vehicle type. Therefore, transport planners and operators in Vietnam can draw on the findings of this research by applying the models to data collection, count traffic and monitor intersections. These models might be modified to other countries where motorcycles are dominant.
      原文链接:
    • NETL
    • NSTL