☆ 4.4 Article

Urban network-wide traffic volume estimation under sparse deployment of detectors

TRANSPORTMETRICA A-TRANSPORT SCIENCE (2023)

Related references

Note: Only part of the references are listed.

Article Transportation

Link dynamic vehicle count estimation based on travel time distribution using license plate recognition data

Chunguang He et al.

Summary: This paper proposes a method for estimating the dynamic vehicle count considering recognition errors using license plate recognition data. The method reconstructs the cumulative arrival-departure curve to calculate the vehicle count. The results show that the method has high accuracy in different levels of matched rate of LPR data.

TRANSPORTMETRICA A-TRANSPORT SCIENCE (2023)

Add to Collection

Article Engineering, Civil

A Gaussian-Process-Based Data-Driven Traffic Flow Model and Its Application in Road Capacity Analysis

Zhiyuan Liu et al.

Summary: This paper proposes a novel framework that extends the classical fundamental diagram models to incorporate more dimensions of traffic state variables and consider the impact of supply-side factors. The framework is suitable for real-time traffic management, especially in urban areas, due to its minimal assumptions, flexibility to various data sources, and scalability to higher-dimensional data. The Gaussian process model is adopted as the base model for learning the optimal mapping from input features to traffic volume. An in-depth analysis of the properties of the kernel and likelihood function is provided. The experiments demonstrate the ability of the proposed framework to capture complex relationships between traffic variables and supply-side factors, and estimate dynamic road capacity.

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS (2023)

Add to Collection

Article Transportation

Full-scale spatio-temporal traffic flow estimation for city-wide networks: a transfer learning based approach

Yuan Zhang et al.

Summary: This study proposes an instance-based transfer learning method to tackle traffic flow estimation problem in urban transport networks. Case studies based on simulation data and empirical data demonstrate the effectiveness of the method. It outperforms existing methods by reducing the estimation error by two percentage points for road segments without detectors.

TRANSPORTMETRICA B-TRANSPORT DYNAMICS (2023)

Add to Collection

Article Engineering, Electrical & Electronic

Predicting network flows from speeds using open data and transfer learning

Vishal Mahajan et al.

Summary: This article presents an indirect traffic flow estimation approach using transfer learning to address the scarcity of traffic flow data and model generalization across cities. The study demonstrates successful transfer learning scenarios by pre-training the model on data from one city (Paris) and testing it on data from another city (Madrid). Experimental results show that transfer learning outperforms newly trained models when the data for the target task is minimal.

IET INTELLIGENT TRANSPORT SYSTEMS (2023)

Add to Collection

Article Engineering, Civil

Low-Rank Hankel Tensor Completion for Traffic Speed Estimation

Xudong Wang et al.

Summary: This paper proposes a data-driven and model-free solution for the traffic state estimation problem using sparse observations from mobile sensors. The approach transforms the incomplete matrix into a fourth-order Hankel structured tensor and characterizes spatiotemporal patterns using a low-rank assumption. An efficient solution algorithm based on ADMM is developed, and numerical experiments on real-world data demonstrate the effectiveness and superiority of the proposed model.

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS (2023)

Add to Collection

Article Economics

Bayesian optimization for congestion pricing problems: A general framework and its instability

Jinbiao Huo et al.

Summary: In this study, a generic Bayesian optimization (BO) framework was proposed to solve congestion pricing problems. The Gaussian process (GP) was used as a surrogate model to approximate the highly nonlinear and expensive-to-evaluate objective functions. The study revealed the instability phenomenon of GP, and an improved GP (IGP) model was proposed to address this issue, leading to higher computational efficiency and solution accuracy compared to benchmark approaches.

TRANSPORTATION RESEARCH PART B-METHODOLOGICAL (2023)

Add to Collection

Article Computer Science, Artificial Intelligence

Deep spatial-temporal bi-directional residual optimisation based on tensor decomposition for traffic data imputation on urban road network

Jinlong Li et al.

Summary: The ST-BiRT model proposed in this study effectively enhances the imputation performance of traffic data through a bi-directional residual structure, demonstrating a significant advantage on the Guangzhou traffic speed dataset.

APPLIED INTELLIGENCE (2022)

Add to Collection

Article Transportation Science & Technology

Real-time joint traffic state and model parameter estimation on freeways with fixed sensors and connected vehicles: State-of-the-art overview, methods, and case studies

Yibing Wang et al.

Summary: This paper addresses the real-time joint traffic state and model parameter estimation on freeways using data from fixed sensors and connected vehicles. It investigates the performance improvement of traffic state estimation by combining both types of sensing data, and examines the role of online model parameter estimation in this process. The paper provides an overview of the current state of freeway TSE and presents three approaches to design freeway traffic state estimators using mixed sensing data. The designed estimators are evaluated using NGSIM data, providing answers to several key questions.

TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES (2022)

Add to Collection

Article Transportation

Incremental unscented Kalman filter for real-time traffic estimation on motorways using multi-source data

Xuan-Sy Trinh et al.

Summary: In this study, an incremental Unscented Kalman Filter (UKF) was developed to handle data from multiple sources for real-time motorway traffic estimation. The proposed framework showed similar performance with the incremental Extended Kalman Filter (EKF), but exhibited more reliability with smaller variance estimates, especially during free-flow periods. By combining multiple data sources, the filter was able to compensate for deficiencies in each source and produce more accurate estimates.

TRANSPORTMETRICA A-TRANSPORT SCIENCE (2022)

Add to Collection

Article Computer Science, Artificial Intelligence

Spatio-Temporal Meta Learning for Urban Traffic Prediction

Zheyi Pan et al.

Summary: This paper proposes a deep meta learning model, ST-MetaNet(+), for predicting urban traffic. The model captures complex spatio-temporal correlations using an encoder and a decoder, and generates weights using embeddings of geo-graph attributes and traffic context. Experimental results demonstrate the effectiveness of ST-MetaNet(+) in surpassing other methods.

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING (2022)

Add to Collection

Review Physics, Multidisciplinary

Traffic state estimation of urban road networks by multi-source data fusion: Review and new insights

Jiping Xing et al.

Summary: This paper reviews studies on estimating traffic states on segments without detectors. It categorizes existing research into three types and highlights challenges and future research directions.

PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS (2022)

Add to Collection

Article Transportation Science & Technology

Estimating key traffic state parameters through parsimonious spatial queue models

Qixiu Cheng et al.

Summary: The fluid-based queueing model is important for traffic flow modeling and state estimation. This paper proposes a spatial queue model for oversaturated traffic systems and demonstrates its effectiveness through empirical data.

TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES (2022)

Add to Collection

Article Transportation Science & Technology

Integrating public transit signal priority into max-pressure signal control: Methodology and simulation study on a downtown network

Te Xu et al.

Summary: This paper proposes a novel max-pressure signal control method that considers transit signal priority to achieve maximum stability for private vehicles and reliable transit service. The method, validated through simulations, shows promising results in reducing travel time.

TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES (2022)

Add to Collection

Article Engineering, Civil

Gaussian Process Regression for Transportation System Estimation and Prediction Problems: The Deformation and a Hat Kernel

Zhiyuan Liu et al.

Summary: Gaussian process regression (GPR) is a promising machine learning model for transportation system estimation and prediction. The radial basis function (RBF) kernel, commonly used in GPR, often faces difficulties in finding the optimal hyperparameter. This paper addresses the issue by promoting the use of the hat kernel and investigating the connection between deformation and the Bayesian generalization error of GPR.

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS (2022)

Add to Collection

Article Engineering, Civil

Multitask Neural Tensor Factorization for Road Traffic Speed-Volume Correlation Pattern Learning and Joint Imputation

Yiting Zhu et al.

Summary: Missing data is a common and critical problem in traffic data collection and processing. Tensor-based methods have been effective in imputing missing values in spatio-temporal traffic data. However, most previous studies did not consider the joint imputation of multiple correlated data such as traffic speed and volume. This paper proposes a novel method called Multi-Task Neural Tensor Factorization (MTNTF) to address the joint imputation of traffic speed and volume, and experiments demonstrate its superiority over state-of-the-art methods.

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS (2022)

Add to Collection

Article Physics, Multidisciplinary

Pattern-adaptive generative adversarial network with sparse data for traffic state estimation

Jing Tian et al.

Summary: Accurate traffic state estimation is crucial for traffic control and management applications. However, the multi-modality and sparse sampling of traffic state patterns pose challenges for adaptation and introduce bias and uncertainty in estimation. To address this, a pattern-adaptive generative adversarial network (PA-GAN) is proposed, which utilizes Bayesian inference and posterior sampling to adaptively activate parameters for each traffic pattern. PA-GAN learns traffic patterns from sparse sampling data and uses an error-feedback mechanism to improve estimation accuracy under an encoder-decoder framework. Experimental results demonstrate the superiority of PA-GAN over other estimation methods and the effectiveness of Bayesian inference in adapting to various traffic states.

PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS (2022)

Add to Collection

Review Transportation Science & Technology

Macroscopic traffic flow modelling of large-scale freeway networks with field data verification: State-of-the-art review, benchmarking framework, and case studies using METANET

Yibing Wang et al.

Summary: This paper presents a comprehensive review of the latest works on macroscopic model calibration and validation and proposes a benchmarking framework for traffic flow modeling. By conducting numerous case studies using the macroscopic traffic flow model METANET on the urban expressway network in Shanghai, the paper provides more comprehensive results on model calibration and reports many model validation results. The results demonstrate that METANET is capable of accurately modeling complex traffic flow dynamics in large-scale freeway networks.

TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES (2022)

Add to Collection

Article Transportation Science & Technology

Truncated tensor Schatten p-norm based approach for spatiotemporal traffic data imputation with complicated missing patterns

Tong Nie et al.

Summary: This paper explores an innovative method for imputing missing spatiotemporal traffic data using tensors. The proposed method utilizes a nonconvex truncated Schatten p-norm (TSpN) to approximate tensor rank and combines the alternating direction method of multipliers (ADMM) with generalized soft-thresholding (GST) to derive global optimal solutions. Experimental results show that the proposed method performs well under various missing cases, even with high rates of data loss, outperforming other state-of-the-art tensor-based imputation models in almost all scenarios.

TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES (2022)

Add to Collection

Article Transportation Science & Technology

Network-scale traffic prediction via knowledge transfer and regional MFD analysis

Junyi Li et al.

Summary: This paper proposes a physics-informed transfer learning method for network-scale link-wise traffic flow prediction, aiming to address the issues of data insufficiency and dataset shift. Experimental results show that the proposed framework can facilitate traffic flow transfer between different regions and alleviate problems related to data insufficiency, dataset shift, and heavy computational cost.

TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES (2022)

Add to Collection

Article Transportation Science & Technology

Route flow estimation based on the fusion of probe vehicle trajectory and automated vehicle identification data

Wanjing Ma et al.

Summary: This study proposes a route flow estimation framework by fusing probe vehicle trajectory and automated vehicle identification (AVI) data. The model uses the concept of probe vehicle route penetration rate (RPR) to construct a novel data-driven objective function. Numerical studies show that the proposed model outperforms traditional path flow estimation model, especially when prior flow information is not available.

TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES (2022)

Add to Collection

Article Engineering, Electrical & Electronic

Dynamic Origin-Destination Flow Prediction Using Spatial-Temporal Graph Convolution Network With Mobile Phone Data

Zhichen Liu et al.

Summary: Massive mobile phone data is used to predict origin-destination flows, with two spatial-temporal graph convolutional network-based models focusing on edges and vertices proposed. These models effectively capture correlations among OD flows and explore complex spatial-temporal features, showing significant improvements over baseline models.

IEEE INTELLIGENT TRANSPORTATION SYSTEMS MAGAZINE (2022)

Add to Collection

Article Computer Science, Interdisciplinary Applications

A generative adversarial network for travel times imputation using trajectory data

Kunpeng Zhang et al.

Summary: This study introduces a travel times imputation method based on generative adversarial networks, which can infer travel times under missing data by modeling links with rich data, showing superior performance in experiments.

COMPUTER-AIDED CIVIL AND INFRASTRUCTURE ENGINEERING (2021)

Add to Collection

Article Economics

An s-shaped three-parameter (S3) traffic stream model with consistent car following relationship

Qixiu Cheng et al.

Summary: A new S3 traffic flow model was proposed in this study to represent the relationship between flow, speed, and density in highway traffic, which was calibrated using real-world traffic data. This study also derived a consistent car-following model based on the proposed S-shaped speed-density function.

TRANSPORTATION RESEARCH PART B-METHODOLOGICAL (2021)

Add to Collection

Article Computer Science, Interdisciplinary Applications

Inferencing hourly traffic volume using data-driven machine learning and graph theory

Zhiyan Yi et al.

Summary: This paper introduces an innovative spatial prediction method for hourly traffic volume on a network scale, utilizing the XGBoost tree ensemble model to handle large-scale features and hourly traffic volume samples. In addition, spatial dependency among road segments is considered using graph theory and a graph-based approach in the proposed model. The results from testing on Utah's road network show high computational efficiency and significant improvement in prediction accuracy compared to benchmarked models.

COMPUTERS ENVIRONMENT AND URBAN SYSTEMS (2021)

Add to Collection

Article Transportation Science & Technology

Urban network-wide traffic speed estimation with massive ride-sourcing GPS traces

Jingru Yu et al.

TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES (2020)

Add to Collection

Article Transportation

Real-time headway state identification and saturation flow rate estimation: a hidden Markov Chain model

Hongsheng Qi et al.

TRANSPORTMETRICA A-TRANSPORT SCIENCE (2020)

Add to Collection

Review Transportation Science & Technology

Trajectory data-based traffic flow studies: A revisit

Li Li et al.

TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES (2020)

Add to Collection

Article Transportation Science & Technology

Network-wide traffic flow estimation with insufficient volume detection and crowdsourcing data

Zhengchao Zhang et al.

TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES (2020)

Add to Collection

Article Transportation Science & Technology

Semi-supervised route choice modeling with sparse Automatic vehicle identification data

Qi Cao et al.

TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES (2020)

Add to Collection

Article Transportation

Ensemble of ARIMA: combining parametric and bootstrapping technique for traffic flow prediction

Siroos Shahriari et al.

TRANSPORTMETRICA A-TRANSPORT SCIENCE (2020)

Add to Collection

Article Transportation

Estimation of urban arterial travel time distribution considering link correlations

Wenwen Qin et al.

TRANSPORTMETRICA A-TRANSPORT SCIENCE (2020)

Add to Collection

Article Engineering, Civil

Minimum Sampling Size of Floating Cars for Urban Link Travel Time Distribution Estimation

Meiping Yun et al.

TRANSPORTATION RESEARCH RECORD (2019)

Add to Collection

Article Transportation Science & Technology

Traffic parameters estimation for signalized intersections based on combined shockwave analysis and Bayesian Network

Shuling Wang et al.

TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES (2019)

Add to Collection

Article Transportation

Short-term traffic flow prediction based on spatio-temporal analysis and CNN deep learning

Weibin Zhang et al.

TRANSPORTMETRICA A-TRANSPORT SCIENCE (2019)

Add to Collection

Article Computer Science, Information Systems

Think Like A Graph: Real-Time Traffic Estimation at City-Scale

Zhidan Liu et al.

IEEE TRANSACTIONS ON MOBILE COMPUTING (2019)

Add to Collection

Article Economics

On the estimation of connected vehicle penetration rate based on single-source connected vehicle data

Wai Wong et al.

TRANSPORTATION RESEARCH PART B-METHODOLOGICAL (2019)

Add to Collection

Article Transportation Science & Technology

Spatial-temporal inference of urban traffic emissions based on taxi trajectories and multi-source urban data

Jielun Liu et al.

TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES (2019)

Add to Collection

Article Transportation Science & Technology

A tailored machine learning approach for urban transport network flow estimation

Zhiyuan Liu et al.

TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES (2019)

Add to Collection

Article Engineering, Electrical & Electronic

Traffic Volume Estimation in Multimodal Urban Networks Using Cellphone Location Data

Jiping Xing et al.

IEEE INTELLIGENT TRANSPORTATION SYSTEMS MAGAZINE (2019)

Add to Collection

Article Transportation Science & Technology

Missing data imputation for traffic flow speed using spatio-temporal cokriging

Bumjoon Bae et al.

TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES (2018)

Add to Collection

Article Transportation Science & Technology

Network-wide traffic state estimation using a mixture Gaussian graphical model and graphical lasso

Yusuke Hara et al.

TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES (2018)

Add to Collection

Article Transportation Science & Technology

On the imputation of missing data for road traffic forecasting: New for insights and novel techniques

Ibai Lana et al.

TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES (2018)

Add to Collection

Article Transportation Science & Technology

Heteroscedastic Gaussian processes for uncertainty modeling in large-scale crowdsourced traffic data

Filipe Rodrigues et al.

TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES (2018)

Add to Collection

Article Computer Science, Artificial Intelligence

Citywide Traffic Volume Estimation Using Trajectory Data

Xianyuan Zhan et al.

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING (2017)

Add to Collection

Article Engineering, Civil

Mining Road Network Correlation for Traffic Estimation via Compressive Sensing

Zhidan Liu et al.

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS (2016)

Add to Collection

Article Transportation Science & Technology

Efficient multiple model particle filtering for joint traffic state estimation and incident detection

Ren Wang et al.

TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES (2016)

Add to Collection

Article Computer Science, Information Systems

Urban Link Travel Time Prediction Based on a Gradient Boosting Method Considering Spatiotemporal Correlations

Faming Zhang et al.

ISPRS INTERNATIONAL JOURNAL OF GEO-INFORMATION (2016)

Add to Collection

Article Engineering, Civil

Untitled

JOURNAL OF ADVANCED TRANSPORTATION (2016)

Add to Collection

Article Geography

Spatial variation of the urban taxi ridership using GPS data

Xinwu Qian et al.

APPLIED GEOGRAPHY (2015)

Add to Collection

Article Transportation Science & Technology

A tensor-based method for missing traffic data completion

Huachun Tan et al.

TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES (2013)

Add to Collection

Article Computer Science, Artificial Intelligence

LIBSVM: A Library for Support Vector Machines

Chih-Chung Chang et al.

ACM TRANSACTIONS ON INTELLIGENT SYSTEMS AND TECHNOLOGY (2011)

Add to Collection

Article Computer Science, Artificial Intelligence

A Survey on Transfer Learning

Sinno Jialin Pan et al.

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING (2010)

Add to Collection

Article Transportation Science & Technology

Understanding the variability of speed distributions under mixed traffic conditions caused by holiday traffic

Jungwook Jun

TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES (2010)

Add to Collection

Article Engineering, Civil

PPCA-Based Missing Data Imputation for Traffic Flow Volume: A Systematical Approach

Li Qu et al.

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS (2009)

Add to Collection

Review Physics, Multidisciplinary

Three-phase traffic theory and highway capacity

BS Kerner

PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS (2004)

Add to Collection

© Peeref 2019-2024. All rights reserved.