Link Average Speed of Traffic Flow Estimation Method Based on Floating Car

Zhu, Weihua; Chang, Ande; Jiang, Guiyan; Zhang, W.

doi:10.1061/41064(358)229

Cited by 2 publications

(2 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Traffic flow estimation is complicated by static or dynamic changes in link characteristics such as speed limit, the number of lanes, data collection, data quality (presence of noise and anomalies), and data processing (smoothing, aggregation). Further, the methodological steps play a pivotal role when processing raw FCD to obtain link speed data [34]. These factors can distort and induce scatter in the fundamental diagram, thus rendering indirect traffic flow estimation quite challenging.…”

Section: Literature Reviewmentioning

confidence: 99%

Predicting network flows from speeds using open data and transfer learning

Mahajan

Cantelmo

Rothfeld

et al. 2022

IET Intelligent Trans Sys

View full text Add to dashboard Cite

Traffic flow/volume data are commonly used to calibrate and validate traffic simulation models. However, these data are generally obtained from stationary sensors (e.g. loop detectors), which are expensive to install and maintain and cover a small number of locations in the transport network. On the other hand, Floating Car Data (FCD) are readily available at the network level, usually from a sample of vehicles. We present an indirect traffic flow estimation approach using transfer learning to address the traffic flow data scarcity and model generalization across cities. Using two cities (Paris and Madrid) as study areas, we demonstrate the indirect estimation using only exogenous features for flow prediction, mirroring limited predictive features without past link flows. Subsequently, we use the model pre‐trained on data from Paris city and test on data from Madrid city, and investigate the scenarios for successful transfer learning. Overall, the training set must adequately capture the flow‐speed relationship for successful indirect flow estimation. Transfer learning is beneficial when the data for the target task is minimal, in which case transferred models outperform newly trained models from scratch. Using real‐world and publicly available data, our approach and models can help scale a smaller traffic flow dataset to a larger sample across cities.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Predicting network flows from speeds using open data and transfer learning

Mahajan

Cantelmo

Rothfeld

et al. 2022

IET Intelligent Trans Sys

View full text Add to dashboard Cite

show abstract

“…Lee, Hyunjo [3] used a Bayesian classification model to establish a road network dynamic driving time prediction model and compared it with a link-based prediction model and time-varying coefficient linear regression model. Nihad K. Chowdhury [4] improved the conventional NBC and SMA prediction algorithms and proposed a faster and more accurate travel time prediction model.Jinjin Zhang, Aihua Zhu and S. Vasantha Kumar [5][6][7] adopted the Kalman filtering algorithm to predict short-term and long-term travel time based on travel time data from license plate recognition and a BP neural network. Tao Xu [8] analyzed the predictability of travel times andconsidered the multifactor influence of the backpropagation neural network model for predictive analysis.Yanjie Duan [9] used the LSTM neural network model to predict the travel time on the road, using the driving data provided by the British highway.…”

Section: Introductionmentioning

confidence: 99%

Rainy-day travel time prediction based on Kalman filter algorithm

Li,

Chen,

2024

Seventh International Conference on Traffic Engineering and Transportation System (ICTETS 2023)

View full text Add to dashboard Cite

Precipitation creates many uncertainties in travel times on urban road networks. Travel time prediction involves a multiparameter non-linear mapping relationship, so artificial neural networks are widely used in prediction. Artificial Intelligence This paper designs a travel time calculation method based on non-minimum sections, integrating floating car data and precipitation data. Accordingly, we propose a travel time prediction model based on Kalman Filter and design its effective algorithm. Finally, we use ten-day GPS data gathered from taxis in Zhongguancun West district in Beijing to verify the effectiveness of our proposed approach. These results show that the accuracy of this prediction algorithm in guaranteeing a prediction accuracy of more than 90% is 0.75 and the improved Kalman filter travel time prediction has higher accuracy than traditional.

show abstract

Link Average Speed of Traffic Flow Estimation Method Based on Floating Car

Cited by 2 publications

References 2 publications

Predicting network flows from speeds using open data and transfer learning

Predicting network flows from speeds using open data and transfer learning

Rainy-day travel time prediction based on Kalman filter algorithm

Contact Info

Product

Resources

About