Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Travel Time Reliability Prediction Using Quantile Random Forest Regression
https://orcid.org/http://orcid.org/0000-0002-1137-9656
The prediction of travel time is of paramount interest to the planning, design, operations, and management of any transportation facility. While the average travel time provides an idea of how long a trip will take, it does not provide information on its reliability. In contrast, percentiles provide more detailed information on reliability by determining the range of travel times that can be expected for a given trip. Thus, the prediction of travel time percentiles helps in travel time reliability studies. In this study, the use of Quantile Random Forest (QRF) Regressor is used to predict travel time percentiles. QRF is a flexible machine learning algorithm that can capture the complex relationships between predictor variables and the response variable. The study uses Wi-Fi sensors based data collected from Rajiv Gandhi IT Expressway in Chennai. The performance of the QRF model is evaluated using mean absolute percentage error (MAPE). The results show that the QRF model performed well in predicting travel time percentiles, with the best performance observed for the median percentile. Thus, the QRF model can provide accurate and reliable travel time predictions, which can be used by transportation planners and traffic engineers to optimize traffic flow and improve transportation efficiency.
Travel Time Reliability Prediction Using Quantile Random Forest Regression
https://orcid.org/http://orcid.org/0000-0002-1137-9656
The prediction of travel time is of paramount interest to the planning, design, operations, and management of any transportation facility. While the average travel time provides an idea of how long a trip will take, it does not provide information on its reliability. In contrast, percentiles provide more detailed information on reliability by determining the range of travel times that can be expected for a given trip. Thus, the prediction of travel time percentiles helps in travel time reliability studies. In this study, the use of Quantile Random Forest (QRF) Regressor is used to predict travel time percentiles. QRF is a flexible machine learning algorithm that can capture the complex relationships between predictor variables and the response variable. The study uses Wi-Fi sensors based data collected from Rajiv Gandhi IT Expressway in Chennai. The performance of the QRF model is evaluated using mean absolute percentage error (MAPE). The results show that the QRF model performed well in predicting travel time percentiles, with the best performance observed for the median percentile. Thus, the QRF model can provide accurate and reliable travel time predictions, which can be used by transportation planners and traffic engineers to optimize traffic flow and improve transportation efficiency.
Travel Time Reliability Prediction Using Quantile Random Forest Regression
https://orcid.org/http://orcid.org/0000-0002-1137-9656
The prediction of travel time is of paramount interest to the planning, design, operations, and management of any transportation facility. While the average travel time provides an idea of how long a trip will take, it does not provide information on its reliability. In contrast, percentiles provide more detailed information on reliability by determining the range of travel times that can be expected for a given trip. Thus, the prediction of travel time percentiles helps in travel time reliability studies. In this study, the use of Quantile Random Forest (QRF) Regressor is used to predict travel time percentiles. QRF is a flexible machine learning algorithm that can capture the complex relationships between predictor variables and the response variable. The study uses Wi-Fi sensors based data collected from Rajiv Gandhi IT Expressway in Chennai. The performance of the QRF model is evaluated using mean absolute percentage error (MAPE). The results show that the QRF model performed well in predicting travel time percentiles, with the best performance observed for the median percentile. Thus, the QRF model can provide accurate and reliable travel time predictions, which can be used by transportation planners and traffic engineers to optimize traffic flow and improve transportation efficiency.
Travel Time Reliability Prediction Using Quantile Random Forest Regression
Transp. in Dev. Econ.
Anil Kumar, B. (Autor:in) / Chandana, Gunda (Autor:in) / Vanajakshi, Lelitha (Autor:in)
01.04.2025
Aufsatz (Zeitschrift)
Elektronische Ressource
Englisch
Travel Time Reliability Prediction Using Quantile Random Forest Regression
| Springer Verlag | 2025
Travel time prediction with support vector regression
| IEEE | 2003
Travel Time Prediction with Support Vector Regression
| British Library Conference Proceedings | 2003
Urban Arterial Travel Time Prediction Using Support Vector Regression
| Springer Verlag | 2018