Multi-Task Fusion Deep Learning Model for Short-Term Intersection Operation Performance Forecasting
Urban road intersection bottleneck has become an important factor in causing traffic delay and restricting traffic efficiency. It is essential to explore the prediction of the operating performance at intersections in real-time and formulate corresponding strategies to alleviate intersection delay....
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-05-01
|
Series: | Remote Sensing |
Subjects: | |
Online Access: | https://www.mdpi.com/2072-4292/13/10/1919 |
_version_ | 1797534118682034176 |
---|---|
author | Deqi Chen Xuedong Yan Xiaobing Liu Liwei Wang Fengxiao Li Shurong Li |
author_facet | Deqi Chen Xuedong Yan Xiaobing Liu Liwei Wang Fengxiao Li Shurong Li |
author_sort | Deqi Chen |
collection | DOAJ |
description | Urban road intersection bottleneck has become an important factor in causing traffic delay and restricting traffic efficiency. It is essential to explore the prediction of the operating performance at intersections in real-time and formulate corresponding strategies to alleviate intersection delay. However, because of the sophisticated intersection traffic condition, it is difficult to capture the intersection traffic Spatio-temporal features by the traditional data and prediction methods. The development of big data technology and the deep learning model provides us a good chance to address this challenge. Therefore, this paper proposes a multi-task fusion deep learning (MFDL) model based on massive floating car data to effectively predict the passing time and speed at intersections over different estimation time granularity. Moreover, the grid model and the fuzzy C-means (FCM) clustering method are developed to identify the intersection area and derive a set of key Spatio-temporal traffic parameters from floating car data. In order to validate the effectiveness of the proposed model, the floating car data from ten intersections of Beijing with a sampling rate of 3s are adopted for the training and test process. The experiment result shows that the MFDL model enables us to capture the Spatio-temporal and topology feature of the traffic state efficiently. Compared with the traditional prediction method, the proposed model has the best prediction performance. The interplay between these two targeted prediction variables can significantly improve prediction accuracy and efficiency. Thereby, this method predicts the intersection operation performance in real-time and can provide valuable insights for traffic managers to improve the intersection’s operation efficiency. |
first_indexed | 2024-03-10T11:25:07Z |
format | Article |
id | doaj.art-b8846cf2c08a4012afa4bd6a897e9239 |
institution | Directory Open Access Journal |
issn | 2072-4292 |
language | English |
last_indexed | 2024-03-10T11:25:07Z |
publishDate | 2021-05-01 |
publisher | MDPI AG |
record_format | Article |
series | Remote Sensing |
spelling | doaj.art-b8846cf2c08a4012afa4bd6a897e92392023-11-21T19:43:20ZengMDPI AGRemote Sensing2072-42922021-05-011310191910.3390/rs13101919Multi-Task Fusion Deep Learning Model for Short-Term Intersection Operation Performance ForecastingDeqi Chen0Xuedong Yan1Xiaobing Liu2Liwei Wang3Fengxiao Li4Shurong Li5MOT Key Laboratory of Transport Industry of Big Data Application Technologies for Comprehensive Transport, School of Traffic and Transportation, Beijing Jiaotong University, Beijing 100044, ChinaMOT Key Laboratory of Transport Industry of Big Data Application Technologies for Comprehensive Transport, School of Traffic and Transportation, Beijing Jiaotong University, Beijing 100044, ChinaMOT Key Laboratory of Transport Industry of Big Data Application Technologies for Comprehensive Transport, School of Traffic and Transportation, Beijing Jiaotong University, Beijing 100044, ChinaMOT Key Laboratory of Transport Industry of Big Data Application Technologies for Comprehensive Transport, School of Traffic and Transportation, Beijing Jiaotong University, Beijing 100044, ChinaMOT Key Laboratory of Transport Industry of Big Data Application Technologies for Comprehensive Transport, School of Traffic and Transportation, Beijing Jiaotong University, Beijing 100044, ChinaMOT Key Laboratory of Transport Industry of Big Data Application Technologies for Comprehensive Transport, School of Traffic and Transportation, Beijing Jiaotong University, Beijing 100044, ChinaUrban road intersection bottleneck has become an important factor in causing traffic delay and restricting traffic efficiency. It is essential to explore the prediction of the operating performance at intersections in real-time and formulate corresponding strategies to alleviate intersection delay. However, because of the sophisticated intersection traffic condition, it is difficult to capture the intersection traffic Spatio-temporal features by the traditional data and prediction methods. The development of big data technology and the deep learning model provides us a good chance to address this challenge. Therefore, this paper proposes a multi-task fusion deep learning (MFDL) model based on massive floating car data to effectively predict the passing time and speed at intersections over different estimation time granularity. Moreover, the grid model and the fuzzy C-means (FCM) clustering method are developed to identify the intersection area and derive a set of key Spatio-temporal traffic parameters from floating car data. In order to validate the effectiveness of the proposed model, the floating car data from ten intersections of Beijing with a sampling rate of 3s are adopted for the training and test process. The experiment result shows that the MFDL model enables us to capture the Spatio-temporal and topology feature of the traffic state efficiently. Compared with the traditional prediction method, the proposed model has the best prediction performance. The interplay between these two targeted prediction variables can significantly improve prediction accuracy and efficiency. Thereby, this method predicts the intersection operation performance in real-time and can provide valuable insights for traffic managers to improve the intersection’s operation efficiency.https://www.mdpi.com/2072-4292/13/10/1919intersectionsfloating car datamulti-task fusion deep learning modelgrid model |
spellingShingle | Deqi Chen Xuedong Yan Xiaobing Liu Liwei Wang Fengxiao Li Shurong Li Multi-Task Fusion Deep Learning Model for Short-Term Intersection Operation Performance Forecasting Remote Sensing intersections floating car data multi-task fusion deep learning model grid model |
title | Multi-Task Fusion Deep Learning Model for Short-Term Intersection Operation Performance Forecasting |
title_full | Multi-Task Fusion Deep Learning Model for Short-Term Intersection Operation Performance Forecasting |
title_fullStr | Multi-Task Fusion Deep Learning Model for Short-Term Intersection Operation Performance Forecasting |
title_full_unstemmed | Multi-Task Fusion Deep Learning Model for Short-Term Intersection Operation Performance Forecasting |
title_short | Multi-Task Fusion Deep Learning Model for Short-Term Intersection Operation Performance Forecasting |
title_sort | multi task fusion deep learning model for short term intersection operation performance forecasting |
topic | intersections floating car data multi-task fusion deep learning model grid model |
url | https://www.mdpi.com/2072-4292/13/10/1919 |
work_keys_str_mv | AT deqichen multitaskfusiondeeplearningmodelforshorttermintersectionoperationperformanceforecasting AT xuedongyan multitaskfusiondeeplearningmodelforshorttermintersectionoperationperformanceforecasting AT xiaobingliu multitaskfusiondeeplearningmodelforshorttermintersectionoperationperformanceforecasting AT liweiwang multitaskfusiondeeplearningmodelforshorttermintersectionoperationperformanceforecasting AT fengxiaoli multitaskfusiondeeplearningmodelforshorttermintersectionoperationperformanceforecasting AT shurongli multitaskfusiondeeplearningmodelforshorttermintersectionoperationperformanceforecasting |