Multi-Task Fusion Deep Learning Model for Short-Term Intersection Operation Performance Forecasting

Abstract

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.

Analysis of Spatiotemporal Data Imputation Methods for Traffic Flow Data in Urban Networks

“…To solve these issues, the weighted mean absolute percentage error (WMAPE) [46][47][48] is considered to describe the imputation performance of each method. WMAPE is defined by the following formula…”

Spatio-Temporal Traffic Flow Prediction Based on Coordinated Attention

“…Lee et al [31], to research traffic speed in future moments, combined three spatial dependencies of distance, direction, and location with a graph convolutional network to form a variety of different spatial graph elements, and used 1D convolution to extract temporal features to form a spatio-temporal convolutional block, which performed better in long-term prediction but did not perform as well as long-term prediction in short-term prediction. Chen et al [32] used floating vehicle data as the basis and extracted traffic parameters of floating vehicle data through a grid model, combined with GCN to consider topological propagation patterns of intersections to construct a multi-task fusion deep learning (MFDL) model for predicting the passage time and speed of intersections at future moments.…”

An integrated two‐dimensional merging trajectory optimization model for automated vehicles considering mixed traffic flow

“…Recently, the convolution neural network (Conv) and the long-short term memory (LSTM) network have been widely acknowledged as powerful tools in addressing the highdimensional visual imagery input and time-sequence input [72][73][74][75]. Because our input label involves both spatial and temporal factors, we combine the Conv and LSTM networks to construct the neural network predictor.…”