Prediction of Queue Dissipation Time for Mixed Traffic Flows With Deep Learning

Abstract

Queue dissipation has been extensively studied about traffic signalization, work zone operations, and ramp metering. Various methods for estimating the intersection's queue length and dissipation time have been reported in the literature, including the use of car-following models with simulation, vehicle trajectories from GPS, shock-wave theory, statistical estimation from traffic flow patterns, and artificial neural networks (ANN). However, most of such methods cannot account for the impacts of interactions between different vehicle types and their spatial distributions in the queue length on the initial discharge time and the resulting total dissipation duration. As such, this study presents a system, named TrafficTalk, that applies a deep learning-based method to reliably capture the queue characteristics of mixed traffic flows, and produce a robust estimate of the dissipating duration for the design of the optimal signal plan. The proposed TrafficTalk, featuring the effectiveness in transforming video-imaged traffic conditions into vehicle density maps, has proved its performance under extensive field evaluations. For instance, compared with the benchmark model, XGBoost in the literature, it has reduced the MAPE from 25.8% to 10.4%., and from 31.3% to 10.4% if the queue discharging stream comprises motorcycles. INDEX TERMS Deep learning (DL), traffic queue dissipation time, traffic queue pattern, mixed traffic flows, object detection, traffic signal countdown timer (TSCT).

The Optimalisasi Kinerja Simpang Lalu Lintas: Studi Transformasi Dari Simpang Tidak Bersinyal ke Simpang Bersinyal

“…Simpang menjadi titik kritis dalam regulasi lalu lintas karena merupakan pertemuan berbagai arus kendaraan. Pengaturan yang baik pada simpang, seperti penggunaan lampu lalu lintas, perintah berhenti, atau prioritas tertentu, membantu mengkoordinasikan aliran dari berbagai arah, meminimalkan risiko tabrakan, dan memastikan aliran lalu lintas yang lebih efisien (Chen et al, 2022). Pengaturan yang tepat pada simpang membantu mengurangi risiko kecelakaan, karena dengan aturan yang jelas, pengemudi memiliki prediksi yang lebih baik tentang perilaku kendaraan lain di sekitarnya, mengurangi kebingungan dan risiko kesalahan (Hu et al, 2023).…”

Application of CNN-LSTM Model for Vehicle Acceleration Prediction Using Car-following Behavior Data

“…Second, the CNN part is utilized to extract diferent features. CNN is a deep neural network that employs convolutional computation [44,45]. It has been shown to be efective in extracting features from matrices and accelerating the training process [46].…”

A Bayesian Optimization Approach for Calibrating Large-Scale Activity-Based Transport Models

“…The deep learning methodology has been shown in numerous applications to be a valuable approach in high-dimensional spaces, but it is known to be dataintensive [58], which in the context of transportation activitybased models means a greater number of executions of the models. Outside the activity-based applications, deep learning has nevertheless been applied in the transportation domain, e.g., to estimate the intersection's queue length and dissipation time [59] or to enhance prediction fairness in spatial-temporal demand forecasting of ride-hailing services [60].…”