Augmentation of Deep Learning Models for Multistep Traffic Speed Prediction

Abstract

Traffic speed prediction is a vital part of the intelligent transportation system (ITS). Predicting accurate traffic speed is becoming an important and challenging task with the rapid development of deep learning and increasing traffic data size. In this study, we present a deep-learning-based architecture for network-wide traffic speed prediction. We propose a deep-learning-based model consisting of a fully convolutional neural network, bidirectional long short-term memory, and attention mechanism. Our design aims to consider both backward and forward dependencies of traffic data to predict multistep network-wide traffic speed. Thus, we propose a model named AttBDLTSM-FCN for multistep traffic speed prediction. We augmented the attention-based bidirectional long short-term memory recurrent neural network with the fully convolutional network to predict the network-wide traffic speed. In traffic speed prediction, this is the first time that augmentation of AttBDLSTM and FCN have been exploited to measure the backward dependency of traffic data, as a building block for a deep architecture model. We conducted comprehensive experiments, and the experimental evaluations illustrated that the proposed architecture achieved better performance compared to state-of-the-art models when considering the short and long traffic speed prediction, e.g., 15, 30, and 60 min, in multistep traffic speed prediction.

A Systematic Literature Review of 3D Deep Learning Techniques in Computed Tomography Reconstruction

“…Furthermore, enhancements in regularization methods can prove beneficial for the application of CNNs in computed tomography reconstruction. Computed tomography reconstruction has been made more effective and efficient by using deep learning regularization (DLR), which typically refers to the use of regularization in machine learning or neural network models to prevent overfitting and enhance model generalization [113,114] using techniques such as the efficient dense learning framework (EDLF). These regularization techniques make use of techniques to improve deep learning models, producing better reconstruction outcomes.…”

Prediction Method of PHEV Driving Energy Consumption Based on the Optimized CNN BiLSTM Attention Network

“…The model is built using an LSTM network, and the output is the vehicle's energy consumption over 100 km [22]. Furthermore, models employing convolutional neural networks (CNN), long short-term memory (LSTM), or bidirectional long short-term memory recurrent neural networks with full convolutional networks are utilized to predict vehicle speed trajectories over a future period, contingent on road and traffic conditions [23,24].…”