Resultado de búsqueda
In our paper, we review some of the latest works in deep learning for traffic flow prediction. Many deep learning architectures include Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM), Restricted Boltzmann Machines (RBM), and Stacked Auto Encoder (SAE).
- Download PDF
various existing deep learning architectures used for...
- Download PDF
10 de feb. de 2021 · Deep Learning on Traffic Prediction: Methods, Analysis, and Future Directions Abstract: Traffic prediction plays an essential role in intelligent transportation system. Accurate traffic prediction can assist route planing, guide vehicle dispatching, and mitigate traffic congestion.
27 de mar. de 2024 · In this work, we propose to solve both issues using a Convolutional Neural Network (CNNs) with Long Short Term Memory (LSTM) deep learning architecture to successfully predict traffic flow, while leveraging a cellular automata-based statistical mechanics model of traffic flow to generate training and test data.
9 de mar. de 2023 · Precise traffic flow prediction is essential to the ITS as it can help traffic stakeholders (Individual passengers, traffic administrators, policymakers, and road users), shown in Fig. 1, utilize transport networks more safely and intelligently [ 5, 6 ].
1 de dic. de 2019 · Deep learning models for traffic flow prediction in autonomous vehicles: A review, solutions, and challenges - ScienceDirect. Vehicular Communications. Volume 20, December 2019, 100184. Deep learning models for traffic flow prediction in autonomous vehicles: A review, solutions, and challenges. ArzooMiglani, NeerajKumar. Show more. Add to Mendeley.
1 de jun. de 2017 · Deep learning is a form of machine learning which provides good short-term forecasts of traffic flows by exploiting the dependency in the high dimensional set of explanatory variables, we capture the sharp discontinuities in traffic flow that arise in large-scale networks.
13 de sept. de 2022 · Recent deep learning approaches of spatiotemporal neural networks to predict traffic flow show promise, but could be difficult to separately model the spatiotemporal aggregation in traffic data and intrinsic correlation or redundancy of spatiotemporal features extracted by the filter of the convolutional network.
