… model the traffic data of actual road networks. Additionally, we learn the spatial-temporal
features of the traffic … graph based neural network, we design a residual graph model to replace …

… To address the above challenges, in this article, we propose a novel traffic prediction
framework, named Dynamic Graph Convolutional Recurrent Network (DGCRN). In DGCRN, hyper-…

… , where the traffic flow is modeled as a diffusion process on a directed graph [… models for
traffic flow prediction, we propose a novel hybrid model integrating CNN and Bi-LSTM networks …

… The work presented in [27] by Rezaei et al. surveyed DL models for encrypted traffic
classification. This paper addressed different DL-based classification models for network traffic …

… on the actual model used. We will now discuss the different types of prediction models that
have been used for traffic prediction in the past. The field of traffic prediction has existed for …

… This paper proposes a short-term traffic flow prediction model for urban sections that is
based on time series analysis and optimization of an LSTM. In the experiments, the following …

… more spatio-temporal aspects of a complicated traffic network to increase the prediction
accuracy. In summary, by combining the GCN model and the LSTM approach, the hybrid GCN-…

… network (FedGRU) in this article, where GRU is an advanced time-series prediction model
that can be used to predict traffic flow. … ], FedGRU aggregates model parameters from different …

… of network traffic, the imbalance of classification still affects. Faced with imbalanced network
traffic data, we propose a novel … the class imbalance problem in network traffic. This method …

… In this paper, we investigate the traffic flow prediction problem on road network. We
propose T-MGCN, a novel deep learning based model that encodes the non-Euclidean spatial …