T Theodoropoulos, AC Maroudis… - 2021 IEEE Seventh …, 2021 - ieeexplore.ieee.org
… With the rapid development of data centers, the large-scale network trafficprediction requires more suitable methods to deal with the complex properties of high-dimension, longrange …
Z He, CY Chow, JD Zhang - 2019 20th IEEE international …, 2019 - ieeexplore.ieee.org
… It consists of two parts: the encoder for modeling traffic dynamics and decoder for … predicted spatio-temporal matrix by the decoder that is another ConvLSTM. As the final hidden state …
… results (5min/10min/15min), while Table III focuses on longertermpredictions (30min/45min/60min). The results indicate that the SVR model was not able to model the temporal …
S Du, T Li, Y Yang, X Gong… - 2019 International Joint …, 2019 - ieeexplore.ieee.org
… an encoder-decoder model with temporal attention mechanism for multi-step forward traffic flow prediction task, which uses LSTM as the encoder … forecasting performance and longtime-…
X Zhang, J You - IEEE Access, 2020 - ieeexplore.ieee.org
… forecasting. We enhance the encoder-decoder architecture by adopting gated dilated … by weekday respectively are used to capture the weekly patterns from a short to longterm. …
B Pu, Y Liu, N Zhu, K Li, K Li - Applied Soft Computing, 2020 - Elsevier
… In summary, the CNN-based models are suitable for current human trafficprediction. Recently, many scholars have presented several approaches based on CNNs [5], [29], [30], [31], [32]…
… longtermtrafficprediction. STANN captures the spatial-temporal dependencies based on the encoder-decoder … we enhance the encoder-decoder architecture for trafficprediction, by …
C Zheng, X Fan, C Wang, J Qi - Proceedings of the AAAI conference on …, 2020 - aaai.org
… different prediction time steps in the longtime horizon, we add a transform attention layer between the encoder and the decoder. It models the direct relationship between each future …
X Shi, H Qi, Y Shen, G Wu, B Yin - IEEE Transactions on …, 2020 - ieeexplore.ieee.org
… end framework for trafficprediction, which can model spatial, short-term and longterm periodical … After encoder-decoder, we use a feedforward neural network to obtain the final output of …