no code implementations • 9 May 2022 • Sajal Saha, Anwar Haque, Greg Sidebottom
In this paper, we investigated and evaluated the performance of the deep transfer learning technique in traffic prediction with inadequate historical data leveraging the knowledge of our pre-trained model.
no code implementations • 9 May 2022 • Sajal Saha, Anwar Haque, Greg Sidebottom
However, our proposed hybrid model considerably reduces the performance gap between identical and out-of-distribution evaluation compared with the standalone model, indicating the decomposition technique's effectiveness in the case of out-of-distribution generalization.
no code implementations • 3 May 2022 • Sajal Saha, Anwar Haque, Greg Sidebottom
Several deep sequences models were implemented to predict real traffic without and with outliers and show the significance of outlier detection in real-world traffic prediction.
no code implementations • 3 May 2022 • Sajal Saha, Anwar Haque, Greg Sidebottom
As a result, many different mathematical models have been studied to capture the general trend of the network traffic and predict accordingly.
no code implementations • 3 May 2022 • Sajal Saha, Anwar Haque, Greg Sidebottom
Then, we performed a comparative performance analysis among AutoRegressive Integrated Moving Average (ARIMA), Seasonal ARIMA (SARIMA), SARIMA with eXogenous factors (SARIMAX), and Holt-Winter for single-step prediction.