From: Time-series analysis with smoothed Convolutional Neural Network
Title | Year | Method | Resume |
---|---|---|---|
Convolutional Neural Network–Component Transformation (CNN–CT) for confirmed COVID-19 cases [25] | 2021 | CNN-CT (ARIMA and ES) | The combination of strategies outperformed most individual methods |
A comparison between Seasonal Autoregressive Integrated Moving Average (SARIMA) and Exponential Smoothing (ES) based on Time Series Model for forecasting road accidents [26] | 2021 | SARIMA and ES | The ES model outperformed the SARIMA model of mean absolute error, and root mean square error, mean absolute percentage error, and normalized Bayesian information criteria |
On short-term load forecasting using machine learning techniques and a Novel Parallel Deep LSTM-CNN approach [27] | 2021 | ARIMA, ES, Linear Regression, SVR, DNN, LSTM, LSTM-CNN, PLCNet | ARIMA and ES are two well-known time-series analysis approaches that need some parameter adjustment to work with these methods |
A study on the prediction of power demand for electric vehicles using exponential smoothing techniques [28] | 2021 | ES and ARIMA | ES is 9% more accurate than ARIMA as a model of electric vehicle power-demand prediction models |
Smoothing and stationarity enforcement framework for deep learning time-series forecasting [17] | 2021 | ES and CNN-LSTM | ES increases the deep learning forecasting performance |
A hybrid method of exponential smoothing and recurrent neural networks for time series forecasting [18] | 2020 | ES-RNN | The winning hybrid method is used for data deseasonalization, normalization, and extrapolation |
Forecasting time series with multiplicative trend exponential smoothing and LSTM: COVID-19 case study [29] | 2020 | MTES and LSTM | MTES outperformed LSTM in terms of RSME |