A Hybrid Model for Short-Term Traffic Flow Prediction Based on Variational Mode Decomposition, Wavelet Threshold Denoising, and Long Short-Term Memory Neural Network

Table 5

The prediction errors of different models using the traffic flow data of detector C.

Prediction models	RMSE (veh/5 min)	MAE (veh/5 min)	MAPE (%)
LSTM	18.248	13.444	6.137
WD-LSTM	16.939	12.442	5.885
EMD-WD-LSTM	17.157	13.071	6.620
VMD-WD-ANN	60.737	49.949	17.915
EEMD-ANN	61.205	51.208	15.970
TSD-BiLSTM	20.801	15.161	6.616
ARIMA-LSTM	22.969	17.244	9.057
VMD-WD-LSTM	13.980	10.965	5.268