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 7

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

Prediction models	RMSE (veh/5 min)	MAE (veh/5 min)	MAPE (%)
LSTM	11.462	8.290	22.69
WD-LSTM	9.795	7.382	21.316
EMD-WD-LSTM	13.976	10.824	32.833
VMD-WD-ANN	9.909	7.702	20.667
EEMD-ANN	9.688	7.546	20.461
TSD-BiLSTM	14.898	10.929	27.831
ARIMA-LSTM	10.269	7.936	28.417
VMD-WD-LSTM	5.623	4.301	12.500

Bold indicates the best value of each evaluation index.