预训练长短时空交错Transformer在交通流预测中的应用

马莉,王永顺,胡瑶,范磊

Pre-trained long-short spatiotemporal interleaved Transformer for traffic flow prediction applications

Li MA,Yongshun WANG,Yao HU,Lei FAN

表 2 不同交通流预测模型在4个交通流标准数据集上的性能对比

Tab.2 Performance comparison of different traffic flow prediction models in four traffic flow benchmark datasets

模型 PEMS03数据集 PEMS04数据集 PEMS07数据集 PEMS08数据集 MAE RMSE MAPE/% MAE RMSE MAPE/% MAE RMSE MAPE/% MAE RMSE MAPE/% ARIMA [2] 35.31 47.59 33.78 33.73 48.80 24.18 38.17 59.27 19.46 31.09 44.32 22.73 Transformer[18] 17.50 30.24 16.80 23.83 37.19 15.57 26.80 42.95 12.11 18.52 28.68 13.66 DCRNN[8] 18.18 30.31 18.91 24.70 38.12 17.12 25.30 38.58 11.66 17.86 27.83 11.45 STGCN[11] 17.49 30.12 17.15 22.70 35.55 14.59 25.38 38.78 11.08 18.02 27.83 11.40 GWNet[12] 19.85 32.94 19.31 25.45 39.70 17.29 26.85 42.78 12.12 19.13 31.05 12.68 SVR[3] 21.97 35.29 21.51 28.70 44.56 19.20 32.49 50.22 14.26 23.25 36.16 14.64 LSTM[6] 21.33 35.11 23.33 27.14 41.59 18.20 29.98 45.84 13.20 22.20 34.06 14.20 AGCRN[10] 16.06 28.49 15.85 19.83 32.26 12.97 21.29 35.12 8.97 15.95 25.22 10.09 ASTGNN[29] 15.07 26.88 15.80 19.26 31.16 12.65 22.23 35.95 9.25 15.98 25.67 9.97 DSTAGNN[28] 15.57 27.21 14.68 19.30 31.46 12.70 21.42 34.51 9.01 15.67 24.77 9.94 STSFGACN[17] 14.98 26.24 14.07 19.14 31.64 12.56 20.61 33.84 8.73 15.14 24.61 10.63 ADMSTNODE[30] 15.47 26.76 15.59 19.28 31.25 12.68 21.40 34.44 9.02 15.58 25.09 9.92 PLSSIFormer 14.67 26.36 14.92 18.11 29.51 12.22 20.29 33.39 8.62 14.35 23.37 9.48