From: A new deep learning architecture with inductive bias balance for transformer oil temperature forecasting
Dataset
Window size
SCINet
SRCNet
ETTh1
24
1.10
0.50
48
2.14
1.26
72
2.81
1.90
96
3.70
1.01
120
1.75
1.04
ETTh2
3.97
3.23
5.23
1.20
5.60
1.57
5.05
1.17
7.24
1.25