Skip to main content

Table 2 The MAE and RMSE indexes of time series prediciton over the five datasets(ε=120)

From: VAECGAN: a generating framework for long-term prediction in multivariate time series

Models SML2020 NASDAQ100 Energy EEG KDDCUP
LSTM 0.8015 0.4751 1.3270 0.4091 0.4174
  0.7023 0.4635 0.8197 0.4933 0.5352
Seq2Seq 0.8012 0.3921 1.3653 0.3674 0.4228
  0.6974 0.4562 0.8214 0.5017 0.4811
DARNN 0.5327 0.3393 1.2671 0.3298 0.3973
  0.5526 0.4074 0.7489 0.4666 0.3596
TCN 0.5387 0.2565 1.1232 0.2713 0.2667
  0.5001 0.3672 0.6152 0.3938 0.3231
DSTPRNN 0.4543 0.2285 1.0910 0.2821 0.2588
  0.4109 0.3613 0.6457 0.3667 0.3182
VAE 0.5879 0.2915 1.2218 0.3017 0.2884
  0.5454 0.4237 0.7322 0.4511 0.3469
VAECGAN 0.4499 0.2193 0.8411 0.2562 0.2418
  0.3965 0.3782 0.6267 0.3599 0.3118