Deep learning-driven intelligent data anomaly detection and repair technology for power grids

Artificial Intelligence in Mechanical Manufacturing: From Machine Learning to Generative Pre-trained Transformer

Open Access

Table 2

Comparison of error metrics on current data modelling betweens different algorithms.

MASK_RATE	0.1	0.2	0.3	0.4
METRIC	MAE MSE	MAE MSE	MAE MSE	MAE MSE
LSTM	0.632 1.221	0.665 1.236	0.698 1.245	0.707 1.291
GRU	0.658 1.126	0.692 1.137	0.631 1.152	0.675 1.174
TRANSFORMER	0.661 1.127	0.695 1.138	0.634 1.153	0.678 1.175
TIMEMIXER++	0.567 0.927	0.592 0.927	0.593 0.948	0.595 0.973

Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.

Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.

Initial download of the metrics may take a while.