Fig. 6 | Scientific Reports

Fig. 6

From: Research on temperature prediction method for rail transit train inverters based on spatial and timing improving Transformer

Fig. 6

Error variation under progressive feature corruption. Note: \({\sigma }\) denotes feature perturbation intensity (0 → 1 corresponds to random masking ratio of high-importance features increasing from 0 to 100%). Metrics include MAE (Mean Absolute Error), \({\text{R}}^{2}\) (Coefficient of Determination), and ACC (Accuracy), with values reflecting model tolerance to feature corruption.

Back to article page