Semi-automated urban rail transit systems still rely on human intervention during safety-critical events, yet emergency takeover performance has received far less attention than in SAE Level-3 road automation. This study focuses on the reaction phase of emergency takeover, defined as the interval from anomaly onset to the train operator’s first control action. We propose a conditional two-stage evaluation framework that jointly assesses event recognition and control execution quality. A simulation-based experiment was conducted to replicate GoA2 operating conditions under controlled emergency scenarios. Three indicators were extracted: (i) event recognition accuracy derived from eye-tracking and retrospective recall, (ii) takeover reaction time, and (iii) initial action accuracy reflecting compliance with operational speed or braking limits. An attention-enhanced multilayer perceptron (MLP) was developed to dynamically weight input features and improve interpretability. The proposed model achieved stable subject-wise performance, with an average accuracy of 0.86 and a macro F1-score of 0.857. These results support the feasibility of interpretable learning-based evaluation for human-in-the-loop safety assessment and provide practical implications for improving operator readiness monitoring and operational safety management in semi-automated metro systems.

To investigate the regulatory effects of emotional states on the evolution of fatigue in metro drivers, this study conducts an experimental investigation based on an urban rail transit driving simulation platform. A total of 21 participants complete a 90 min simulated driving task, during which electroencephalogram (EEG) and electrocardiogram (ECG) signals are synchronously collected from drivers for fatigue assessment and emotion recognition, respectively. An emotion recognition model based on a multi-scale convolutional neural network (MSCNN) combined with an attention mechanism is constructed. The proposed model uses ECG signals to classify three emotional states—neutral, positive, and negative—where the neutral state is defined as an emotionally undefined baseline that is neither positive nor negative. The model achieves a classification accuracy of 86.96% on the DREAMER dataset. By temporally aligning the emotion recognition results with EEG frequency-domain fatigue indicators, the results show that fatigue exhibits the highest growth and largest fluctuation in amplitude under negative emotions, demonstrating a pronounced fatigue-accelerating effect. Under positive emotions, fatigue decreases considerably and has smaller fluctuations, indicating a certain buffering and restorative effect. In contrast, the neutral emotional state exhibits intermediate and transitional fatigue characteristics. This study innovatively integrates ECG-based emotion recognition with EEG-based fatigue assessment to reveal the mechanisms based on which emotions influence fatigue in metro driving tasks from a physiological perspective. This work provides a basis for emotion-aware fatigue monitoring and safety intervention strategies.