As a forward-looking development in air traffic control (ATC), remote towers rely on virtualized information presentation, which may exacerbate visual fatigue among controllers and compromise operational safety. This study proposes a visual fatigue recognition model based on multimodal physiological signals. A 60-min simulated remote tower task was conducted with 36 participants, during which eye-tracking (ET), electroencephalography (EEG), electrocardiography (ECG), and electrodermal activity (EDA) signals were collected. Subjective fatigue questionnaires and objective ophthalmic measurements were also recorded before and after the task. Statistically significant features were identified through paired t-tests, and fatigue labels were constructed by combining subjective and objective indicators. LightGBM was then employed to rank feature importance by integrating split frequency and information gain into a composite score. The top 12 features were selected and used to train a multilayer perceptron (MLP) for classification. The model achieved an average balanced accuracy of 0.92 and an F1 score of 0.90 under 12-fold cross-validation, demonstrating excellent predictive performance. The high-ranking features spanned four modalities, revealing typical physiological patterns of visual fatigue across ocular behavior, cortical activity, autonomic regulation, and arousal level. These findings validate the effectiveness of multimodal fusion in modeling visual fatigue and provide theoretical and technical support for human factor monitoring and risk mitigation in remote tower environments.

In recent years, with the increasing complexity of air traffic management and the rapid development of automation technology, efficiently and accurately extracting key information from large volumes of air traffic control (ATC) instructions has become essential for ensuring flight safety and improving the efficiency of air traffic control. However, this task is challenging due to the specialized terminology involved and the high real-time requirements for data collection and processing. While existing keyword extraction methods have made some progress, most of them still perform unsatisfactorily on ATC instruction data due to issues such as data irregularities and the lack of domain-specific knowledge. To address these challenges, this paper proposes a Roberta-Attention-BiLSTM-CRF model for keyword extraction from ATC instructions. The RABC model introduces an attention mechanism specifically designed to extract keywords from multi-segment ATC instruction texts. Moreover, the BiLSTM component enhances the model’s ability to capture detailed semantic information within individual sentences during the keyword extraction process. Finally, by integrating a Conditional Random Field (CRF), the model can predict and output multiple keywords in the correct sequence. Experimental results on an ATC instruction dataset demonstrate that the RABC model achieves an accuracy of 89.5% in keyword extraction and a sequence match accuracy of 91.3%, outperforming other models across multiple evaluation metrics. These results validate the effectiveness of the proposed model in extracting keywords from ATC instruction data and demonstrate its potential for advancing automation in air traffic control.

To enhance flight safety and operational efficiency, extracting key actions, flight parameters, and status information from civil aviation flight crew instructions generated during pre-flight and in-flight procedures is crucial. However, such texts are highly condensed and involve complex multi-role interactions, easily leading to entity boundary drift and category misclassification. To address this, this paper proposes a joint key information extraction framework based on a lightweight pre-trained language model (TinyBERT) and a Role-Aware Fusion mechanism, abbreviated as TR-BiGRU-CRF. This framework introduces the Role-Aware Fusion mechanism to resolve semantic ambiguity caused by multi-party interactions, utilizes TinyBERT for semantic representation that balances accuracy and computational efficiency, and employs BiGRU-CRF for robust sequence feature modeling and decoding. Experiments on a flight crew instruction dataset show that the proposed method achieves 92.2% precision, 91.8% recall, a 92.0% F1 score, and an overall prediction accuracy of 92.6%. Compared to the BiGRU-CRF baseline, it significantly improves accuracy, precision, and F1 score by 11.4, 13.3, and 13.5 percentage points, respectively. These results prove that the proposed method effectively mitigates boundary drift and category confusion, providing strong support for flight crew instruction understanding and safety decision-making.