An Integrated Perception Model for Predicting and Analyzing Urban Rail Transit Emergencies Based on Unstructured Data

The accurate prediction and analysis of emergencies in Urban Rail Transit Systems (URTS) are essential for the development of effective early warning and prevention mechanisms. This study presents an integrated perception model designed to predict emergencies and analyze their causes based on historical unstructured emergency data. To address issues related to data structuredness and missing values, we employed label encoding and an Elastic Net Regularization-based Generative Adversarial Interpolation Network (ER-GAIN) for data structuring and imputation. Additionally, to mitigate the impact of imbalanced data on the predictive performance of emergencies, we introduced an Adaptive Boosting Ensemble Model (AdaBoost) to forecast the key features of emergencies, including event types and levels. We also utilized Information Gain (IG) to analyze and rank the causes of various significant emergencies. Experimental results indicate that, compared to baseline data imputation models, ER-GAIN improved the prediction accuracy of key emergency features by 3.67% and 3.78%, respectively. Furthermore, AdaBoost enhanced the accuracy by over 4.34% and 3.25% compared to baseline predictive models. Through causation analysis, we identified the critical causes of train operation and fire incidents. The findings of this research will contribute to the establishment of early warning and prevention mechanisms for emergencies in URTS, potentially leading to safer and more reliable URTS operations.