Link prediction to optimize network performance is of great significance in network evolution. Because of the complexity of network systems and the uncertainty of network evolution, it faces many challenges. This paper proposes a new link prediction method based on neural networks trained on scale-free networks as input data, and optimized networks trained by link prediction models as output data. In order to solve the influence of the generalization of the neural network on the experiments, a greedy link pruning strategy is applied. We consider network efficiency and the proposed global network structure reliability as objectives to comprehensively evaluate link prediction performance and the advantages of the neural network method. The experimental results demonstrate that the neural network method generates the optimized networks with better network efficiency and global network structure reliability than the traditional link prediction models.
As the narrative part to extend the accident-related content, text data can help understand the mechanism of accidents, which is always neglected in quantitative accident analysis. This paper presents a novel expert generation model to extract incidents from text reports for accident analysis. By using expert knowledge to complete the text labeling work, this paper uses a supervised text mining method to train the expert generation model. Then, the pre-trained language model is used to train the model for incident and relationship extraction. An application based on text dataset of Beijing metros is implemented to certify the effectiveness of the proposed methods. Two lines in Beijing metro are analyzed and the results of path analysis model show that different mechanism exists in the two lines, indicating that the high-order information extracted from text data is significant for understanding the incident, accident analysis, and accident prevention.