Improving the ability of the urban rail transit system to cope with rainstorm disasters is of great significance to ensure the safe travel of residents. In this study, a model of the hierarchical relationship of the influencing factors is constructed from the resilience perspective, in order to research the action mechanisms of the influencing factors of urban rail transit stations susceptible to rainstorm disaster. Firstly, the concept of resilience and the three attributes (resistance, recovery, and adaptability) are interpreted. Based on the relevant literature, 20 influencing factors are discerned from the 3 attributes of the resilience of urban rail transit stations. Subsequently, an interpretative structural model (ISM) is utilised to analyse the hierarchical relationship among the influencing factors. The key influencing factors of station resilience are screened out using social network analysis (SNA). Combined with ISM and SNA for analysis, the result shows that the key influencing factors are: “Flood prevention monitoring capability”; “Water blocking capacity”; “Flood prevention capital investment”; “Personnel cooperation ability”; “Emergency plan for flood prevention”; “Flood prevention training and drill”; “Publicity and education of flood prevention knowledge”; and “Regional economic development level”. Therefore, according to the critical influencing factors and the action path of the resilience influencing factors, station managers can carry out corresponding flood control work, providing a reference for enhancing the resilience of urban rail transit stations.
Due to outstanding feature extraction ability, neural networks have recently achieved great success in sentiment analysis. However, one of the remaining challenges of sentiment analysis is to model long texts to consider the intrinsic relations between two sentences in the semantic meaning of a document. Moreover, most existing methods are not powerful enough to differentiate the importance of different document features. To address these problems, this paper proposes a new neural network model: AttBiLSTM-2DCNN, which entails two perspectives. First, a two-layer, bidirectional long short-term memory (BiLSTM) network is utilized to obtain the sentiment semantics of a document. The first BiLSTM layer learns the sentiment semantic representation from both directions of a sentence, and the second BiLSTM layer is used to encode the intrinsic relations of sentences into the document matrix representation with a feature dimension and a time-step dimension. Second, a two-dimensional convolutional neural network (2DCNN) is employed to obtain more sentiment dependencies between two sentences. Third, we utilize a two-layer attention mechanism to distinguish the importance of words and sentences in the document. Last, to validate the model, we perform an experiment on two public review datasets that are derived from Yelp2015 and IMDB. Accuracy, F1-Measure, and MSE are used as evaluation metrics. The experimental results show that our model can not only capture sentimental relations but also outperform certain state-of-the-art models.
The Chinese environment is experiencing the “U-Type” course from sharp deterioration to significant improvement. In order to achieve the fundamental improvement of the ecological environment, China has implemented several relevant policies and strategies. Among them, the development of urban rail transit, as an essential measure to improve the ecological environment in China, has attracted more and more attention, but the research on the interactive coercion relationship between rail transit and the ecological environment is minimal. Therefore, this study selected ten cities opening urban rail transit before 2005 in mainland China as research objects and established an urban rail transit and ecological environment comprehensive evaluation index system. Then, the interactive coercing model and coupling coordination model were used, and the dynamic relationship between urban rail transit and the ecological environment was explored. The research results in this study showed that (1) there is an apparent interactive coercion relationship between urban rail transit and the ecological environment, and the evolution trajectory conforms to a double exponential curve. (2) From 2006 to 2019, Wuhan’s ecological environment pressure index showed a continuous downward trend. The ecological environment improved the fastest. The rest of the cities showed a trend of first rising and then falling. (3) The type of coupling coordination degree of urban rail transit and ecological environment showed a changing coordination trend from severe incoordination—slight to incoordination—basic to coordination—good. Beijing has the highest degree of overall coordinated development in urban rail transit and the ecological environment. The results of this study can provide a theoretical reference for the realisation of the virtuous circle development of rail transit and the ecological environment.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.