Search

• A new concept to understand the mobility and location features of subway stations. • Transplant Language Processing to understand subway stations as compound words. • Obtain mobility and location semantics from neural net and affinity propagation. • Interpretsemantic results in an urban planning aspect. Rapid urbanization and modern civilization require sound integration with public transportation systems. In the same time, the volume and complexity of public transportation network are increasing, making it harder to understand the public transportation dynamics. As a first step, understanding the similarity among subway stations is imperative. In this paper, we proposed a semantic framework inspired from natural language processing (NLP) to interpret subway stations as compound words. Specifically, we transplanted context and literal meaning of compound words into mobility and location attributes of stations. Using smart card data, we trained stacked autoencoders (SAE) with designed flow matrices as an embedding method to learn the mobility attributes. Subsequently, to discover the location attributes, we have applied affinity propagation clustering to classify 9 point of interest (POI) categories. Combined with urban planning knowledge, we manage to comprehend the land use meanings of 9 POI clusters. The location semantics is chosen from those categories reflecting its urban land use pattern. By choose meaningful combination of mobility and location semantics for stations' similarity case studies, we summarized potential applications of this semantic framework. [ABSTRACT FROM AUTHOR]

Traffic crashes present substantial challenges to human safety and socio-economic development in urban areas. Developing a reliable and responsible traffic crash prediction model is crucial to address growing public safety concerns and improve the safety of urban mobility systems. Traditional methods face limitations at fine spatiotemporal scales due to the sporadic nature of high-risk crashes and the predominance of non-crash characteristics. Furthermore, while most current models show promising occurrence prediction, they overlook the uncertainties arising from the inherent nature of crashes, and then fail to adequately map the hierarchical ranking of crash risk values for more precise insights. To address these issues, we introduce the S patio t emporal Z ero- I nflated T wee d ie G raph N eural N etworks (STZITD-GNN), the first uncertainty-aware probabilistic graph deep learning model in road-level daily-basis traffic crash prediction for multi-steps. Our model combines the interpretability of the statistical Tweedie family with the predictive power of graph neural networks, excelling in predicting a comprehensive range of crash risks. The decoder employs a compound Tweedie model, handling the non-Gaussian distribution inherent in crash data, with a zero-inflated component for accurately identifying non-crash cases and low-risk roads. The model accurately predicts and differentiates between high-risk, low-risk, and no-risk scenarios, providing a holistic view of road safety that accounts for the full spectrum of probability and severity of crashes. Empirical tests using real-world traffic data from London, UK, demonstrate that the STZITD-GNN surpasses other baseline models across multiple benchmarks, including a reduction in regression error of up to 34.60% in point estimation metrics and an improvement of above 47% in interval-based uncertainty metrics. • Introduces a novel probabilistic graph deep learning model (STZITD-GNN) for road-level crash risk assessment. • Combines graph neural networks with a four-parameter statistical distribution to effectively handle zero-inflated traffic crash data. • Demonstrates superior performance in multi-step road-level crash prediction for both point estimation and uncertainty quantification. • Exhibits stable performance in multi-step predictions and provides insights on deep learning model uncertainties. [ABSTRACT FROM AUTHOR]