Search

This study introduces a hybrid Latent Dirichlet Allocation (LDA) model to excavate hidden crash patterns from the large-scale crash dataset. External semantic descriptions have been attached to raw GPS coordinates of crash events. The K-means clustering algorithm is first applied to determine land use characteristics of crash points by grouping surrounding Points of Interests (POIs). Then, each crash record is transformed into a formalized label consisting of land use, Annual Average Daily Traffic (AADT), and time stamps, allowing the analysis of massive traffic crash data as document corpora. Finally, a data-driven modeling approach based on the LDA is conducted to discover hidden crash patterns from traffic crash records combining the external semantic information. The approach is verified using motor vehicle crash data in Manhattan County of New York City. The novel semantic analysis of crash records provides an effective method to investigate the hidden information in traffic crashes. Identifying spatial-temporal patterns on motor vehicle crashes would provide insights into underlying traffic behaviors for intelligent policy-making and resource allocation. [ABSTRACT FROM AUTHOR]

The primary objective of this study was to investigate the bikesharing travel patterns and trip purposes by combining smart card data and online point of interests (POIs). A large-scale smart card trip data was collected from the bikesharing system in New York City. The POIs surrounding each station were obtained from Google Places API. K-means clustering analysis was first applied to divide bikesharing stations into five types based on their surrounding POIs. The Latent Dirichlet Allocation (LDA) analysis was then conducted to discover the hidden bikesharing travel patterns and trip purposes using the identified station types and smart card data. The performance of the LDA models with and without POI data was compared to identify whether the POI data should be used. Finally, a practical application of the proposed methods in bikesharing planning and operation was discussed. The result of comparative analyses verified the importance of POI data in exploring bikesharing travel patterns and trip purposes. The results of LDA model showed that the most prevalent travel purpose in New York City is taking public bike for eating, followed by shopping and transferring to other public transit systems. In addition, the result also suggested that people living around the bikesharing stations are more likely to transfer to other commuting tools on the morning peak and ride for home after work. The proposed methods can be used to provide useful guidance and suggestions for transportation agency to develop strategies and regulation that aim at improving the operations of bikesharing systems. [ABSTRACT FROM AUTHOR]