Accurate travel time prediction (TTP) is a significant aspect in the intelligent transportation system (ITS). Travel times of certain road segments explicitly reflect the traffic conditions of those sections. Effective TTP of road segments is instrumental in route planning, traffic control, and traffic management. However, the accuracy of TTP is greatly affected by the intricate topological structure of traffic network and the dynamics of traffic flow over time. This paper develops a TTP method based on the spatial-feature-based hierarchical clustering (SFHC) and deep multi-input gated recurrent unit (DMGRU). The proposed two-stage method is capable of capturing the spatial-temporal features of traffic network. Specifically, the SFHC divides the road segments into several clusters having similar traffic features, and then the clustered data is fed into the DMGRU for TTP. Our experiments conducted on the practical dataset demonstrate that the designed prediction method can achieve the mean absolute percentage error (MAPE) of 3.3109% and mean absolute error (MAE) of 2.5658, which outperform various combinations of baseline clustering algorithms and prediction models.
Improving the capability of geohazard data online analysis and evaluation for geohazard prevention and mitigation is the major developing trend of geohazard information service and relevant research. Making use of the information technologies to solve the technical challenges and difficulties encountered in geohazard big data processing and analysis is important to effectively improve the capacity of geohazard information service. By using the micro-service, one of the advanced information technology, this study proposed an technical solution for the construction of geohazard data online analysis and processing service, which was designed and constructed based on the working mechanism and procedure of the analysis. As an example, the geohazard online susceptibility analysis service was designed and developed. In the proposed technical solution, the online susceptibility analysis service was splitted into multiple operational-independent and also interconnected micro-services for the completion of the analytical process. The developments of each individual micro-service provide support for further revision, upgrade and expansion of the data analysis ultimization or model optimization. The propose of the technical solution further deepens the integration of geohazard research and information technology to improve the level and practical efficiency of geohazard information service leading by the advancement of information technology.
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.