Search

In high‐frequency transit, providing real‐time crowding information (RTCI) is a potential way to promote passenger satisfaction and reduce negative crowding externalities, by assisting passengers in choosing less crowded vehicles. To make RTCI convincing and reliable, it is necessary to provide predictive RTCI, in which bus passenger load (BPL) prediction is the primary problem. This paper proposes a novel two‐stage BPL prediction method using automatic passenger counting (APC) data. The first stage is to predict short‐term passenger flows at stops based on an adaptive Kalman filter approach. Using the outputs from the first stage as well as other variables directly from APC data, the second stage is to predict BPL based on a support vector regression algorithm. Several methods from the existing literature are used as benchmarks to test the relative performance of the proposed method. An empirical study on bus line 1 in Suzhou, China shows that the proposed method outperforms all the benchmarks, and shows significant superiority over other methods for stops with sharp increases in BPL and for multi‐step ahead prediction. This study contributes to the limited literature on BPL prediction and lays the foundation for providing accurate and reliable predictive RTCI in the future. [ABSTRACT FROM AUTHOR]

As a rapidly expanding type of shared mobility, bike sharing is facing severe challenges of bike over-supply and demand fluctuation in many Chinese cities. In this paper, a large-scale method is developed to determine the minimum fleet size under future demand uncertainty, which is applied in a case study with millions of bike sharing trips in Nanjing. The findings show that if future uncertainty is not considered, more than 12% of trip demands may not be satisfied. Nevertheless, the proposed algorithm for minimizing fleet size based on historical trip data is effective in handling future uncertainty. For a bike sharing system, supplying 14.5% of the original fleet could be sufficient to meet 96.8% of trip demands. Meanwhile, the results suggest a unified platform that integrates multiple companies can significantly reduce the total fleet size by 44.6%. Moreover, in view of the Coronavirus Disease 2019 (COVID-19) pandemic, this paper proposes a contact delay policy that maintains a suitable usage interval, which results in increased bike amount requirements. These findings provide useful insights for improving resource efficiency and operational services in shared mobility applications. [Display omitted] • Our method can minimize the fleet size for millions of trips in large size networks. • Our improved algorithm can handle the uncertainty of future trip demands. • Supplying 14.5% of the original fleet can meet 96.8% of dockless bike sharing trips. • A contact delay policy is proposed and tested for the COVID-19 pandemic response. • Integrating multiple companies into a unified platform can reduce fleet size. [ABSTRACT FROM AUTHOR]