Low-income commuters have distinct activity-travel characteristics from non-low-income commuters. This study examines low-income commuters’ activity-travel pattern for a better understanding the mechanism of activity participation and travel behaviour based on the travel survey data collected in Nanjing, China. Structural equations modelling (SEM) methodology was adopted to estimate the complex relationships among socio-demographics, accessibility, activity participation, trip generation and mode choice. Results show that strong relationships do exist among socio-demographics, activity engagement and travel behavior. Specifically, we can understand travel behaviour better by including activity participation endogenously in the model. Furthermore, it allows us to better forecast how increasing any one type of activity will affect demand for other activities, as well as trip generation and mode choice. Lastly, the results reveal the effects of accessibility variables on activity participation and travel behaviour in which population density measure has more ubiquitous effects. Findings in this study might provide insightful policy implications for improving the travel environment of the low-income commuters.

Integration between bike sharing and rail transit provides users with a more flexible travel pattern in an effort to address the “first/last mile” problem. This study aims to examine the determinants influencing the ridership of station-based bike sharing (SBBS) and free-floating bike sharing (FFBS) at rail transit stations. The empirical analysis is based on user transaction records of two bike sharing systems in Nanjing, China. We first apply the k-means cluster method to classify rail transit stations into five types according to the temporal profiles of bike sharing usage for rail transit access. Later, ordinary least squares (OLS) and partial least squares (PLS) regression models are developed respectively by differentiating SBBS and FFBS. Compared with the OLS models, PLS models could address the issue of multi-collinearity and generally have better interpretation abilities. The PLS results reveal that the usage of SBBS for rail transit access shares similarities with FFBS. For example, both of them are positively influenced by population density and the number of restaurants. Meanwhile, different types of rail transit stations exhibit different impacts on the ridership of the two bike sharing systems. Our results show that there exists a substitution effect for rail transit access between two bike sharing systems, that is, SBBS may be more frequently used for commuting trips than FFBS. The findings of this study provide a better understanding of the impact of various factors on the SBBS and FFBS ridership at rail transit stations, thereby helping to promote the integration of rail transit and bike sharing systems.

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.

Dockless bike‐sharing (DBS) is a novel and prevalent bike‐sharing system without stations or docks. DBS has the advantages of convenience and real‐time positioning, whereas it brings about some problems such as bike over‐supply, disordered parking, and inefficient rebalancing. Forecasting usage and bike distribution are critical in the rebalancing operation for maintaining DBS inventory. By dividing the virtual stations through K ‐means clustering and processing the four‐week Mobike journey data of Nanjing, China, the data of usage and bike count in the 4000 virtual stations are identified. Random forest (RF) is developed to predict the real‐time passenger departure, passenger arrival and bike count in the virtual stations. The operation analyses indicate that there is a positive correlation between bike count and usage. RF provides accurate predictions of usage and bike distribution, and almost outperforms five benchmark methods. Forecasting bike distribution is more challenging than forecasting usage because of the volatility of many factors. The results also suggest that bike distribution forecasting based on the usage gap prediction is better than that based on the departure and arrival prediction. This study can help DBS companies in dynamically rebalancing bikes from over‐supply regions to over‐demand regions in a better way.