An Open Access Journal
Study | Objective | Type of data | Methodology |
---|---|---|---|
Ni et al. [44] | Station flows prediction | Twitter data and turnstile usage | Linear regression and seasonal autoregressive integrated moving average |
Xue et al. [45] | Onboard passenger prediction | Passenger boarding data | Algorithm based on interactive multiple model (IMM) filter and different types of moving averages |
Zhang et al. [46] | Onboard passenger estimation and prediction | Smart card data and GPS data | Extended Kalman filter |
Liu et al. [47] | Station flows prediction | Passenger measured flow | Deep learning |
Liu & Chen [48] | Station flows prediction | Passenger flow data from automated passenger counting (APC) | Deep learning |
Wang et al. [49] | Incoming flows prediction at station | Automated fare collection (AFC) data | Dynamic spatiotemporal hypergraph neural networks |
Baek and Sohn [50] | Bus stop flows and onboard passenger prediction | Smart card data | Deep learning |
Samaras et al. [51] | Onboard passenger prediction | Automated vehicle location (AVL) and APC data | Several machine learning algorithms |
Ding et al. [52] | Onboard passenger prediction | AFC data | Gradient boosting decision trees |
Vandewiele et al. [53] | Onboard passenger prediction | Crowd-sourcing data | Neural networks and XGBoost |
Gallo et al. [54] | Onboard passenger prediction | APC data | Linear regression and LightGBM |
Jenelius [55] | Onboard passenger prediction | Weight measurements in the air suspension system of the train cars | Lasso and stepwise regression, boosted trees ensembles |
Wiecek et al. [56] | Onboard passenger prediction | APC data | Markov chains |
This paper | Station flows prediction | AFC data | Markov chain Monte Carlo |