Abstract Understanding human mobility in urban areas is important for transportation, from planning to operations and online control. This paper proposes the concept of user-station attention, which describes the user’s (or user group’s) interest in or dependency on specific stations. The concept contributes to a better understanding of human mobility (e.g., travel purposes) and facilitates downstream applications, such as individual mobility prediction and location recommendation. However, intrinsic unsupervised learning characteristics and untrustworthy observation data make it challenging to estimate the real user-station attention. We introduce the user-station attention inference problem using station visit counts data in public transport and develop a matrix decomposition method capturing simultaneously user similarity and station-station relationships using knowledge graphs. Specifically, it captures the user similarity information from the user-station visit counts matrix. It extracts the stations’ latent representation and hidden relations (activities) between stations to construct the mobility knowledge graph (MKG) from smart card data. We develop a neural network (NN)-based nonlinear decomposition approach to extract the MKG relations capturing the latent spatiotemporal travel dependencies. The case study uses both synthetic and real-world data to validate the proposed approach by comparing it with benchmark models. The results illustrate the significant value of the knowledge graph in contributing to the user-station attention inference. The model with MKG improves the estimation accuracy by 35% in MAE and 16% in RMSE. Also, the model is not sensitive to sparse data provided only positive observations are used.

This paper formulates the car-specific metro train crowding prediction problem based on real-time load data and evaluates the performance of several data-driven prediction methods (lasso, stepwise regression, and boosted tree ensembles). Two variants of the prediction problem are considered: 1) train-centered prediction, focusing on in-vehicle crowding information provision and 2) station-centered prediction focusing on crowding information provision at stations. The methodology is applied to a metro line in Stockholm, Sweden. The prediction accuracy is evaluated with respect to absolute passenger loads and discrete crowding levels. When available, predictions with real-time load data significantly outperform historical averages, with accuracy improvements varying in magnitude across target stations and train cars depending on load variability. The results suggest that the real-time crowding information can be provided sufficiently early to influence travelers' route, train, and car choices, in order to reduce in-vehicle crowding.

Massive data broadcast by GPS-equipped vehicles provide unprecedented opportunities. One of the main tasks in order to optimize our transportation networks is to build data-driven real-time decision support systems. However, the dynamic environments where the networks operate disallow the traditional assumptions required to put in practice many off-the-shelf supervised learning algorithms, such as finite training sets or stationary distributions. In this paper, we propose BRIGHT: a drift-aware supervised learning framework to predict demand quantities. BRIGHT aims to provide accurate predictions for short-term horizons through a creative ensemble of time series analysis methods that handles distinct types of concept drift. By selecting neighborhoods dynamically, BRIGHT reduces the likelihood of overfitting. By ensuring diversity among the base learners, BRIGHT ensures a high reduction of variance while keeping bias stable. Experiments were conducted using three large-scale heterogeneous real-world transportation networks in Porto (Portugal), Shanghai (China), and Stockholm (Sweden), as well as with controlled experiments using synthetic data where multiple distinct drifts were artificially induced. The obtained results illustrate the advantages of BRIGHT in relation to state-of-the-art methods for this task.

The dynamic behavior of urban mobility patterns makes matching taxi supply with demand as one of the biggest challenges in this industry. Recently, the increasing availability of massive broadcast GPS data has encouraged the exploration of this issue under different perspectives. One possible solution is to build a data-driven real-time taxi-dispatching recommender system. However, existing systems are based on strong assumptions such as stationary demand distributions and finite training sets, which make them inadequate for modeling the dynamic nature of the network. In this paper, we propose BRIGHT: a drift-aware supervised learning framework which aims to provide accurate predictions for short-term horizon taxi demand quantities through a creative ensemble of time series analysis methods that handle distinct types of concept drift. A large experimental set-up which includes three real-world transportation networks and a synthetic test-bed with artificially inserted concept drifts, was employed to illustrate the advantages of BRIGHT when compared to S.o.A methods for this problem.

This paper proposes a network travel time prediction methodology based on probe data. The model is intended as a tool for traffic management, trip planning, and online vehicle routing, and is designed to be efficient and scalable in calibration and real-time prediction; flexible to changes in network, data, and model extensions; and robust against noisy and missing data. A multivariate probabilistic principal component analysis (PPCA) model is proposed. Spatio-temporal correlations are inferred from historical data based on MLE and an efficient EM algorithm for handling missing data. Prediction is performed in real time by computing the expected distribution of link travel times in future time intervals, conditional on recent current-day observations. A generalization of the methodology partitions the network and applies a distinct PPCA model to each subnetwork. The methodology is applied to the network of downtown Shenzhen, China, using taxi probe data. The model captures variability over months and weekdays as well as other factors. Prediction with PPCA outperforms k-nearest neighbors prediction for horizons from 15 to 45 min, and a hybrid method of PPCA and local smoothing provides the highest accuracy.