Abstract
Fleet tracking technology collects real-time information about geolocation of vehicles as well as driving-related data. This information is typically used for location monitoring as well as for analysis of routes, vehicles and drivers. From an operational point of view, the geolocation simply identifies the state of a vehicle in terms of positioning and navigation. From a management point of view, the geolocation may be used to infer the state of a vehicle in terms of process (e.g., driving, fueling, maintenance, or lunch break). Meaningful information may be extracted from these inferred states using process mining. An innovative methodology for inferring process states from geolocation data is proposed in this paper. Also, it is presented the potential of applying process mining techniques on geolocation data for process discovery. © 2020 The Authors. Published by Elsevier B.V.

Abstract
This work apply a deep learning artificial neural network model-the Multilayer Perceptron- A s a regression model to estimate the demand of bus passengers. Transit bus ridership and weather conditions were collected over a year from a medium-size European metropolitan area and linked under the assumption: Individuals choose the travel mode based on the weather conditions that are observed during (a) the departure hour, (b) the hour before or (c) two hours prior to the travel start. The transit ridership data were also labelled according to the hour of the day, day of the week, month, and whether there was a strike and/or holiday or not. The results show that the prediction error of the model decrease by ~9% when the weather conditions observed two hours before travel start is taken into account. The model sensitivity analyses reveals that the worst performance is obtained for a strike day of a weekday in spring (typically Wednesdays or Thursdays). © 2020 Tânia Fontes et al., published by Sciendo.

Abstract
Accessibility is one of the key measures of urban transportation planning, which quantify how easy is the access to a facility. Public transport accessibility concerns of the access level of geographical locations to public transport. In this paper, accessibility is used as an indicator to estimate social exclusion based on the maximum distance that someone has to walk to reach the public transport. The concept of the 6-minute walking distance (6MWD) is applied to measure accurately the walking ability for different groups of the population. A real life case study is conducted to get insight into the transportation network of the Porto Metropolitan Area, Portugal. For this purpose, geographic, demographic and infrastructure data were collected and integrated. Also, webservices are used to measure walking distances between locations. The results of this study allowed to characterize regions by different levels of accessibility, providing insight into the social exclusion in public transport. This assessment is used not only to identify inequities but also to get an overview of the service quality of public transport. © 2020 The Authors. Published by ELSEVIER B.V.

Abstract
Urban population is increasing fast. This is creating new challenges to public transport systems since some groups of citizens as elderly people may have sensory, cognitive or motor impairments that need to be addressed. This work explores the potential of a Demand Responsive Transport (DRT) system for people with reduced mobility in an urban environment. For this purpose, the Dial-A-Ride Problem (DARP) was implemented using a multivariable minimisation approach. In this approach, an Assigning Request to Vehicles (ARV) algorithm is used to obtain an initial solution. Then a Multi-Objective Tabu Search Algorithm (MOTSA) is applied to the initial solution to search for the non-dominated solution (optimisation phase). In this optimisation phase, the total travelled distance, the deadheading distance and the number of vehicles were minimised. The performance of the model was computed combining different parameters' values of the number of requests, boarding time for each user, the number of seats in each vehicle, vehicle's speed, the total number of iterations, and candidate threshold number (the algorithm's parameter). The computational results found a strong positive correlation between the number of requests and the: total travelled distance (rs = 0.977, p-value<0.001) and the number of vehicles (rs =0.883, p-value<0.001); and a low positive correlation between the number of requests and the optimised total travelled distance (rs =0.331, p-value<0.001) and the optimised number of vehicles (rs =0.340, p-value<0.001). © 2020 The Authors. Published by ELSEVIER B.V.

Abstract
Weather conditions have a major impact on citizens’ daily mobility. Depending on weather conditions trips may be delayed, demand may be changed as well as the modal shift. These variations have a major impact on the use and operation of public transport, particularly in transport systems that operate close to capacity. However, the influence of weather conditions on transport demand is difficult to predict and quantify. For this purpose, an artificial neural network model – the Multilayer Perceptron – is used as a regression model to estimate the demand of urban public transport buses based on weather conditions. Transit bus ridership and weather conditions were collected along a year from a medium-size European metropolitan area (Oporto, Portugal) and linked under the assumption that individuals choose the travel mode based on the weather conditions that are observed during the departure hour, the hour before and two hours before. The transit ridership data were also labelled according to the hour, day of the week, month, and whether there was a strike and/or holiday or not. The results demonstrate that it is possible to predict the demand of public transport buses using the weather conditions observed two hours before with low error for the entire network (MAE = 143 and RMSE = 322). The use of weather conditions allow to decreases the error of the prediction by ~8% for the entire network. © 2021, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG.

Abstract
Public opinion is nowadays a valuable data source for many sectors. In this study, we analysed the transportation sector using messages extracted from Twitter. Contrasting with the traditional surveying methods that are high-cost and inefficient used in transportation sector, social media are popular sources of crowdsensing. This work used BERT embeddings, an unsupervised pre-trained model released in 2018, to classify travel-related terms using tweets collected from three distinct cities: New York, London, and Melbourne. In order to understand if a simple model can have a good performance, we used unigrams. A list of 24 travel-related words was used to classify the messages. Popular words are train, walk, car, station, street, and avenue. Between 3% to 5% of all messages are classified as traffic-related, while along the typical working hours of the day the values is around 5-6%. A high model performance was obtained, with precision and accuracy higher than 0.80 and 0.90, respectively. The results are consistent for all the three cities assessed. © 2021 IEEE.