Abstract
Geolocation data is fundamental to businesses relying on vehicles such as logistics and transportation. With the advance of the technology, collecting geolocation data become increasingly accessible and affordable, which raised new opportunities for business intelligence. This paper addresses the application of geolocation data for monitoring logistics processes, namely for detecting vehicle-based operations in real time. A stream of geolocation entries is used for inferring stationary events. Data from an international logistics company is used as a case study, in which operations of loading/unloading of goods are not only identified but also quantified. The results of the case study demonstrate the effectiveness of the solution, showing that logistics operations can be inferred from geolocation data. Further meaningful information may be extracted from these inferred operations using process mining techniques.

Abstract
Geolocation data identifies the geographic location of people or objects, which may unveil the performance of some activity or operation. A good example is, if a vehicle is in a gas station then one may assume that the vehicle is being refuelled. This work aims to obtain vehicle-based operations from geolocation data by analysing the stationary states of vehicles, which may identify some motionless event (e.g. bus line stops and traffic incidents). Ultimately, these operations may be analysed with Process Mining techniques in order to discover the most significant ones and extract process related information. In this work, we studied the application of diverse approaches for detecting vehicle-based operations and identified different operations related to the bus services. The operations were also characterized according the distribution of their events, allowing to identify specific operations characteristics. The public transport network of Rio de Janeiro is used as a case study, which is supported by a real-time data stream of buses geolocations.

Abstract
Subgroup discovery (SD) aims at finding significant subgroups of a given population of individuals characterized by statistically unusual properties of interest. SD on event logs provides insight into particular behaviors of processes, which may be a valuable complement to the traditional process analysis techniques, especially for low -structured processes. This paper proposes a scalable and efficient method to search significant SD rules on frequent sequences of events, exploiting their multidimensional nature. With this method, it is intended to identify significant subsequences of events where the distribution of values of some target aspect is significantly different than the same distribution for the entire event log. A publicly available real -life event log of a Dutch hospital is used as a running example to demonstrate the applicability of our method. The proposed approach was applied on a real -life case study based on the public transport of a medium size European city (Porto, Portugal), for which the event data consists of 133 million smartcard travel validations from buses, trams and trains. The results include a characterization of mobility flows over multiple aspects, as well as the identification of unexpected behaviors in the flow of commuters (public transport). The generated knowledge provided a useful insight into the behavior of travelers, which can be applied at operational, tactical and strategic business levels, enhancing the current view of the transport services to transport authorities and operators.

Abstract
Machine learning algorithms offer the capability to analyze large volumes of real-time data, providing transport authorities with valuable insights into traffic conditions, congestion hotspots, and incident detection from diverse data sources. However, these algorithms face challenges related to data quality and reliability. We conducted a comparative analysis of machine-learning models that can be used to identify and filter transportation content from social media or other sources that can provide small and concise text. The filtrated result can then feed models and/or tools used to improve and automate traffic control, operational management, and tactical management decision-making. We consider factors such as run time, generalization capacity, and performance metrics as criteria to assess their suitability for different decision levels. The analysis is supported by a dataset consisting of Twitter content. The predictions from three groups of algorithms are evaluated: traditional machine learning algorithms (Support Vector Machines, Logistic Regression, and Random Forest), a fine-tuned Google BERT model, and Google BERT models without training (BERT-base and BERT-large). The tests are performed using New York, London, and Melbourne data. The findings of this research aim to assist decision-makers in making informed choices when selecting the most appropriate method to filtrate information subsequently used for models that contribute to different traffic management tasks.

Abstract
Traffic flow prediction is a critical component of intelligent transportation systems. This study introduces a Bidirectional Long Short-Term Memory (Bi-LSTM) neural network for predicting traffic flow. The model utilizes traffic, weather, and holiday data. To evaluate the model's performance, three experiments were assessed: E1, using all available inputs; E2, excluding weather conditions; and E3 excluding holiday information. The model was trained using the previous 3, 12, and 24 h of data to predict traffic flow for the next 12 h, and its performance was compared with a LSTM model. Traffic predictions benefit from having a large and diverse dataset. Bi-LSTM model can capture temporal patterns more effectively than the LSTM. The MAPE value is improved in around 1% when we increase the historical from 3h to 24 h, plus 1% if Bi-LSTM model is used. Better results are obtained when contextual information is provided. These results reinforce the potential that deep learning models have in the prediction of traffic conditions and the impact of a large and varied dataset in the accuracy of these predictions.

Abstract
Background: In many urban areas, 80% to 90% of pollutant emissions are generated by road traffic, particularly from heavy vehicles. With the anticipated surge in e-commerce logistics, the need for effective urban mobility control measures has become urgent, focusing on traffic restrictions and efficient enforcement tools. This work introduces Log-ON, a multi-stakeholder information system designed to facilitate the implementation and management of sustainable traffic restrictions. Methods: The proposed system was developed through extensive literature reviews, expert consultations, and feedback from logistics fleet managers. User-centered mock-ups were created for various stakeholders, including the public, regulatory authorities, logistics operators, and enforcement agencies, ensuring that the system effectively addresses a diverse set of needs. Results: By taking into account a wide range of influencing factors, Log-ON functions as a decision-support tool designed to optimize access restrictions for vehicles, particularly heavy vehicles, in urban environments. Conclusions: Log-ON's adoption promises significant improvements in urban mobility by reducing traffic-related pollution and fostering healthier, cleaner cities. However, traffic restrictions could increase delivery costs, potentially disrupting logistics operations. To address this, the development of new business models for last-mile delivery is essential, ensuring that sustainable traffic management strategies align with the economic challenges faced by logistics providers.