Abstract
As cities grow and sustainability becomes a key driver of urban policy, active modes of transport such as walking and cycling are increasingly promoted. However, current route planning applications rarely consider factors beyond time and distance. This paper presents the design and evaluation of a mobile application prototype that supports multicriteria route planning for active transport modes. The proposed solution incorporates user-defined weights for dimensions such as safety, comfort, accessibility, and environmental quality. To ensure adaptability and up-to-date information, the study also explores the feasibility of crowdsourcing as a complementary data source. A mixed-method approach was followed, including literature review, user surveys (n=242), interface prototyping, and usability testing with real users. The results demonstrate strong user interest in contributing to data updates, especially when motivated by non-monetary incentives such as gamified rankings. The final prototype was positively evaluated for usability and interface quality. This research confirms the potential of user-centered, crowdsourcing-enhanced route planning to improve the experience of active mobility users and support sustainable urban mobility goals. Copyright © 2025. Published by Elsevier B.V.

Abstract
Urban mobility in large cities faces increasing pressure due to population growth and congestion. Automated Fare Collection (AFC) systems offer a rich source of data for understanding public transport usage and informing data-driven improvements. This paper presents a case study in Fortaleza, Brazil, where we explore AFC smart card data to predict users’ next bus trips and travel volume. We develop a machine learning pipeline combining feature engineering and classification/regression models. A comparative evaluation of algorithms, including Random Forest, XGBoost, and Support Vector Machines, shows that decision-tree-based models achieve the best performance, particularly in handling noisy and imbalanced data. Our approach considers both user-level predictions and cluster-based analyses to improve model generalizability across user types. The results demonstrate the potential of AFC data to enhance transit planning, reduce overcrowding, and personalize mobility services. This study contributes to the growing body of research on smart mobility analytics in developing urban contexts. Copyright © 2025. Published by Elsevier B.V.

Abstract
The rapid expansion of information production presents a growing challenge in identifying high-quality, relevant studies necessary for a solid research foundation in Systematic Literature Reviews (SLR). Traditional methods often struggle with academic publications' increasing volume and dynamic nature, necessitating more efficient analytical tools. Artificial Intelligence (AI) and Natural Language Processing (NLP) offer significant potential in streamlining literature reviews through advanced analytical techniques. This work explores how AI and NLP tools enhance article screening and information synthesis, particularly through Retrieval-Augmented Generation (RAG). While large language models demonstrate strong text generation capabilities, they frequently lack comprehensive contextual understanding. RAG addresses this limitation by retrieving precise information, enabling more accurate and context-aware literature reviews. A novel approach is proposed that transforms the traditionally linear SLR workflow into a dynamic, continuously updatable bundle- a unified framework that integrates search, screening, data extraction, and synthesis. This approach is inspired by the RAPTOR Python package, which recursively embeds, clusters, and summarizes text to construct a hierarchical knowledge structure. The adapted model, DSA.VE, extends RAPTOR's capabilities to improve contextual summarization and structured synthesis, enhancing its applicability in multidisciplinary research fields. To demonstrate the effectiveness of this approach, a case study examines the potential of methanol as an alternative fuel in transport systems. The results highlight how AI-driven methodologies facilitate large-scale literature synthesis and knowledge integration. By leveraging AI, this work contributes to developing more efficient, systematic, and scalable literature review processes, addressing a critical challenge in modern research.

Abstract
Car sharing, car clubs and short-term rentals could support the transition toward net zero but their success depends on them being financially sustainable for service providers and attractive to end users. Dynamic pricing could support this by incentivizing users while balancing supply and demand. We describe the usage of a round trip car sharing fleet by a continuous time Markov chain model, which reduces to a multi-server queuing model where hire duration is assumed independent of the hourly rental price. We present analytical and simulation optimization models that allow the development of dynamic pricing strategies for round trip car sharing systems; in particular identifying the optimal hourly rental price. The analytical tractability of the queuing model enables fast optimization to maximize expected hourly revenue for either a single fare system or a system where the fare depends on the number of cars on hire, while accounting for stochasticity in customer arrival times and durations of hire. Simulation optimization is used to optimize prices where the fare depends on the time of day or hire duration depends on price. We present optimal prices for a given customer population and show how the expected revenue and car availability depend on the customer arrival rate, willingness-to-pay distribution, dependence of the hire duration on price, and size of the customer population. The results provide optimal strategies for pricing of car sharing and inform strategic managerial decisions such as whether to use time-or state-dependent pricing and optimizing the fleet size.

Abstract
Effective warehouse management plays a pivotal role in optimizing supply chain performance, particularly in high-demand, time-sensitive environments. This study introduces a simulation-based decision support system designed to improve the management of Picking-By-Line (PBL) operations in cross-docking distribution centres. Developed in FlexSim and calibrated with empirical data from an industrial case study, the model replicates real-world warehouse conditions and is validated against observed operational performance. The tool supports warehouse managers in evaluating and comparing operational strategies, such as dynamic storage allocation policies and picker routing constraints, with the goal of reducing operator travel distances, mitigating congestion, and enhancing overall efficiency. A key contribution of this work is the integration of congestion-sensitive performance indicators that allow for a detailed analysis of the trade-offs between travel efficiency and localized congestion-an aspect often overlooked in traditional optimization methods. This study demonstrates the value of simulation as a scalable and realistic decision-support tool for optimizing PBL operations in complex and variable environments where human movement is a major cost and performance driver. The proposed tool bridges the gap between theoretical modelling and practical implementation, offering actionable insights for warehouse layout, space utilization, and resource allocation.

Abstract
This paper introduces PRISMA, a hybrid multi-agent Deep Reinforcement Learning (DRL) framework for solving the Flexible Job-shop Scheduling Problem (FJSP). It uses Constraint Programming (CP) solutions to pretrain decentralized policies and to guide exploration during training. Although DRL can generate fast solutions for large combinatorial problems, it often fails to match the quality of optimization methods, motivating the integration with hybrid frameworks. The growing interest in embedding domain knowledge into learning algorithms has produced several hybrid formulations, yet their potential remains underexplored, particularly in multi-agent settings. PRISMA combines supervised and reinforcement learning within a multi-agent framework, where CP solutions are used to (i) learn expert decisions through imitation learning, and (ii) train an auxiliary network that guides DRL training via reward shaping. A shared graph network is adopted for transferring system-level knowledge into machine-level observations, enabling fast and consistent inference from enriched local embed-dings. To the best of our knowledge, PRISMA introduces the first expert-derived guidance mechanism for the FJSP and is among the earliest to apply imitation learning within a multi-agent formulation. By combining both modules, it strengthens the bridge between optimization and learning-based methods, where such dual integrations remain scarce. Experimental results show faster convergence and higher solution quality than state-ofthe-art DRL models. PRISMA achieves an average optimality gap of 6.74%, corresponding to a 50% relative improvement over the single-agent baseline, while reducing inference time. These findings reinforce the value of merging optimization accuracy with the flexibility of multi-agent DRL for efficient scheduling.