Repositório Comunidade:http://hdl.handle.net/10071/150792026-04-27T22:38:13Z2026-04-27T22:38:13ZReinforcement learning-based adaptive quantum-safe cryptography for DN25-compliant smart environmentsNoetzold, D.Barbosa, J. L. V.Santana, J. F. P.Leithardt, V. R. Q.http://hdl.handle.net/10071/370112026-04-23T15:16:22Z2026-01-01T00:00:00ZTítulo próprio: Reinforcement learning-based adaptive quantum-safe cryptography for DN25-compliant smart environments
Autoria: Noetzold, D.; Barbosa, J. L. V.; Santana, J. F. P.; Leithardt, V. R. Q.
Resumo: The emergence of quantum computing challenges traditional security mechanisms, particularly in heterogeneous and resource-constrained IoT and smart environments that must satisfy DN25 requirements. This work introduces a reinforcement learning-driven model for the adaptive selection and orchestration of cryptographic algorithms. Acting as an intelligent decision layer, the system observes contextual, network, and operational metrics to recommend or enforce configurations combining classical schemes, post-quantum cryptography, and Quantum Key Distribution when available. The selection problem is formulated as a Markov Decision Process with state and action spaces aligned with protocol control flows and is embedded into a security middleware with negotiation and fallback mechanisms to ensure interoperability and policy compliance without modifying application logic. Experimental results demonstrate that the model dynamically adjusts key lengths, algorithm families, and security policies according to risk and resource conditions, increasing post-quantum cryptography and Quantum Key Distribution usage by up to 33.4% and 23.9% in high-risk scenarios while favoring low-latency classical or hybrid options for less critical traffic. The system achieves success rates above 78% while maintaining stable latency and resource usage during extended operation.2026-01-01T00:00:00ZA systematic literature review on Web3 applications in trucking logistics: Impacts and emerging trends in logistics 5.0Čale, D.Ferreira, J. C.Madureira, A.Coutinho, C.http://hdl.handle.net/10071/369642026-04-21T10:09:43Z2026-01-01T00:00:00ZTítulo próprio: A systematic literature review on Web3 applications in trucking logistics: Impacts and emerging trends in logistics 5.0
Autoria: Čale, D.; Ferreira, J. C.; Madureira, A.; Coutinho, C.
Resumo: Web3 technologies, representing the next generation of a decentralised and user-centric Internet, offer innovative solutions to enhance adaptability, sustainability, and resilience in logistics systems aligned with the principles of Logistics 5.0. This study conducts a Systematic Literature Review (SLR) following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) methodology, analysing peer-reviewed journal articles published between 2018 and 2024 and retrieved from Scopus, Web of Science Core Collection, IEEE Xplore, and ACM Digital Library. The review specifically focuses on trucking logistics, a sector characterised by high fossil-fuel dependency, operational fragmentation, and significant environmental impact. The findings reveal that Artificial Intelligence and Internet of Things technologies dominate current implementations, mainly supporting fleet management, route optimisation, accident prevention, and risk assessment. In contrast, blockchain applications remain limited, and metaverse-based solutions are largely exploratory and confined to training scenarios. Key research gaps include the scarcity of integrated Web3 solutions, the limited consideration of human-centric Logistics 5.0 dimensions, and the lack of large-scale empirical validation in real-world trucking operations. Based on the analysis, this paper proposes a conceptual framework that maps Web3 technologies to trucking logistics areas, investment priorities, and Logistics 5.0 objectives, offering actionable guidance for Logistics Service Providers transitioning from Logistics 4.0 to Logistics 5.0.2026-01-01T00:00:00ZNetwork algorithm to model automotive supply chain structureBarros, J.Turner, C.http://hdl.handle.net/10071/369132026-04-15T14:57:44Z2026-01-01T00:00:00ZTítulo próprio: Network algorithm to model automotive supply chain structure
Autoria: Barros, J.; Turner, C.
Resumo: A network algorithm that models the structure of automotive supply chains, compiled from a proprietary database, is presented. An initial structural analysis was conducted using key performance indicators, including average path length, clustering coefficient, and degree distribution, to assess network configurations. The networks were then partitioned into subnetworks, with an emphasis on reflecting the operational dynamics of supply chain activities. Regression analysis was applied to each subnetwork, using the number of vertices as the independent variable, to develop an algorithm for generating synthetic networks. These synthetic constructs serve as benchmarks for the automotive sector and have shown a strong average correlation (0.94) with the structure of actual supply networks. This methodological contribution provides tools for analysing and optimising supply chain structures that underpin automotive engineering and manufacturing, ensuring robustness and efficiency in vehicle production systems. The prevalence of tree-like structures within supply networks challenge conventional beliefs regarding the complexity of automotive supply chains and prompts further investigation into the determinants of their resilience.2026-01-01T00:00:00ZApplication of indirect methods to optimal control problems in epidemiologyCaio, P.Silva, C. J.http://hdl.handle.net/10071/368132026-04-23T04:00:28Z2025-01-01T00:00:00ZTítulo próprio: Application of indirect methods to optimal control problems in epidemiology
Autoria: Caio, P.; Silva, C. J.
Editor: Aguiar, Antonio Pedro; Malonek, Paula Rocha; Pinto, Vítor Hugo; Fontes, Fernando A. C. C.; Chertovskih, Roman
Resumo: Currently most of the numerical resolution of optimal control problems is done using direct methods where the increase accuracy of indirect methods is overshadowed by the necessary analytical derivation required beforehand. With recent developments from the control-toolbox ecosystem team the application of indirect methods as become more streamline enabling a wider range of problems to be solved, like, for example, optimal control problems applied to the transmission of infectious diseases. In this work, we aim to extend the application of indirect methods to optimal control problems applied to epidemiological models, using the control-toolbox2025-01-01T00:00:00Z