https://hdl.handle.net/10259/8984 2026-06-29T08:15:10Z 2026-06-29T08:15:10Z Martin Reizabal, Sergio Caballero Quiroga, Adrian Gil Arroyo, Beatriz Basurto Hornillos, Nuño Ruiz González, Rubén https://hdl.handle.net/10259/11860 2026-06-19T05:15:47Z 2026-03-01T00:00:00Z

Transformer-based classification of IoT network traffic with flow-to-window aggregation Martin Reizabal, Sergio; Caballero Quiroga, Adrian; Gil Arroyo, Beatriz; Basurto Hornillos, Nuño; Ruiz González, Rubén The explosive growth of the IoT has led to an increasingly complex and heterogeneous network traffic, posing major challenges for intrusion detection. Most existing machine learning and deep learning approaches model network traffic at the level of individual flows, which limits their ability to capture contextual relationships among concurrent communications. This paper introduces a Transformer-based framework for IoT intrusion detection that aggregates network flows into fixed-duration windows and treats each flow as a token within the input sequence. The self-attention mechanism captures contextual relationships among concurrent flows, enabling effective modeling of temporal dependencies without recurrence. Experiments conducted on the CICIoT2023 dataset show that the proposed model achieves a weighted F1-score of 97.9% and a macro ROC–AUC of 99.6% under temporally blocked cross-validation, while maintaining high computational efficiency. These results demonstrate that flow-to-window aggregation combined with self-attention provides a robust and scalable foundation for IoT network security, suitable for deployment in edge and smart-home environments.

2026-03-01T00:00:00Z Gorakifard, Mohsen Sierra García, Jesús Enrique Kian Far, Ehsan https://hdl.handle.net/10259/11627 2026-05-15T06:48:33Z 2026-04-01T00:00:00Z

Polymer extrusion processes in tire manufacturing: a systematic review and bibliometric analysis Gorakifard, Mohsen; Sierra García, Jesús Enrique; Kian Far, Ehsan Tire extrusion is a thermo-mechanical process in advanced tire manufacturing in which compound rheology, die/tooling design, and operating history jointly govern dimensional accuracy, stability, scrap, and downstream performance. This study provides a systematic review and bibliometric analysis of tire-extrusion research published between 2000 and early 2025 using an integrated Scopus–Web of Science corpus enriched with OpenAlex, CrossRef, and OpenCitations, complemented by automated keyword completion (YAKE) and cited-reference completion. We map production and collaboration patterns and reveal conceptual and intellectual structures using co-word/thematic analysis, thematic evolution, co-citation networks, and Reference Publication Year Spectroscopy (RPYS). To mitigate terminology-driven topic drift and enable engineering-centred interpretation, we introduce a technology-depth sensitivity (scope-control) layer that separates a broad tire-related corpus from nested, technology-explicit extrusion cores and organizes evidence through non-exclusive tagging by engineering degrees of freedom (rheology/constitutive behaviour; tooling/flow/die engineering; extrusion hardware/process window; simulation/CAE; monitoring/control). Results show that the broad corpus is dominated by materials/circular-economy themes, whereas the technology-explicit cores reveal a distinct process-engineering and CAE stream centred on die design, flow balancing, constitutive modelling, and simulation-supported optimisation. Finally, we translate these findings into actionable industrial levers and KPI-level implications for tire-profile extrusion/co-extrusion, including gauge stability, interface integrity, thermal hotspots/scorch risk, and reduced die-qualification time.

2026-04-01T00:00:00Z Bayona Blanco, Eduardo Sierra García, Jesús Enrique Santos Peñas, Matilde https://hdl.handle.net/10259/11615 2026-05-14T12:06:58Z 2025-03-01T00:00:00Z

Improving Safety and Efficiency of Industrial Vehicles by Bio‐Inspired Algorithms Bayona Blanco, Eduardo; Sierra García, Jesús Enrique; Santos Peñas, Matilde In the context of industrial automation, optimising automated guided vehicle (AGV) trajectories is crucial for enhancing op-erational efficiency and safety. They must travel in crowded work areas and cross narrow corridors with strict safety and timerequirements. Bio-inspired optimization algorithms have emerged as a promising approach to deal with complex optimiza-tion scenarios. Thus, this paper explores the ability of three novel bio-inspired algorithms: the Bat Algorithm (BA), the WhaleOptimization Algorithm (WOA) and the Gazelle Optimization Algorithm (GOA); to optimise the AGV path planning in complexenvironments. To do it, a new optimization strategy is described: the AGV trajectory is based on clothoid curves and a specialisedpiece-wise fitness function which prioritises safety and efficiency is designed. Simulation experiments were conducted acrossdifferent occupancy maps to evaluate the performance of each algorithm. WOA demonstrates faster optimization providingsuitable safety solutions 4 times faster than GOA. Meanwhile, GOA gives solutions with better safety metrics but demands morecomputational time. The study highlights the potential of bio-inspired approaches for AGV trajectory optimisation and suggestsavenues for future research, including hybrid algorithm development.

2025-03-01T00:00:00Z Dakkach, Mohamed Rubio Pérez, Gabriel Alaoui, Fatima E. M. Muñoz Rujas, Natalia Aguilar Romero, Fernando Montero García, Eduardo https://hdl.handle.net/10259/11457 2026-03-03T01:05:34Z 2020-10-01T00:00:00Z

High-Pressure Volumetric Properties of the Binary Mixtures (Di-isopropyl Ether + n-Heptane or Methylcyclohexane) Dakkach, Mohamed; Rubio Pérez, Gabriel; Alaoui, Fatima E. M.; Muñoz Rujas, Natalia; Aguilar Romero, Fernando; Montero García, Eduardo This work reports the experimental density data for the binary mixtures of n-heptane or methylcyclohexane + di-isopropyl ether, measured over the full composition range between 0.1 and 140 MPa, and for temperatures from 298.15 to 393.15 K, by means of a vibrating tube densitometer calibrated with an uncertainty of 0.0007 g·cm–3. Then, the experimental density data were fitted using a Tait-like equation to derive mixing thermodynamic coefficients, including the isobaric expansivity and isothermal compressibility. Finally, the excess volumes of the abovementioned binary mixtures were calculated, and their nonideal behavior was investigated.

2020-10-01T00:00:00Z