https://hdl.handle.net/11000/30412 2026-07-16T23:46:13Z 2026-07-16T23:46:13Z Martínez-Rach, Miguel Ruiz-Atencia, Javier López-Granado, Otoniel Pérez-Malumbres, Manuel https://hdl.handle.net/11000/40186 2026-07-14T01:04:11Z 2026-07-13T17:33:55Z

Título : Classification algorithm analysis for texture detection in block-based hybrid video coding Autor : Martínez-Rach, Miguel; Ruiz-Atencia, Javier; López-Granado, Otoniel; Pérez-Malumbres, Manuel Resumen : This study presents a comprehensive comparison of various supervised classification algorithms for texture detection in the context of block-based hybrid video coding. To accomplish this, a dataset of images extracted directly from video encoder block partitions was created and manually classified according to their texture levels. The study utilizes the Mean Directional Variance (MDV) algorithm to extract orientation information from each block in the form of average variances for specific rational slopes. This vector of variances is then processed to obtain a set of descriptive statistics that serve as input elements for training and evaluating four popular supervised learning models: Decision Tree (DT), Random Forest (RF), Support Vector Machine (SVM), and Supervised Neural Networks (SNN). The objective is to identify the most effective algorithm for accurately classifying texture levels and utilizing this information in perceptual video coding.

2026-07-13T17:33:55Z Belazi, Akram Migallón-Gomis, Héctor https://hdl.handle.net/11000/40185 2026-07-14T01:04:03Z 2026-07-13T17:19:49Z

Título : Drone-Captured Wildlife Data Encryption: A Hybrid 1D–2D Memory Cellular Automata Scheme with Chaotic Mapping and SHA-256 Autor : Belazi, Akram; Migallón-Gomis, Héctor Resumen : In contemporary wildlife conservation, drones have become essential for the non-invasive monitoring of animal populations and habitats. However, the sensitive data captured by drones, including images and videos, require robust encryption to prevent unauthorized access and exploitation. This paper presents a novel encryption algorithm designed specifically for safeguarding wildlife data. The proposed approach integrates one-dimensional and two-dimensional memory cellular automata (1D MCA and 2D MCA) with a bitwise XOR operation as an intermediate confusion layer. The 2D MCA, guided by chaotic rules from the sine-exponential (SE) map, utilizes varying neighbor configurations to enhance both diffusion and confusion, making the encryption more resilient to attacks. A final layer of 1D MCA, controlled by pseudo-random number generators, ensures comprehensive diffusion and confusion across the image. The SHA-256 hash of the input image is used to derive encryption parameters, providing resistance against plaintext attacks. Extensive performance evaluations demonstrate the effectiveness of the proposed scheme, which balances security and complexity while outperforming existing algorithms.

2026-07-13T17:19:49Z Belazi, Akram Migallón-Gomis, Héctor González-Sánchez, Daniel González-García, Jorge Jimeno-Morenilla, Antonio Sánchez-Romero, José Luis https://hdl.handle.net/11000/40184 2026-07-14T01:04:08Z 2026-07-13T17:19:34Z

Título : Enhanced Parallel Sine Cosine Algorithm for Constrained and Unconstrained Optimization Autor : Belazi, Akram; Migallón-Gomis, Héctor; González-Sánchez, Daniel; González-García, Jorge; Jimeno-Morenilla, Antonio; Sánchez-Romero, José Luis Resumen : The sine cosine algorithm’s main idea is the sine and cosine-based vacillation outwards or towards the best solution. The first main contribution of this paper proposes an enhanced version of the SCA algorithm called as ESCA algorithm. The supremacy of the proposed algorithm over a set of state-of-the-art algorithms in terms of solution accuracy and convergence speed will be demonstrated by experimental tests. When these algorithms are transferred to the business sector, they must meet time requirements dependent on the industrial process. If these temporal requirements are not met, an efficient solution is to speed them up by designing parallel algorithms. The second major contribution of this work is the design of several parallel algorithms for efficiently exploiting current multicore processor architectures. First, one-level synchronous and asynchronous parallel ESCA algorithms are designed. They have two favors; retain the proposed algorithm’s behavior and provide excellent parallel performance by combining coarse-grained parallelism with fine-grained parallelism. Moreover, the parallel scalability of the proposed algorithms is further improved by employing a two-level parallel strategy. Indeed, the experimental results suggest that the one-level parallel ESCA algorithms reduce the computing time, on average, by 87.4% and 90.8%, respectively, using 12 physical processing cores. The two-level parallel algorithms provide extra reductions of the computing time by 91.4%, 93.1%, and 94.5% with 16, 20, and 24 processing cores, including physical and logical cores. Comparison analysis is carried out on 30 unconstrained benchmark functions and three challenging engineering design problems. The experimental outcomes show that the proposed ESCA algorithm behaves outstandingly well in terms of exploration and exploitation behaviors, local optima avoidance, and convergence speed toward the optimum. The overall performance of the proposed algorithm is statistically validated using three non-parametric statistical tests, namely Friedman, Friedman aligned, and Quade tests.

2026-07-13T17:19:34Z Piñol, Pablo Moscardó, Mª José Migallón-Gomis, Héctor Martínez-Rach, Miguel López-Granado, Otoniel https://hdl.handle.net/11000/40183 2026-07-14T01:04:08Z 2026-07-13T17:19:18Z

Título : Hybrid single operator HHO, SMA and HGS based metaheuristic algorithms Autor : Piñol, Pablo; Moscardó, Mª José; Migallón-Gomis, Héctor; Martínez-Rach, Miguel; López-Granado, Otoniel Resumen : There are many population-based meta-heuristic optimization algorithms, but none can outperform all existing algorithms on all existing optimization problems, or solve all optimization problems. This leads some algorithms to use one or more control parameters to adjust the properties of the algorithm depending on the problem to be solved. The optimization behavior of these algorithms can be improved by, among other aspects, incorporating hybridization techniques. Hybrid algorithms are suitable for a wide range of applications, but they are usually intended for specific engineering problems, and they increase the difficulty of correctly adjusting the control parameters. This paper presents hybrid algorithms based on three operators from prevalent configuration parameter-free optimization algorithms. Each hybrid approach uses a different strategy to change the algorithm responsible for generating each new individual. These algorithms are HHO, SMA and HGS. Experimental results show that the proposed algorithms perform better than the original algorithms, which implies that the optimal use of these basic algorithms depends on the problem to be solved. Another advantage of the hybrid algorithms is that there is no need for a prior process of adjusting the control parameters.

2026-07-13T17:19:18Z Martínez-Peral, Francisco José Migallón-Gomis, Héctor Borrell-Méndez, Jorge Martínez-Rach, Miguel Pérez-Vidal, Carlos https://hdl.handle.net/11000/40182 2026-07-14T01:04:09Z 2026-07-13T17:19:01Z

Título : Manipulation order optimization in industrial pick-and-place operations: application to textile and leather industry Autor : Martínez-Peral, Francisco José; Migallón-Gomis, Héctor; Borrell-Méndez, Jorge; Martínez-Rach, Miguel; Pérez-Vidal, Carlos Resumen : This work addresses the problem of the development of a robotic system for the picking of parts cut by a CNC machine and the optimization of the sequencing of this picking process. An automated parts collection system is optimized to reduce the time required to perform the task of both picking and the subsequent classification by the type of part. The automated picking system, which is located at the end of a cutting machine, uses a robot equipped with an additional axis to expand its working space. Therefore, in this proposal, the industrial equipment necessary to automate this process is designed and the process to be optimized is computationally modeled. In particular, three discrete optimization algorithms are analyzed, with different evolution strategies and operators, but all of them are free of specific configuration parameters. The whole process is shown in this research, from the design of the procedure to the design of the tool, the algorithm selection, and elements validation. Finally, the first steps towards its industrial implementation are presented, and the hypothesis behind this project is validated.

2026-07-13T17:19:01Z Migallón-Gomis, Héctor Jimeno-Morenilla, Antonio Duta-Costache, Eduard Sánchez-Romero, José Luis https://hdl.handle.net/11000/40181 2026-07-14T01:04:10Z 2026-07-13T17:18:36Z

Título : Efficient tool path computing for Industry 5.0: Application to turning lathe machining Autor : Migallón-Gomis, Héctor; Jimeno-Morenilla, Antonio; Duta-Costache, Eduard; Sánchez-Romero, José Luis Resumen : This paper presents an efficient approach to toolpath generation tailored to the needs of Industry 5.0, with a focus on turning lathe machining. The study addresses the challenge of rapidly and accurately generating helical toolpaths in personalized manufacturing, where traditional sequential methods often become computational bottlenecks. To overcome this limitation, we propose efficient parallel implementations of the Virtual Digitizing (VD) algorithm, specifically designed to accelerate the computation of machining trajectories on both multicore and manycore architectures. The multicore implementation achieves notable speedups, especially when execution is properly tuned. The manycore strategy explores both asynchronous (coarsegrained) and synchronous (fine-grained) execution models. In the asynchronous method, independent trajectory computations are assigned to separate CUDA threads, whereas the synchronous method further parallelizes the internal processing of each trajectory point, providing finer computational granularity. Experimental evaluations conducted on authentic industrial shoe last models reveal notable gains in computational efficiency. The manycore implementation achieves up to 70𝑥 acceleration on low-end GPUs, over 80𝑥 on high-range devices and over 270𝑥 on state-of-the-art GPU devices when compared to their respective CPU-based computations. Although the synchronous method introduces additional complexity, it delivers the best performance on powerful GPU platforms, whereas the asynchronous method is better suited for resource-constrained systems. Therefore, the study concludes that the optimal parallelization strategy depends on the available hardware.

2026-07-13T17:18:36Z García Crespí, Federico https://hdl.handle.net/11000/39810 2026-04-28T01:03:28Z 2026-04-27T07:58:03Z

Título : Engineering a Scalable Laboratory Infrastructure for Assembly Language Scaffolding: Design and Deployment of a Locally Optimized GenAI Assistant for the CODE-2 Educational Architecture Autor : García Crespí, Federico Resumen : The transition from high-level programming to assembly language constitutes a welldocumented pedagogical bottleneck in computer engineering curricula, particularly in largecohort laboratory settings where individualized scaffolding cannot scale. This paper presents the design, implementation, and technical evaluation of a locally deployable generative AI assistant engineered specifically for the CODE-2 educational processor architecture. The system is intended as laboratory infrastructure, not as a replacement for human instruction; its primary contribution is enabling scalable, privacy-preserving syntax scaffolding without dependency on cloud services or internet connectivity. A synthetic task bank of 50,000 instruction pairs was procedurally generated to cover the full CODE-2 curriculum. Three fine-tuning strategies were compared on a consumer GPU: Prompt Tuning, Low-Rank Adaptation (LoRA), and Full Fine-Tuning of a T5-Small encoder-decoder model. Full Fine- Tuning achieved 94.10% Exact Match on the held-out evaluation set, demonstrating that rigid assembly syntax requires full parameter adaptation. Post-training INT8 quantization via ONNX Runtime reduced inference latency by 69% (from 1,689 ms to 526 ms) on standard laboratory hardware (Intel i5, 8 GB RAM), with a precision loss below 1%. The resulting system operates entirely offline, precluding data exfiltration by design. The system is integrated into laboratory workflows as a supervised scaffolding tool, requiring mandatory emulator-based verification of all AI-generated code. Pedagogical implications are discussed as plausible benefits; no controlled learning-gains study is reported. The work demonstrates a replicable pipeline for building domain-specific language model infrastructure tailored to CPU-only educational environments.

2026-04-27T07:58:03Z Sarriás, Adrián Martínez-Rach, Miguel O. López-Granado, Otoniel Migallón, Héctor https://hdl.handle.net/11000/39775 2026-04-17T01:07:53Z 2026-04-16T07:59:22Z

Título : Software architecture for real-time hyperspectral analysis in material sorting systems Autor : Sarriás, Adrián; Martínez-Rach, Miguel O.; López-Granado, Otoniel; Migallón, Héctor Resumen : The integration of hyperspectral imaging into industrial sorting systems has enabled high-precision classification of materials with similar visual characteristics but different chemical compositions. However, the real-time processing demands of HSI data acquisition, characterised by high spectral and spatial resolution, require advanced computational strategies. This paper presents a scalable and efficient software architecture designed for real-time hyperspectral analysis in automated material sorting lines. The architecture exploits heterogeneous and homo geneous parallelism to distribute pre-processing, classification and segmentation tasks across multiple threads and processing cores. Two classification methods, based on Spectral Angle Mapper and Artificial Neural Networks, are developed and evaluated, both show high accuracy in material identification, but they impact system scalability in different ways. Extensive performance tests show that the proposed framework meets strict timing constraints and maintains low-latency operation on standard multi-core CPU systems. The modular design of the system ensures adaptability to different hardware configurations and material types, supporting future scalability and integration into diverse industrial environments. The real-time constraint imposed by the camera’s maximum frame rate is 1.493𝑚𝑠. Thanks to the optimisations applied, the critical processes, pre-processing and classification, have been reduced to just over 30𝜇𝑠 each, consuming only about 5% of the available time and leaving almost 95% free for additional operations or performance enhancements. This results in a system that is scalable both from a computational perspective and in terms of increasing the overall performance of the industrial plant.

2026-04-16T07:59:22Z Kessler Martín, Jorge Fernández Lagos, Pablo García Lucas, David Cebrián Márquez, Gabriel Ríos, Belén Vigueras, Guillermo Díaz Honrubia, Antonio Jesús https://hdl.handle.net/11000/39591 2026-03-27T02:06:36Z 2026-03-26T12:00:04Z

Título : Saliency Dataset and Predictive Model for Areas of Interest in VVC Perceptual Coding Autor : Kessler Martín, Jorge; Fernández Lagos, Pablo; García Lucas, David; Cebrián Márquez, Gabriel; Ríos, Belén; Vigueras, Guillermo; Díaz Honrubia, Antonio Jesús Resumen : Video coding standardization organizations have invested significant efforts in achieving greater compression factors over the years. Approved in 2020, the Versatile Video Coding (VVC) standard reduces the bit rate needed to encode a sequence by half compared to its predecessor. However, users today have increasingly demanding requirements, leading to a significant rise in video traffic on the Internet. In this context, perceptual video coding aims to reduce video bit rate by decreasing the objective quality while maintaining the subjective quality. This work presents a novel dataset designed for training models to predict video saliency, i.e., areas in the video to which viewers are more likely to pay attention. The dataset is publicly available. Furthermore, this work also proposes a machine learning model that classifies each Coding Tree Unit (CTU) as salient or not, and adjusts its quality accordingly. The results show that this model has an accuracy of 95% and correctly classifies as salient 98% of the CTUs that are actually salient.

2026-03-26T12:00:04Z Valera, María Rodríguez Sánchez, Rafael Cuenca, Pedro Cebrián Márquez, Gabriel Díaz Honrubia, Antonio Jesús García Lucas, David https://hdl.handle.net/11000/39590 2026-03-27T02:06:47Z 2026-03-26T11:59:06Z

Título : Comparing V-Nova LCEVC SDK with Practical Open-Source Video Codecs Autor : Valera, María; Rodríguez Sánchez, Rafael; Cuenca, Pedro; Cebrián Márquez, Gabriel; Díaz Honrubia, Antonio Jesús; García Lucas, David Resumen : This paper presents a comparative evaluation of the V-Nova LCEVC SDK against several practical open-source video encoders, namely SVT-AV1, XEVE, VVenC, x265, and x264. We analyze the trade-offs between the compression efficiency and encoder/decoder runtime of these encoders for high-resolution (UHD and HD) 10-bit consumer applications under a random access configuration. Rate–distortion behavior is assessed using Video Multimethod Assessment Fusion (VMAF, and VMAF-NEG) and Peak Signal-to-Noise Ratio (PSNR), while computational cost is measured through the encoder/decoder runtime. We also analyze the impact of LCEVC’s enhancement layer in terms of both bitrate increase and rate–distortion improvement. The results show that V-Nova LCEVC SDK delivers notable reductions in encoding time with respect to its base codecs, highlighting its suitability as a low-complexity enhancement layer. By comparison, VVenC exhibits a strong compression performance at the expense of high complexity, XEVE also displays considerable encoding times, and SVT-AV1 offers a more balanced compromise between efficiency and computational requirements.

2026-03-26T11:59:06Z