Alejandro Tapia Córdoba

The COVID-19 pandemic exposed critical fragilities in health systems, particularly regarding the equitable distribution of resources and the logistical capacity of early warning systems. This study addresses the optimization of the Sentinel Surveillance Network in Andalusia, Spain, proposing a shift from traditional efficiency-based models to an equity-oriented approach. The facility location problem is formulated using a Capacitated Vertex-Restricted P-center model, which aims to minimize the maximum access time for the most remote population, thereby preventing the creation of “healthcare deserts” common in P-median approaches that minimize average distance or total travel cost. To solve this NP-hard combinatorial problem, a hybrid metaheuristic, named the ACME-GA (Acceleration by Clustering and Memetic Exploitation) refined with Simulated Annealing, is introduced. Using real-Andalusia demographic data and road travel times across 406 municipalities and 133 candidate hospitals, the proposed method is compared against standard evolutionary schemes. The results demonstrate that ACME-GA consistently yields superior solution quality and stability. Furthermore, the analysis confirms that the P-center approach significantly enhances territorial equity compared to density-focused models, ensuring that even sparsely populated rural areas maintain robust access to epidemiological surveillance. This work provides a resilient methodological framework for public health planning in post-pandemic scenarios.

In the context of smart agriculture, accurate soil moisture monitoring is crucial to optimise irrigation, improve water usage efficiency and increase crop yields. Although low-cost capacitive sensors are used to make monitoring affordable, these sensors face accuracy challenges that often result in inefficient irrigation practices. This paper presents a method for calibrating capacitive soil moisture sensors through data assimilation. The method was validated using data collected from a farm in Dos Hermanas, Seville, Spain, which utilises a drip irrigation system. The proposed solution integrates the Hydrus 1D model with particle filter (PF) and the Iterative Ensemble Smoother (IES) to continuously update and refine the model and sensor calibration parameters. The methodology includes the implementation of physical constraints, ensuring that the updated parameters remain within physically plausible ranges. Soil moisture was measured using low-cost SoilWatch 10 capacitive sensors and ThetaProbe ML3 high-precision sensors as a reference. Furthermore, a comparison was carried out between the PF and IES methods. The results demonstrate that the data assimilation approach markedly enhances the precision of sensor readings, aligning them closely with reference measurements and model simulations. The PF method demonstrated superior performance, achieving an 84.8% improvement in accuracy compared to the raw sensor readings. This substantial improvement was measured against high-precision reference sensors, confirming the effectiveness of the PF method in calibrating low-cost capacitive sensors. In contrast, the IES method showed a 68% improvement in accuracy, which, while still considerable, was outperformed by the PF. By effectively mitigating observation noise and sensor biases, this approach proves robust and practical for large-scale implementations in precision agriculture.

Irrigation based on non‐compensated drip emitters is extremely common in agriculture, especially due to its simplicity, robustness and competitive cost. Nevertheless, because of friction losses in the pipe, together with irregular terrain, these systems often suffer from uneven water distribution in the drip emitters, which not only results in inefficient use of water resources but also might lead to inadequate irrigation in certain parts of the field. This work proposes to design the topology of the irrigation network to compensate for these discharge differences. To this end, a graph‐based mathematical model is developed to determine the discharge flows at different emitters for any network topology. This model is employed to formulate an integer nonlinear optimization problem, for which a messy genetic algorithm is proposed. The methodology is validated on an example problem, which is based on a rectangular agricultural crop of 49 fruit trees. The results revealed a 70% reduction in the coefficient of variation of the irrigation discharge rates, which was employed as a metric of irrigation uniformity. This caused a 75% reduction in the water excess. The results demonstrate that the uniformity can be improved simply by choosing a proper connectivity layout to build the pipe network.

Resumen En este estudio se presenta un enfoque basado en algoritmos genéticos (AG) para optimizar el diseño de redes de riego por goteo. El objetivo es reducir las inhomogeneidades en los caudales de salida en cada toma de riego, de manera que toda la parcela se riegue lo más parecido posible. Se asume que las tomas de riego y la entrada de agua son conocidas, centrándose en el diseño de la red de tuberías. El AG se utiliza para determinar la configuración óptima de las tuberías, es decir, qué tomas están conectadas entre sí. Para lograr esto, se emplea una estructura de cromosoma en la que cada par de genes representa la conexión entre dos tomas. El algoritmo evolutivo busca maximizar la uniformidad en los caudales de salida y minimizar la longitud total de la tubería. Los resultados demuestran que el enfoque propuesto logra reducir de manera significativa las inhomogeneidades en los caudales de salida, mejorando así la eficiencia del sistema de riego por goteo. Además, se logra una reducción en el coste total del sistema al minimizar la longitud de la tubería utilizada.

En este trabajo se revisita un problema clásico: el diseño óptimo de actuadores y/o sensores para sistemas lineales e invariantes en el tiempo. Considerando el sistema descrito en el espacio de estados, el objetivo sería el de escoger, bajo ciertas restricciones, la matriz de entrada B y/o la matriz de salida C para optimizar algún criterio asociado, habitualmente, con el grado de controlabilidad y/u observabilidad del sistema. Este trabajo propone resolver este problema empleando algoritmos genéticos. La principal ventaja de esta herramienta es que permite introducir las restricciones de forma muy sencilla, permitiendo resolver el problema de una forma mucho más general de las que existen en la literatura. Además, esta metodología permite considerar optimización multi-objetivo de forma directa, pudiendo analizar la situación en la que más de uno de estos criterios sean interesantes para la aplicación.

Data processing in sports is a phenomenon increasingly present at all levels, from professionals in search of tools to improve their performance to beginners motivated by the quantification of their physical activity. In this work, a comparison between some of the main machine learning and deep learning algorithms is carried out in order to classify padel tennis strokes. Up to 13 representative padel tennis strokes are classified. Before a classification of padel tennis strokes is performed, a sufficiently representative data set is needed that collects numerous examples of the performance of these strokes. Since there was no similar data set in the literature, we proceeded to the creation of such a data set, for which we developed a data collection system based on an electronic device with an inertial measurement unit. Using the developed data set, the machine learning and deep learning algorithms were hyperparameterized to compare their performance under the best possible configurations. The algorithms were fed with both the temporal series of the acceleration and speed of the six degrees of freedom and also with feature engineering input, consisting in calculating the mean, maximum, and minimum values for each axis. The algorithms evaluated are: fully connected or dense neural networks, 1D convolutional neural networks, decision tree, K nearest neighbors, support vector machines, and eigenvalue classification. According to the results achieved, the best algorithm is the 1D convolutional neural network with temporal series input that achieves an accuracy higher than 93%. However, other simpler algorithms such as dense networks and support vector machines achieve similar results.

Despite the clear advantages of mini hydropower technology to provide energy access in remote areas of developing countries, the lack of resources and technical training in these contexts usually lead to suboptimal installations that do not exploit the full potential of the environment. To address this drawback, the present work proposes a novel method to optimize the design of mini-hydropower plants with a robust and efficient formulation. The approach does not involve typical 2D simplifications of the terrain penstock layout. On the contrary, the problem is formulated considering arbitrary three-dimensional terrain profiles and realistic penstock layouts taking into account the bending effect. To this end, the plant layout is modeled on a continuous basis through the cubic Hermite interpolation of a set of key points, and the optimization problem is addressed using a genetic algorithm with tailored generation, mutation and crossover operators, especially designed to improve both the exploration and intensification. The approach is successfully applied to a real-case scenario with real topographic data, demonstrating its capability of providing optimal solutions while dealing with arbitrary terrain topography. Finally, a comparison with a previous discrete approach demonstrated that this algorithm can lead to a noticeable cost reduction for the problem studied.