Articles publicats (Matemàtica)
Permanent URI for this collection
Browse
Recent Submissions
- ItemOpen AccessA genetic algorithm for site-specific management zone delineation(MDPI, 2025) Huguet, Francisco; Pla Aragonés, Lluís Miquel; Albornoz, Víctor M.; Pohl, MauricioThis paper presents a genetic algorithm-based methodology to address the Site-Specific Management Zone (SSMZ) delineation problem. A SSMZ is a subregion of a field that is homogeneous with respect to a soil or crop property, enabling farmers to apply customized management strategies for optimizing resource use. The algorithm generates optimized field partitions using rectangular zones, applicable to both regular and irregularly shaped fields. To the best of our knowledge, the Genetic Algorithm for Zone Delineation (GAZD) is the first approach to handle the rectangular SSMZ delineation problem in irregular-shaped lands without introducing non-real data. The algorithm’s performance is compared with an exact solution based on integer linear programming. Experimental tests conducted on real-field and generated irregular-shaped instances show that while the GAZD requires longer execution times than the exact approach, it proves to be functional and robust in solving the SSMZ problem. Furthermore, the GAZD offers a set of “good enough” solutions that can be evaluated for feasibility and practical convenience, making it a valuable tool for decision-making processes. Moreover, strategies such as implementation in a compiled language and parallel processing can be used to improve the execution time performance of the algorithm.
- ItemOpen AccessMathematical methods applied to the problem of dairy cow replacements: a scoping review(MDPI, 2025) Palma, Osvaldo; Pla Aragonés, Lluís Miquel; Mac Cawley, Alejandro; Albornoz, Víctor M.This study provides a comprehensive scoping review with the aim of determining the mathematical methods applied to dairy cow replacements that will serve as a basis for future research in this field. In the WOS and Scopus databases, a search was carried out for peer-reviewed, English articles, where a process of discarding those that did not address the topic related to our objective was carried out, and where the titles, keywords, and full text were reviewed sequentially. We obtained a total of 40 selected articles. Dynamic programming is the most commonly used optimization technique, present in 58% of the studies, followed by stochastic simulation in 40%, and deterministic simulation in 8%. Machine learning methods or hybrid approaches are applied in only 5% of the cases. The review identifies milk production as the most frequently used response variable, appearing in at least 58% of the studies, and profit as the primary economic indicator, utilized in 78% of the cases. This research underscores the importance of these methods in improving the efficiency, profitability, and sustainability of dairy farming operations. Future research could address the inclusion in models of diseases and animal characteristics that have not yet been considered, as well as expand the scarce use of machine learning tools and the hybridization of such models with statistical ones.
- ItemOpen AccessDemographic effects of sanitary policies on European vulture population dynamics: a retrospective modeling approach(WILEY, 2025) Colomer, M. Àngels (Maria Àngels); Margalida, AntoniThe prediction of population responses to environmental changes, including the effects of different management scenarios, is a useful tool and a necessary contributor to improving conservation decisions. Empirical datasets based on long-term monitoring studies are essential to assess the robustness of retrospective modeling predictions on biodiversity. These allow checks on the performance of modeling projections and enable improvements to be made to future models, based on the errors detected. Here, we assess the performance of our earlier model to assess the impact of vulture food shortages caused by sanitary regulations on the population dynamics of Spanish vultures during the past decade (2009-2019). This model forecasts the population trends of three vulture species (griffon, Egyptian, and bearded vultures) in Spain (home to 90% of the European vulture population) under various food shortage scenarios. We show that it underestimated bearded and griffon vulture population numbers and overestimated Egyptian vultures. The model suggested that the most plausible food shortage scenario involved an approximate 50% reduction of livestock carcass availability in the ecosystem compared with the previous situation without sanitary carcass removal. However, the observed annual population growth for the period 2009-2019 (7.8% for griffon vulture, 2.4% for Egyptian vulture, and 3.5% for bearded vulture) showed that food shortages had little impact on vulture population dynamics. After assessing the robustness of the model, we developed a new model with updated demographic parameters and foraging movements under different hypothetical food shortage scenarios for the period 2019-2029. This model forecasts annual population increases of about 3.6% for the bearded vulture, 3.7% for the Egyptian vulture, and 1.1% for the Griffon vulture. Our findings suggest that food shortages due to the implementation of sanitary policies resulted in only a moderate impact on vulture population growth, probably thanks to the supplementary feeding network which provided alternative food. Also important was the availability of alternative food sources (intensive farms, landfills) that were used more regularly than expected. We discuss the computational performance of our modeling approach and its management consequences to improve future conservation measures for these threatened species, which provide essential ecosystem services.
- ItemOpen AccessRurality and COVID-19 outcomes: unraveling the impact of nursing home residency using bayesian analysis(MDPI, 2024) Martínez-Redondo, Javier; Crespo Pons, Montserrat; Mateu Llevadot, Alicia; Pujol Salud, Jesús; Comas Rodríguez, CarlesBackground and Objectives: Many studies have analyzed the impact of rurality on the incidence and consequences of COVID-19 infection. However, these studies have not considered the impact of different numbers of nursing homes in rural, semi-urban, or urban areas. Our objective was to analyze the effect of the factor of rurality on the incidence and mortality of COVID-19 while accounting for the impact of the variable of nursing home residency. In addition, we performed a comparative analysis of the infected population in semi-urban and rural areas. Methods: We first analyzed COVID-19 infection in all populations in the Balaguer Primary Health Care Area before examining the impact of rurality using Bayesian logistic regression analysis, specifically excluding the population living in nursing homes. We also performed an epidemiological and clinical analysis comparing rural and semi-urban areas. Results: We found higher incidence of and higher relative and absolute mortality from COVID-19 infection in semi-urban areas than in rural areas. After excluding nursing home residents from our sample, the Bayesian analysis indicated that rurality was not protective against COVID-19 infection or mortality. The incidence rates, specific mortality rates, and case fatality rates were similar in semi-urban and rural areas. All comorbidities, except chronic obstructive pulmonary disease, were associated with higher mortality, while no symptoms were associated with higher mortality. Conclusions: Excluding the population residing in nursing homes from the analysis, we found that rurality was not a protective factor against either infection or mortality during the first COVID-19 wave. Our Bayesian model analysis confirmed that rurality alone did not enhance survival among residents of rural areas.
- ItemOpen AccessA Deep Learning Approach for Image Analysis and Reading Body Weight From Digital Scales in Pigs Farms(IEEE, 2025) Reyes-Reyes, Nicolás A.; Doja, Mihai Catalin; Llagostera Blasco, Pol; Pla Aragonés, Lluís Miquel; González Araya, Marcela CeciliaBody weight is an important measure in fattening farms that allows pig farmers to monitor weight gain, manage feeding, and care for animal health. Traditionally, pig weighing is done directly, i.e. placing one or more pigs at a time on a scale while the total body weight is displayed and recorded. However, this process is labor-intensive, causes stress to the animals, and is highly prone to manual recording errors. Recently, several deep learning-based image analysis methods have emerged to estimate pig body weight, but these only consider the animal’s body characteristics. For this reason, an automatic deep learning-based approach is introduced for reading pig body weight from digital scale images. This reading is done by recognizing the body weight values indicated on the scale screen during the weighing process. For this purpose, convolutional neural network models are developed from scale screen segmentation to scale digit classification used to build the body weight value. The proposed approach is applied and validated in a real case study of fattening pigs from a Spanish company. Computational results showed that our approach read body weight with an average error of 20.2 g for a group of pigs with an average weight of 44 kg, taking less than 50 milliseconds to individually recognize the weight value. Therefore, our approach is reliable to support decisions in pig fattening management and suitable to be embedded into real-time weighing systems and useful too for image annotation purposes.