The occurrence of HAB has a direct impact on shellfish farming, leading to economic losses due to the contamination of shellfish with toxins harmful to human health. Predicting these blooms accurately is therefore crucial for minimizing their negative effects on the industry. The DoME machine learning model is particularly notable for its high interpretability, as the trained model is expressed as a mathematical equation, allowing for transparent analysis and a better understanding of the factors driving the predictions. This characteristic distinguishes DoME from other black-box models, making it a valuable tool for stakeholders seeking not only accurate predictions but also insights into the dynamics behind HAB events. In this study, we evaluated the novel DoME (Development of Mathematical Expressions) algorithm for the prediction of Harmful Algal Blooms (HAB) associated with Diarrhoeic Shellfish Poisoning (DSP), a significant concern for the shellfish industry. Our testing involved analysing the model's performance in various environmental conditions, demonstrating its robustness and adaptability. DoME achieved a F1-score of 97.80%, which corresponds to an improvement of around 8% over previous studies. This superior performance, combined with its explainability, underscores the model's potential as a practical and reliable solution for early warning systems in the shellfish industry, helping to protect both public health and economic stability.

Decentralized Federated Learning (DFL) offers a promising paradigm for collaborative machine learning training without centralized coordination, addressing critical limitations of centralized federated learning such as single points of failure, communication bottlenecks, and scalability constraints. However, the adoption of DFL has been hindered by the lack of robust, flexible, and user-friendly frameworks. This paper introduces P2PFL, an open-source framework that enables broader adoption of DFL through a highly modular and extensible architecture. P2PFL decouples communication protocols, learning modules, aggregation algorithms, and orchestration workflows into independent, interchangeable components. This modularity enables researchers and practitioners to efficiently prototype and deploy federated learning systems tailored to their specific requirements. A key contribution is the introduction of optimized gossip-based protocols with incremental partial aggregation whose equivalence to centralized federated learning is formally proven, with communication savings that scale with network size, achieving up to 88\% reduction in model data transfer at 128 nodes. We demonstrate P2PFL's effectiveness through functional validation on standard benchmarks (\textit{MNIST} and \textit{CIFAR-10}) under various network topologies and data heterogeneity settings, a scalability analysis from 8 to 128 nodes quantifying communication overhead and round duration across topologies, and a real-world deployment on the \textit{CASA} IoT dataset across 10 geographically distributed machines.

Over the years, several approaches have tried to tackle the problem of performing an automatic scoring of the sleeping stages. Although any polysomnography usually collects over a dozen of different signals, this particular problem has been mainly tackled by using only the Electroencephalograms presented in those records. On the other hand, the other recorded signals have been mainly ignored by most works. This paper explores and compares the convenience of using additional signals apart from electroencephalograms. More specifically, this work uses the SHHS-1 dataset with 5,804 patients containing an electromyogram recorded simultaneously as two electroencephalograms. To compare the results, first, the same architecture has been evaluated with different input signals and all their possible combinations. These tests show how, using more than one signal especially if they are from different sources, improves the results of the classification. Additionally, the best models obtained for each combination of one or more signals have been used in ensemble models and, its performance has been compared showing the convenience of using these multi-signal models to improve the classification. The best overall model, an ensemble of Depth-wise Separational Convolutional Neural Networks, has achieved an accuracy of 86.06\% with a Cohen's Kappa of 0.80 and a $F_{1}$ of 0.77. Up to date, those are the best results on the complete dataset and it shows a significant improvement in the precision and recall for the most uncommon class in the dataset.

The presence of toxin-producers phytoplankton is a natural phenomenon that threatens marine ecosystems, endangers human health, and causes significant economic losses in shellfish harvesting. The Galician Rías Baixas (NW Spain) are one of the main mussels producing regions worldwide and the leading producer in Europe. Annual occurrence of Dinophysis acuminata, responsible for diarrhetic shellfish poisoning toxins, lead to a ban on the mussel harvesting for several months, each year. To help mitigate these impacts, this study explores the prediction of D. acuminata cells densities 3-days ahead in the outer and inner parts of three of the Rías Baixas (Arousa, Pontevedra and Vigo), testing three local machine learning (ML) models: Artificial Neural Network (ANN), Random Forest (RF) and Support Vector Machine (SVM). Local ML models were selected to account for the differences in occurrence and variability of D. acuminata densities across the different parts of each Ría. These ML models were assessed by (1) reducing the number of features through a feature selection approach to identify the most relevant ones, (2) exploring different sets of features and (3) comparing models trained with 7 and 30 days of past information. The dataset combined daily hydrodynamic and biological features, from 2013 to 2019, obtained from a high-resolution 3D hydrodynamic model (CROCO), and in-situ observations. Our results show that RF provided the best predictive performance. Increasing the number of days of past information did not significantly improve results, as similar averaged R2 values were obtained for 7 and 30 days: 0.75 for Ría de Arousa, 0.72 for Ría de Pontevedra, and 0.67 for Ría de Vigo. Feature selection process showed that, as expected, previous cells densities of D. acuminata were essential for capturing bloom timing and amplitude. Also, the temperature, salinity, and the vertical and meridional components of current velocity were key predictors at outer stations of the Ría de Pontevedra and Vigo, where more features were required. In contrast, for the other stations, good predictions were achieved using only five features. This study represents one of the first attempts to predict D. acuminata in the Rías Baixas using local ML models. Our findings highlight the need for local approaches, as bloom dynamics vary between Rías and within different parts of each Ría. We also demonstrate the value of hydrodynamic model outputs to train ML models and compensate for the lack of long-term, spatially extensive in-situ data.

Diarrhetic Shellfish Poisoning (DSP) is a global health issue caused by shellfish contaminated with toxins from dinoflagellates, posing significant risks to public health and the shellfish industry. Harmful Algal Blooms (HABs), driven by toxin-producing algae like DSP, require effective monitoring and forecasting systems. Predicting HABs is challenging due to the time-series nature of the problem, influenced by historical seasonal patterns and recent anomalies from meteorological and oceanographic changes. Stream Learning shows promise for handling time-series problems with concept drifts but has yet to be validated for HAB prediction compared to Batch Learning. Limited historical data availability in oceanography highlights the importance of advanced tools like the CROCO ocean hydrodynamic model, which provides high-resolution temporal and spatial data. This study developed a machine learning workflow to predict toxic dinoflagellate (Dinophysis acuminata) cell counts, comparing seven algorithms across two learning paradigms. The CROCO model data addressed historical data gaps. The DoME model, with an average R 2 of 0.77 for 3-day-ahead predictions, proved the most effective and interpretable, underscoring the value of model explainability and rigorous comparison methodologies.

Orthopoxvirus infections must be accurately classified from medical pictures for an easy and early diagnosis and epidemic prevention. The necessity for automated and scalable solutions is highlighted by the fact that traditional diagnostic techniques can be time-consuming and require expert interpretation and there are few and biased data sets of the different types of Orthopox. In order to improve classification performance and lower computational costs, a hybrid strategy is put forth in this paper that uses Machine Learning models combined with pretrained Deep Learning models to extract deep feature representations without the need for augmented data. The findings show that this feature extraction method, when paired with other methods in the state-of-the-art, produces excellent classification outcomes while preserving training and inference efficiency. The proposed approach demonstrates strong generalization and robustness across multiple evaluation settings, offering a scalable and interpretable solution for real-world clinical deployment.

Path Planning methods for the autonomous control of Unmanned Aerial Vehicle (UAV) swarms are on the rise due to the numerous advantages they bring. There are increasingly more scenarios where autonomous control of multiple UAVs is required. Most of these scenarios involve a large number of obstacles, such as power lines or trees. Despite these challenges, there are also several advantages; if all UAVs can operate autonomously, personnel expenses can be reduced. Additionally, if their flight paths are optimized, energy consumption is reduced, leaving more battery time for other operations. In this paper, a Reinforcement Learning-based system is proposed to solve this problem in environments with obstacles by utilizing Q-Learning. This method allows a model, in this case, an Artificial Neural Network, to self-adjust by learning from its mistakes and successes. Regardless of the map's size or the number of UAVs in the swarm, the goal of these paths is to ensure complete coverage of an area with fixed obstacles for tasks like field prospecting. Setting goals or having any prior information apart from the provided map is not required. During the experimentation phase, five maps of varying sizes were used, each with different obstacles and a varying number of UAVs. To evaluate the quality of the results, the number of actions taken by each UAV to complete the task in each experiment was considered. The results indicate that the system achieves solutions with fewer movements as the number of UAVs increases. An increasing number of UAVs on a map lead to solutions in fewer moves. The results have been compared, and a statistical significance analysis has been conducted on the proposed model's outcomes, demonstrating its capabilities. Thus, it is shown that a two-layer Artificial Neural Network used to implement a Q-Learning algorithm is sufficient to operate on maps with obstacles.

Diarrhetic Shellfish Poisoning (DSP) is a global health threat arising from shellfish contaminated with toxins produced by dinoflagellates. The condition, with its widespread incidence, high morbidity rate, and persistent shellfish toxicity, poses risks to public health and the shellfish industry. High biomass of toxin-producing algae such as DSP are known as Harmful Algal Blooms (HABs). Monitoring and forecasting systems are crucial for mitigating HABs impact. Predicting harmful algal blooms involves a time-series-based problem with a strong historical seasonal component, however, recent anomalies due to changes in meteorological and oceanographic events have been observed. Stream Learning stands out as one of the most promising approaches for addressing time-series-based problems with concept drifts. However, its efficacy in predicting HABs remains unproven and needs to be tested in comparison with Batch Learning. Historical data availability is a critical point in developing predictive systems. In oceanography, the available data collection can have some constrains and limitations, which has led to exploring new tools to obtain more exhaustive time series. In this study, a machine learning workflow for predicting the number of cells of a toxic dinoflagellate, Dinophysis acuminata, was developed with several key advancements. Seven machine learning algorithms were compared within two learning paradigms. Notably, the output data from CROCO, the ocean hydrodynamic model, was employed as the primary dataset, palliating the limitation of time-continuous historical data. This study highlights the value of models interpretability, fair models comparison methodology, and the incorporation of Stream Learning models. The model DoME, with an average R2 of 0.77 in the 3-day-ahead prediction, emerged as the most effective and interpretable predictor, outperforming the other algorithms.

Path Planning methods for autonomously controlling swarms of unmanned aerial vehicles (UAVs) are gaining momentum due to their operational advantages. An increasing number of scenarios now require autonomous control of multiple UAVs, as autonomous operation can significantly reduce labor costs. Additionally, obtaining optimal flight paths can lower energy consumption, thereby extending battery life for other critical operations. Many of these scenarios, however, involve obstacles such as power lines and trees, which complicate Path Planning. This paper presents an evolutionary computation-based system employing genetic algorithms to address this problem in environments with obstacles. The proposed approach aims to ensure complete coverage of areas with fixed obstacles, such as in field exploration tasks, while minimizing flight time regardless of map size or the number of UAVs in the swarm. No specific goal points or prior information beyond the provided map is required. The experiments conducted in this study used five maps of varying sizes and obstacle densities, as well as a control map without obstacles, with different numbers of UAVs. The results demonstrate that this method can determine optimal paths for all UAVs during full map traversal, thus minimizing resource consumption. A comparative analysis with other state-of-the-art approach is presented to highlight the advantages and potential limitations of the proposed method.

In recent years, mainly due to the application of smartphones in this area, research in human activity recognition (HAR) has shown a continuous and steady growth. Thanks to its wide range of sensors, its size, its ease of use, its low price and its applicability in many other fields, it is a highly attractive option for researchers. However, the vast majority of studies carried out so far focus on laboratory settings, outside of a real-life environment. In this work, unlike in other papers, progress was sought on the latter point. To do so, a dataset already published for this purpose was used. This dataset was collected using the sensors of the smartphones of different individuals in their daily life, with almost total freedom. To exploit these data, numerous experiments were carried out with various machine learning techniques and each of them with different hyperparameters. These experiments proved that, in this case, tree-based models, such as Random Forest, outperform the rest. The final result shows an enormous improvement in the accuracy of the best model found to date for this purpose, from 74.39% to 92.97%.

Nowadays, the field of human activity recognition (HAR) is a remarkably hot topic within the scientific community. Given the low cost, ease of use and high accuracy of the sensors from different wearable devices and smartphones, more and more researchers are opting to do their bit in this area. However, until very recently, all the work carried out in this field was done in laboratory conditions, with very few similarities with our daily lives. This paper will focus on this new trend of integrating all the knowledge acquired so far into a real-life environment. Thus, a dataset already published following this philosophy was used. In this way, this work aims to be able to identify the different actions studied there. In order to perform this classification, this paper explores new designs and architectures for models inspired by the ones which have yielded the best results in the literature. More specifically, different configurations of Convolutional Neural Networks (CNN) and Long-Short Term Memory (LSTM) have been tested, but on real-life conditions instead of laboratory ones. It is worth mentioning that the hybrid models formed from these techniques yielded the best results, with a peak accuracy of 94.80% on the dataset used.

Year after year, one recurrent complaint made by the students is always related to the grading of assignments and practical exercises. They usually perceive the correction and marking method as unclear or non-existent until the submission. For this last reason, this work explores the different alternatives available within the e-learning tool of the University of A Coruña, to correct this perception. To carry it out, we focused on two subjects in the fourth year of the Degree in Computer Science, which are taken by students in consecutive four-month terms, thereby, simplifying the implementation of a comparative study within the same groups without interfering with the normal development of the subjects. The evaluation was carried out from two points of view, firstly, the perception of the students reflected in the course surveys within the university's quality evaluation program. Secondly, the purely academic performance on the average of the academic qualifications. The results show that among the proposed qualification schemes, the public rubric is the one that produces the best academic results over time, while the correction guides are the best perceived by students.

Loans are financing services for clients of a bank and are one of the main activities in a financial institution since they are the means through which they make money. When a customer misses one or more payments cause grave problems at the bank at the point of crash. The bank loan manager to decide decides whether to approve or not the loan application using the client’s financial and personal information. This decision always has associated risks. Currently, financial institutions, to reduce the risks associated with loan approval and take advantage of the large repositories of historical data from their clients, are using machine learning algorithms to identify if a client will comply with the loan payment. That information helps managers in their decision-making process. This paper presents the development of an application to support the process of authorizing or not a bank loan in the Acción Imbaburapak Savings and credit cooperative; to choose the model to use in the application, select after training three predictive methods. The analytical process followed the phases proposed by the KDD methodology. Three supervised classification methods were selected: logistic regression, decision trees, and neural networks. Since the neural network showed the best results during the evaluation, we chose this to build the application.

Harmful algal blooms (HABs) are episodes of high concentrations of algae that are potentially toxic for human consumption. Mollusc farming can be affected by HABs because, as filter feeders, they can accumulate high concentrations of marine biotoxins in their tissues. To avoid the risk to human consumption, harvesting is prohibited when toxicity is detected. At present, the closure of production areas is based on expert knowledge and the existence of a predictive model would help when conditions are complex and sampling is not possible. Although the concentration of toxin in meat is the method most commonly used by experts in the control of shellfish production areas, it is rarely used as a target by automatic prediction models. This is largely due to the irregularity of the data due to the established sampling programs. As an alternative, the activity status of production areas has been proposed as a target variable based on whether mollusc meat has a toxicity level below or above the legal limit. This new option is the most similar to the actual functioning of the control of shellfish production areas. For this purpose, we have made a comparison between hybrid machine learning models like Neural-Network-Adding Bootstrap (BAGNET) and Discriminative Nearest Neighbor Classification (SVM-KNN) when estimating the state of production areas. The study has been carried out in several estuaries with different levels of complexity in the episodes of algal blooms to demonstrate the generalization capacity of the models in bloom detection. As a result, we could observe that, with an average recall value of 93.41% and without dropping below 90% in any of the estuaries, BAGNET outperforms the other models both in terms of results and robustness.

Human activity recognition (HAR) has garnered significant scientific interest in recent years. The widespread use of smartphones enabled convenient and cost-effective data collection, eliminating the need for additional wearables. Given that, this paper introduces a novel HAR dataset in which participants had freedom in choosing smartphone orientation and placement during activities, ensuring data variability. It also includes contributions from diverse individuals, reflecting unique smartphone usage habits. Moreover, it comprises measurements from accelerometer, gyroscope, magnetometer, and GPS, corresponding to one of four activities: inactive, active, walking, or driving. Unlike other datasets, the collected data in this study were obtained from smartphones used in real-life scenarios

Based on a solid mathematical background, this paper proposes a method for Symbolic Regression that enables the extraction of mathematical expressions from a dataset. Contrary to other approaches, such as Genetic Programming, the proposed method is deterministic and, consequently, does not require the creation of a population of initial solutions. Instead, a simple expression is grown until it fits the data. This method has been compared with four well-known Symbolic Regression techniques with a large number of datasets. As a result, on average, the proposed method returns better performance than the other techniques, with the advantage of returning mathematical expressions that can be easily used by different systems. Additionally, this method makes it possible to establish a threshold at the complexity of the expressions generated, i.e., the system can return mathematical expressions that are easily analyzed by the user, as opposed to other techniques that return very large expressions.

There has been steady growth in the adoption of Unmanned Aerial Vehicle (UAV) swarms by operators due to their time and cost benefits. However, this kind of system faces an important problem, which is the calculation of many optimal paths for each UAV. Solving this problem would allow control of many UAVs without human intervention while saving battery between recharges and performing several tasks simultaneously. The main aim is to develop a Reinforcement Learning based system capable of calculating the optimal flight path for a UAV swarm. This method stands out for its ability to learn through trial and error, allowing the model to adjust itself. The aim of these paths is to achieve full coverage of an overflight area for tasks such as field prospection, regardless of map size and the number of UAVs in the swarm. It is not necessary to establish targets or to have any previous knowledge other than the given map. Experiments have been conducted to determine whether it is optimal to establish a single control for all UAVs in the swarm or a control for each UAV. The results show that it is better to use one control for all UAVs because of the shorter flight time. In addition, the flight time is greatly affected by the size of the map. The results give starting points for future research, such as finding the optimal map size for each situation.

Mussel farming is one of the most important aquaculture industries. The main risk to mussel farming is harmful algal blooms (HABs), which pose a risk to human consumption. In Galicia, the Spanish main producer of cultivated mussels, the opening and closing of the production areas is controlled by a monitoring program. In addition to the closures resulting from the presence of toxicity exceeding the legal threshold, in the absence of a confirmatory sampling and the existence of risk factors, precautionary closures may be applied. These decisions are made by experts without the support or formalisation of the experience on which they are based. Therefore, this work proposes a predictive model capable of supporting the application of precautionary closures. Achieving sensitivity, accuracy and kappa index values of 97.34%, 91.83% and 0.75 respectively, the kNN algorithm has provided the best results. This allows the creation of a system capable of helping in complex situations where forecast errors are more common.

The number of applications using unmanned aerial vehicles (UAVs) is increasing. The use of UAVs in swarms makes many operators see more advantages than the individual use of UAVs, thus reducing operational time and costs. The main objective of this work is to design a system that, using Reinforcement Learning (RL) and Artificial Neural Networks (ANNs) techniques, can obtain a good path for each UAV in the swarm and distribute the flight environment in such a way that the combination of the captured images is as simple as possible. To determine whether it is better to use a global ANN or multiple local ANNs, experiments have been done over the same map and with different numbers of UAVs at different altitudes. The results are measured based on the time taken to find a solution. The results show that the system works with any number of UAVs if the map is correctly partitioned. On the other hand, using local ANNs seems to be the option that can find solutions faster, ensuring better trajectories than using a single global network. There is no need to use additional map information other than the current state of the environment, like targets or distance maps.