Search

In recent years, Unmanned Aerial Vehicles (UAVs) have presented a variety of applications. Recent studies show their advantages when quantifying areas for storm runoff estimation. However, there are uncertainties about their actual range. Therefore, the objective of this study was to estimate the volume of rainfall captured by roofs using UAVs. The methodology consisted of selecting a study area composed of a variety of canopies, in which the areas were digitally measured, the latter by processing images captured by UAV. For the calculation of runoff volume, the average monthly precipitation data of the last 11 years were taken, and the Runoff Coefficients (Ce) reported in the literature were considered. Then, the mean monthly runoff volume was calculated for each canopy. The results show that the roofs studied (Coliseum - Library) have the capacity to capture an annual volume of 2237.75 m3. With an average volume of 406.74 m3 during the rainy season (November to March) and 29.15 m3 during the dry season (April to October). Although the use of UAV allows determining one of the values within the runoff volume calculation, in order to achieve a more accurate result, it is necessary to analyze and evaluate the other variables (Ce and precipitation)., En los últimos años, los Vehículos Aéreos No Tripulados (VANT) han presentado una variedad de aplicaciones. Estudios recientes demuestran sus ventajas al momento de cuantificar áreas para la estimación de escorrentía pluvial. Sin embargo, existen incertidumbres sobre su alcance real. Ante ello, el objetivo del estudio es estimar el volumen pluvial captado por cubiertas mediante VANT. La metodología consistió en seleccionar una zona de estudio compuesta por una variedad de cubiertas, en el que las áreas fueron medidas digitalmente, esta última por medio del procesamiento de imágenes captadas por VANT. Para el cálculo de volumen de escurrimiento, se tomaron los datos de precipitación media mensual de los últimos 11 años, y se consideraron los Coeficientes de Escorrentía (Ce) reportados en la literatura. A continuación, se calculó el volumen de escurrimiento medio mensual para cada cubierta. Los resultados muestran que las cubiertas estudiadas (Coliseo - Biblioteca), tienen la capacidad de captar un volumen anual de 2237.75 m3. Con un volumen promedio de 406.74 m3 durante la época lluviosa (noviembre a marzo) y 29.15 m3 en la época seca (abril a octubre). Aunque el uso de VANT permite determinar uno de los valores dentro del cálculo de volumen de escorrentía, para lograr un resultado más exacto, es preciso analizar y evaluar las otras variables (Ce y precipitación).

Our study determines alterations in the vasoconstrictor response elicited by electric field stimulation (EFS) in mesenteric arteries from cirrhotic rats treated with CCl(4), and how calcitonin gene-related peptide (CGRP) participates in this response. Vasoconstriction induced by EFS was analysed in the absence and presence of the CGRP receptor antagonist CGRP(8-37) in arterial segments from control and cirrhotic rats. The vasodilator response to exogenous CGRP was tested in both groups of rats, and the interference of the guanylate cyclase inhibitor ODQ or the K(ATP) channel blocker glibenclamide was analysed only in segments from cirrhotic rats. The vasodilator response to the K(ATP) channel opener pinacidil and to 8-bromo-cyclic GMP was tested. The K(ATP) currents were recorded using the patch-clamp technique. Expression of receptor activity-modifying protein 1 (RAMP1), calcitonin receptor-like receptor, Kir 6.1 and sulfonylurea receptor 2B (SUR2B) was also analysed. Release of CGRP and cGMP was measured. The EFS-elicited vasoconstriction was less in segments from cirrhotic rats. The presence of CGRP(8-37) increased the EFS-induced response only in segments from cirrhotic rats. The CGRP-induced vasodilatation was greater in segments from cirrhotic rats, and was inhibited by ODQ or glibenclamide. Both pinacidil and 8-bromo-cyclic GMP induced a stronger vasodilator response in segments from cirrhotic rats. Pinacidil induced greater K(ATP) currents in cirrhotic myocytes. Expression of RAMP1, calcitonin receptor-like receptor, Kir 6.1 and SUR2B was not modified by liver cirrhosis. Liver cirrhosis increased CGRP release, but did not modify cGMP formation. The decreased vasoconstrictor response to EFS in cirrhosis is mediated by increased vasodilator response to CGRP, as well as increased K(ATP) channel gating. This effect of CGRP may play a role in the splanchnic vasodilatation present in liver cirrhosis., Instituto de Salud Carlos III Spanish Government DEP2006-56187-C04-04, Ministerio de Ciencia e Innovación (SAF09-10374), Depto. de Biología Celular, Fac. de Odontología, TRUE, pub

Este proyecto tiene como objetivo reducir el proceso necesario para la detección del Alzheimer, para lograr este objetivo, se ha intentado desarrollar una herramienta que a través del aprendizaje automático y utilizando la información volumétrica extraída de resonancias magnéticas, permita un diagnóstico fiable del Alzheimer.

Non-motor manifestations of Parkinson’s disease (PD) appear early and have a significant impact on the quality of life of patients, but few studies have evaluated their predictive potential with machine learning algorithms. We evaluated 9 algorithms for discriminating PD patients from controls using a wide collection of non-motor clinical PD features from two databases: Biocruces (96 subjects) and PPMI (687 subjects). In addition, we evaluated whether the combination of both databases could improve the individual results. For each database 2 versions with different granularity were created and a feature selection process was performed. We observed that most of the algorithms were able to detect PD patients with high accuracy (>80%). Support Vector Machine and Multi-Layer Perceptron obtained the best performance, with an accuracy of 86.3% and 84.7%, respectively. Likewise, feature selection led to a significant reduction in the number of variables and to better performance. Besides, the enrichment of Biocruces database with data from PPMI moderately benefited the performance of the classification algorithms, especially the recall and to a lesser extent the accuracy, while the precision worsened slightly. The use of interpretable rules obtained by the RIPPER algorithm showed that simply using two variables (autonomic manifestations and olfactory dysfunction), it was possible to achieve an accuracy of 84.4%. Our study demonstrates that the analysis of non-motor parameters of PD through machine learning techniques can detect PD patients with high accuracy and recall, and allows us to select the most discriminative non-motor variables to create potential tools for PD screening.

Nowadays, considering society’s highly demanding lifestyles, it is important to consider the usefulness of relaxation from the perspective of both psychology and clinical practice. The response towards relaxation (RResp) is a mind-body interaction that relaxes the organism or compensates for the physiological effects caused by stress. This work aims to automatically detect the different mental states (relaxation, rest and stress) in which RResps may occur so that complete feedback about the quality of the relaxation can be given to the subject itself, the psychologist or the doctor. To this end, an experiment was conducted to induce both states of stress and relaxation in a sample of 20 university students (average age of 25.76±3.7 years old). The electrocardiographic and electrodermal activity signals collected from the participants produced a dataset with 1641 episodes or instances in which the previously mentioned mental states take place. This data was used to extract up to 50 features and train several supervised learning algorithms (rule-based, trees, probabilistic, ensemble classifiers, etc.) using and not using feature selection techniques. Besides, the authors synthesised the cardiac activity information into a single new feature and discretised it down to three levels. The experimentation revealed which features were most discriminating, reaching a classification average accuracy of up to 94.01±1.73% with the 6 most relevant features for the own-collected dataset. Finally, being restrictive, the same solution/subspace was tested with a dataset referenced in the bibliography (WESAD) and scored an average accuracy of 90.36±1.62%.

More than half of patients with high spinal cord injury (SCI) suffer from episodes of autonomic dysreflexia (AD), a condition that can lead to lethal situations, such as cerebral haemorrhage, if not treated correctly. Clinicians assess AD using clinical variables obtained from the patient’s history and physiological variables obtained invasively and non-invasively. This work aims to design a machine learning-based system to assist in the initial diagnosis of AD. For this purpose, 29 patients with SCI participated in a test at Cruces University Hospital in which data were collected using both invasive and non-invasive methods. The system proposed in this article is based on a two-level hierarchical classification to diagnose AD and only uses 35 features extracted from the non-invasive stages of the experiment (clinical and physiological features). The system achieved a 93.10% accuracy with a zero false negative rate for the class of having the disease, an essential condition for treating patients according to medical criteria.

[EN] The use of decision trees considerably improves the discriminating capacity of ensemble classifiers. However, this process results in the classifiers no longer being interpretable, although comprehensibility is a desired trait of decision trees. Consolidation (consolidated tree construction algorithm, CTC) was introduced to improve the discriminating capacity of decision trees, whereby a set of samples is used to build the consolidated tree without sacrificing transparency. In this work, PCTBagging is presented as a hybrid approach between bagging and a consolidated tree such that part of the comprehensibility of the consolidated tree is maintained while also improving the discriminating capacity. The consolidated tree is first developed up to a certain point and then typical bagging is performed for each sample. The part of the consolidated tree to be initially developed is configured by setting a consolidation percentage. In this work, 11 different consolidation percentages are considered for PCTBagging to effectively analyse the trade-off between comprehensibility and discriminating capacity. The results of PCTBagging are compared to those of bagging, CTC and C4.5, which serves as the base for all other algorithms. PCTBagging, with a low consolidation percentage, achieves a discriminating capacity similar to that of bagging while maintaining part of the interpretable structure of the consolidated tree. PCTBagging with a consolidation percentage of 100% offers the same comprehensibility as CTC, but achieves a significantly greater discriminating capacity.

A pesar de que en la actualidad el ser humano disponga de múltiples herramientas con las que poder anticipar la enfermedad de Alzheimer, a día de hoy sigue habiendo técnicas desconocidas con las que poder predecir dicha muerte neuronal. Una manera de lograr pronosticarla es mediante la realización de una punción lumbar, donde analizan principalmente diferentes tipos de proteínas. Hallar esta enfermedad a tiempo es fundamental puesto que de esta manera se podría ralentizar el proceso del envejecimiento cerebral. El objetivo al que aspira este proyecto es evitar la realización de punciones lumbares y estimar el riesgo de Alzheimer a través del análisis de resonancias magnéticas, con el fin de anticipar la enfermedad de manera más sencilla y del modo menos invasivo posible. Sin embargo, a pesar de haber trabajado tanto con modelos supervisados como semi-supervisados, no se ha logrado obtener una gran tasa de acierto. Por lo que se ha llegado a la conclusión de que a día de hoy poder predecir el Alzheimer mediante volúmenes cerebrales no es un método fiable. [Castellano]