Jesus Salido

Esta nueva versión surge de los comentarios de realimentación recibidos por los usuarios de esta y un proceso natural de evolución de este proyecto. Cada poco tiempo descubro algo nuevo que puedo modificar y que, en mi opinión, mejora el resultado final o la experiencia del usuario. En esta nueva release de la plantilla he decidido incluir bastantes cambios para facilitar su uso y configuración.

Currently, microalgae (i.e., diatoms) constitute a generally accepted bioindicator of water quality and therefore provide an index of the status of biological ecosystems. Diatom detection for specimen counting and sample classification are two difficult time-consuming tasks for the few existing expert diatomists. To mitigate this challenge, in this work, we propose a fully operative low-cost automated microscope, integrating algorithms for: (1) stage and focus control, (2) image acquisition (slide scanning, stitching, contrast enhancement), and (3) diatom detection and a prospective specimen classification (among 80 taxa). Deep learning algorithms have been applied to overcome the difficult selection of image descriptors imposed by classical machine learning strategies. With respect to the mentioned strategies, the best results were obtained by deep neural networks with a maximum precision of 86% (with the YOLO network) for detection and 99.51% for classification, among 80 different...

Given that angiogenesis and lymphangiogenesis are strongly related to prognosis in neoplastic and other pathologies and that many methods exist that provide different results, we aim to construct a morphometric tool allowing us to measure different aspects of the shape and size of vascular vessels in a complete and accurate way. The developed tool presented is based on vessel closing which is an essential property to properly characterize the size and the shape of vascular and lymphatic vessels. The method is fast and accurate improving existing tools for angiogenesis analysis. The tool also improves the accuracy of vascular density measurements, since the set of endothelial cells forming a vessel is considered as a single object.

Diatom identification is a crucial process to estimate water quality, which is essential in biological studies. This process can be automated with machine learning algorithms. For this purpose, a dataset with 10 common taxa is collected, with annotations provided by an expert diatomist. In this work, a comparison of the classical state-of-the-art general purpose methods along with two different deep learning approaches is carried out. The classical methods are based on Viola-Jones and scale and curvature invariant ridge object detectors. The deep learning based methods are Semantic Segmentation and YOLO. This is the first time that Viola-Jones and Semantic Segmentation techniques are applied and compared for diatom segmentation in microscopic images containing several taxon shells. While all methods provide relatively good results in specific species, the deep learning approaches are consistently better in terms of sensitivity and specificity (up to 0.99 for some taxa) and up to 0.8...

There is a great need to implement preventive mechanisms against shootings and terrorist acts in public spaces with a large influx of people. While surveillance cameras have become common, the need for monitoring 24/7 and real-time response requires automatic detection methods. This paper presents a study based on three convolutional neural network (CNN) models applied to the automatic detection of handguns in video surveillance images. It aims to investigate the reduction of false positives by including pose information associated with the way the handguns are held in the images belonging to the training dataset. The results highlighted the best average precision (96.36%) and recall (97.23%) obtained by RetinaNet fine-tuned with the unfrozen ResNet-50 backbone and the best precision (96.23%) and F1 score values (93.36%) obtained by YOLOv3 when it was trained on the dataset including pose information. This last architecture was the only one that showed a consistent improvement—aroun...

Deep learning (henceforth DL) has become most powerful machine learning methodology. Under specific circumstances recognition rates even surpass those obtained by humans. Despite this, several works have shown that deep learning produces outputs that are very far from human responses when confronted with the same task. This the case of the so-called “adversarial examples” (henceforth AE). The fact that such implausible misclassifications exist points to a fundamental difference between machine and human learning. This paper focuses on the possible causes of this intriguing phenomenon. We first argue that the error in adversarial examples is caused by high bias, i.e. by regularization that has local negative effects. This idea is supported by our experiments in which the robustness to adversarial examples is measured with respect to the level of fitting to training samples. Higher fitting was associated to higher robustness to adversarial examples. This ties the phenomenon to the tra...

Currently, microalgae (i.e., diatoms) constitute a generally accepted bioindicator of water quality and therefore provide an index of the status of biological ecosystems. Diatom detection for specimen counting and sample classification are two difficult time-consuming tasks for the few existing expert diatomists. To mitigate this challenge, in this work, we propose a fully operative low-cost automated microscope, integrating algorithms for: (1) stage and focus control, (2) image acquisition (slide scanning, stitching, contrast enhancement), and (3) diatom detection and a prospective specimen classification (among 80 taxa). Deep learning algorithms have been applied to overcome the difficult selection of image descriptors imposed by classical machine learning strategies. With respect to the mentioned strategies, the best results were obtained by deep neural networks with a maximum precision of 86{\%} (with the YOLO network) for detection and 99.51{\%} for classification, among 80 dif...

Several studies have established a relationship between the preoperative hemoglobin level and the need for postoperative blood transfusion. We analyzed the relationship between preoperative hemoglobin levels, as well as other factors such as age, gender, weight, height, type and duration of the total joint replacement surgery, and the need for postoperative blood transfusion. A retrospective study of 296 patients treated with 370 procedures (209 total hip arthroplasties [56.5%] and 161 total knee arthroplasties [43.5%]) from 1994 to 1998 was carried out. A univariate analysis was performed to establish the relationship between all independent variables and the need for postoperative transfusion. Variables that were determined to have a significant relationship were included in a multivariate analysis. The univariate analysis revealed a significant relationship between the need for postoperative blood transfusion and preoperative hemoglobin levels (p = 0.0001), duration of surgery (p = 0.0001), weight (p = 0.002), height (p = 0.019), and gender (p = 0.0056). However, the multivariate analysis identified a significant relationship only between the need for transfusion and the preoperative hemoglobin level (p = 0.0001) and weight (p = 0.011); height (p = 0.776) and gender (p = 0.122) were discounted as significant factors. Patients with a preoperative hemoglobin level of <130 g/L had a four times greater risk of having a transfusion than did those with a hemoglobin level between 130 and 150 g/L and a 15.3 times greater risk than did those with a hemoglobin level of >150 g/L. The preoperative hemoglobin level (p = 0.0001) and weight of the patient (p = 0.011) were shown to predict the need for blood transfusion after hip and knee replacement.

Deals with the optimization of the reactive navigation performed with fuzzy behaviors in partially known environments. It offers the integration of the fuzzy behaviors with global path-planning techniques in a nested hierarchical architecture for autonomous vehicle navigation. A three level architecture is proposed based on a global path-planner level, a fuzzy behaviors level and an execution level. While the global

Contenido: 1) Introducción; 2) Conceptos básicos de robótica; 3) Sistemas de locomoción de robots; 4) Hardware de control; 5) Control de robots móviles; 6) Programación de robots móviles; 7) Sistemas sensoriales; 8) Dispositivos de actuación; 9) Sistemas mecánicos de transmisión de potencia; 10) Alimentación eléctrica de sistemas autónomos.

Delayed wound healing after total arthroplasty puts the patient at risk for superficial and deep infection, with substantial economic and social consequences. The objective of this study was to assess serum zinc levels as a tool for predicting such a delay in patients with primary osteoarthritis or osteoarthritis secondary to avascular necrosis. We conducted a prospective study of 80 total hip arthroplasties, analyzing possible correlations between delayed healing and serum zinc, nutritional parameters, and other demographic and epidemiological variables. The predictive value of preoperative serum zinc levels and lymphocyte counts was confirmed; thus, an arthroplasty procedure could be timed to minimize risk.

After emergency fasciotomy in acute compartment syndrome, skin graft techniques are usually necessary to cover the wound. The shoelace technique for gradual skin closure was retrospectively analyzed after having been applied in 20 patients with acute compartment syndrome. With the application of this technique, none of the cases required new surgical interventions to close the wound. Closure was reached in an average time of 8.8 days, with an average hospital stay of 10 days and a low rate of complications. Gradual skin closure using the shoelace technique avoids the use of free skin grafts to close the dermotomy-fasciotomy wounds, reducing the need for anesthesia, nursing care, and hospital stays of patients, resulting in lower healthcare costs.