Showing papers by "Miguel Ferrer published in 2020"

Handwriting Biometrics: Applications and Future Trends in e-Security and e-Health

Abstract: Online handwritten analysis presents many applications in e-security, signature biometrics being the most popular but not the only one. Handwriting analysis also has an important set of applications in e-health. Both kinds of applications (e-security and e-health) have some unsolved questions and relations among them that should be addressed in the next years. We summarize the state of the art and applications based on handwriting signals. Later on, we focus on the main achievements and challenges that should be addressed by the scientific community, providing a guide for future research. Among all the points discussed in this article, we remark the importance of considering security, health, and metadata from a joint perspective. This is especially critical due to the risks inherent when using these behavioral signals.

iDeLog: Iterative Dual Spatial and Kinematic Extraction of Sigma-Lognormal Parameters

Abstract: The Kinematic Theory of rapid movements and its associated Sigma-Lognormal model have been extensively used in a large variety of applications. While the physical and biological meaning of the model have been widely tested and validated for rapid movements, some shortcomings have been detected when it is used with continuous long and complex movements. To alleviate such drawbacks, and inspired by the motor equivalence theory and a conceivable visual feedback, this paper proposes a novel framework to extract the Sigma-Lognormal parameters, namely iDeLog. Specifically, iDeLog consists of two steps. The first one, influenced by the motor equivalence model, separately derives an initial action plan defined by a set of virtual points and angles from the trajectory and a sequence of lognormals from the velocity. In the second step, based on a hypothetical visual feedback compatible with an open-loop motor control, the virtual target points of the action plan are iteratively moved to improve the matching between the observed and reconstructed trajectory and velocity. During experiments conducted with handwritten signatures, iDeLog obtained promising results as compared to the previous development of the Sigma-Lognormal.

NFKB2 polymorphisms associate with the risk of developing rheumatoid arthritis and response to TNF inhibitors : Results from the REPAIR consortium

Abstract: This study sought to evaluate the association of 28 single nucleotide polymorphisms (SNPs) within NFKB and inflammasome pathway genes with the risk of rheumatoid arthritis (RA) and response to TNF inhibitors (TNFi). We conducted a case-control study in a European population of 1194 RA patients and 1328 healthy controls. The association of potentially interesting markers was validated with data from the DANBIO (695 RA patients and 978 healthy controls) and DREAM (882 RA patients) registries. The meta-analysis of our data with those from the DANBIO registry confirmed that anti-citrullinated protein antibodies (ACPA)-positive subjects carrying the NFKB2rs11574851T allele had a significantly increased risk of developing RA (PMeta_ACPA + = 0.0006) whereas no significant effect was found in ACPA-negative individuals (PMeta_ACPA- = 0.35). An ACPA-stratified haplotype analysis including both cohorts (n = 4210) confirmed that ACPA-positive subjects carrying the NFKB2TT haplotype had an increased risk of RA (OR = 1.39, P = 0.0042) whereas no effect was found in ACPA-negative subjects (OR = 1.04, P = 0.82). The meta-analysis of our data with those from the DANBIO and DREAM registries also revealed a suggestive association of the NFKB2rs1056890 SNP with larger changes in DAS28 (OR = 1.18, P = 0.007). Functional experiments showed that peripheral blood mononuclear cells from carriers of the NFKB2rs1005044C allele (in LD with the rs1056890, r2 = 1.00) showed increased production of IL10 after stimulation with LPS (P = 0.0026). These results provide first evidence of a role of the NFKB2 locus in modulating the risk of RA in an ACPA-dependent manner and suggest its implication in determining the response to TNFi. Additional studies are now warranted to further validate these findings.

Neumonía intrahospitalaria. Normativa de la Sociedad Española de Neumología y Cirugía Torácica (SEPAR). Actualización 2020

Abstract: Resumen La neumonia intrahospitalaria (NIH) es la segunda causa de infeccion nosocomial y la que conlleva mayor movilidad y mortalidad. Hoy en dia se clasifica en tres grupos: NIH que no requiere ventilacion artificial, NIH que requiere ventilacion artificial y NIH adquirida durante la ventilacion artificial (NAV). Las ultimas normativas para el manejo de la NIH se han publicado en 2016 (IDSA/ATS) y el 2017 (ERS/ESCMID/ESICM y ALAT). Las ultimas normativas espanolas se publicaron en el ano 2011 en Archivos de Bronconeumologia. Las normativas americanas del 2016 y las internacionales del 2017 presentan sus recomendaciones en un marco de gran aumento de resistencias de los microorganismos a los antibacterianos, tanto para Gram positivos y muy especialmente para Gram negativos. La SEPAR celebro en el 2019 el ano de la neumonia y creyo conveniente actualizar las normativas publicadas en el 2011.En estas normativas han participado neumologos, intensivistas,infectologos y metodologos. Se consensuo realizar las normativas con el siguiente esquema 1. Formulacion de preguntas - ?Son similares la epidemiologia y microbiologia de la NIH y la NAV - Son validos los factores de riesgo para predecir la etiologia de las NIH y NAV causada por microorganismos multirresistentes (MDR) y extremadamente resistentes (XDR) - ?Son efectivos los biomarcadores para el diagnostico y para guiar la duracion del tratamiento? - Cual es el algoritmo de tratamiento empirico actual? - ?Influye la duracion del tratamiento antibiotico de 7-8 dias vs 14 dias en el desenlace de los pacientes? - Cual es la indicacion mas adecuada de los nuevos antibioticos? 2. Cada pregunta contiene los siguientes apartados - Controversia - Evidencia - Directrices - Estudios para recomendados para resolver la controversia - Todas las directrices se consensuaron por el 100% de los expertos

Investigating the Common Authorship of Signatures by Off-Line Automatic Signature Verification Without the Use of Reference Signatures

Abstract: In automatic signature verification, questioned specimens are usually compared with reference signatures. In writer-dependent schemes, a number of reference signatures are required to build up the individual signer model while a writer-independent system requires a set of reference signatures from several signers to develop the model of the system. This paper addresses the problem of automatic signature verification when no reference signatures are available. The scenario we explore consists of a set of signatures, which could be signed by the same author or by multiple signers. As such, we discuss three methods which estimate automatically the common authorship of a set of off-line signatures. The first method develops a score similarity matrix, worked out with the assistance of duplicated signatures; the second uses a feature-distance matrix for each pair of signatures; and the last method introduces pre-classification based on the complexity of each signature. Publicly available signatures were used in the experiments, which gave encouraging results. As a baseline for the performance obtained by our approaches, we carried out a visual Turing Test where forensic and non-forensic human volunteers, carrying out the same task, performed less well than the automatic schemes.

Transporting Biodiversity Using Transmission Power Lines as Stepping-Stones?

Abstract: The most common ecological response to climate change is the shifts in species distribution ranges. Nevertheless, landscape fragmentation compromises the ability of limited dispersal species to move following these climate changes. Building connected environments that enable species to track climate changes is an ultimate goal for biodiversity conservation. Here, we conducted an experiment to determine if electric power transmission lines could be transformed in a continental network of biodiversity reserves for small animals. We analysed if the management of the habitat located inside the base of the transmission electric towers (providing refuge and planting seedlings of native shrub) allowed to increase local richness of target species (i.e., small mammals and some invertebrates’ groups). Our results confirmed that by modifying the base of the electric transmission towers we were able to increase density and diversity of several species of invertebrates and small mammals as well as number of birds and bird species, increasing local biodiversity. We suggest that modifying the base of the electric towers would potentially facilitate the connection of fragmented populations. This idea would be easily applicable in any transmission line network anywhere around the world, making it possible for the first time to build up continental scale networks of connectivity.

Human or Machine? It Is Not What You Write, But How You Write It

Abstract: Online fraud often involves identity theft. Since most security measures are weak or can be spoofed, we investigate a more nuanced and less explored avenue: behavioral biometrics via handwriting movements. This kind of data can be used to verify whether a user is operating a device or a computer application, so it is important to distinguish between human and machine-generated movements reliably. For this purpose, we study handwritten symbols (isolated characters, digits, gestures, and signatures) produced by humans and machines, and compare and contrast several deep learning models. We find that if symbols are presented as static images, they can fool state-of-the-art classifiers (near 75% accuracy in the best case) but can be distinguished with remarkable accuracy if they are presented as temporal sequences (95% accuracy in the average case). We conclude that an accurate detection of fake movements has more to do with how users write, rather than what they write. Our work has implications for computerized systems that need to authenticate or verify legitimate human users, and provides an additional layer of security to keep attackers at bay.

Juvenile dispersal in an uninhabited continent: young Spanish Imperial Eagles in Africa

Abstract: The Spanish Imperial Eagle (Aquila adalberti) disappeared from Africa as a breeding species in the 1960s coincident with a general decline of their populations in the Iberian Peninsula. Because of a combination of successful conservation actions and a general change in human attitudes, the Spanish Imperial Eagle population has been increasing in Iberia from 103 pairs in 1980 to more than 500 breeding pairs in 2018. As a consequence, the number of juveniles that cross the Strait of Gibraltar into Africa has increased recently. Abundance and distribution of potential prey should affect young eagles’ behaviour and could be a limiting factor for a potential re-colonization of previous North-African populations. Additionally, determination of temporary settlement areas is crucial from a conservation point of view. Conservation actions in these areas, particularly reduction of juvenile mortality, are a priority to facilitate future reestablishment of breeding populations of the species in North Africa. Here we report on the dispersal movements of juvenile Spanish Imperial Eagles marked with GPS-GSM transmitters in Andalusia (southern Spain), some of which crossed the Strait of Gibraltar into north-western Africa, an area that does not have populations of the eagle’s main prey, the European rabbit. We analysed the differences in dispersal patterns and temporary settlement behaviour in the two study areas. We found that dispersal movements were greater, temporary settlement areas were larger, and individuals stayed longer in areas and moved greater distances among them in Africa than in Iberia. We believe that our results are best explained by applying the Marginal Value Theorem, which predicts that individuals will leave a foraging area when the availability of prey drops to similar levels of those of the surrounding environment. We suggest that the increase in the records of the species in Africa could lead to a recolonization of the species in Africa based on birds coming from the “source” Iberian population, but only if the Iberian population continues to increase. We recommend that conservation measures must be established in these temporary settlement areas in Africa.

Towards a Man - Machine Interaction in Programming Robotic Subject

Abstract: This article begins by generally addressing the fundamentals of educational robotics, to later conclude that human-robot interaction practices constitute an activity that meets the purposes of this new discipline, and that significantly improves motivation and involvement of students in academic work. Specifically, teachers are provided with a proposal for laboratory practice that develops robot control by hand movement. This lab activity, aimed at developing students' programming skills, includes the installation of Leap Motion, which recognizes the hand gestures, and the steps to follow to achieve its communication with the ABB industrial robot, model IRB 120, which will execute the commands within specific coordinates that the student will program. through the connection between Leap Motion-Matlab RobotStudio-Robot ABB IRB 120.

Off-line Signature Verification Using Multidirectional Run-Length Features

Abstract: Run-length features have shown its effectivity in off-line signature verification. Configurations of these handcrafted features include four direction-based features. In this paper, we propose to add further spatial information of the signature to the standard run-length features. Such information is worked out in two stages: firstly, beyond classical four directions, more directions are studied. Secondly, improving the knowledge of each direction by combining the information of the neighbor directions. This new configuration has been used in two classifiers, one based on Euclidean distance and another based on a one-class support vector machine. We outperformed previous performances with the proposed configuration regarding the last ICFHR 2018 competition on Thai student signatures and GPDS-960 signature database.