A Machine Learning Approach to Predict Radiation Effects in Microelectronic Components.

This paper presents an innovative technique, Advanced Predictor of Electrical Parameters, based on machine learning methods to predict the degradation of electronic components under the effects of radiation. The term degradation refers to the way in which electrical parameters of the electronic components vary with the irradiation dose. This method consists of two sequential steps defined as 'recognition of degradation patterns in the database' and 'degradation prediction of new samples without any kind of irradiation'. The technique can be used under two different approaches called 'pure data driven' and 'model based'. In this paper, the use of Advanced Predictor of Electrical Parameters is shown for bipolar transistors, but the methodology is sufficiently general to be applied to any other component.

Characteristics of mucocutaneous vascular malformations drawn from a decade of a multidisciplinary committee experience.

Vascular malformations (VM) are congenital, benign, and relatively frequent lesions. Scant data have been published about the epidemiology, clinical presentation, and treatment of VM from a dermatologist's perspective. The substantial differences between subtypes, broad range of specialists consulted and confusing nomenclature used over previous years may hamper a correct diagnosis. The main objective of this study is to describe VM epidemiology. As a secondary endpoint we evaluate clinical characteristics, clinical-radiological correlation and treatment approaches. We carried out an observational, descriptive, retrospective study. Cases presented to the multidisciplinary committee of our hospital from 2009 to 2019 were retrieved. Electronic medical records, monthly committee reports and the iconographic archive were reviewed and statistically analyzed. Overall, venous malformations (VeM) are the most frequent VM, followed by capillary malformations (CM), arterioVeM and lymphatic malformations (LM). Considering only patients under 16, CMs are the most frequent ones. Capillary and LMs are larger than venous or arteriovenous. While CMs are usually asymptomatic, symptomatic cases are threefold more frequent in the other subtypes. Decisions on active or conservative management depend on VM size but not location or patient age. CMs are mainly treated with laser therapy; venous with sclerotherapy or surgery; arteriovenous with surgery and lymphatic with surgery or sirolimus. Dermatologists play an important role in VM diagnosis and management. Our 10-year multidisciplinary experience should contribute to the literature and represent a practical resource for clinicians and researchers.

Type V aplasia cutis congenita in a preterm newborn successfully resolved.

Aplasia cutis congenita (ACC) associated with fetus papyraceus is a rare subtype of aplasia cutis categorized as type V in Frieden's classification. It is characterized by stellate lesions in a symmetrical distribution over the trunk and proximal extremities. Conservative treatment is recommended, but there is not a well-defined therapeutic protocol. We report the case of a type V ACC in a preterm male newborn with lesions on the trunk and scalp successfully treated with topical 1% silver sulfadiazine and petrolatum gauze with an excellent evolution. This case associates a severe affectation of the scalp which represents a rare variant of type V ACC.

Leishmaniasis mucocutánea labial, las apariencias pueden engañar / Mucocutaneous lip leishmaniasis, a diagnonstic challenge

La leishmaniasis es una infección endémica en nuestro medio. Dentro de sus presentaciones, la forma mucocutánea es la menos frecuente. A pesar de ello se ha de tener en cuenta incluso en casos clínicamente sugestivos de patología tumoral, como el que presentamos

Leishmaniasis is an endemic disease in the mediterranean region. Although mucocutaneous presentation is not frequent, we should considerate it in the differential diagnosis of tumoral pathology

Enfermedad de Riga-Fede / Riga-Fede disease

No disponible

Modelo computacional para la formación de clases de equivalencia / A Computational Model for the Formation of Equivalence Classes

A computational model of neuronal net closely related with the formation of equivalence classes is developed. First the formal pattern of the neuronal net is presented and then its operation and its direct relationship with the phenomenon of the formation of the equivalence classes and with the derived relationships are explained. Later on, the validation of the pattern is described carrying out several simulations allowing verification of the pattern so it is able to generate relationships not explicitly trained, these results being adjusted to the basic results of this investigation line. These simulations were carried out using a training of classic conditioning and a test phase by means of conditional discriminations (AU)

Se desarrolla un modelo computacional de red neuronal que está estrechamente relacionado con la formación de clases de equivalencia. Primero se presenta el modelo formal de la red neuronal para luego explicar su funcionamiento y su relación directa con el fenómeno de la formación de las clases de equivalencia y con las relaciones derivadas. Posterior- mente, se describe la validación del modelo realizando varias simulaciones permitiendo verificar así que el modelo es capaz de generar relaciones no explícitamente entrenadas, ajustándose estos resultados a los resultados básicos de esta línea de investigación. Dichas simulaciones se realizaron utilizando un entrenamiento de condicionamiento clásico y una fase de prueba mediante discriminaciones condicionales (AU)

Toxicidad cutánea inducida por el tratamiento con bleomicina / Blemycin-induced skin toxicity

No disponible