Graph-Based Audio Classification Using Pre-Trained Models and Graph Neural Networks.

Sound classification plays a crucial role in enhancing the interpretation, analysis, and use of acoustic data, leading to a wide range of practical applications, of which environmental sound analysis is one of the most important. In this paper, we explore the representation of audio data as graphs in the context of sound classification. We propose a methodology that leverages pre-trained audio models to extract deep features from audio files, which are then employed as node information to build graphs. Subsequently, we train various graph neural networks (GNNs), specifically graph convolutional networks (GCNs), GraphSAGE, and graph attention networks (GATs), to solve multi-class audio classification problems. Our findings underscore the effectiveness of employing graphs to represent audio data. Moreover, they highlight the competitive performance of GNNs in sound classification endeavors, with the GAT model emerging as the top performer, achieving a mean accuracy of 83% in classifying environmental sounds and 91% in identifying the land cover of a site based on its audio recording. In conclusion, this study provides novel insights into the potential of graph representation learning techniques for analyzing audio data.

Artificial Neural Networks as an alternative to traditional fall detection methods.

Falls are common events among older adults and may have serious consequences. Automatic fall detection systems are becoming a popular tool to rapidly detect such events, helping family or health personal to rapidly help the person that falls. This paper presents the results obtained in the process of testing a new fall detection method, based on Artificial Neural Networks (ANN). This method intends to improve fall detection accuracy, by avoiding the traditional threshold - based fall detection methods, and introducing ANN as a suitable option on this application.Also ANN have low computational cost, this characteristic makes them easy to implement on a portable device, comfortable to be wear by the patient.

Pioderma gangrenoso: reporte de caso / Pyoderma gangrenosum: case report

El pioderma gangrenoso es una enfermedad inflamatoria crónica, poco común, con una incidencia de 3 a 10 casos por millón de habitantes, su etiología aún se desconoce pero se ha asociado con múltiples condiciones sistémicas dentro de las que sobresale la enfermedad inflamatoria intestinal. Hasta el momento se conocen cuatro variantes clínicas y la más común de todas es la forma ulcerativa. El diagnóstico es principalmente clínico y de descarte. En la histología se caracteriza por un infiltrado neutrofílico de la dermis. El tratamiento de elección son los glucocorticoides orales, aunque hay otras opciones terapéuticas descritas. Reportamos un caso representativo de un pioderma gangrenoso ulcerativo asociado con enfermedad inflamatoria intestinal.

Pyoderma gangrenosum is a chronic inflammatory disease, uncommon, with an incidence of 3 to 10 cases per million inhabitants, whose etiology remains unknown but has been associated with multiple systemic conditions in which stands out inflammatory bowel disease. So far, four clinical variants are known to be the most common ulcerative form of all. The diagnosis is mainly clinical and of discard. In histology its characterized by a neutrophilic infiltrate in the dermis. The treatment of choice is oral corticosteroids, although there are many other therapeutic options described. we report a representative case of an ulcerative pyoderma gangrenosum associated with inflammatory bowel disease

Carcinoma de células de Merkel: reporte de caso / Merkel cell carcinoma: a case report

El carcinoma de células de Merkel es un tumor cutáneo inusual de características agresivas, clasificado dentro de los carcinomas neuroendocrinos; clínicamente polimorfos y su forma histológica es muy similar a otros tumores cutáneos, lo que dificulta su diagnóstico precoz. Dada su baja incidencia, la etiopatogenia de este tumor, la reciente descripción de una asociación viral y su tratamiento, son todavía motivo de investigación; por esta razón es importante conocer su fisiopatología y sus manifestaciones clínicas para hacer un diagnóstico claro, en estadios tempranos, y un tratamiento de acuerdo con la condición del paciente. Se describe el caso de un paciente inmunosuprimido con un carcinoma de células de Merkel en cara y cuero cabelludo, recidivante y metastásico, con un comportamiento conforme a lo descrito en la literatura.

Merkel cell carcinoma is an unusual cutaneous neoplasm of aggressive characteristics, classified within neuroendocrine carcinomas; clinically polymorphic and histologically similar to other skin tumors making it difficult for early diagnosis. Given its low incidence; the pathogenesis of this tumor, the recent description of a viral association and its treatment, are still matter of research; for this reason it is important to know its pathophysiology and clinical manifestations in order to perform a clear diagnostic approach in early stages, and treatment in accordance with the patient's condition. We describe the case of an inmunosupressed patient with a Merkel cell carcinoma on face and scalp, recurrent and metastatic, with an evolution consistent to reports in the literature.