Programa del congreso

Sound Event Localization and Detection (SELD) is a problem related to the field of machine listening whose objective is to recognize individual sound events, detect their temporal activity, and estimate their spatial location. Thanks to the emergence of more hard-labeled audio datasets, deep learning techniques have become state-of-the-art solutions. The most common ones are those that implement a convolutional recurrent network (CRNN) having previously transformed the audio signal into multichannel 2D representation. The squeeze-excitation technique can be considered as a convolution enhancement that aims to learn spatial and channel feature maps independently rather than together as standard convolutions do. This is usually achieved by combining some global clustering operators, linear operators and a final calibration between the block input and its learned relationships. This work aims to improve the accuracy results of the baseline CRNN presented in DCASE 2020 Task 3 by adding residual squeeze-excitation (SE) blocks in the convolutional part of the CRNN. The followed procedure involves a grid search of the ratio parameter (used in the linear relationships) of the residual SE block, whereas the hyperparameters of the network remain the same as in the baseline. Experiments show that by simply introducing the residual SE blocks, the results obtained are able to improve the baseline considerably.

We present our solution for the IEEE Signal Processing Cup 2021 challenge. The goal is to maximize the weighted average achievable rate for a set of N_u = 50 users assisted by an intelligent reflecting surface (IRS). We combined a modified least-squares smoothing estimator, several variations over the strongest-tap maximization (STM) algorithm, and a final fine-tuning optimization that explored solutions in the vicinity of the STM solutions. Simulations show that our IRS configurations yield an estimated weighted achievable rate slightly over 117 Mbps.

In the context of statistics, survival analysis is commonly used for clinical research, although the biased and/or incomplete nature of the clinical data hampers its direct application. This work presents a survival analysis using standard methods (Kaplan-Meier estimator and Cox model), applied to kidney transplantations in the population of Andalusia, with data collected between 2006 and 2019 and following a methodology for the adequacy of the clinical data. The study allows the analysis of the influence of the donor age in the outcomes of renal transplant. As result, we conclude that the donor age is an important factor for the failure probability of the kidney graft, although differences of this influence can be reported when diverse populations are considered by age ranges.

Virtual reality (VR) experiences are transforming the way cultural heritage institutions exhibit their works of art and the contextual information in which they were conceived. This paper presents a VR experience intended to bring closer to the public the figure of the Dutch painter Piet Mondrian. The tool, completely immersive, make use of Oculus Rift S head mounted display (HMD) to introduce the user in the life and work of this artist. Playing around with “Composition A”, the subject could achieve a better comprehension of the wok itself. The tool, programmed with Unity, guides the subject who is constantly appealed by the numerous interactive elements present in the scene. This application could be extended to any artist or any artwork to shorten the gap between the public and art itself. Digital exhibitions, art museums, universities, are only some of the possible benefited of such immersive tools

In recent years, the main problem to be solved by the whole world has been the Covid-19 pandemic. Most countries have taken measures aimed at reducing mobility as the main tool in the fight against the spread of the virus. This article presents a case study of the impact of mobility in contagions for the municipality of Málaga, Spain. Aggregated point of sale purchase registers are used as mobility data within the area of study. The obtained results hint that commercial activity is not the main vector of contagion on the available data on Málaga, although the data volume is insufficient to draw a sharp conclusion.