Prediction of COVID-19 cases and location-allocation optimization model for bases and ambulances considering vulnerability factors

This work addresses the problem of strategic location of bases and ambulances, considering the number of inhabitants and a vulnerability weight, confirmed by socioeconomic and epidemiological elements. To this aim, we use a generalized linear model (GLM) for predicting the COVID-19 cases and a mathematical optimization model for location and allocation which maximizes coverage of population care. The methodology is applied in the Metropolitan region in Chile, analyzing the current situation of the institution of the Emergency Medical Attention Service (SAMU), institution in charge of ambulance management in the region. Likewise, the Social Priority Index (IPS) will be used as a socioeconomic factor and the number of patients confirmed by COVID-19 from March 30 to June 12, 2020. In the results, for the prediction model, a consistent projection was obtained for one week of study, with acceptable residual errors. For the optimization model, the action of the vulnerability is verified, both for a reassignment of ambulances in the system and for the incorporation of bases and/or ambulances, obtaining results in acceptable calculation times. © 2021, Universidad de Tarapaca. All rights reserved.

A Proposal for the Deep Unsupervised Identification of Relevant Areas in X-Rays for Covid Detection

Since the beginning of 2020, the diagnosis of the COVID-19 virus has been a major problem that has affected the lives of millions of people around the world. The detection time for COVID-19 with a standard detection method ranges from approximately 1 to 5 days. An efficient and fast way to detect the presence of both the COVID-19 virus is through the use of artificial intelligence (AI) techniques applied to images obtained by lung radiography. Typically, AI algorithms to detect COVID-19 consider the whole picture. However, there may be parts that affect the performance of the classifier. Furthermore, these algorithms do not indicate which is the most relevant area of this disease. In this work, we propose a deep learning approach to detect the presence of COVID-19 in lung images by recognizing the most relevant areas affected by the virus without considering human supervision. In the experiment, we considered different proposals, where the best one obtained an 88% reduction of the logit loss with respect to the baseline based on random regions near the center of the image. © 2021 IEEE.

Predicting the COVID-19 in the Metropolitan Region (Chile) using a GCN-LSTM neural network

COVID-19 is considered one of the largest pandemics in recent times. Predicting the number of future COVID-19 cases is extremely important for governments in order to make decisions about mobility restrictions, and for hospitals to be able to manage medical supplies, as well as health staff. Most of the predictions of COVID-19 cases are based on mathematical-epidemiological models such as the SEIR and SIR models. In our work, we propose a model of neural networks GCN-LSTM (Graph Convolutional Network - Long Short Term Memory) to predict the spatio-temporal rate incidence of COVID-19 in the Metropolitana Region, Chile. While the GCN network incorporates the spatial correlation in the nearby municipalities, the LSTM network considers the temporal correlation for the prediction over time. To interpolate the missing daily data for the network input, the use of the GAM (Generalized Additive Model) model is proposed. The results show better predictions for some municipalities with higher habitat density. © 2021 IEEE.

Pandemic learning ontology: Methodological aspects to assess skills in a public health emergency

The purpose of this work is to show the experience of methodological aspects which were used to assess competencies with regard to conceiving, designing, implementing and operating (CDIO), in a curriculum for competencies in the face of state of emergency in public health due to coronavirus. The situation and advances are displayed as a case study, in training civil engineering professionals in computer science at the Catholic University of Temuco (CUT) in Chile. The questions intented to be resolved are: Is it possible to improve the capacities of students from the Araucanía region (Chile) in a social-economic-cultural system, through teaching and learning based on education which allows them to discover, expand and exploit the improvement of the training of professional human capital with competencies in an emergency situation in public health due to coronavirus?. The process of validation of competencies responds to conceive, design, implement and operate (CDIO) being adapted. The way in which the transition in the levels of competencies that the progressing student advances occurs is achieved in different teaching and learning activities through online training. The implementation of competency validation is produced in different contexts in the phases: conceive, design, implement and operate, which have had to be faced by teachers, instructors, assistants for the achievement of students. © 14th IADIS International Conf. Infor. Sys. 2021. All rights reserved.