Monitoring COVID-19 spread in selected Prague's schools based on the presence of SARS-CoV-2 RNA in wastewater.

The COVID-19 pandemic has demanded a broad range of techniques to better monitor its extent. Owing to its consistency, non-invasiveness, and cost effectiveness, wastewater-based epidemiology has emerged as a relevant approach to monitor the pandemic's course. In this work, we analyzed the extent of the COVID-19 pandemic in five primary schools in Prague, the Czech Republic, and how different preventive measures impact the presence of SARS-CoV-2 RNA copy numbers in wastewaters. Copy numbers were measured by reverse transcription-multiplex quantitative real-time PCR. These copy numbers were compared to the number of infected individuals in each school identified through regular clinical tests. Each school had a different monitoring regime and subsequent application of preventive measures to thwart the spread of COVID-19. The schools that constantly identified and swiftly quarantined infected individuals exhibited persistently low amounts of SARS-CoV-2 RNA copies in their wastewaters. In one school, a consistent monitoring of infected individuals, coupled with a delayed action to quarantine, allowed for the estimation of a linear model to predict the number of infected individuals based on the presence of SARS-CoV-2 RNA in the wastewater. The results show the importance of case detection and quarantining to stop the spread of the pandemic and its impact on the presence of SARS-CoV-2 RNA in wastewaters. This work also shows that wastewater-based epidemiological models can be reliably used even in small water catchments, but difficulties arise to fit models due to the nonconstant input of viral particles into the wastewater systems.

The Intelligent System for Mask Detection using Deep Learning

The main goal of the paper is to develop and design an intelligent system for automatic conditional access in critical virologic situations. The detection of proper use of face-mask, touchless temperature measurement, and counting incoming/outcoming people for single or multiple entrance doors or gates are the main objectives of this system. Originality and innovativeness of the paper are already in the idea, to create a new generation of affordable guard systems based on artificial intelligence with an emphasis on the pandemic situation in the world. In this paper, we will describe relevant works that used deep learning in security with compliance with pandemic regulations in comparison with proposed solution. The proposed technology will enable the start of a new generation of guard systems based on artificial intelligence with an emphasis on the pandemic regulations. This will create space for innovative solutions in the security of buildings, shops, factories, public transport stations, airports, etc. The implementation of this technology can bring revolutionary changes in society in actual situation and in the future. © 2022 IEEE.

Hyperparameter Tuning of ConvLSTM Network Models

Deep learning algorithms have achieved amazing performance in computer vision area. However, a biggest problem deep learning has, is the high dependency on hyper-parameters. The algorithm results may be different, depending on hyper-parameters. This paper presents an effective method for hyper-parameter tuning using deep learning. The deep neural network structure for video classification using Convolutional Long Short-Term Memory (ConvLSTM) was used. The proposed method for hyper-parameter tuning using ConvLSTM was described. This proposed method with hyper-parameter tuning methods (Grid search, Bayesian optimization and Genetic algorithm) was compared. The experiment results show that proposed approach using ConvLSTM can be compared with the results obtained from the methods analogs to the proposed approach. However, we are looking for other hyper-parameters, for example number of filters, filter size, number of epochs, batch size and training optimization algorithm. The proposed approach can be used for correct or incorrect use of face mask during COVID-19 pandemic. © 2021 IEEE.