Coronavirus Label-Free Immunosensor: Preliminary Results

Real-time detection of airborne infection agents present in human breath and environmental airways, such as the human respiratory Coronavirus, is important for public health. For this, a model label-free immunosensor, based on multi-walled nanotubes (MWNT)-based screen-printed graphite electrodes (SPEs), was proposed and studied. For sensing applications, MWNTs have many advantages such as small size with larger surface area, excellent electron transfer promoting ability when used for antibody immobilization, with retention of its selectivity for potential immunosensors development. In order to verify the selectivity of the selected primary antibody (anti-CoV 229E antibody) and the effective immunocomplex formation (antigen-antibody), an in-depth voltammetric characterization of MWNT-SPEs interface was carried out during the multistep fabrication of CoV immunosensor using [Fe(CN)6]3−/4− as an electroactive probe.After that, the analytical robustness of the performances of these immunosensing platforms was estimated and verified. Indeed, a nanomolar range detection limit (180 TCID50/mL)g/mL) with excellent reproducibility (RSD% = 8%) was obtained. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

Deep Learning-Based Multi-modal COVID-19 Screening by Socially Assistive Robots Using Cough and Breathing Symptoms

In this paper, we present the development of a novel autonomous social robot deep learning architecture capable of real-time COVID-19 screening during human-robot interactions. The architecture allows for autonomous preliminary multi-modal COVID-19 detection of cough and breathing symptoms using a VGG16 deep learning framework. We train and validate our VGG16 network using existing COVID datasets. We then perform real-time non-contact preliminary COVID-19 screening experiments with the Pepper robot. The results for our deep learning architecture demonstrate: 1) an average computation time of 4.57 s for detection, and 2) an accuracy of 84.4% with respect to self-reported COVID symptoms. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Fighting for a future free from violence: A framework for real-time detection of "Signal for Help”

In April 2020, by the start of isolation all around the world to counter the spread of COVID-19, an increase in violence against women and kids has been observed such that it has been named The Shadow Pandemic. To fight against this phenomenon, a Canadian foundation proposed the "Signal for Help” gesture to help people in danger to alert others of being in danger, discreetly. Soon, this gesture became famous among people all around the world, and even after COVID-19 isolation, it has been used in public places to alert them of being in danger and abused. However, the problem is that the signal works if people recognize it and know what it means. To address this challenge, we present a workflow for real-time detection of "Signal for Help” based on two lightweight CNN architectures, dedicated to hand palm detection and hand gesture classification, respectively. Moreover, due to the lack of a "Signal for Help” dataset, we create the first video dataset representing the "Signal for Help” hand gesture for detection and classification applications which includes 200 videos. While the hand-detection task is based on a pre-trained network, the classifying network is trained using the publicly available Jesture dataset, including 27 classes, and fine-tuned with the "Signal for Help” dataset through transfer learning. The proposed platform shows an accuracy of 91.25% with a video processing capability of 16 fps executed on a machine with an Intel i9-9900K@3.6 GHz CPU, 31.2 GB memory, and NVIDIA GeForce RTX 2080 Ti GPU, while it reaches 6 fps when running on Jetson Nano NVIDIA developer kit as an embedded platform. The high performance and small model size of the proposed approach ensure great suitability for resource-limited devices and embedded applications which has been confirmed by implementing the developed framework on the Jetson Nano Developer Kit. A comparison between the developed framework and the state-of-the-art hand detection and classification models shows a negligible reduction in the validation accuracy, around 3%, while the proposed model required 4 times fewer resources for implementation, and inference has a speedup of about 50% on Jetson Nano platform, which make it highly suitable for embedded systems. The developed platform as well as the created dataset are publicly available. © 2022

Real Time Face Mask Detection Using Tiny YOLOv3

To stop the Covid-19 from spreading different techniques were developed and implemented. To make the use of face mask was effective to control the spread of it, as it transmits from one person to other. The use of face mask correctly is also important. The main objective is to develop a technique which can be used to monitor the people wearing face mask, not wearing the face mask or incorrect face mask and also to make use of the model which can be used on portable devices without the use of GPU for real time detection. The Yolov3-tiny model was used for detection. It achieved the mean average precision of 68% and it runs at 13 FPS without the use of GPU. The model was tested for image detection and also for real time detection. © 2022 IEEE.

A traveling SARS-CoV-2 laboratory as part of a pandemic response among vulnerable Brazilian populations.

BACKGROUND: Brazil has been dramatically hit by the SARS-CoV-2 pandemic and is a world leader in COVID-19 morbidity and mortality. Additionally, the largest country of Latin America has been a continuous source of SARS-CoV-2 variants and shows extraordinary variability of the pandemic strains probably related to the country´s outstanding position as a Latin American economical and transportation hub. Not all regions of the country show sufficient infrastructure for SARS-CoV-2 diagnosis and genotyping which can negatively impact the pandemic response. METHODS: Due to this reason and to disburden the diagnostic system of the inner São Paulo State, the Butantan Institute established the Mobile Laboratory (in Portuguese: LabMovel) for SARS-CoV-2 testing which started a trip of the most important "hotspots" of the most populous Brazilian region. The LabMovel initiated in two important cities of the State: Aparecida do Norte (an important religious center) and the Baixada Santista region which incorporates the port of Santos, the busiest in Latin America. The LabMovel was fully equipped with an automatized system for SARS-CoV-2 diagnosis and sequencing/genotyping. It also integrated the laboratory systems for patient records and results divulgation including in the Federal Brazilian Healthcare System. RESULTS: Currently,16,678 samples were tested, among them 1,217 from Aparecida and 4,564 from Baixada Santista. We tracked the delta introductio in the tested regions with its high diversification. The established mobile SARS-CoV-2 laboratory had a major impact on the Public Health System of the included cities including timely delivery of the results to the healthcare agents and the Federal Healthcare system, evaluation of the vaccination status of the positive individuals in the background of exponential vaccination process in Brazil and scientific and technological divulgation of the fieldwork to the most vulnerable populations. CONCLUSIONS: The SARS-CoV-2 pandemic has demonstrated worldwide the importance of science to fight against this viral agent and the LabMovel shows that it is possible to integrate researchers, clinicians, healthcare workers and patients to take rapid actions that can in fact mitigate this and other epidemiological situations.

Real-Time Face Mask Detection Using Streamlit,TensorFlow, Keras and Open-CV

This paper is based on the protection of our health from coronavirus officially known as COVID-19. Real-time detection of a face mask can help to prevent of the coronavirus, detecting the mask with the help of machine learning and data science algorithms such as Streamlit, MoblieNetV2, OpenCV, etc., are widely used in this ideal methodology. This paper is about the method that provides an accuracy of 99.78% in detecting the mask with live video stream. The method proposes building accurate model and integrating the model with a graphical interface which can improve the experience of the user. © 2022 IEEE.

A Crowd Alert System for Pandemic Control using Yolov4

The Covid-19 pandemic in the late 2019 caused the world to shut down. Even though it is recommended to reduce overcrowding it still cannot be avoided. This can cause the pandemic to spread even more, especially since offices, schools and colleges are slowly reopening. With image detection making huge breakthroughs in the last decade, modern image detection technologies can now be combined with the current hardware to combat problems like overcrowding, which massively spreads the pandemic. In this paper, the YOLO v4 algorithm has been used, which greatly speeds up the process of detection and improves the overall accuracy of the system. © 2022 IEEE.

Real-Time Detection of Face Mask and Social Distancing

According to the World Health Organization data, the global epidemic of COVID-19 has profoundly affected the world and has now infected more than eight million people worldwide. The COVID-19 epidemic forced governments worldwide to close their doors to prevent the spread of the virus. Reports indicate that wearing a facemask and maintaining public distance while at work reduces the risk of infection. CCTV cameras are installed in educational and industrial spaces, residential areas, and crowded places. However, it is difficult to physically monitor buildings to find people without masks and people who do not keep public distance, and it is challenging to monitor video footage of large buildings and find people without a facemask and social distance correction. A mixed model that uses in-depth reading and machine learning to face masks and correct public distances will help managers look after people roaming the grounds without hiding their faces and distance from the public. The supervised machine-learning algorithm will train the model with the data available online. The facemask data acquisition set contains masked and non-masked images. OpenCV will be used for real-time face recognition and social distance adjustment from live streaming videos from web-enabled videos. The Convolution Neural Network will be used to extract features from the database. After the feature removal process, the newly installed photo/video will be classified as face masked or face masked. The proposed methodology has shown that person detection, social distance, and F.I. scores approximate 91.2%, and the average F1 score is 90.79%. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

A Computer Vision-based System for Surgical Waste Detection

The world population is going through a difficult time due to the pandemic of COVID-19 while other disasters prevail. However, a new environmental catastrophe is coming because surgical masks and gloves are putting down anywhere, leading to the massive spreading of COVID-19 and environmental disasters. A significant number of masks and gloves are not properly managed. They are scattered around us such as roads, rivers, beaches, oceans and other places. Since these types of waste are turned into microplastics and chemicals are deadly harmful to the environment, human health and other species, especially for the aquatic animals on this planet. During the outbreaks of corona pandemic, surgical waste in the open place or seawater can create a fatal contagious environment. Putting them in a particular area can protect us from spreading infectious diseases. This study proposed a system that can detect surgical masks, gloves and infectious/biohazard symbols to put down infectious waste in a specific place or a container. Among the various types of surgical waste, this study prefers mask and gloves since it is currently the most widely used element due to the COVID-19. A novel dataset is created named MSG (Mask, Bio-hazard Symbol and Gloves), containing 1153 images and their corresponding annotations. Different versions of the You Only Look Once (YOLO) are applied as the architecture of this study;however, the YOLOX model outperforms.

Real-time Face Mask Detection System on Edge using Deep Learning and Hardware Accelerators

Real-time face mask detection with the use of Artificial Intelligence is one of the most advanced ways of detecting face masks and their wearing condition in public or private areas. In this work, a system based on Object Detection models is proposed which can detect and classify the type of mask wearing conditions in real-time. The system is implemented with two latest deep convolutional neural networks;YOLOv5s and YOLOv5l. The proposed system can efficiently detect and classify face masks based on their wearing condition as well as count them and store the count into a CSV file format with a timestamp. To perform real-time inference, the deep learning models were deployed on Nvidia Jetson Nano and Jetson Xavier NX which are embedded solutions inspired by Edge AI. The detection algorithms achieved mAP of 86.43 and 92.49 for YOLOv5s and YOLOv5l respectively. Comparing the mAP of both detection models, YOLOv5l achieved higher mAP than YOLOv5s while comparing fps on both hardware, Nvidia Jetson Xavier NX provides more fps than Nvidia Jestion Nano for realtime inference. © 2021 IEEE.

Real-time detection of atmospheric fine particle mass concentration based on laser forward small angle scattering

The level of fine particulate air pollution exposure is positively correlated with the death rate of individuals infected with COVID-19. Monitoring is the first step to prevent fine particulate pollution. The instrument based on light scattering method to detect particle concentration has unparalleled advantages over other instruments due to its rapidity, real-time and low cost. Traditional light scattering instruments are limited by the light absorption and particle properties of particles, and their ability to monitor some particles with strong light absorption is greatly reduced. Moreover, when the measured environment is greatly different from the calibration environment, the measurement results often have large errors. In this research, an instrument is designed to detect the forward scattering of light from small angles of particles. It can monitor the number concentration of particles in the environment in real time in four particle size ranges (PM1, PM2.5, PM4 and PM10) and convert it into the mass concentration of particles. By using the simulated atmospheric smoke box and the standard instrument to conduct a field comparison experiment, the reliability and stability of the measurement results are verified. © 2021 SPIE.

Understanding digital bubbles amidst the COVID-19 pandemic: Evidence from DeFi and NFTs.

This paper investigates digital financial bubbles amidst the COVID-19 pandemic. Using a sample of 9 DeFi tokens, 3 NFTs, Bitcoin, and Ethereum, we detect several bubbles overlapping the examined cryptoassets. We also uncover DeFi and NFT-specific bubbles in Summer 2020 suggesting distinct driving factors for this class of assets. We document that DeFi and NFTs bubbles are less recurrent but have higher magnitudes than cryptocurrencies' bubbles. We also find that COVID-19 and trading volume exacerbate bubble occurrences, while Total Value Locked (TVL) is negatively associated with cryptoassets' bubbles. Our results suggest that TVL can be used as a tool for market monitoring.

Harnessing recombinase polymerase amplification for rapid multi-gene detection of SARS-CoV-2 in resource-limited settings.

The COVID-19 pandemic is challenging diagnostic testing capacity worldwide. The mass testing needed to limit the spread of the virus requires new molecular diagnostic tests to dramatically widen access at the point-of-care in resource-limited settings. Isothermal molecular assays have emerged as a promising technology, given the faster turn-around time and minimal equipment compared to gold standard laboratory PCR methods. However, unlike PCR, they do not typically target multiple SARS-CoV-2 genes, risking sensitivity and specificity. Moreover, they often require multiple steps thus adding complexity and delays. Here we develop a multiplexed, 1-2 step, fast (20-30 min) SARS-CoV-2 molecular test using reverse transcription recombinase polymerase amplification to simultaneously detect two conserved targets - the E and RdRP genes. The agile multi-gene platform offers two complementary detection methods: real-time fluorescence or dipstick. The analytical sensitivity of the fluorescence test was 9.5 (95% CI: 7.0-18) RNA copies per reaction for the E gene and 17 (95% CI: 11-93) RNA copies per reaction for the RdRP gene. The analytical sensitivity for the dipstick method was 130 (95% CI: 82-500) RNA copies per reaction. High specificity was found against common seasonal coronaviruses, SARS-CoV and MERS-CoV model samples. The dipstick readout demonstrated potential for point-of-care testing in decentralised settings, with minimal or equipment-free incubation methods and a user-friendly prototype smartphone application. This rapid, simple, ultrasensitive and multiplexed molecular test offers valuable advantages over gold standard tests and in future could be configurated to detect emerging variants of concern.