A Mask Detection Algorithm Based on Improved Yolov5s

Aiming at the severe form of new coronavirus epidemic prevention and control, a target detection algorithm is proposed to detect whether masks are worn in public places. The Ghostnet and SElayer modules with fewer design parameters replace the BottleneckCSP part in the original Yolov5s network, which reduces the computational complexity of the model and improves the detection accuracy. The bounding box regression loss function DIOU is optimized, the DGIOU loss function is used for bounding box regression, and the center coordinate distance between the two bounding boxes is considered to achieve a better convergence effect. In the feature pyramid, the depthwise separable convolution DW is used to replace the ordinary convolution, which further reduces the amount of parameters and reduces the loss of feature information caused by multiple convolutions. The experimental results show that compared with the yolov5s algorithm, the proposed method improves the mAP by 4.6% and the detection rate by 10.7 frame/s in the mask wearing detection. Compared with other mainstream algorithms, the improved yolov5s algorithm has better generalization ability and practicability. © 2022 ACM.

An Automatic CNN-based Face Mask Detection Algorithm Tested During the COVID-19 Pandemics

The ongoing COVID-19 pandemic has highlighted the importance of wearing face masks as a preventive measure to reduce the spread of the virus. In medical settings, such as hospitals and clinics, healthcare professionals and patients are required to wear surgical masks for infection control. However, the use of masks can hinder facial recognition technology, which is commonly used for identity verification and security purposes. In this paper, we propose a convolutional neural network (CNN) based approach to detect faces covered by surgical masks in medical settings. We evaluated the proposed CNN model on a test set comprising of masked and unmasked faces. The results showed that our model achieved an accuracy of over 96% in detecting masked faces. Furthermore, our model demonstrated robustness to different mask types and fit variations commonly encountered in medical settings. Our approaches reaches state of the art results in terms of accuracy and generalization. © 2022 Copyright for this paper by its authors.

Design of People Count System Based on Object Detection Algorithm

At present, the Covid-19 epidemic is still spreading globally. Although the domestic epidemic has been well controlled, the prevention and control of the epidemic must not be taken lightly. Being able to count the number of people in public places in real time has played a vital role in the prevention and control of the epidemic. Deep learning networks usually cannot be directly deployed on embedded devices with low computing power due to the huge amount of parameters of convolutional neural networks. This article is based on the YOLOv5 object detection algorithm and Jetson Nano embedded platform with TensorRT and C++ accelerating, it can realize the function of counting the number of people in the classroom, on the elevator entrance, and other scenes. © 2022 SPIE.

COVID-19 X-RAY IMAGE DETECTION ALGORITHM BASED ON DEEP LEARNING

In order to enhance the ability to diagnose and distinguish COVID-19 from ordinary pneumonia, and to assist medical staff in chest X-ray detection of pneumonia patients, this paper proposes a COVID-19 X-ray image detection algorithm based on deep learning network. First of all, a model of deep learning network is set up based on VGG - 16, and then, the network structure and parameter optimization is adjusted, which makes the network model can be applied to COVID - 19 x ray imaging detection task. In the end, through adjusting the image size of the original data set, the input data meets the requirements of the deep learning network. Experimental results show that the proposed algorithm can effectively learn the characteristics of the COVID-19 X-ray image data set and accurately detect three states of COVID-19, common viral pneumonia and non-pneumonia, with a very high detection accuracy of 95.8%. © 2023 SPIE.

Mask Wear Detection Algorithm Based on YOLOv5m

Wearing a mask during the COVID-19 epidemic can effectively prevent the spread of the virus. In view of the problems of small target size, crowd blocking each other and dense arrangement of targets in crowded places, a target detection algorithm based on the improved YOLOv5m model is proposed to achieve efficient detection of whether a mask is worn or not. This paper introduces four attention mechanisms in the feature extraction network based on the YOLOv5m model to suppress irrelevant information, enhance the information representation of the feature map, and improve the detection capability of the model for small-scale targets. The experimental results showed that the introduction of the SE module increased the mAP value of the original network by 9.3 percentage points, the most significant increase among the four attention mechanisms. And then a dual-scale feature fusion network is used in the Neck layer, giving different weights to the feature layers to convey more effective feature information. In the image pre-processing, the Mosaic method was used for data enhancement, and the CIoU loss function was used for coordinate frame positioning in the prediction layer. Experiments on the improved YOLOv5m algorithm demonstrate that the mean recognition accuracy of the method improves by 10.7 percentage points over the original method while maintaining the original model size and detection speed, and better solves the problems of small scale, dense arrangement and mutual occlusion of targets in mask wearing detection tasks in crowded places. © 2023 IEEE.

Hiv Detection in Wastewater as a New Epidemiological Tool

Background: Wastewater represents a broad, immediate, and unbiased accounting of the pathgens in the population. We aimed to develop methods to track HIV in wastewater utilizing a viral detection pipeline adapted from platforms developed to track SARS-COV-2. Method(s): We used samples from 6 wastewater treatment plants in the Houston area. We focused on regions of higher prevalence and lower prevalence. First, employing wastewater processing and nucleic acid extraction methods described by our group to detect SARS-COV-2, we tested a single high and low prevalence site in triplicate with all 3 primer sets. nucleic acid extracts from HIV and SIV cell culture supernatants were used as controls. Next, in subsequent samples, RT-PCR reactions with detections were subjected to gel electrophoresis to determine the amplified product sizes. To further confirm HIV detection, we sequenced the RT-PCR products and compared the proportion of reads which mapped to the expected amplified product. In a later set of studies, we fractionated samples into supernatant and pellet. We further tested HIV presence by performing whole virome sequencing on the extracts from some samples that produced detections and mapped reads to published genomes. A crAssphage genome was used as a negative control. Result(s): Samples from all sites resulted in signal detection at least once. Only reactions with gag and pol primers appeared to amplify the expected product. Products from the HIV positive control mapped almost exclusively to the HIV genome (97-100% of reads), with a fraction of reads from the SIV negative control doing the same (16-18% of reads). The ltr and pol products did not map the HIV genome while gag products did (34-44% of reads). Among the fractionated sample, in total, 6 supernatant fractions produced no detection compared to 7 of 8 pellet fractions. The whole virome sequencing produced reads that mapped to the HIV genome with at least 8X depth coverage. The sample with the lowest Ct detection (26) yielded HIV coverage several logs greater than those samples with higher Ct detection (37). Reads from all samples mapped to at least 20% of the HIV genome. Conclusion(s): This work provides the first evidence that HIV can be detected in municipal wastewater systems and has the potential to be developed into a new public health tool.

Object detection and activity recognition in video surveillance using neural networks

Purpose: This paper aims to implement and extend the You Only Live Once (YOLO) algorithm for detection of objects and activities. The advantage of YOLO is that it only runs a neural network once to detect the objects in an image, which is why it is powerful and fast. Cameras are found at many different crossroads and locations, but video processing of the feed through an object detection algorithm allows determining and tracking what is captured. Video Surveillance has many applications such as Car Tracking and tracking of people related to crime prevention. This paper provides exhaustive comparison between the existing methods and proposed method. Proposed method is found to have highest object detection accuracy. Design/methodology/approach: The goal of this research is to develop a deep learning framework to automate the task of analyzing video footage through object detection in images. This framework processes video feed or image frames from CCTV, webcam or a DroidCam, which allows the camera in a mobile phone to be used as a webcam for a laptop. The object detection algorithm, with its model trained on a large data set of images, is able to load in each image given as an input, process the image and determine the categories of the matching objects that it finds. As a proof of concept, this research demonstrates the algorithm on images of several different objects. This research implements and extends the YOLO algorithm for detection of objects and activities. The advantage of YOLO is that it only runs a neural network once to detect the objects in an image, which is why it is powerful and fast. Cameras are found at many different crossroads and locations, but video processing of the feed through an object detection algorithm allows determining and tracking what is captured. For video surveillance of traffic cameras, this has many applications, such as car tracking and person tracking for crime prevention. In this research, the implemented algorithm with the proposed methodology is compared against several different prior existing methods in literature. The proposed method was found to have the highest object detection accuracy for object detection and activity recognition, better than other existing methods. Findings: The results indicate that the proposed deep learning–based model can be implemented in real-time for object detection and activity recognition. The added features of car crash detection, fall detection and social distancing detection can be used to implement a real-time video surveillance system that can help save lives and protect people. Such a real-time video surveillance system could be installed at street and traffic cameras and in CCTV systems. When this system would detect a car crash or a fatal human or pedestrian fall with injury, it can be programmed to send automatic messages to the nearest local police, emergency and fire stations. When this system would detect a social distancing violation, it can be programmed to inform the local authorities or sound an alarm with a warning message to alert the public to maintain their distance and avoid spreading their aerosol particles that may cause the spread of viruses, including the COVID-19 virus. Originality/value: This paper proposes an improved and augmented version of the YOLOv3 model that has been extended to perform activity recognition, such as car crash detection, human fall detection and social distancing detection. The proposed model is based on a deep learning convolutional neural network model used to detect objects in images. The model is trained using the widely used and publicly available Common Objects in Context data set. The proposed model, being an extension of YOLO, can be implemented for real-time object and activity recognition. The proposed model had higher accuracies for both large-scale and all-scale object detection. This proposed model also exceeded all the other previous methods that were compared in extending and augmenting the object detection to activity recognition. The proposed model resulted in the highest accuracy for car crash detection, fall detection and social distancing detection. © 2023, Emerald Publishing Limited.

A Comprehensive Alert System Based on Social Distancing for Cautioning People Amidst the COVID-19 Pandemic Using Deep Neural Network Models

The World Health Organization (WHO) has suggested a successful social distancing strategy for reducing the COVID-19 virus spread in public places. All governments and national health bodies have mandated a 2-m physical distance between malls, schools, and congested areas. The existing algorithms proposed and developed for object detection are Simple Online and Real-time Tracking (SORT) and Convolutional Neural Networks (CNN). The YOLOv3 algorithm is used because YOLOv3 is an efficient and powerful real-time object detection algorithm in comparison with several other object detection algorithms. Video surveillance cameras are being used to implement this system. A model will be trained against the most comprehensive datasets, such as the COCO datasets, for this purpose. As a result, high-risk zones, or areas where virus spread is most likely, are identified. This may support authorities in enhancing the setup of a public space according to the precautionary measures to reduce hazardous zones. The developed framework is a comprehensive and precise solution for object detection that can be used in a variety of fields such as autonomous vehicles and human action recognition. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

The COVID'19 Dashboard with Implementation of Face Mask Detection and Social Distancing Detection Algorithm

With the outbreak of the global pandemic, India seemed to reach its peak with regard to the number of confirmed positive cases in the months of April and May. Hence, the decision was made to develop a data visualization project with one of the efficient visualization tools Tableau to help people analyze the scenario of the cases across the country. To contribute to state-wise and country-wise analysis of COVID cases in India, 2 dashboards have been developed. The first dashboard consists of the analysis of cases across the country giving a holistic and overall view of the number of deaths, positive cases, and density of cases in each state which is done through color variation. On the other hand, the second dashboard gives a detailed state-wise analysis of cases with the necessary parameters and details catering to every individual state as per the preference of the user. On merging these components, users can get an all-inclusive analysis based on different parameters on the COVID'19 cases across India at a glance. In order to prevent a further spike in cases, implementing a face mask detection system will also take place after conducting a thorough analysis of the possible machine learning algorithms. Two major object detection algorithms were taken into consideration and based on the conclusion drawn, the best algorithm - RCNN was used to implement the face mask detection system. This project is solely motivated by the current extreme situation in the world and as an attempt to provide a solution to combat the same. © 2023 IEEE.

Enhanced electrochemiluminescence immunoassay: 2. Enabling signal detection at an early stage of incubation for rapid point-of-care testing

Signal detection in a label-based immunoassay is performed normally when the antigen/antibody binding reaction reaches the equilibrium state during the incubation period of an assay process. Shortening the incubation period in an assay helps reduce the turnaround time and is particularly valuable for point-of-care testing, but the cost is the reduction of signal level and, possibly, measurement precision as well. This work demonstrates that the signal loss could be offset by the stronger emission of an electronically neutral ruthenium(II) complex label, Ru(2, 2′-bipyridine) (bathophenanthroline disulfonate)[4-(2, 2′-bipyridin-4-yl)butanoic acid], used in the electrochemiluminescence (ECL) immunoassay. Combined with the uniquely well-established flow-through washing process in the automated ECL analyzers and the precise control over liquid handling, the assays performed with a 5-minute incubation period showed the same signal level and measurement precision as those of conventional ECL assays. Additionally, the absence of biotin and streptavidin components in the reagent formulation avoids the biotin-streptavidin interaction during assay incubation and fundamentally eliminates the interference of biotin, especially when used in some high-dose therapies. The results obtained from the procalcitonin prototype kit and the supporting evidence from other preliminary reagents (for SARS-CoV-2 N protein and troponin T) are general. The nonequilibrium detection, along with the downsized instrument design, makes the enhanced ECL (EECL) technology a fast high-performance POCT platform that provides the same high-quality data as those generated from the widely deployed [Ru(bpy)3]2+ based laboratorial ECL systems. The anticipated regulatory approval and follow-up clinical implementation will be a significant stride in the decade-long pursuit of novel ECL labels. © 2023 The Author(s)

A more accurate mask detection algorithm based on Nao robot platform and YOLOv7

With the global outbreak of Corona Virus Disease 2019(COVID-19), many countries had made it mandatory for people to wear masks in public places. This paper proposed a novel mask detection algorithm RMPC (Restructing the Maxpool layer and the Convolution layer)-YOLOv7 based on YOLOv7 for detecting whether people wear masks in public places. The RMPC-YOLOv7 algorithm reconstructed the downsampling structure in the original YOLOv7 algorithm. We changed the stacking of the maxpooling layer and the convolutional layer. This enabled the feature information to be fully integrated to achieve the accuracy improvement of the new model. Through comparison experiments, our proposed RMPC-YOLOv7 had was improved 0.9% and 1.2% for mAP0.5 and mAP0.5:0.95, respectively. The experimental results demonstrated the feasibility of RMPC-YOLOv7. © 2023 IEEE.

Uppsala Monitoring Centre and WHO Programme of International Drug Monitoring

Uppsala Monitoring Centre (UMC) is an independent and self-funded Swedish foundation. There are many stakeholders in the field of medicines safety, and by drawing on our different competences, skills and roles in the PV world, UMC strives to always pursue our vision: working together to advance medicines safety. UMC's different business areas focus on various external stakeholders, one of which focuses on the WHO Programme of International Drug Monitoring (WHO PIDM). Since 1968, the programme has provided a forum for WHO Member States to collaborate in pharmacovigilance. This enables programme members to be alerted to patterns of harm emerging across the world, but which might not be evident from their local data alone. There are now over 170 member countries/territories. The programme's operational activities were moved to Uppsala in 1978 under the sponsorship of the Swedish government, which marked the starting point for our organization and its designation as one of WHO's 800 Collaborating centres - the WHO Collaborating Centre for International Drug Monitoring.1 UMC is custodian and manager of VigiBase, WHO's global database of reported potential side effects of medicinal products. This gold mine is used to generate insights for various PV stakeholders. The WHO PIDM members, which are usually the national regulatory authorities, collect reports of adverse events from patients, physicians, the pharmaceutical industry and other stakeholders within their national PV systems. VigiBase accumulates the data from programme members, and currently contains about 33 million case reports. For other external stakeholders, VigiBase data can be made available with limited level of detail via VigiBase Services, open to, for example, academia, the pharmaceutical industry and health care providers.2,3 Besides VigiBase maintenance, our Collaborating Centre also provides programme members with IT solutions for data collection and analysis in their national setting to support their mission for safe products in their markets. There are many IT solutions, but to highlight two: VigiFlow, for example, is a data collection and management system, used by over 100 members as their national safety database. And in VigiLyze, members have a powerful analysis tool free of charge, which can analyse national data as well as data in regional collaborations with instant access to the global data in VigiBase and others' experiences as a reference. Safety signals found by UMC and other programme members are also available in VigiLyze. The Collaborating Centre generates and shares credible and evidence-based information on the safety of medicines and vaccines for further decision-making by regulators and scientific high-level committees. That work relies on the use of sophisticated methods for signal detection, but also on internal and external clinical expertise. Selected signals are also published in scientific journals to reach a broader audience such as the prescribers. In addition, our centre helps national pharmacovigilance centres to support safe use of medicines by offering training aligned with their needs. We get many training requests from WHO PIDM members and WHO regions. Our hands-on and web-based courses provide national centres with the technical knowhow and skills to strengthen their pharmacovigilance systems and practices. We also facilitate the sharing of PV insights and know-how globally using a variety of channels for information;for example, Uppsala Reports magazine and website, our podcast called Drug Safety Matters and our various social media channels. COVID-19 vaccine safety monitoring is a top priority at UMC, and significant resources have been allocated to this. Our recent insights and experiences have enriched us and brought us even closer to our collaborating partners and we are better prepared for the next challenges.4.

Enhanced Automated Oxygen Level controller for COVID Patient By Using Internet of Things (IoT)

The Internet of Things (IoT) shall be merged firmly and interact with a higher number of altered embedded sensor networks. It provides open access for the subsets of information for humankind's future aspects and on-going pandemic situations. It has changed the way of living wirelessly, with high involvement and COVID-related issues that COVID patients are facing. There is much research going on in the recent domain, like the Internet of Things. Considering the financial-economic growth, there isn't much significance as IoT is growing with industry 5.0 as the latest version. The newly spreading COVID-19 (Coronavirus Disease, 2019) will emphasize the IoT based technologies in a greater impact. It is growing with an increase in productivity. In collaboration with Cloud computing, it shows wireless communication efficiently and makes the COVID-19 eradication in a greater way. The COVID-19 issues which are faced by the COVID patients. Many patients are suffering from inhalation because of lung problems. The second wave attacks mainly on the lungs, where there is a shortage of breathing problems because of less supply of oxygen (insufficient amount of oxygen). The challenges emphasized as proposed are like the shortage of monitoring the on-going process. Readily being active in this pandemic situation, the mentioned areas are from which need to be discussed. The frameworks and services are given the correct data and information for supply of oxygen to the COVID patients to an extent. The Internet of Things also analyzes the data from the user perspective, which will later be executed for making on-demand technology more reliable. The outcome for the COVID-19 has been taken completely to help the on-going COVID patients live, which can be monitored through Oxygen Concentration based on the IoT framework. Finally, this article discusses and mentions all the parameters for COVID patients with complete information based on IoT. © 2022 IEEE.

High sensitivity and selectivity vertically-oriented silicon nanowire array-based bioelectronic sensor platform

Silicon nanowires are next-generation high performance biosensor materials compatible with multiple types of biomolecules. Bioelectronic sensors, which output electrical signals for biological detection, have unique advantages in miniaturization, fast response, and portability. Despite that these nanomaterials have demonstrated high performance, complex fabrication methods that are not compatible with industrial production are usually implemented. This work deals with the development, fabrication, and testing of a rapid and cost-effective silicon nanowire biosensor that is less than one inch in width and suited for industrial mass production. The silicon nanowires are fabricated using a silver-assisted chemical etching which can be mass-producible and CMOS-compatible, tunable etch rate, and high consistency. The nanowire sensor is then fabricated using a series of nanofabrication instruments that are commonly used for semiconductor processing. The fabrication process is developed and modified to be suited for biosensing applications, and the scanning electron microscopy demonstrates that the fabricated sensor has etched vertical silicon nanowire arrays of around 350 nm in length and 1010 per 1 cm2 in density.The fabricated vertically-oriented silicon nanowire array-based sensor consists of a p-n diode. Since the diode type nanowire biosensors have not been thoroughly implemented and studied, in this work, in order to simulate and validate the operation mechanisms of the proposed biosensor, an operation protocol is proposed to characterize the sensor by measuring its current as a function of the applied voltage and calculating the derivative the current-voltage function. Then the mathematical and physical models of the device are studied, and a water-gate experiment is conducted to justify the models. In the case when the unexpected disturbance occurs, the model also provides with a method to eliminate the noise in the effective resistance of the sensor.The fabricated biosensors are then functionalized for the testing of three types of analytes including two cancer cell antibodies and the spike protein of the severe acute respiratory syndrome coronavirus 2. The results show that the developed sensors have high sensitivity and specificity against bovine serum albumin. Although still with a preliminary design, the proposed sensor has already been demonstrated to be able to detect clinically relevant concentrations of the target for the diagnosis of the disease. This technology offers the potential to complement conventional biosensor systems in applications of portable and rapid responding biosensing. (PsycInfo Database Record (c) 2022 APA, all rights reserved)

Pair-Less Bluetooth for Touchless Interaction

The Covid-19 pandemic accelerated the need for touchless interactions with technology in public spaces. By leveraging mobile phones which are equipped with Bluetooth wireless transmitters, we enable touchless and app-less interactions between people and technology. The Bluetooth signal broadcast from everyday devices such as smart phones is used by Bluetooth receivers, such as wireless earbuds, to pair the devices and communicate data. In this work, on the other hand, the broadcasted Bluetooth signal is detected, along with any change in the signal caused by rotating one's phone or waving one's hand by the phone. These intentional gestures with one's phone in the presence of an equipped Bluetooth receiver are interpreted as 'words' of a communication language. Without the need to pair devices or download any software, the communication language enables touchless interactions between a user holding a phone and a computing system in a public space © 2023 IEEE.

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.

Medical Small-scale Transportation Object Detection Algorithm Based on Multimodal Data Fusion

The emergence of the Covid-19 pandemic has greatly impact transportation, and unmanned transportation has been widely used in medical. The average precision of object detection as an important part in unmanned medical transportation. Object detection mainly relies on sensors of vehicles to obtain information about the surrounding obstacles like camera and LIDAR. In this paper, we introduce a new fusion way to fuse data from different modalities, as 2D and 3D object detection encouraging performance, they are typically based on a single modality and are unable to leverage information from other modalities. We leverage the geometric semantic consistency of 2D and 3D detection to obtain more accurate fusion results, and address the weaknesses of IoU in fusion network by using a generalized version as both a new loss and a new metric. The experimental evaluation on the challenging KITTI object detection benchmark, shows significant improvements in average precision, especially at bird's eye view metrics, which shows the feasibility and applicability of the network. © 2022 IEEE.

Detection of Face Wearing Mask Based on AdaBoost and YCrCb

At the beginning of 2020, COVID-19 broke out and swept the world. Wearing masks remains an important means of preventing epidemics. Many scholars have developed and studied mask wearing detection based on YOLO algorithm, and have made some achievements. AdaBoost algorithm has the advantages of high precision and low complexity, and is also suitable for solving this problem. This paper uses OpenCV to propose a face detection algorithm based on AdaBoost. This algorithm is based on face detection, including initialization of background estimation example, background subtraction preprocessing, obtaining eye position, face detection and other steps. LBP features are used as the training basis of the classifier. The trained classifier is generated and used as a function in the mask detection algorithm. At present, there are two problems in the research of mask wearing detection: first, only consider whether the tested object wears a mask, but not analyze the non-standard wearing of masks;Secondly, due to the influence of light and other external environments, the real-time detection effect of targets in complex scenes changes greatly. In view of the above problems, this paper adopts the following methods to solve them: pre-processing the image to reduce noise, light spots and other external environmental interference;For the case that the mask is not standardized, the condition that the mask covers the nose and mouth shall be detected. Finally, the Adaboost algorithm for facial mask wearing detection is obtained. Experiments show that the algorithm has high adaptability, robustness and accuracy, and can be used to promote the development of epidemic prevention. © 2022 IEEE.

Safety monitoring of COVID-19 therapy and vaccines

Since late 2019, the pandemic of COVID-19, caused by SARS-CoV-2, has resulted in high morbidity and mortality worldwide. During 2020, safety monitoring of medicinal treatments for this novel disease was performed by Uppsala Monitoring Centre (UMC) in VigiBase, WHO's global database of suspected adverse drug reactions, which is the largest international repository of reported ADRs. Initially, COVID-19 treatments included numerous repurposed medicines previously approved for other indications, such as chloroquine and hydroxychloroquine. Although chloroquine is a widely used drug which has been on the market for a very long time, the efficacy and safety profile have not been thoroughly studied in COVID-19 patients. In early 2020, chloroquine and hydroxychloroquine were authorized by major regulatory agencies for emergency use, or only for use within clinical trials. Given the interest over the use of these drugs in COVID-19, the ADR reports in VigiBase for them were summarized and communicated to reiterate their toxicities, in particular the cardiac reactions which may result in fatal outcomes.1 Remdesivir, the first novel antiviral drug authorized for use in treatment for COVID-19, was the most commonly reported COVID-19 medicine within VigiBase during 2020. Employing indication- focused descriptive statistics (disproportionality analysis), together with the use of a comparator tocilizumab with a known safety profile, it was possible to identify known safety information for both remdesivir and tocilizumab and suggest potential safety concerns for remdesivir. The most reported adverse events were liver dysfunction, kidney injury, death and bradycardia.2 In late 2020, several new vaccines for COVID-19 were developed, received emergency authorization and rolled out on a large scale. The vaccines used novel technology and a rapid and vast deployment was anticipated. For this scale of activity, a well-functioning international postmarketing safety surveillance system is essential. The unprecedented volume of reports of suspected adverse events following immunization has led to the development of new routines and the use of new tools at UMC, for example, a digital reporting form designed for mobile devices was implemented;more frequent updates of VigiBase data allowed timely data analyses;a COVID-19 vaccine-specific standardized drug grouping (SDG) was created enabling the data analysis on a vaccine platform level;and a monthly descriptive report regarding COVID-19 vaccine reporting in VigiBase was made available for member countries of the WHO Programme for International Drug Monitoring (PIDM).3 UMC regularly screened VigiBase for previously unknown or incompletely documented COVID- 19 vaccines adverse reactions. These signals were shared with all WHO PIDM members to complement their signal detection and support local action to protect patients from harm. Some signals were also published outside the WHO PIDM to raise awareness or encourage data collection.4,5 In summary, successful adaptations were made at UMC in a short period to handle the COVID- 19 pandemic situation. However, the pandemic has not ended yet and further challenges are anticipated. The safety monitoring of COVID- 19 therapies and vaccines still needs to continue.

A Face Mask Detection Algorithm Based on YOLOv5

As a new machine learning method, deep learning has been widely used in computer vision. YOLOv5, a target detection algorithm based on deep learning, has a good detection effect. In the case of COVID-19, masks should be worn correctly in public places. Therefore, it is urgent to design an accurate and effective face mask detection algorithm. To solve the problem of mask-wearing detection, a face mask detection algorithm based on YOLOv5 is proposed. The main research contents include training of the YOLOv5 model, verification of face mask detection function, and analysis and comparison of detection effects of three different sizes of detection models: YOLOv5s, YOLOv5m and YOLOv5l. The proposed model realizes the mask detection function and obtains the advantages and disadvantages of different scale models through performance evaluation. The maximum mAP of the model reached 88.1%, with good detection accuracy. © 2022 IEEE.