4
views
0
recommends
+1 Recommend
1 collections
    0
    shares
      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

      FMDNet: An Efficient System for Face Mask Detection Based on Lightweight Model during COVID-19 Pandemic in Public Areas

      Read this article at

      Bookmark
          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

          Abstract

          A new artificial intelligence-based approach is proposed by developing a deep learning (DL) model for identifying the people who violate the face mask protocol in public places. To achieve this goal, a private dataset was created, including different face images with and without masks. The proposed model was trained to detect face masks from real-time surveillance videos. The proposed face mask detection (FMDNet) model achieved a promising detection of 99.0% in terms of accuracy for identifying violations (no face mask) in public places. The model presented a better detection capability compared to other recent DL models such as FSA-Net, MobileNet V2, and ResNet by 24.03%, 5.0%, and 24.10%, respectively. Meanwhile, the model is lightweight and had a confidence score of 99.0% in a resource-constrained environment. The model can perform the detection task in real-time environments at 41.72 frames per second (FPS). Thus, the developed model can be applicable and useful for governments to maintain the rules of the SOP protocol.

          Related collections

          Most cited references48

          • Record: found
          • Abstract: found
          • Article: not found

          Respiratory virus shedding in exhaled breath and efficacy of face masks

          We identified seasonal human coronaviruses, influenza viruses and rhinoviruses in exhaled breath and coughs of children and adults with acute respiratory illness. Surgical face masks significantly reduced detection of influenza virus RNA in respiratory droplets and coronavirus RNA in aerosols, with a trend toward reduced detection of coronavirus RNA in respiratory droplets. Our results indicate that surgical face masks could prevent transmission of human coronaviruses and influenza viruses from symptomatic individuals.
            Bookmark
            • Record: found
            • Abstract: found
            • Article: not found

            Covid-19 — Navigating the Uncharted

            The latest threat to global health is the ongoing outbreak of the respiratory disease that was recently given the name Coronavirus Disease 2019 (Covid-19). Covid-19 was recognized in December 2019. 1 It was rapidly shown to be caused by a novel coronavirus that is structurally related to the virus that causes severe acute respiratory syndrome (SARS). As in two preceding instances of emergence of coronavirus disease in the past 18 years 2 — SARS (2002 and 2003) and Middle East respiratory syndrome (MERS) (2012 to the present) — the Covid-19 outbreak has posed critical challenges for the public health, research, and medical communities. In their Journal article, Li and colleagues 3 provide a detailed clinical and epidemiologic description of the first 425 cases reported in the epicenter of the outbreak: the city of Wuhan in Hubei province, China. Although this information is critical in informing the appropriate response to this outbreak, as the authors point out, the study faces the limitation associated with reporting in real time the evolution of an emerging pathogen in its earliest stages. Nonetheless, a degree of clarity is emerging from this report. The median age of the patients was 59 years, with higher morbidity and mortality among the elderly and among those with coexisting conditions (similar to the situation with influenza); 56% of the patients were male. Of note, there were no cases in children younger than 15 years of age. Either children are less likely to become infected, which would have important epidemiologic implications, or their symptoms were so mild that their infection escaped detection, which has implications for the size of the denominator of total community infections. On the basis of a case definition requiring a diagnosis of pneumonia, the currently reported case fatality rate is approximately 2%. 4 In another article in the Journal, Guan et al. 5 report mortality of 1.4% among 1099 patients with laboratory-confirmed Covid-19; these patients had a wide spectrum of disease severity. If one assumes that the number of asymptomatic or minimally symptomatic cases is several times as high as the number of reported cases, the case fatality rate may be considerably less than 1%. This suggests that the overall clinical consequences of Covid-19 may ultimately be more akin to those of a severe seasonal influenza (which has a case fatality rate of approximately 0.1%) or a pandemic influenza (similar to those in 1957 and 1968) rather than a disease similar to SARS or MERS, which have had case fatality rates of 9 to 10% and 36%, respectively. 2 The efficiency of transmission for any respiratory virus has important implications for containment and mitigation strategies. The current study indicates an estimated basic reproduction number (R0) of 2.2, which means that, on average, each infected person spreads the infection to an additional two persons. As the authors note, until this number falls below 1.0, it is likely that the outbreak will continue to spread. Recent reports of high titers of virus in the oropharynx early in the course of disease arouse concern about increased infectivity during the period of minimal symptoms. 6,7 China, the United States, and several other countries have instituted temporary restrictions on travel with an eye toward slowing the spread of this new disease within China and throughout the rest of the world. The United States has seen a dramatic reduction in the number of travelers from China, especially from Hubei province. At least on a temporary basis, such restrictions may have helped slow the spread of the virus: whereas 78,191 laboratory-confirmed cases had been identified in China as of February 26, 2020, a total of 2918 cases had been confirmed in 37 other countries or territories. 4 As of February 26, 2020, there had been 14 cases detected in the United States involving travel to China or close contacts with travelers, 3 cases among U.S. citizens repatriated from China, and 42 cases among U.S. passengers repatriated from a cruise ship where the infection had spread. 8 However, given the efficiency of transmission as indicated in the current report, we should be prepared for Covid-19 to gain a foothold throughout the world, including in the United States. Community spread in the United States could require a shift from containment to mitigation strategies such as social distancing in order to reduce transmission. Such strategies could include isolating ill persons (including voluntary isolation at home), school closures, and telecommuting where possible. 9 A robust research effort is currently under way to develop a vaccine against Covid-19. 10 We anticipate that the first candidates will enter phase 1 trials by early spring. Therapy currently consists of supportive care while a variety of investigational approaches are being explored. 11 Among these are the antiviral medication lopinavir–ritonavir, interferon-1β, the RNA polymerase inhibitor remdesivir, chloroquine, and a variety of traditional Chinese medicine products. 11 Once available, intravenous hyperimmune globulin from recovered persons and monoclonal antibodies may be attractive candidates to study in early intervention. Critical to moving the field forward, even in the context of an outbreak, is ensuring that investigational products are evaluated in scientifically and ethically sound studies. 12 Every outbreak provides an opportunity to gain important information, some of which is associated with a limited window of opportunity. For example, Li et al. report a mean interval of 9.1 to 12.5 days between the onset of illness and hospitalization. This finding of a delay in the progression to serious disease may be telling us something important about the pathogenesis of this new virus and may provide a unique window of opportunity for intervention. Achieving a better understanding of the pathogenesis of this disease will be invaluable in navigating our responses in this uncharted arena. Furthermore, genomic studies could delineate host factors that predispose persons to acquisition of infection and disease progression. The Covid-19 outbreak is a stark reminder of the ongoing challenge of emerging and reemerging infectious pathogens and the need for constant surveillance, prompt diagnosis, and robust research to understand the basic biology of new organisms and our susceptibilities to them, as well as to develop effective countermeasures.
              Bookmark
              • Record: found
              • Abstract: found
              • Article: not found

              Rational use of face masks in the COVID-19 pandemic

              Since the outbreak of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), the virus that caused coronavirus disease 2019 (COVID-19), the use of face masks has become ubiquitous in China and other Asian countries such as South Korea and Japan. Some provinces and municipalities in China have enforced compulsory face mask policies in public areas; however, China's national guideline has adopted a risk-based approach in offering recommendations for using face masks among health-care workers and the general public. We compared face mask use recommendations by different health authorities (panel ). Despite the consistency in the recommendation that symptomatic individuals and those in health-care settings should use face masks, discrepancies were observed in the general public and community settings.1, 2, 3, 4, 5, 6, 7, 8 For example, the US Surgeon General advised against buying masks for use by healthy people. One important reason to discourage widespread use of face masks is to preserve limited supplies for professional use in health-care settings. Universal face mask use in the community has also been discouraged with the argument that face masks provide no effective protection against coronavirus infection. Panel Recommendations on face mask use in community settings WHO 1 • If you are healthy, you only need to wear a mask if you are taking care of a person with suspected SARS-CoV-2 infection. China 2 • People at moderate risk* of infection: surgical or disposable mask for medical use. • People at low risk† of infection: disposable mask for medical use. • People at very low risk‡ of infection: do not have to wear a mask or can wear non-medical mask (such as cloth mask). Hong Kong 3 • Surgical masks can prevent transmission of respiratory viruses from people who are ill. It is essential for people who are symptomatic (even if they have mild symptoms) to wear a surgical mask. • Wear a surgical mask when taking public transport or staying in crowded places. It is important to wear a mask properly and practice good hand hygiene before wearing and after removing a mask. Singapore 4 • Wear a mask if you have respiratory symptoms, such as a cough or runny nose. Japan 5 • The effectiveness of wearing a face mask to protect yourself from contracting viruses is thought to be limited. If you wear a face mask in confined, badly ventilated spaces, it might help avoid catching droplets emitted from others but if you are in an open-air environment, the use of face mask is not very efficient. USA 6 • Centers for Disease Control and Prevention does not recommend that people who are well wear a face mask (including respirators) to protect themselves from respiratory diseases, including COVID-19. • US Surgeon General urged people on Twitter to stop buying face masks. UK 7 • Face masks play a very important role in places such as hospitals, but there is very little evidence of widespread benefit for members of the public. Germany 8 • There is not enough evidence to prove that wearing a surgical mask significantly reduces a healthy person's risk of becoming infected while wearing it. According to WHO, wearing a mask in situations where it is not recommended to do so can create a false sense of security because it might lead to neglecting fundamental hygiene measures, such as proper hand hygiene. However, there is an essential distinction between absence of evidence and evidence of absence. Evidence that face masks can provide effective protection against respiratory infections in the community is scarce, as acknowledged in recommendations from the UK and Germany.7, 8 However, face masks are widely used by medical workers as part of droplet precautions when caring for patients with respiratory infections. It would be reasonable to suggest vulnerable individuals avoid crowded areas and use surgical face masks rationally when exposed to high-risk areas. As evidence suggests COVID-19 could be transmitted before symptom onset, community transmission might be reduced if everyone, including people who have been infected but are asymptomatic and contagious, wear face masks. Recommendations on face masks vary across countries and we have seen that the use of masks increases substantially once local epidemics begin, including the use of N95 respirators (without any other protective equipment) in community settings. This increase in use of face masks by the general public exacerbates the global supply shortage of face masks, with prices soaring, 9 and risks supply constraints to frontline health-care professionals. As a response, a few countries (eg, Germany and South Korea) banned exportation of face masks to prioritise local demand. 10 WHO called for a 40% increase in the production of protective equipment, including face masks. 9 Meanwhile, health authorities should optimise face mask distribution to prioritise the needs of frontline health-care workers and the most vulnerable populations in communities who are more susceptible to infection and mortality if infected, including older adults (particularly those older than 65 years) and people with underlying health conditions. People in some regions (eg, Thailand, China, and Japan) opted for makeshift alternatives or repeated usage of disposable surgical masks. Notably, improper use of face masks, such as not changing disposable masks, could jeopardise the protective effect and even increase the risk of infection. Consideration should also be given to variations in societal and cultural paradigms of mask usage. The contrast between face mask use as hygienic practice (ie, in many Asian countries) or as something only people who are unwell do (ie, in European and North American countries) has induced stigmatisation and racial aggravations, for which further public education is needed. One advantage of universal use of face masks is that it prevents discrimination of individuals who wear masks when unwell because everybody is wearing a mask. It is time for governments and public health agencies to make rational recommendations on appropriate face mask use to complement their recommendations on other preventive measures, such as hand hygiene. WHO currently recommends that people should wear face masks if they have respiratory symptoms or if they are caring for somebody with symptoms. Perhaps it would also be rational to recommend that people in quarantine wear face masks if they need to leave home for any reason, to prevent potential asymptomatic or presymptomatic transmission. In addition, vulnerable populations, such as older adults and those with underlying medical conditions, should wear face masks if available. Universal use of face masks could be considered if supplies permit. In parallel, urgent research on the duration of protection of face masks, the measures to prolong life of disposable masks, and the invention on reusable masks should be encouraged. Taiwan had the foresight to create a large stockpile of face masks; other countries or regions might now consider this as part of future pandemic plans. © 2020 Sputnik/Science Photo Library 2020 Since January 2020 Elsevier has created a COVID-19 resource centre with free information in English and Mandarin on the novel coronavirus COVID-19. The COVID-19 resource centre is hosted on Elsevier Connect, the company's public news and information website. Elsevier hereby grants permission to make all its COVID-19-related research that is available on the COVID-19 resource centre - including this research content - immediately available in PubMed Central and other publicly funded repositories, such as the WHO COVID database with rights for unrestricted research re-use and analyses in any form or by any means with acknowledgement of the original source. These permissions are granted for free by Elsevier for as long as the COVID-19 resource centre remains active.
                Bookmark

                Author and article information

                Contributors
                (View ORCID Profile)
                (View ORCID Profile)
                (View ORCID Profile)
                (View ORCID Profile)
                (View ORCID Profile)
                (View ORCID Profile)
                (View ORCID Profile)
                Journal
                SENSC9
                Sensors
                Sensors
                1424-8220
                July 2023
                July 02 2023
                : 23
                : 13
                : 6090
                Article
                10.3390/s23136090
                37447939
                087dc2e3-717e-404a-b4a3-963fd88b77af
                © 2023

                https://creativecommons.org/licenses/by/4.0/

                History

                Comments

                Comment on this article