Wear Face Research Articles

Acceptance, Knowledge and Attitudes toward COVID-19 Vaccines: A Cross-Sectional Study from Jigawa State, Nigeria

Vaccination is one of the strategies to contain a pandemic such as coronavirus disease 2019. Nigeria with the highest number of people in Africa has fully vaccinated only 3.69% of its citizens as of February 2022. This study aims to assess the level of Covid-19 vaccine acceptance. A cross-sectional survey was carried out by adopting a systematic random sampling sum of 220 primary school teachers in Dutse municipal (the capital of Jigawa state, Nigeria). Data was gathered between August 2021 and September 2021 through a self-administered questionnaire. A total of 220 primary school teachers participated in this survey, majority of them are married (85.9%) and are above the age of 36 (40.5%). Most of the respondents (47.3%) possessed national certificate of education (N.C.E) or national diploma (N.D). 85.5% of the general participants believed that; physical distancing, wearing of face mask and use of hand sanitizers can reduce the spread of the virus. Only 25.5% of the respondents are ready and willing to be vaccinated if it is available for them while the highest percentages of the participants (57.3) are not willing to take the vaccine and the remaining percentage are yet to decide. Similarly, 64.1% of the respondents believed that fear of side effect is one of the reasons why they are not willing to be vaccinated against the virus. Though, participants’ awareness about the pandemic is moderate but the low level of the vaccine acceptability is worrisome to the Jigawa state health authorities as well as Nigeria at large and should stir more efforts on the sensitization campaigns and strict measures.

Human rhinoviruses prevailed among children in the setting of wearing face masks in Shanghai, 2020

BackgroundHuman rhinovirus (HRV) is the predominant etiological agent of the common cold in children and adults. A recent study showed that the inhibitory effect of face masks on viral shedding of HRV was less prominent than that on other respiratory viruses. Considering that most Chinese people have worn face masks in public area since the outbreak of coronavirus disease 2019, we aimed to find out whether HRV prevailed among children in 2020 and demonstrate the details of the epidemiological features of HRV under such a special circumstance.MethodsWe summarized the incidences of various respiratory virus infections in patients who visited the Children’s Hospital of Fudan University during 2018–2020, and genotyped HRV positive nasopharyngeal specimens collected from 316 inpatients and 72 outpatients that visited the hospital in 2020.ResultsThere was a major prevalence of HRV among children in the latter half of 2020, with a clear seasonality that HRV-As prevailed in summer while HRV-Cs in autumn. HRV-As were more prone to cause severe lower respiratory tract infections (LRTI), while HRV-Cs were closely associated with childhood wheezing. The predominant genotypes were A11, A28, A47, A82, A101, C40 and C43. Notably, A21, A82 and A101 took up larger proportions in severe cases than in non-severe cases.ConclusionsOur findings described a major prevalence of HRVs among children in 2020, which highlight the unique transmitting pattern of HRV and help to narrow the targets for antiviral strategies.

The sci-commodity sensibilities of performative Covid-19 face masking.

This article explores how extravagantly visible mask-wearing relates with consumer culture. Methodologically, three purposively chosen case studies of spectacular or performative mask-wearing are used to show what the face mask can teach us about consumer culture in a pandemic. First, a Daily Mail (UK) article in which an 'elderly shopper' is shamed for wearing a sanitary towel as a face mask is used to explore the politics of disposable commodities. Second, the multiplying portraits of people wearing masks archived under Instagram's #MaskSelfie hashtag allows an examination of how consumer-citizenship is performed. Third, the presence of extremely expensive luxury designer masks, as evidenced by Rich Mnisi's Swarovski-encrusted offering, is a base for considering how virtue signalling has become a platform for luxury branding. Building on these three examples, the argument is made that waste, selfies and luxury are modalities for a pandemic commodity politics that is layered over and into the scientific citizenship signalled by the wearing of face masks. Together these create what I call a 'sci-commodity' sensibility, in which the face mask as a technology has become integrated with the modalities of consumption. This has resonance with ongoing debates about the object, subject and brand in consumer culture.

Ensure the Proper Wearing of Face Masks Using Machine Learning to Fight Covid-19 Virus

In this pandemic time, wearing face masks is mandatory to all because of the possibility that a person can get COVID-19 virus through their mouth, nose or eyes, which could possibly happen when a person has a direct or close contact to a person with that virus. But, despite the strict implementation, some people disregard the proper wearing of face masks and unaware the risks of possible virus transmission for such negligence. In this paper, it will demonstrate how a Convolutional Neural Network (CNN) can detect if a person is wearing a face mask or not and the additional parameter to support to detect if the face mask is properly worn by a person by considering the facial landmarks thru face recognition using Histogram of Oriented Gradients (HOG) feature descriptor with a linear SVM machine learning algorithm. Two (2) processes are involved in proper wearing of face masks detection. It needs to pass in Face Mask Detection to proceed to the next process which is the Face detection wherein the result of checking should return false to confirm the proper wearing of the face mask of a person.

Factors influencing wearing face mask in public during COVID-19 outbreak: a qualitative study.

Wearing face masks is believed to mitigate COVID-19 virus transmission by filtering respiratory droplets. This study was to explore the factors influencing wearing face masks in public in China during COVID-19 outbreak. This study was a qualitative semi-structured interview research design and was guided by the Protection Motivation Theory. Participants from Jiangxi Province China were interviewed via WeChat video call. Thematic analysis was used to analyze the data. Recruitment efforts were suspended when 21 participants (aged 23 to 72) were successfully enrolled and the data reached thematic saturation. Four themes were identified when participants described factors influencing them to wear face masks: knowledge of disease (subthemes were severity of disease, and individual vulnerability to disease), environmental facilitators and constraints (subthemes were government recommendations, public opinion, and affordability and availability of face masks), understanding of protection effectiveness (subthemes were protection effectiveness of wearing face masks, and selection of protective measures), and past experiences. Individuals' decision to wear face masks was influenced by the combination of factors identified. Identification of these factors provides guidance for explaining wearing face masks in public and helps policy makers develop feasible recommendations for wearing face masks during COVID-19 outbreak.

Object Detection Frameworks fo Real-Time, Scale-Invariant Face Mask Detection

As the world experiences a pandemic caused by the spread of COVID-19, following health protocols like the proper wearing of face masks is essential to help prevent the spread of the virus as stressed by the World Health Organization (WHO). In the Philippines, manual monitoring of these measures may not be as efficient when handling large crowds. The authors were able to generate a real-time, scale-invariant face mask recognition model that also handles occlusions. It was trained using images from the wild to simulate real-world conditions. Existing state-of-the-art object detection frameworks such as MobileNet, RetinaNet, and YOLOv4 were implemented to detect and localize the proper use of face masks in public. To evaluate the performance of the models, the mAP, inference time, and precision curve were used. The performance of the model has resulted to as high as .94 mAP with an inference time of 73 ms.

Assessment of the Chemical Composition of Respiratory and Dermal Protective Equipment Used by the Population during the COVID-19 Pandemic

Introduction: The use of personal protective equipment during the COVID-19 pandemic has affected the majority of the global population. The use of face masks has been proven to reduce the incidence of COVID-19 by 53 % and to be an effective means of prevention, both separately and in combination with other non-pharmaceutical measures. Wearing of face masks and gloves was mandated in different regions of the Russian Federation depending on the epidemiological situation, and it is still required in certain areas and workplaces at high risk of this severe infectious disease. Our literature review has shown that the prolonged mask and gloves use has adverse health effects including headaches, difficulty breathing, and various skin reactions. Objective: To analyze chemicals contained in commercially available face masks and protective gloves as one of the stages of hygienic assessment of personal protective equipment and to assess whether the established chemical composition can pose a risk of adverse health outcomes. Materials and methods: In 2021, four types of commercial face masks and protective gloves were analyzed in an accredited testing laboratory center to establish concentrations of chemicals after modeling their release into the aquatic and air environment. Results: We established that, in all types of masks, the levels of detected chemicals did not exceed their appropriate permissible values. Formaldehyde was found in cotton and latex coated cotton gloves in concentrations exceeding the permissible ones by 1.48 and 1.16 times, respectively. A 1.17-fold excess of the acceptable limit was also registered for zinc in latex coated cotton gloves. Conclusions: Increased levels of formaldehyde and zinc were found in cotton and latex coated cotton gloves. Formaldehyde can induce adverse skin reactions. Stricter control over production of respiratory and dermal protective equipment and a comprehensive hygienic assessment of PPE are required.

The Non-Pharmaceutical Interventions to Control the Spread of Covid-19

The COVID-19 pandemic is considered the most crucial global health problem of the 21st century and the greatest challenge that affects humans globally. In late December 2019, a new infectious respiratory disease emerged from Wuhan city of Hubei province in China. Since then, it has since spread around the world, thus declared a pandemic on 11th March 2020 by the World Health Organisation. The outbreak of the novel coronavirus has become a clinical threat to the common population and healthcare workers worldwide. The intensity and speed with which it struck were almost unimaginable as it turns out to have infected over 327,793,472 people and caused more than 5,539,108 deaths globally as of the 17th of January 2022. Likewise, in Nigeria, as of 17th of January 2022; 250,929 confirmed cases, 3,103 deaths, and 224,052 recovered had been reported by NCDC, 2022. At the time of writing this review, no approved antiviral chemotherapy is available instead, use of some recommended vaccines by WHO. Therefore, nonpharmaceutical interventions are adopted by the national government as possible preventive measures to mitigate the spread of the virus globally. These measures include total lockdown, wearing of face mask in public, regular handwashing with soap and water, use of alcohol-based hand sanitizers, maintaining social and physical distance and coughing or sneezing into the elbow, and general enlightenment.

Strategies adopted by Ghana during first and second waves of COVID-19 in Ghana

Though developed countries were the most hit by COVID-19, Sub-Saharan Africa has had a fair share of the pandemic. A year after recording its first two cases, Ghana has recorded over 90,000 cases with over 700 deaths. This write-up describes the enhanced contact tracing and surveillance strategies the country implemented during the first and second wave of COVIID-19 pandemic in Ghana. The standard contact tracing algorithm for COVID-19 was adopted by the country during the initial stages of the pandemic. As the pandemic progressed, the enhanced surveillance strategy which laid emphasis on active and reactive case detection was then introduced with the aim of detecting all COVID-19 infections and ensuring immediate response to them. Adaptation of these strategies in the first wave of COVID-19 in Ghana were marked by achievements including gaining global commendation for the approaches used in tackling the COVID-19 pandemic. As COVID-19 cases declined, some pitfalls in the response during the first phase led the country to experiencing the second wave of infections. With the start of the second wave, response strategies had to be revisited and revamped to address the increasing infection rates. Ghana has experienced two major waves of COVID-19 since the emergence of the pandemic. From using basic strategies such as contact tracing, other strategies such as enhanced surveillance, mapping of risk zone and enforcing of protocols such as mandatory wearing of face masks. Adaptation of dynamic strategies base

Conspiracy beliefs and distrust of science predicts reluctance of vaccine uptake of politically right-wing citizens

It is not uncommon for conspiracy theories to have a political agenda, some conspiracies are more endorsed by the political left-wing than the political right-wing and vice-versa. Conspiracy theories quickly flourished as the COVID-19 pandemic emerged and this may have been an underlying factor in a reluctance by some in following public health policies such as the wearing of face masks. In the present study, we surveyed a community sample of 1358 adults just prior to the COVID-19 vaccine rollout in Aotearoa New Zealand. Our first aim was to determine whether one’s political orientation, whether they are politically left- or right-wing, would be predictive of an individual’s belief in conspiracy theories and determine whether this relationship can be exacerbated by a distrust in science. The second aim was to determine how such a relationship could explain an individual’s vaccine hesitancy. Our results supported that indeed those that identify as right-wing tended to have higher hesitancy associated with taking the COVID-19 vaccine. However, we demonstrated that this association, in part, can be explained by a corresponding belief in COVID-19 related conspiracies. Interestingly, such a relationship only emerged in the presence of a general distrust in science. In other words, if a right-wing individual has at least a moderate trust in science, they demonstrated similarly low endorsement of COVID-19 conspiracies as their left-wing counterparts. Mitigating the right-wing endorsement of COVID-19 conspiracies then aligned with a reduction in vaccine hesitancy. Our findings indicated that public interventions seeking to increase trust in science may mitigate right-wing endorsement of conspiracy theories and thus lead to a more unified and positive response to public health behaviours such as vaccination.

Are estimates of faces\u2019 ages less accurate when they wear sunglasses or face masks and do these disguises make it harder to later recognise the faces when undisguised?

This study examined whether our ability to accurately estimate unfamiliar faces’ ages declines when they are wearing sunglasses or surgical-style face masks and whether these disguises make it harder to later recognise those faces when undisguised. In theory, both disguises should harm age estimation accuracy and later face recognition as they occlude facial information that is used to determine a face’s age and identity. To establish whether this is the case, we had participants estimate the age of unfamiliar faces that were pictured wearing no disguises, sunglasses, or face masks. The participants then completed a face recognition test where they had to distinguish between the previously seen faces and new faces. Importantly, none of faces wore disguises in this latter test. Participants’ estimates of the undisguised faces’ ages were inaccurate by a Median of 5.15 years. Their accuracy barely changed when the faces wore sunglasses but declined by a Median of 1.30 years when they wore face masks. Moreover, subsequent undisguised face recognition was less likely to occur when the faces previously wore sunglasses or face masks, with large effects observed. These findings demonstrate the relative importance of different facial areas when estimating faces’ ages and later recognising them. They also have implications for policing as they suggest it may be harder for eyewitnesses to accurately estimate the age of criminals who wear face masks during offences, and it may be harder for them to later recognise criminals in line-ups if the criminals wear sunglasses or face masks during offences.

Compliance with Covid-19 measures: Evidence from New Zealand.

Governments around the world are seeking to slow the spread of Covid-19 by implementing measures that encourage, or mandate, changes in people’s behaviour. These changes include the wearing of face masks, social distancing, and testing and self-isolating when unwell. The success of these measures depends on the commitment of individuals to change their behaviour accordingly. Understanding and predicting the motivation of individuals to change their behaviour is therefore critical in assessing the likely effectiveness of these measures in slowing the spread of the virus. In this paper we draw on a novel framework, the I3 Compliance Response Framework, to understand and predict the motivation of residents in Auckland, New Zealand, to comply with measures to prevent the spread of Covid-19. The Framework is based on two concepts. The first uses the involvement construct to predict the motivation of individuals to comply. The second separates the influence of the policy measure from the influence of the policy outcome on the motivation of individuals to comply. In short, the Framework differentiates between the strength of individuals’ motivation and their beliefs about the advantages and disadvantages of policy outcomes and policy measures. We found this differentiation was useful in predicting an individual’s possible behavioural responses to a measure and discuss how it could assist government agencies to develop strategies to enhance compliance.

Estimating the effect of non-pharmaceutical interventions to mitigate COVID-19 spread in Saudi Arabia

BackgroundThe Kingdom of Saudi Arabia (KSA) quickly controlled the spread of SARS-CoV-2 by implementing several non-pharmaceutical interventions (NPIs), including suspension of international and national travel, local curfews, closing public spaces (i.e., schools and universities, malls and shops), and limiting religious gatherings. The KSA also mandated all citizens to respect physical distancing and to wear face masks. However, after relaxing some restrictions during June 2020, the KSA is now planning a strategy that could allow resuming in-person education and international travel. The aim of our study was to evaluate the effect of NPIs on the spread of the COVID-19 and test strategies to open schools and resume international travel.MethodsWe built a spatial-explicit individual-based model to represent the whole KSA population (IBM-KSA). The IBM-KSA was parameterized using country demographic, remote sensing, and epidemiological data. A social network was created to represent contact heterogeneity and interaction among age groups of the population. The IBM-KSA also simulated the movement of people across the country based on a gravity model. We used the IBM-KSA to evaluate the effect of different NPIs adopted by the KSA (physical distancing, mask-wearing, and contact tracing) and to forecast the impact of strategies to open schools and resume international travels.ResultsThe IBM-KSA results scenarios showed the high effectiveness of mask-wearing, physical distancing, and contact tracing in controlling the spread of the disease. Without NPIs, the KSA could have reported 4,824,065 (95% CI: 3,673,775–6,335,423) cases by June 2021. The IBM-KSA showed that mandatory mask-wearing and physical distancing saved 39,452 lives (95% CI: 26,641–44,494). In-person education without personal protection during teaching would have resulted in a high surge of COVID-19 cases. Compared to scenarios with no personal protection, enforcing mask-wearing and physical distancing in schools reduced cases, hospitalizations, and deaths by 25% and 50%, when adherence to these NPIs was set to 50% and 70%, respectively. The IBM-KSA also showed that a quarantine imposed on international travelers reduced the probability of outbreaks in the country.ConclusionsThis study showed that the interventions adopted by the KSA were able to control the spread of SARS-CoV-2 in the absence of a vaccine. In-person education should be resumed only if NPIs could be applied in schools and universities. International travel can be resumed but with strict quarantine rules. The KSA needs to keep strict NPIs in place until a high fraction of the population is vaccinated in order to reduce hospitalizations and deaths.

Consequences of the COVID-19 pandemic on lung cancer care and patient health in a German lung cancer center: results from a cross-sectional questionnaire

BackgroundThe novel coronavirus SARS-CoV-2 has caused a global COVID-19 pandemic, leading to worldwide changes in public health measures. In addition to changes in the public sector (lockdowns, contact restrictions), hospitals modified care to minimize risk of infection and to mobilize resources for COVID-19 patients. Our study aimed to assess the impact of these measures on access to care and behaviour of patients with thoracic malignancies.MethodsThoracic oncology patients were surveyed in October 2020 using paper-based questionnaires to assess access to ambulatory care services and tumor-directed therapy during the COVID-19 pandemic. Additionally, behaviour regarding social distancing and wearing of face masks were assessed, as well as COVID-19 exposure, testing and vaccination. Results are presented as absolute and relative frequencies for categorical variables and means with standard deviation for numerical variables. We used t-test, and ANOVA to compare differences in metric variables and Chi2-test to compare proportions between groups.Results93 of 245 (38%) patients surveyed completed the questionnaire. Respiration therapy and physical therapy were unavailable for 57% to 70% of patients during March/April. Appointments for tumor-directed therapy, tumor imaging, and follow-up care were postponed or cancelled for 18.9%, 13.6%, and 14.8% of patients, respectively. Patients reported their general health as mostly unaffected. The majority of patients surveyed did not report reducing their contacts with family. The majority reduced contact with friends. Most patients wore community masks, although a significant proportion reported respiratory difficulties during prolonged mask-wearing. 74 patients (80%) reported willingness to be vaccinated against SARS-CoV-2.ConclusionsThis survey provides insights into the patient experience during the second wave of the COVID-19 pandemic in Munich, Germany. Most patients reported no negative changes to cancer treatments or general health; however, allied health services were greatly impacted. Patients reported gaps in social distancing, but were prepared to wear community masks. The willingness to get vaccinated against SARS-CoV-2 was high. This information is not only of high relevance to policy makers, but also to health care providers.

COVID 19: Knowledge, opinions and prevention among the populace

Objective: There was a lot of panic when the COVID-19 pandemic started because a lot was not known about it. However, as the disease unfolded, proven scientific universal precautions are recommended to curb its spread.
 Methods: This was a cross-sectional online survey of people living in Nigeria. Questionnaires were distributed to consenting participants using the SurveyMonkey and data was collected on sociodemographic knowledge of the aetiology and prevention of COVID-19. Analysis was done with the SPSS version 25.
 Results: Eighty-five participants with age ranging from 18 to 60 years took part in the study. The mean age was 37.35 ± 11.7years. Forty-seven (47%) had knowledge that COVID-19 infection is from a virus. 29.4% thought it is caused by biological weapons, 1.2% from 5G internet, 7.1% as government’s ploy to embezzle money and 9.4% conspiracy theory from the world leaders to reduce world’s population. All participants knew that hand washing is a preventive measure against the spread of COVID-19 and majority agreed to the use of sanitizers, social distancing and disinfection of surfaces. Only 30.6% agreed that wearing of facemasks will serve as a preventive measure. Over 90% of the participants agreed that dissemination of appropriate information, use of universal precautions, isolation and intensive treatment of those infected can help prevent the spread of COVID-19. 11.8% of participants knew that additional precautions are needed for aerosol generating procedures.
 Conclusion: The knowledge of COVID-19 aetiology is poor among the populace and the need to wear face masks as a preventive measure in curtailing the spread of COVID-19 needs to be emphasized.

The Influence of Face Masks on Verbal Communication in Persian in the Presence of Background Noise in Healthcare Staff.

Wearing face masks has resulted in verbal communication being more challenging during the COVID-19 pandemic. This study aimed to investigate the effect of face masks on the speech comprehensibility of Persian nurses in healthcare settings. Twenty female nurses from the governmental hospitals randomly participated in an experiment on seven typical commercial face masks at two background noise levels. Nurses' speech intelligibility from a human talker when wearing each face mask was determined based on the speech discrimination score. The vocal effort of nurses wearing each face mask was determined based on the Borg CR10 scale. Based on the linear mixed model, the speech intelligibility of nurses from a human speaker wearing surgical masks, N95 masks, and a shield with face masks were approximately 10%, 20%, and 40–50% lower, respectively, than no-mask conditions (p < 0.01). The background noise decreased the speech intelligibility of nurses by approximately 22% (p < 0.01). The use of a face shield further decreased speech intelligibility up to 30% compared to using a face mask alone (p < 0.01). The vocal efforts of nurses when wearing surgical masks were not significant compared with the baseline vocal efforts (p > 0.05); however, vocal efforts of nurses when wearing N95 and N99 respirators were at an unacceptable level. The face masks had no considerable effect on the speech spectrum below 2.5 kHz; however, they reduced high frequencies by different values. Wearing face masks has a considerable impact on the verbal communication of nurses in Persian. The level of background noise in the healthcare setting can aggravate the effect sizes of face masks on speech comprehensibility.

A novel DeepMaskNet model for face mask detection and masked facial recognition

Coronavirus disease (COVID-19) has significantly affected the daily life activities of people globally. To prevent the spread of COVID-19, the World Health Organization has recommended the people to wear face mask in public places. Manual inspection of people for wearing face masks in public places is a challenging task. Moreover, the use of face masks makes the traditional face recognition techniques ineffective, which are typically designed for unveiled faces. Thus, introduces an urgent need to develop a robust system capable of detecting the people not wearing the face masks and recognizing different persons while wearing the face mask. In this paper, we propose a novel DeepMasknet framework capable of both the face mask detection and masked facial recognition. Moreover, presently there is an absence of a unified and diverse dataset that can be used to evaluate both the face mask detection and masked facial recognition. For this purpose, we also developed a largescale and diverse unified mask detection and masked facial recognition (MDMFR) dataset to measure the performance of both the face mask detection and masked facial recognition methods. Experimental results on multiple datasets including the cross-dataset setting show the superiority of our DeepMasknet framework over the contemporary models.

To Mask or Not to Mask-Evaluation of Cognitive Performance in Children Wearing Face Masks during School Lessons (MasKids).

In the current SARS-CoV-2 pandemic, wearing a face mask is mandatory again during school lessons. There are no controlled studies in children to date indicating an effect on cognitive performance from wearing face masks. In a randomized controlled trial, we analysed the influence of face masks on cognitive performance of pupils during regular school lessons. Pupils (n = 133, fifth to seventh grade) were randomized by alternating allocation into control (with masks, n = 65) and intervention groups (without mask, n = 68). After two school lessons with (control) and without (intervention) face masks in class, all pupils performed digital tests for cognitive performance regarding attention and executive functions (switch, Corsi block-tapping, 2-back and flanker task). Overall, there were no significant differences in cognitive performance between both groups, masks vs. no masks. Wearing face masks has no significant influence on attention and executive functions of pupils and can still be recommended during school lessons.

TinyML-Based Concept System Used to Analyze Whether the Face Mask Is Worn Properly in Battery-Operated Conditions

As the COVID-19 pandemic emerged, everyone’s attention was brought to the topic of the health and safety of the entire human population. It has been proven that wearing a face mask can help limit the spread of the virus. Despite the enormous efforts of people around the world, there still exists a group of people that wear face masks incorrectly. In order to provide the best level of safety for everyone, face masks must be worn correctly, especially indoors, for example, in shops, cinemas and theaters. As security guards can only handle a limited area of the frequently visited objects, intelligent sensors can be used. In order to mount them on the shelves in the shops or near the cinema cash register queues, they need to be capable of battery operation. This restricts the sensor to be as energy-efficient as possible, in order to prolong the battery life of such devices. The cost is also a factor, as cheaper devices will result in higher accessibility. An interesting and quite novel approach that can answer all these challenges is a TinyML system, that can be defined as a combination of two concepts: Machine Learning (ML) and Internet of Things (IoT). The TinyML approach enables the usage of ML algorithms on boards equipped with low-cost, low-power microcontrollers without sacrificing the classifier quality. The main goal of this paper is to propose a battery-operated TinyML system that can be used for verification whether the face mask is worn properly. To this end, we carefully analyze several ML approaches to find the best method for the considered task. After detailed analysis of computation and memory complexity as well as after some preliminary experiments, we propose to apply the K-means algorithm with carefully designed filters and a sliding window technique, since this method provides high accuracy with the required energy-efficiency for the considered classification problem related to verification of using the face mask. The STM32F411 chip is selected as the best microcontroller for the considered task. Next, we perform wide experiments to verify the proposed ML framework implemented in the selected hardware platform. The obtained results show that the developed ML-system offers satisfactory performance in terms of high accuracy and lower power consumption. It should be underlined that the low-power aspect makes it possible to install the proposed system in places without the access to power, as well as reducing the carbon footprint of AI-focused industry which is not negligible. Our proposed TinyML system solution is able to deliver very high-quality metric values with accuracy, True Positive Ratio (TPR), True Negative Ratio (TNR), precision and recall being over 96% for masked face classification while being able to reach up to 145 days of uptime using a typical 18650 battery with capacity of 2500 mAh and nominal voltage of 3.7 V. The results are obtained using a STM32F411 microcontroller with 100 MHz ARM Cortex M4, which proves that execution of complex computer vision tasks is possible on such low-power devices. It should be noted that the STM32F411 microcontroller draws only 33 mW during operation.

Mask wearing behavior in hot urban spaces of Novi Sad during the COVID-19 pandemic

Urban overheating (due to climate change and urbanization) and COVID-19 are two converging crises that must be addressed in tandem. Fine-scale, place-based, people-centric biometeorological and behavioral data are needed to implement context-specific preventative measures such as mask-wearing. This study collected local biometeorological measurements in diverse urban spaces (square, urban park, river quay) in Novi Sad, Serbia on hot sunny summer days (27–30 August 2020) during the COVID-19 pandemic. Observations were supplemented by an online survey asking questions about thermal sensation, comfort, and concurrent protective behavior of the local population. Biometeorological measurements show that the main square in the city center was the most thermally uncomfortable area. According to the survey, it was also perceived as the least safe space to not contract the virus. The urban park was perceived as the most thermally comfortable area in the morning and during midday. It was also considered the safest urban space for outdoor activities. In the evening, the river quay was the most thermally comfortable area in the city. Intra-urban differences in Physiologically Equivalent Temperatures were highest during midday, while differences in air temperatures were highest in the evening. More than 70% of the respondents did not wear face masks when it was hot because of breathing issues and feeling warmer than without mask. Most people wearing a mask felt “slightly warm” in the morning and evening, while the majority of respondents felt “hot” during midday. Only 3% of the respondents felt comfortable while wearing a mask, while 97% experienced some degree of discomfort (from slight discomfort to very uncomfortable). Our study shows that fine scale temporal and spatial urban biometeorological data and population surveys should be included in decision-making processes during the pandemic to develop climate-sensitive health services that are place-based, people-centric, and facilitate planning towards green, resilient, and inclusive cities.