Search Results (14)

With the widespread adoption of face masks due to global health crises and heightened security concerns, traditional face recognition systems have struggled to maintain accuracy, prompting significant research into masked face recognition (MFR). Although various models have been proposed, a comprehensive and systematic understanding of recent deep learning (DL)-based approaches remains limited. This paper addresses this research gap by providing an extensive review and comparative analysis of state-of-the-art MFR techniques. We focus on DL-based methods due to their superior performance in real-world scenarios, discussing key architectures, feature extraction strategies, datasets, and evaluation metrics. This paper also introduces a structured methodology for selecting and reviewing relevant works, ensuring transparency and reproducibility. As a contribution, we present a detailed taxonomy of MFR approaches, highlight current challenges, and suggest potential future research directions. This survey serves as a valuable resource for researchers and practitioners seeking to advance the field of robust facial recognition in masked conditions. Full article

By 2050, 700 million people will have hearing loss, requiring rehabilitation services. For about 80% of deaf and hard-hearing individuals, face coverings hinders their ability to lip-read. Also, the normal hearing population experiences issues socializing when wearing face masks. Therefore, there is a need to evaluate and further develop transparent face masks. In this work, the properties of polymers used in ten commercial transparent face masks were determined. The chemical composition of the polymers including nose bridges and ear loops was determined by FTIR spectroscopy. The focus of the characterizations was on the polymers in the transparent portion of each face mask. In half of the masks, the transparent portion contained PET, while in the other masks it consisted of PETG, PC, iPP, PVC, or SR (silicone rubber). Most masks had been coated with anti-fog material, and a few with scratch-resistant compounds, as indicated by XRF/EDX, SEM/EDX, and contact angle measurements. Thermal, molecular weight, and mechanical properties were determined by TGA/DSC, SEC, and tensile tests, respectively. To measure optical properties, UV-Vis reflectance and UV-Vis haze were applied. An assessment of the ten masks and recommendations to develop better transparent face masks were made, including improvement of their sustainability. Full article

As the demand for interpretable machine learning approaches continues to grow, there is an increasing necessity for human involvement in providing informative explanations for model decisions. This is necessary for building trust and transparency in AI-based systems, leading to the emergence of the Explainable Artificial Intelligence (XAI) field. Recently, a novel counterfactual explanation model, CELS, has been introduced. CELS learns a saliency map for the interests of an instance and generates a counterfactual explanation guided by the learned saliency map. While CELS represents the first attempt to exploit learned saliency maps not only to provide intuitive explanations for the reason behind the decision made by the time series classifier but also to explore post hoc counterfactual explanations, it exhibits limitations in terms of its high validity for the sake of ensuring high proximity and sparsity. In this paper, we present an enhanced approach that builds upon CELS. While the original model achieved promising results in terms of sparsity and proximity, it faced limitations in terms of validity. Our proposed method addresses this limitation by removing mask normalization to provide more informative and valid counterfactual explanations. Through extensive experimentation on datasets from various domains, we demonstrate that our approach outperforms the CELS model, achieving higher validity and producing more informative explanations. Full article

This study investigates the public relations (PR) challenges faced by the airline industry during the COVID-19 pandemic, with Spirit Airlines as a focal case. Using a mixed-methods approach, this study analyzes a dataset of 344 LinkedIn online reviews and digital reactions to an incident where a family was removed from a Spirit Airlines flight after their two-year-old child refused to wear a mask. The case study highlights the complex PR challenges airlines face in balancing public health protocols with customer relations during health crises. Through thematic and sentiment analyses, this research identifies gaps in traditional crisis communication models, advocating for empathetic, transparent strategies that align with pandemic-related sensitivities. It underscores the need for specialized staff training to effectively manage such crises. The findings suggest that conventional PR strategies fall short in addressing the multifaceted nature of pandemic-induced crises, calling for a shift towards human-centered communication and robust stakeholder management. This study contributes to the discourse on crisis communication in the airline industry, offering actionable insights for balancing public health responsibilities with customer satisfaction. It calls for a reevaluation of established crisis communication frameworks, urging future research to explore more inclusive and adaptive PR practices in response to health emergencies. Full article

Since the introduction of polydimethylsiloxane (PDMS) microfluidic devices at the beginning of the 21st century, this elastomeric polymer has gained significant attention in the engineering community due to its biocompatibility, exceptional mechanical and optical properties, thermal stability, and versatility. PDMS has been widely used for in vitro experiments ranging from the macro- to nanoscale, enabling advances in blood flow studies, biomodels improvement, and numerical validations. PDMS devices, including microfluidic systems, have been employed to investigate different kinds of fluids and flow phenomena such as in vitro blood flow, blood analogues, the deformation of individual cells and the cell free layer (CFL). The most recent applications of PDMS involve complex hemodynamic studies such as flow in aneurysms and in organ-on-a-chip (OoC) platforms. Furthermore, the distinctive properties of PDMS, including optical transparency, thermal stability, and versality have inspired innovative applications beyond biomedical applications, such as the development of transparent, virus-protective face masks, including those for SARS-CoV-2 and serpentine heat exchangers to enhance heat transfer and energy efficiency in different kinds of thermal systems. This review provides a comprehensive overview of the current research performed with PDMS and outlines some future directions, in particular applications of PDMS in engineering, including biomicrofluidics, in vitro biomodels, heat transfer, and face masks. Additionally, challenges related to PDMS hydrophobicity, molecule absorption, and long-term stability are discussed alongside the solutions proposed in the most recent research studies. Full article

Background/Objectives: This study develops machine learning (ML) models to predict hypoxemia severity during emergency triage, particularly in Chemical, Biological, Radiological, Nuclear, and Explosive (CBRNE) scenarios, using physiological data from medical-grade sensors. Methods: Tree-based models (TBMs) such as XGBoost, LightGBM, CatBoost, Random Forests (RFs), Voting Classifier ensembles, and sequential models (LSTM, GRU) were trained on the MIMIC-III and IV datasets. A preprocessing pipeline addressed missing data, class imbalances, and synthetic data flagged with masks. Models were evaluated using a 5-min prediction window with minute-level interpolations for timely interventions. Results: TBMs outperformed sequential models in speed, interpretability, and reliability, making them better suited for real-time decision-making. Feature importance analysis identified six key physiological variables from the enhanced NEWS2+ score and emphasized the value of mask and score features for transparency. Voting Classifier ensembles showed slight metric gains but did not outperform individually optimized models, facing a precision-sensitivity tradeoff and slightly lower F1-scores for key severity levels. Conclusions: TBMs were effective for real-time hypoxemia prediction, while sequential models, though better at temporal handling, were computationally costly. This study highlights ML’s potential to improve triage systems and reduce alarm fatigue, with future plans to incorporate multi-hospital datasets for broader applicability. Full article

Previous research has found that, when firms engage in environmental sustainability practices, they tend to give a consistent signal to external stakeholders by acting in a more responsible, transparent, and ethical manner, and these firms tend to exhibit high earnings quality. However, other studies have found that those activities may mask a poor earnings quality. On the other hand, firms with high debt levels face constraints in raising funds. In this study, we expect these firms, when involved in environmental reporting practices, to reveal an increase in their earnings quality in order to improve their ability to capture financing. Thus, we analyze whether the level of environmental disclosure and a firm’s debt increase earnings quality. To analyze the former association, we develop an environmental sustainability reporting index (ESReporting), based on GRI standards, using the content analysis for Portuguese firms from 2016 to 2020. We use earnings persistence as a proxy for earnings quality because it is a fundamental characteristic to determine firm value. Regarding debt, we include a financial indicator to analyze its effect on earnings persistence. To test the hypotheses, we estimate a multiple linear regression, applying panel data. Our results suggest that ESReporting and debt tend to positively affect earnings persistence. In addition, our evidence suggests that ESReporting produces a higher positive impact then debt. These results show that ESReporting and debt may be used as regulating mechanisms of earnings management. Besides, this article brings some insights to the improvement of earnings quality resulting from a higher commitment to environmental disclosure and contributing to monitoring managers’ activities. Full article

Background: This study aimed to explore the effect of knowledge, COVID-19-related perceptions, and public trust on protective behaviors in Turkish people. Methods: Data were collected from an online survey (Turkish COVID-19 Snapshot Monitoring) conducted between July 2020 and January 2021. The recommended protective behaviors (hand cleaning, wearing a face mask, and physical distancing) to prevent COVID-19 were examined. The impacts of the following variables on protective behaviors were investigated using logistic regression analysis: knowledge, cognitive and affective risk perception, pandemic-related worry content, public trust, conspiracy thinking, and COVID-19 vaccine willingness. Results: Out of a total of 4210 adult respondents, 13.8% reported nonadherence to protection behavior, and 86.2% reported full adherence. Males and young (aged 18–30 years) people tend to show less adherence. Perceived self-efficacy, susceptibility, and correct knowledge were positively related to more adherence to protective behavior. Perceptual and emotional factors explaining protective behavior were perceived proximity, stress level, and worrying about the relatives who depended on them. Trust in health professionals and vaccine willingness were positive predictors, while conspiracy thinking and acquiring less information (<2, daily) were negative predictors. Unexpectedly, trust in the Ministry of Health showed a weak but negative association with protection behavior. Conclusions: Perceived stress, altruistic worries, and public trust seem to shape protection behaviors in addition to individuals’ knowledge and cognitive risk perception in respondents. Males and young people may have a greater risk for nonadherence. Reliable, transparent, and culture-specific health communication that considers these issues is required. Full article

This paper examines the COVID-19 pandemic response in Iran and offers speculations on the possible impact of its experience on the future response to other health emergencies and disaster risk management based on the lessons learned. The COVID-19 experience in Iran is unique in several aspects, including the significant role played by the healthcare workers’ sharing and exchange of information through Internet-based networking applications, and a sociocultural environment that was weakening public trust and cooperation in the use of preventive strategies such as less than the optimum wearing of face masks and attending large social gatherings. There was also hesitation in receiving the necessary vaccine doses due to public skepticism over the effectiveness of domestic COVID-19 vaccines. Furthermore, healthcare workers and health services were afflicted with a lack of sufficient manpower and material resources to fight the pandemic. Moreover, a strong and mostly negative influence of political agenda and religious influence on preventive health policies, especially an initial governmental ban on the import and use of Western vaccines and the pressure to hold religious festivals during the outbreaks, were prevalent. The lessons that can be learned from this ongoing crisis include the value of independent healthcare information networks, transparency in the communication of health information to the public to get their trust and cooperation, and an emphasis on the separation of health policies from political and religious interference. Full article

Background. The COVID-19 pandemic has imposed radical behavioral and social changes in the general population, significantly impacting the lives of individuals affected by disabilities. The aim of this study was to investigate the impact of COVID-19 on non-institutionalized subjects with sensorineural disabilities during the first COVID-19 wave in Italy. Methods. A 39-item online national survey was disseminated from 1 April 2020 to 31 June 2020 via social media throughout Italy to communities of individuals with proven severe sensorineural disabilities, affiliated to five national patient associations. The survey collected extensive information on the socio-demographic profile, health, everyday activities, and lifestyle of individuals with hearing and visual disabilities. Results. One hundred and sixty-three respondents with hearing (66.9%) and visual (33.1%) disabilities returned a usable questionnaire. The mean age of interviewees was 38.4 ± 20.2 years and 56.3% of them were females. Despite the vast majority of respondents (77.9%) perceiving their health status as unchanged (68.8% of interviewees with hearing deficits vs. 96.3% of those with visual impairments), about half the interviewees reported sleep disorders during lock-down, more likely those with visual deficits. Remote services were seemingly more effective for business than school activities. Furthermore, although just 18.8% of respondents rated remote rehabilitation care unsatisfactory, only 12.8% of interviewees felt supported by health and social services during the COVID-19 emergency. The vast majority of respondents were concerned about the future and the risk of SARS-CoV-2 contagion, particularly individuals with hearing impairments. Among the various risk mitigation measures, facemasks caused the greatest discomfort due to communication barriers, particularly among interviewees affected by hearing disabilities (92.2% vs. 45.7%). The most common request (46.5%) of respondents to reduce the inconveniences of the COVID-19 emergency was improving the access to and delivery of health and social services for individuals with sensorineural disabilities (19.3%), followed by the use of transparent masks (17.5%). Conclusions. Although health protection measures such as face masks and social distancing play a key role in preventing and controlling the spread of SARS-CoV-2, the unmet needs of disabled individuals should be carefully considered, especially those affected by sensory disabilities. Tailored access to health and social services for individuals affected by sensorineural disabilities should be implemented. Additional actions should include the use of face shields as a valid alternative to face masks to reduce communication barriers linked to hearing-impairment, as well as the improvement of remote services, especially distance learning at school. Full article

Here we present a device that suppresses transfer of aerosol between nearby seating areas through the use of optically transparent, sound transmitting barriers and HEPA fan filter unit (FFU). A potential application of this device is to lower the risk of respiratory disease transmission in face-to-face, maskless meetings between individuals in a university setting. We evaluate overall aerosol transmission between users of the device. This is done for two different physical settings: a large space, such as a library, and a small space, such as an enclosed study room. We find that the device can provide lower aerosol transmission compared to the typical transmission between two individuals wearing surgical face masks separated by six feet. Full article

Transparent materials used for facial protection equipment provide protection against microbial infections caused by viruses and bacteria, including multidrug-resistant strains. However, transparent materials used for this type of application are made of materials that do not possess antimicrobial activity. They just avoid direct contact between the person and the biological agent. Therefore, healthy people can become infected through contact of the contaminated material surfaces and this equipment constitute an increasing source of infectious biological waste. Furthermore, infected people can transmit microbial infections easily because the protective equipment do not inactivate the microbial load generated while breathing, sneezing or coughing. In this regard, the goal of this work consisted of fabricating a transparent face shield with intrinsic antimicrobial activity that could provide extra-protection against infectious agents and reduce the generation of infectious waste. Thus, a single-use transparent antimicrobial face shield composed of polyethylene terephthalate and an antimicrobial coating of benzalkonium chloride has been developed for the next generation of facial protective equipment. The antimicrobial coating was analyzed by atomic force microscopy and field emission scanning electron microscopy with elemental analysis. This is the first facial transparent protective material capable of inactivating enveloped viruses such as severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) in less than one minute of contact, and the methicillin-resistant Staphylococcus aureus and Staphylococcus epidermidis. Bacterial infections contribute to severe pneumonia associated with the SARS-CoV-2 infection, and their resistance to antibiotics is increasing. Our extra protective broad-spectrum antimicrobial composite material could also be applied for the fabrication of other facial protective tools such as such as goggles, helmets, plastic masks and space separation screens used for counters or vehicles. This low-cost technology would be very useful to combat the current pandemic and protect health care workers from multidrug-resistant infections in developed and underdeveloped countries. Full article

COVID-19 is spreading globally and causing severe damage across different sectors including social culture, politics, and economy. Governments worldwide are responding in various ways to prevent the spread of COVID-19 and to protect the health and safety of citizens. South Korea is escaping the crisis through rapid and early inspection with ICT technology, isolation for confirmed cases, and transparency and communication through public–private partnerships. This paper presents how face mask shortages can be managed through the disclosure of government data and with effective online services. This study shows how South Korea enhances government transparency and that combining open data with ICT technologies can effectively solve social problems during the COVID-19 pandemic. Full article

Different additive manufacturing technologies have proven effective and useful in remote medicine and emergency or disaster situations. The coronavirus disease 2019 (COVID-19) disease, caused by the Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2) virus, has had a huge impact on our society, including in relation to the continuous supply of personal protective equipment (PPE). The aim of the study is to give a detailed overview of 3D-printed PPE devices and provide practical information regarding the manufacturing and further design process, as well as describing the potential risks of using them. Open-source models of a half-face mask, safety goggles, and a face-protecting shield are evaluated, considering production time, material usage, and cost. Estimations have been performed with fused filament fabrication (FFF) and selective laser sintering (SLS) technology, highlighting the material characteristics of polylactic acid (PLA), polyamide, and a two-compound silicone. Spectrophotometry measurements of transparent PMMA samples were performed to determine their functionality as goggles or face mask parts. All the tests were carried out before and after the tetra-acetyl-ethylene-diamine (TAED)-based disinfection process. The results show that the disinfection has no significant effect on the mechanical and structural stability of the used polymers; therefore, 3D-printed PPE is reusable. For each device, recommendations and possible means of development are explained. The files of the modified models are provided. SLS and FFF additive manufacturing technology can be useful tools in PPE development and small-series production, but open-source models must be used with special care. Full article