Your browser doesn't support javascript.
Show: 20 | 50 | 100
Results 1 - 20 de 105
Filter
1.
Environ Res ; 215:114323, 2022.
Article in English | ScienceDirect | ID: covidwho-2031272

ABSTRACT

Dependency on plastic commodities has led to a recurrent increase in their global production every year. Conventionally, plastic products are derived from fossil fuels, leading to severe environmental concerns. The recent coronavirus disease 2019 pandemic has triggered an increase in medical waste. Conversely, it has disrupted the supply chain of personal protective equipment (PPE). Valorisation of food waste was performed to cultivate C. necator for fermentative production of biopolymer poly(3-hydroxybutyrate-co-3-hydroxyvalerate) (PHBV). The increase in biomass, PHBV yield and molar 3-hydroxy valerate (3HV) content was estimated after feeding volatile fatty acids. The fed-batch fermentation strategy reported in this study produced 15.65+/-0.14g/L of biomass with 5.32g/L of PHBV with 50% molar 3HV content. This is a crucial finding, as molar concentration of 3HV can be modulated to suit the specification of biopolymer (film or fabric). The strategy applied in this study addresses the issue of global food waste burden and subsequently generates biopolymer PHBV, turning waste to wealth.

2.
Frontiers in Psychology ; 13, 2022.
Article in English | Web of Science | ID: covidwho-2022881

ABSTRACT

Recent studies on the effects of mandatory online teaching, resulting from the COVID-19 pandemic, have widely reported low levels of satisfaction, unwillingness to continue online teaching, and negative impacts on the psychological well-being of teachers. Emerging research has highlighted the potential role of psychological need thwarting (PNT), in terms of autonomy, competence, and relatedness thwarting, resulting from online teaching. The aim of this study was to evaluate the immediate and delayed (longitudinal) effects of PNT of online teaching on teachers' well-being (including distress and burnout), intention to continue online teaching, and job satisfaction. Moreover, data collected from both cross-sectional and longitudinal surveys allowed for a systematic validation of an important instrument in the field of teacher psychology, the Psychological Need Thwarting Scale of Online Teaching (PNTSOT), in terms of longitudinal reliability and validity. The data reveal the usefulness of the construct of PNT in terms predicting and explaining teachers' willingness to continue using online teaching as well as the degree of burnout after a period of 2 months, such that PNT is positively associated with burnout and negatively associated with willingness to continue online teaching. As such, the PNTSOT is recommended for future research evaluating the long-term psychological, affective, and intentional outcomes stemming from teachers' PNT. Moreover, based on our findings that the impact from PNT of online teaching is persistent and long-term, we suggest that school leaders provide flexible and sustained professional development, model respectful and adaptive leadership, and create opportunities for mastery for the development of community of practice that can mitigate the thwarting of teachers' autonomy, competence, and relatedness during times of uncertainty. Additionally, in terms of the psychometric properties of the PNTSOT instrument, our empirical findings demonstrate internal reliability, test-retest reliability, measurement invariance, and criterion validity (concurrent and predictive) based on cross-sectional and longitudinal data.

3.
J Telemed Telecare ; : 1357633X221124175, 2022.
Article in English | Web of Science | ID: covidwho-2020652

ABSTRACT

INTRODUCTION: Isolated spaces impair communication and teamwork during tracheal intubation (TI) in suspected coronavirus disease 2019 patients. We thus aimed to evaluate the telemedicine-assisted airway model (TAM) to improve communication and teamwork during the pandemic. METHODS: This two-stage prospective study included adult patients intubated in the emergency department of the National Taiwan University Hospital between 1 August 2020 and 31 July 2021. First, we randomised patients receiving TI in the standard setting into the conventional group (Con-G) and the isolation area into the isolation group (Iso-G). We evaluated the obstacles to communication and teamwork in an isolation scenario. Second, we developed the TAM to facilitate communication and teamwork between staff in separate spaces during TI and assigned patients to the TAM group (TAM-G). Communication and teamwork were evaluated using the Team Emergency Assessment Measure (TEAM). Subjective evaluations were conducted using a questionnaire administered to medical staff. RESULTS: Eighty-nine patients were enrolled: 17, 34, and 38 in the Con-G, Iso-G, and TAM-G, respectively. The communication frequency (CF) of the Con-G and Iso-G was the highest and lowest, respectively. The CF of the TAM-G increased and approached that of the Con-G. The overall TEAM score was the highest in the Con-G and the lowest in the Iso-G, while the overall score in the TAM-G was comparable to that of the Con-G. DISCUSSION: The TAM may improve communication and teamwork for TIs without compromising efficacy during the pandemic. This study was registered at ClinicalTrials.gov;registration numbers: NCT04479332 and NCT04591873.

4.
19th International Joint Conference on Computer Science and Software Engineering, JCSSE 2022 ; 2022.
Article in English | Scopus | ID: covidwho-2018935

ABSTRACT

The ongoing COVID-19 pandemic has wreaked havoc on social and economic systems worldwide. The variance in the rapidly increasing number of illnesses and deaths in each country is primarily due to national policies and actions. As a result, governments and institutions need to get insights into the critical factors influencing COVID-19 future case counts to properly manage the adverse effects of pandemics and promptly prepare appropriate measures. Thus, in this paper, we conduct extensive experiments on the real-world covid-19 datasets to examine the important factors influencing in the pandemic growth. In particular, we perform an exploratory data analysis to get the statistic and characteristics of multivariate time-series data on pandemic dynamic. Also, we utilize a statistical measure such as Pearson correlation to compute the relations of the past on the future daily new cases. The experimental results demonstrate that some restrictions have a positive effect on daily new confirmed cases at the early stage of the local pandemic transmission. Also, the results show that the early trend of COVID-19 can be explained well by human mobility in various categories. Thus, our proposed framework can be served as a guideline for future pandemic prevention and control decision-making. © 2022 IEEE.

5.
Medicine (Baltimore) ; 101(36):e30297, 2022.
Article in English | PubMed | ID: covidwho-2018319

ABSTRACT

Coronavirus disease-2019 (COVID-19), caused by severe acute respiratory syndrome-coronavirus-2 (SARS-CoV-2), has emerged as a global health concern. This study aimed to review the epidemiology and pathophysiology of COVID-19 and provide evidence for the implementation of control measures. We utilized several online databases, including MEDLINE (National Library of Medicine, Bethesda, Maryland, USA), PubMed, EMBASE, Web of Science, and Google Scholar, to collect relevant published papers using a combination of the following keywords: "COVID-19," "SARS-CoV-2," "novel coronavirus," "epidemiology," and "pathophysiology." The Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines were used in this study. Globally, approximately 3-46% of patients with SARS-CoV-2 infection experience gastrointestinal symptoms. The clinical spectrum of COVID-19 is wide, ranging from mild to severe, and even fatal. COVID-19 was initially reported as a respiratory tract disease;however, gastrointestinal symptoms have only recently been reported. COVID-19 Patients with gastrointestinal symptoms may have more severe clinical manifestations and poor prognosis. This study highlights the need to better understand the mechanisms involved in the development of gastrointestinal symptoms in patients with COVID-19 to prevent the further spread of this pathogen.

6.
JAMA Ophthalmology ; 08:08, 2022.
Article in English | MEDLINE | ID: covidwho-2013257
7.
PloS one ; 17(8):e0272546, 2022.
Article in English | MEDLINE | ID: covidwho-2009688

ABSTRACT

OBJECTIVES: The coronavirus disease 2019 pandemic has affected countries around the world since 2020, and an increasing number of people are being infected. The purpose of this research was to use big data and artificial intelligence technology to find key factors associated with the coronavirus disease 2019 infection. The results can be used as a reference for disease prevention in practice. METHODS: This study obtained data from the "Imperial College London YouGov Covid-19 Behaviour Tracker Open Data Hub", covering a total of 291,780 questionnaire results from 28 countries (April 1~August 31, 2020). Data included basic characteristics, lifestyle habits, disease history, and symptoms of each subject. Four types of machine learning classification models were used, including logistic regression, random forest, support vector machine, and artificial neural network, to build prediction modules. The performance of each module is presented as the area under the receiver operating characteristics curve. Then, this study further processed important factors selected by each module to obtain an overall ranking of determinants. RESULTS: This study found that the area under the receiver operating characteristics curve of the prediction modules established by the four machine learning methods were all >0.95, and the RF had the highest performance (area under the receiver operating characteristics curve is 0.988). Top ten factors associated with the coronavirus disease 2019 infection were identified in order of importance: whether the family had been tested, having no symptoms, loss of smell, loss of taste, a history of epilepsy, acquired immune deficiency syndrome, cystic fibrosis, sleeping alone, country, and the number of times leaving home in a day. CONCLUSIONS: This study used big data from 28 countries and artificial intelligence methods to determine the predictors of the coronavirus disease 2019 infection. The findings provide important insights for the coronavirus disease 2019 infection prevention strategies.

8.
Biomed Eng Online ; 21, 2022.
Article in English | PMC | ID: covidwho-2009405

ABSTRACT

Background: Aerosols and droplets are the transmission routes of many respiratory infectious diseases. The COVID-19 management guidance recommends against the use of nebulized inhalation therapy directly in the emergency room or in an ambulance to prevent possible viral transmission. The three-dimensional printing method was used to develop an aerosol inhalation treatment mask that can potentially prevent aerosol dispersion. We conducted this utility validation study to understand the practicability of this new nebulizer mask system. Results: The fit test confirmed that the filter can efficiently remove small particles. The different locations of the mask had an excellent fit with a high pressure making a proper face seal usability. The full-face mask appeared to optimize filtration with pressure and is an example of materials that perform well for improvised respiratory protection using this design. The filtering effect test confirmed that the contamination of designated locations could be protected when using the mask with filters. As in the clinical safety test, a total of 18 participants (10 [55.6%] females;aged 33.1 ± 0.6 years) were included in the final analysis. There were no significant changes in SPO2, EtCO2, HR, SBP, DBP, and RR at the beginning, 20th, 40th, or 60th minutes of the test (all p >.05). The discomfort of wearing a mask increased slightly after time but remained within the tolerable range. The vision clarity score did not significantly change during the test. The mask also passed the breathability test. Conclusion: The results of our study showed that this mask performed adequately in the fit test, the filtering test, and the clinical safety test. The application of a full-face mask with antiviral properties, together with the newly designed shape of a respirator that respects the natural curves of a human face, will facilitate the production of personal protective equipment with a highly efficient filtration system. Methods: We conducted three independent tests in this validation study: (1) a fit test to calculate the particle number concentration and its association with potential leakage;(2) a filtering effect test to verify the mask’s ability to contain aerosol spread;and (3) a clinical safety test to examine the clinical safety, comfortableness, and visual clarity of the mask.

9.
Annals of the Rheumatic Diseases ; 81:959, 2022.
Article in English | EMBASE | ID: covidwho-2009047

ABSTRACT

Background: Several studies have demonstrated immunogenicity after COVID-19 vaccination in patients with autoimmune rheumatic diseases (AIRD) [1], but the differences between mRNA-based and vector vaccines and the cellular responses to COVID-19 vaccines according to distinct immunogenicity in AIRD patients are still unclear. Objectives: To investigate the differences in efficacy and safety between the vector vaccine ChAdOx1 nCoV-19/AZD1222 (Oxford-AstraZeneca) and mRNA-based vaccine mRNA-1273 (Moderna) in patients with AIRD, and to explore the cell-cell interactions between high and low anti-SARS-CoV-2 IgG levels in patients with rheumatic arthritis (RA) by single-cell RNA sequencing (scRNA-seq). Methods: From September 16 to November 15, 2021, we consecutively enrolled 243 participants aged ≥20 years with AIRD who received COVID-19 vaccination, of whom 113 were immunized with AZD1222 and 130 with mRNA-1273. The level of serum IgG antibodies to the SARS-CoV-2 receptor-binding domain on the spike protein S1 subunit was quantifed by electrochemiluminescence immuno-assay at 4-6 weeks after vaccination. Moreover, peripheral blood mononuclear cells were isolated from two RA patient with high anti-SARS-CoV-2 IgG level and four RA patients with low level for scRNA-seq and cell-cell communication signal was analyzed by CellChat. Results: The anti-SARS-CoV-2 IgG seropositivity rate was 78.8% (89/113) for AZD1222 and 83.1% (108/130) for mRNA-1273. The level of anti-SARS-CoV-2 IgG was higher in patients who received mRNA-1273 than in those who received AZD1222 (β: 30.15, 95% CI: 11.67-48.63, p=0.002) (Table 1). Prednisolone-equivalent dose >5 mg/day and methotrexate (MTX) use in AIRD patients, and non-anti-tumor necrosis factor (TNF)-α biologics and Janus kinase (JAK) inhibitor use in RA patients were associated with inferior immunogenicity. ScRNA-seq revealed CD16-monocytes were predominant in RA patients with high anti-SARS-CoV2-IgG antibody level, and enriched pathways related to antigen presentation via major histocompatibility complex class II (MHC class II) were found (Figure 1). HLA-DRA and CD4 interaction was vigorous among all identifed MHC-II pathway and was enhanced in high anti-SARS-CoV2-IgG antibody group. Conclusion: mRNA-1273 and AZD1222 vaccines exhibited differential immunogenicity in patients with AIRD. Enriched pathways related to antigen presentation via MHC class II in CD16-monocytes might be associated with higher anti-SARS-CoV2-IgG level in RA patients and further study is warranted.

10.
Signal Transduct Target Ther ; 7, 2022.
Article in English | PMC | ID: covidwho-2008260
11.
Atmos Pollut Res ; 13(10):101549, 2022.
Article in English | PMC | ID: covidwho-2007442

ABSTRACT

Photochemical regime for ozone (O3) formation is complicated in the sense that reducing emission of nitrogen oxides (NOx) may increase O3 concentration. The lockdown due to COVID-19 pandemic affords a unique opportunity to use real observations to explore the O3 formation regime and the effectiveness of NOx emission control strategies. In this study, observations from ground networks during the lockdowns were used to assess spatial disparity of the Ratio of Ozone Formation (ROF) for nitrogen dioxide (NO2) reduction in the Greater Bay Area (GBA) of China. The health risk model from Air Quality Health Index (AQHI) system in Hong Kong was adopted to evaluate the risk tradeoffs between NO2 and O3. Results show that the levels of O3 increase and NO2 reduction were comparable due to high ROF values in urban areas of central GBA. The ozone reactivity to NO2 reduction gradually declined outwards from central GBA. Despite the O3 increases, the NOx emission controls reduced the Integrated Health Risk (IHR) of NO2 and O3 in most regions of the GBA. When risk coefficients from the AQHI in Canada or the global review were adopted in the risk analyses, the results are extremely encouraging because the controls of NOx emission reduced the IHR of NO2 and O3 almost everywhere in the GBA. Our results underscore the importance of using a risk-based method to assess the effectiveness of emission control measures and the overall health benefit from NOx emission controls in the GBA.

12.
Journal of Arrhythmia ; 2022.
Article in English | Web of Science | ID: covidwho-2003626
13.
BMC Geriatr ; 22(1):697, 2022.
Article in English | PubMed | ID: covidwho-2002119

ABSTRACT

BACKGROUND: The COVID-19 pandemic has required restrictions of daily activities, which has been found to impact the lives of persons living with dementia (PLWDs) and their family caregivers, who have multiple care demands. The lack of relevant studies in Taiwan emphasized the need to explore the experiences of family caregivers of older PLWDs faced with the intensified restrictions to control the spread of COVID-19, and the impact of the availability of a smart-clothes home nursing program. METHODS: This qualitative study used semi-structured interviews with family caregivers of older PLWDs. Participants were recruited from dementia clinics of a medical center in northern Taiwan from a subset of a sample from a larger study on smart-clothes assisted home nursing care. A total of 12 family caregivers who participated in the original study were interviewed during the follow-up period;seven family caregivers of a PLWD wearing a smart-vest, which transmitted information to a home care nurse;five caregivers of a PLWD not wearing a smart-vest. Interviews were conducted by telephone because the conditions of the pandemic prevented face-to-face interviews. Recorded interviews were transcribed and analyzed using content analysis. RESULTS: Interview data showed family caregivers' felt the care recipient's health was compromised and functional conditions intensified as Covid-19-related pandemic restrictions increased. Specific concerns included a lack social interactions, decreased daily activity levels, loss of interest and lack of motivation for activities, increased mood and behavioral problems, a decline in physical function and an increase in health problems. Family caregivers were also impacted by these restrictions, with significant increases in severity of caregiver role strain, including feeling trapped, a lack of in-home support, profound powerlessness, and worries about the PLWD contracting the coronavirus. The smart-clothes assisted home nursing care program offered supplementary support to family caregivers by providing on-time interactions, helping them manage health problems, enhancing predictability of the care recipient's behaviors, and providing caregivers with emotional support. CONCLUSIONS: The findings of this study support alternative care such as implementation of technology-assisted home health services to meet caregiver needs to facilitate family caregiving of PLWDs during the necessary restrictions in activities implemented during the COVID-19 pandemic. TRIAL REGISTRATION: ClinicalTrials.gov Protocol Record NCT05063045.

14.
International Journal of Gerontology ; 16(3):207-212, 2022.
Article in English | Web of Science | ID: covidwho-1988405

ABSTRACT

Background: Geriatric patients with COVID-19 have had poor clinical outcomes globally, especially during the first wave of the pandemic. In Taiwan, the first wave of the COVID-19 pandemic occurred from May to July 2021. This retrospective study aimed to compare the characteristics and outcomes between geriatric and younger patients with COVID-19 infection. Methods: A total of 257 confirmed COVID-19 cases who were hospitalized from May to June 2021 were included. Their characteristics and outcomes, including in-hospital mortality, use of mechanical ventilation, and hospital stay, were collected for analysis. Results: There were 98 elderly patients (aged >= 65 years, median, 72.5 (interquartile range, 69.0-78.0) years) and 159 younger patients (aged < 65 years, median 55.0 (46.0-60.0) years). The elderly patients had a significantly higher Charlson comorbidity score (4.0 (3.0-5.0) vs. 1.0 (1.0-2.0), p < 0.001), and significantly higher D-dimer, procalcitonin, ferritin, and creatinine levels, but lower albumin level than the younger patients. The elderly group also had higher in-hospital mortality (7.1% vs. 1.9%, p < 0.05), were more likely to develop severe disease (83.7% vs. 67.9%, p < 0.01), and had a longer hospital stay (15.0 (11.0-23.0) vs. 12.0 (9.0-16.5) days, p < 0.001). Nevertheless, the elderly patients did not have a higher risk of using high-flow nasal cannulas (17.3% vs. 15.1%, p = 0.63) or mechanic ventilation (23.5% vs. 17.0%, p = 0.20). Conclusion: Elderly COVID-19 patients had significant higher risks of severe disease, mortality, and lon-ger duration of hospitalization, possible due higher rates of comorbidities and pro-inflammatory status. Copyright (c) 2022, Taiwan Society of Geriatric Emergency & Critical Care Medicine.

15.
International Journal of Gerontology ; 16(3):196-201, 2022.
Article in English | Web of Science | ID: covidwho-1988403

ABSTRACT

Background: To evaluate the feasibility, baseline characteristics, and satisfaction of patients receiving telemedicine care during the coronavirus 2019 (COVID-19) pandemic in Taiwan. Methods: We retrospectively analyzed patients during the COVID-19 pandemic between May 2021 and December 2021 in a tertiary medical center in northern Taiwan. Information on the distribution of physician divisions, patients' clinical characteristics, and patterns of prescription use in telemedicine care was analyzed. Data were extracted from both the ordinary outpatient department (OPD) and nursing home systems. Results: A total of 6587 patients (55.8% female, mean age: 57.3 +/- 25.8 years) included in our telemedicine care conducted during the pandemic COVID-19 epidemic. Those who were older, female, and patients of Internal Medicine and Family Medicine utilized telemedicine more frequently than ordinary OPD, with a high refill prescription rate (82.6%) and low mail-back prescription use (35.9%). Patients of Family Medicine comprised the majority (40.3%) of nursing home telemedicine, with lower refill pre-scription use (37.3%). Overall satisfaction was high regarding telemedicine care, physicians profession-alism, and medical problem solving (98.3% and 97.7%, respectively). Conclusion: Older age, female sex, and potentially more health conditions were associated with higher willingness to access telemedicine. We identified medical divisional and disease-based differences in prescription patterns. Copyright (c) 2022, Taiwan Society of Geriatric Emergency & Critical Care Medicine.

16.
International Journal of Gerontology ; 16(3):191-195, 2022.
Article in English | Web of Science | ID: covidwho-1988402

ABSTRACT

Background: Coronavirus disease 2019 (COVID-19) can cause acute respiratory failure and acute respiratory distress syndrome (ARDS). The prone position (PP) is widely used in patients with severe hypoxemia due to ARDS as it improves oxygenation. The aim of this study was to investigate whether improvements in gas exchange and lung mechanics with the PP were associated with survival in ventilated COVID-19 patients. Methods: Fourteen ventilated patients who were placed in the PP were included from May to June 2021. Clinical manifestations and lung mechanics parameters were collected. Results: The overall intensive care unit (ICU) mortality rate was 42.9%. Nonsurvivors were older (p = 0.014) and had higher Charlson comorbidity index (2.1 +/- 1.5 vs. 4.8 +/- 2.4, p = 0.035) and Sepsis-related Organ Failure Assessment (SOFA) (3.3 +/- 1.0 vs. 7.3 +/- 3.5, p = 0.019) scores compared to survivors. There was no difference in PaO2/FiO(2) (P/F ratio) at baseline between the survivors and nonsurvivors. The improvement in P/F ratio (p = 0.0037) and reduction in driving pressure (Pdrive) (p = 0.046) on the second day after first PP were correlated with lower mortality. Significant predictors of successfully stopping prone treatment included a reduction in Pdrive at the first hour, lower tidal volume (Vt) at the fourth hour, and P/F ratio improvement on the second day after PP. Conclusion: Improvement in P/F ratio and reduction in driving pressure on the second day after PP were correlated with reduced mortality. Three parameters could predict successful resumption of the supine position. Copyright (c) 2022, Taiwan Society of Geriatric Emergency & Critical Care Medicine.

17.
Conference on Silicon Photonics XVII Part of SPIE Photonics West OPTO Conference ; 12006, 2022.
Article in English | Web of Science | ID: covidwho-1986323

ABSTRACT

The advent of the SARS-CoV-2 pandemic has rekindled the demand for inexpensive, point-of-care and at-home diagnostic systems that offer high degrees of scalability, sensitivity, and specificity. While several options of sensing modalities have been researched and subsequently commercialized, these sensing systems are yet to simultaneously satisfy the spiked demand for higher accuracy and scalable manufacturing. In this context, the prospect of integrated photonics-enabled biosensors has garnered immense attention from both scientific and business communities. However, realizing low group indices of the photonic structures required for higher bulk sensitivities at commonly used telecom operation wavelengths is typically achieved using design approaches incompatible with foundry process constraints. Siphox Inc., founded in 2020, developed an ensemble biosensing platform by merging the benefits of CMOS-friendly integrated photonic structures with proprietary biochemical assays to realize low-cost, highly sensitive, label and label-free, multiplexed diagnostic system. As a first demonstration, we present our results of 15-plex biosensing utilizing low-loss (<3.5dB/cm) Si3N4 strip-waveguide ring resonators fabricated using 248 nm deep UV (DUV) stepper lithography. We describe the design, simulation, and measurement results of bulk and surface sensitivities and detection limits for our TE-polarized waveguide resonator structures operating at O-band (1310 nm). We demonstrate a bulk sensitivity of >117 nm/RIU and an intrinsic limit of detection of 1.87x10(-4) RIU.

18.
16th IEEE International Symposium on Medical Information and Communication Technology, ISMICT 2022 ; 2022-May, 2022.
Article in English | Scopus | ID: covidwho-1985479

ABSTRACT

Mask mandate has been applied in many countries in the last two years as a simple but effective way to limit the Covid-19 transmission. Besides the guidance from authorities regarding mask use in public, numerous vision-based approaches have been developed to aid with the monitoring of face mask wearing. Despite promising results have been obtained, several challenges in vision-based masked face detection still remain, primarily due to the insufficient of a quality dataset covering adequate variations in lighting conditions, object scales, mask types, or occlusion levels. In this paper, we investigate the effectiveness of a lightweight masked face detection system under different lighting conditions and the possibility of enhancing its performance with the employment of an image enhancement algorithm and an illumination awareness classifier. A dataset of human subjects with and without face masks in different lighting conditions is first introduced. An illumination awareness classifier is then trained on the collected dataset, the labeling of which is processed automatically based on the difference in detection accuracy when an image enhancement algorithm is taken into account. Experimental results have shown that the combination of the masked face detection system with the illumination awareness and an image enhancement algorithm can boost the system performance to up to 8.6%, 7.4%, and 8.5% in terms of Accuracy, F1-score, and AP-M, respectively. © 2022 IEEE.

19.
International Conference on Data Science, Computation, and Security, IDSCS 2022 ; 462:15-29, 2022.
Article in English | Scopus | ID: covidwho-1971615

ABSTRACT

Face mask detection and recognition have been incorporated into many applications in daily life, especially during the current COVID-19 pandemic. To mitigate the spread of coronavirus, wearing face masks has become commonplace. However, traditional face detection and recognition systems utilize main facial features such as the mouth, nose, and eyes to determine a person’s identity. Masks make facial detection and recognition tasks more challenging since certain parts of the face are concealed. Yet, how to improve the performance of existing systems with a face mask overlaid on the original face input images remains an open area of inquiry. In this study, we propose an improved face mask-aware recognition system named ‘MAR’ based on deep learning, which can tackle challenges in face mask detection and recognition. MAR consists of five main modules to handle various kinds of input images. We re-train the CenterNet model with our augmented face mask inputs to perform face mask detection and propose four variations on face mask recognition models based on the pre-trained ArcFace to handle facial recognition. Finally, we demonstrate the effectiveness of our proposed models on the VGGFACE2 dataset and achieve a high accuracy score on both detection and recognition tasks. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

20.
2nd International Conference on Artificial Intelligence and Computer Engineering, ICAICE 2021 ; : 784-789, 2021.
Article in English | Scopus | ID: covidwho-1948776

ABSTRACT

To achieve high prediction accuracy of human body keeps an open issue for decades of years, especially when COVID comes and online retail becomes the major consumption channels. The body measurement is the key to solve cloth matching and recommendation in clothing e-commerce. This paper proposes a practical framework of image-based body measurement, by only taking the user's front and side photos. This framework does not require pure background or precise standing position, and supports manual modification of the measurement results. The framework takes people's height, weight and gender as params to initialize a common body size set, and corrects each part of the set by analyzing the body proportion via the front and side images. The prediction accuracy was tested with the 50 digital models and 10 real people. Results showed that the circumference sizes such as chest, waist, hips, have errors less then 5%, while the length sizes such as arm, leg approach to actual length on net body models. For real people, the errors depend on the wearing clothes. In addition to high accuracy, the method has a rapid process speed, reaching 19QPS on a NVIDIA RTX5000 GPU server. © 2021 IEEE.

SELECTION OF CITATIONS
SEARCH DETAIL