Analysis of Facial Occlusion Challenge in Thermal Images for Human Affective State Recognition.

Several studies have been conducted using both visual and thermal facial images to identify human affective states. Despite the advantages of thermal facial images in recognizing spontaneous human affects, few studies have focused on facial occlusion challenges in thermal images, particularly eyeglasses and facial hair occlusion. As a result, three classification models are proposed in this paper to address the problem of thermal occlusion in facial images, with six basic spontaneous emotions being classified. The first proposed model in this paper is based on six main facial regions, including the forehead, tip of the nose, cheeks, mouth, and chin. The second model deconstructs the six main facial regions into multiple subregions to investigate the efficacy of subregions in recognizing the human affective state. The third proposed model in this paper uses selected facial subregions, free of eyeglasses and facial hair (beard, mustaches). Nine statistical features on apex and onset thermal images are implemented. Furthermore, four feature selection techniques with two classification algorithms are proposed for a further investigation. According to the comparative analysis presented in this paper, the results obtained from the three proposed modalities were promising and comparable to those of other studies.

Active Safety Surveillance of Four Types of COVID-19 Vaccines: A National Study from Jordan.

BACKGROUND: Although the Pfizer-BioNTech (BNT162b2), Oxford-AstraZeneca (ChAdOx1 nCoV-19), Sinopharm (BBIBP-CorV), and Sputnik V coronavirus disease 2019 (COVID-19) vaccines have been granted emergency approval in many nations, their safety has never been studied and compared in one community-based study. This study aimed to investigate and compare the incidence, nature, severity, and predictors of adverse events following immunization (AEFIs) with COVID-19 vaccines. METHOD: This was a prospective observational study conducted in Jordan between 1 January and 21 September 2021. A team of pharmacists and nurses (n = 407) collected the local and systemic AEFIs of four COVID-19 vaccines by prospectively contacting participants registered in the national vaccination program platform. A red-flag technology was inserted to classify and track rare and serious AEFIs. RESULTS: This study included 658,428 participants who were vaccinated with 1,032,430 doses; 610,591, 279,606, 140,843, and 1390 participants received the first and second doses of the BNT162b2, BBIBP-CorV, ChAdOx1 nCoV-19, and Sputnik V vaccines, respectively. The overall incidence of AEFIs was 28.8%, and the overall rates of systemic, local, and immediate hypersensitivity AEFIs were 22.2%, 18.8%, and 0.5%, respectively. The highest proportions of immediate hypersensitivity AEFIs and systemic AEFIs were reported after administration of the Sputnik V vaccine and ChAdOx1 nCoV-19 first dose, respectively. The most severe AEFIs were reported after ChAdOx1 nCoV-19 first dose and BNT162b2 second dose. The hospitalization and mortality rates after vaccination were 20 in 10,000 and 1 in 10,000, respectively. Based on red-flag tracking, the top three outcome events were lymphadenopathy (157.9/100,000), anxiety disorders (136.6/100,000), and lower respiratory tract infection (100.9/100,000), with Guillain-Barré syndrome (1.8/100,000), vasculitis (3.0/100,000), and myopericarditis (4.8/100,000) being the least common. CONCLUSION: The incidence rates of local, systemic, and immediate hypersensitivity AEFIs of four COVID-19 vaccines occur frequently. High incidence rates of rare and serious AEFIs were reported in this study. Younger participants, females, those who had previously had COVID-19, and smokers were more likely to encounter AEFIs.