An Exploratory Study of Masked Face Recognition with Machine Learning Algorithms

Automated face recognition is a widely adopted machine learning technology for contactless identification of people in various processes such as automated border control, secure login to electronic devices, community surveillance, tracking school attendance, workplace clock in and clock out. Using face masks have become crucial in our daily life with the recent world-wide COVID-19 pandemic. The use of face masks causes the performance of conventional face recognition technologies to degrade considerably. The effect of mask-wearing in face recognition is yet an understudied issue. In this paper, we address this issue by evaluating the performance of a number of face recognition models which are tested by identifying masked and unmasked face images. We use six conventional machine learning algorithms, which are SVC, KNN, LDA, DT, LR and NB, to find out the ones which perform best, besides the ones which poorly perform, in the presence of masked face images. Local Binary Pattern (LBP) is utilized as the feature extraction operator. We generated and used synthesized masked face images. We prepared unmasked, masked, and half-masked training datasets and evaluated the face recognition performance against both masked and unmasked images to present a broad view of this crucial problem. We believe that our study is unique in elaborating the mask-aware facial recognition with almost all possible scenarios including half_masked-to-masked and half_masked-to-unmasked besides evaluating a larger number of conventional machine learning algorithms compared the other studies in the literature. © 2023 IEEE.

The practice of COVID-19 vaccination in patients bleeding disorders

Subcutaneous injections are recommended instead of intramuscular for patients with bleeding disorders to avoid bleeding complications. This study aimed to determine whether the intramuscular administration of COVID-19 vaccines would increase bleeding-associated complications in patients with bleeding disorders followed in our clinic. We collected the data of 47 patients with bleeding disorders older than 18 years followed at the hematology outpatient clinic and screened between March 15, 2020, and December 31, 2021. We obtained the data from the hospital's electronic information system, including age, gender, type of bleeding disorder, factor levels, and whether they received prophylaxis. We interviewed the participants about the type of vaccine they received and the duration of compression they applied to the injection site, whether they received factor replacement before and after the injection, and whether there were any complications following the injection. We included in the study thirty-nine male patients vaccinated against COVID-19. The mean age of the patients was 39.05 (18-73 years). Factor VIII deficiency constituted 79.4%, XI 10.3%, and other bleeding disorders 10.3 % of the cases. The patients with bleeding disorders had a mean factor level of 2.02 (0-9). Twenty-nine (74.4%) patients were on regular factor prophylaxis for their bleeding disorder. In terms of the compression duration to the injection site following injection, 6 (15.4%) patients had applied compression for 10 min, 4 (10.3%) for 5-10 min, and 29 (73.4%) for less than 5 min. Two (5.1%) patients developed ecchymosis after the first vaccine dose on the injection arm. The results of this study demonstrate that the rate of bleeding complications remains low in patients with bleeding disorders if they receive intramuscular vaccination after necessary precautions. Copyright © 2022 Ondokuz Mayis Universitesi. All rights reserved.

Clinical Course of Covid-19 in Hematological Disorders

Hematology patients are extremely vulnerable to COVID-19 infection due to the immunosuppression arising from the direct effect of the disease and the medicines administered. Our purpose is to analyze the results of the patients that both have a hematological disease and receive treatment for COVID-19 infection in our hospital. Four hundred COVID-19 positive patients that received inpatient treatment between March 12, 2020 and October 1, 2020 in our center and got a diagnosis by using real -time polymerase chain reaction (RT-PCR) test were scanned retrospectively. Eighty one patients were included in the study. Nineteen patients had a hematological disease;62 had a chronic disease but didn't have a hematological disease. We found that the group with hematological disease had a high level of ferritin (p= 0.0001). While the use of steroids in COVID-19 treatments is more frequent in the group with hematological disease (p= 0.01), the use of LMWH (low molecular weight heparin) is more frequent in the group with no hematological diseases (p= 0.02). Intensive care treatment and mechanical ventilatory support were required more for the patients with hematological disease than the others (p= 0.03. p= 0.008). While the mortality rate is 42.1% in the patients with hematological disease, it is 9.7% in the patients with chronic disease (p= 0.003). In cox regression analysis, the study found that hematological diseases (HR: 4.02, 95% CI: 1.7-1844.5, p= 0.02), cardiac diseases (HR: 2.28, 95% CI: 1.2-77.9, p= 0.03), and intensive care treatment (HR: 4.60, 95% CI: 3.1-3115.0, p= 0.009) are significant risk factors. Hematological patients infected with COVID-19 have a more severe and mortal clinical manifestation than the patients with other chronical disease.