Fusion-Based Segmentation and Classification of Novel Coronavirus or Pneumonia from Chest X-ray Images Using Machine Learning Techniques

The deadfall widespread of coronavirus (SARS-Co V-2) disease has trembled every part of the earth and has significant disruption to health support systems in different countries. In spite of such existing difficulties and disagreements for testing the coronavirus disease, an advanced and low-cost technique is required to classify the disease. For the sense of reason, supervised machine learning (ML) along with image processing has turned out as a strong technique to detect coronavirus from human chest X-rays. In this work, the different methodologies to identify coronavirus (SARS-CoV-2) are discussed. It is essential to expand a fully automatic detection system to restrict the carrying of the virus load through contact. Various deep learning structures are present to detect the SARS-CoV-2 virus such as ResNet50, Inception-ResNet-v2, AlexNet, Vgg19, etc. A dataset of 10,040 samples has been used in which the count of SARS-CoV-2, pneumonia and normal images are 2143, 3674, and 4223 respectively. The model designed by fusion of neural network and HOG transform had an accuracy of 98.81% and a sensitivity of 98.65%. © 2022 IEEE.

Mediating effect of perceived social support between mindfulness level and mental health of nursing undergraduates during the epidemic of novel coronavirus pneumonia

Objective: To study students' mental health status during epidemic of novel coronavirus pneumonia, and to explore the influence of mindfulness level and perceived social support on mental health. Methods: A total of 240 undergraduate nursing students were investigated with Depression Anxiety and Stress Scale, Five Facets Mindfulness Questionnaire, Perceived Social Support Scale and Pittsburgh Sleep Quality Index. SAS and Mplus were applied to describe the data and conduct mediation analysis. Results: About 18.8% of the participants were depressed and 27.9% were anxious, 13.3% were stressed, and 31.7% had problems of sleeping. The mindfulness level could directly affect sleep disorder (beta = - 0.242, P < 0.001), stress (beta = - 0.397, P < 0.001), anxiety (beta = - 0.350, P < 0.001)and depression(beta = - 0.484, P < 0.001), and could also indirectly affect sleep disorder (beta = - 0.171, P < 0.001), stress (beta = - 0.105, P = 0.029), anxiety (beta = - 0.102, P = 0.034) and depression (beta = - 0.180, P < 0.001) via the mediation role of perceived social support with the mediating effects accounted for 41.40%, 20.92%, 22.52% and 37.19%, respectively. Conclusions: Mindfulness level can improve the mental health of nursing undergraduates through direct action and understanding the intermediary role of social support. Nursing educators can consider integrating mindfulness decompression training into daily teaching, and give nursing undergraduates enough psychological and emotional support and encouragement to improve their mental health level.