RESUMO
A paradigm shift can be expected in the education sector, especially after the COVID-19 pandemic. E-learning systems are being adopted by all the stakeholders as physical meetings are not feasible. Different online learning attributes, such as video conferencing tools, coding platforms, online learning frameworks, digital books, and online videos, are available, which are enhancing the traditional learning methodology. Now, the main challenge for the educationists is to identify how these attributes are utilized by the learners. In this article, we have represented any online class as a social network where students are connected through learning platforms. We have mined the network based on several network measuring parameters to recognize the maneuvering pattern of these digital resources or attributes by the students. We have also proposed a community detection method that would form different groups among the students based on their comfortable learning patterns. As a case study, we have scrutinized the accessing patterns of different digital learning resources by some particular students. The experimental results show the significant relationship between the digital resource accessing patterns of the students with their immediate performance in the test. The satisfactory inquisitive results of our approach would definitely inspire the researchers of interdisciplinary areas to probe further in this domain.
RESUMO
Background and Aim: Kawasaki Disease remains an enigma to the world to this day since first described by Dr. Tomisaku Kawasaki in 1967. In the last half a century there has been wide-spread global research elaborating the clinical aspects and patho-genesis of this disease entity. Multisystem Inflammatory Syndrome post Covid (MISC) is a relatively new disease which was described in literature in mid 2020. The striking resemblance as well as differences in spectrum of cardiac involvement of both the conditions has been elaborated in this study from a tertiary care centre in Eastern India. Method(s): The study was conducted over a period of 3 years from June 2018 to June 2021. Fiftyone patients with Kawasaki disease (including atypical and incomplete cases) and sixty children diag-nosed with MISC were included in the study. Echocardiography details were noted by a single observer. Data regarding the patient particulars, clinical aspects, lab parameters, imaging details and treatment particulars were collected and analysed. Patients were followed up for a minimum period of six months to one year. Result(s): In the Kawasaki group(51), infants(20) presented with multiple (and larger) aneurysms. Older children (gt;5 years) had more of single coronary involvement, (mostly LAD) and also had more atypical presentation(18) associated with infections like Dengue, Staphylococcal infection, Scrub Typhus. There were 4 cases of Kawasaki shock syndrome, all below 5 years. In the MISC group (60), there was also multiple coronary involvement in infants (11). But LV dysfunction was more common in older children and adolesecents (20), of whom 18 (90%) presented with severe dysfunction (LVEFlt;35%). Those with coronary involve-ment had normal function and those with dysfunction had no coronary involvement. Mild to moderate aneurysmal dilation of coronaries was found in children one to five years of age. No giant aneurysm was found in MISC. Overall, LMCA with LAD was the commonest pattern of involvement in both the conditions. Conclusion(s): KD and MISC had similar pattern of coronary involve-ment, but absence of giant aneurysm and significantly severe dys-function in older children in MISC indicates a likely different pathogenesis for myocardial involvement in MISC.
RESUMO
The recent outbreak of coronavirus has impacted the whole world. The infectious respiratory disease has killed millions of people all over the world. The process of detecting the disease through RT-PCR and other tests is very time-consuming, and testing kits are not widely available. Chest x-rays and chest CT scans are also very effective techniques for diagnosing respiratory diseases. This paper proposes a DeepAttentiveNet, a deep-based architecture that applies the pre-trained CNN-based architecture DenseNet to extract the spatial features from the images. This is followed by the attention mechanism, which focuses on the information-rich region on the images, thus enhancing the overall classification process. The performance of our model is analyzed on the COVID 19 Radiography dataset, which contains 21,000 x-ray images corresponding to different respiratory infections like COVID 19, lung opacity, and viral pneumonia. Hence our model can categorize the x-rays with a 97.1% F1 score and 97.5% accuracy. We have also compared our architecture with other popular CNN-based models and baseline methods to demonstrate the superior performance of the model. © 2022 IEEE.
RESUMO
COVID-19 disease is an infectious disease caused by the Corona viruses. It is transmitted due to human-human interaction in human population. In the proposed work, we propose and study an epidemic model of COVID-19 disease by considering hospital facility to prevent the disease spreading. The aim of the study is to observe the effects of better hospital facility to control the disease. Explicit formula for the metric, basic reproduction number (R-0) is obtained. At last, we simulate the proposed model and result is analyzed to show the impact of hospital facility in controlling the spreading of COVID-19.
RESUMO
The COVID-19 pandemic has rendered social distancing and use of face masks as an absolute necessity today. Coming out of the epidemic, we're going to see this as the new normal and therefore most workplaces will require an identification system to permit employees based on the compliance of protocols. To ensure minimal contact and security, automatic entrance systems need to be employed in workplaces and institutions. For the implementation of such systems, we have investigated the performance of three object detection algorithms, namely SSD MobileNet V2, YOLO v3 and YOLO v4 in the context of real-time face mask detection. We conducted training and testing of these algorithms on our dataset focusing on various type of masks in the Indian community. We have exhibited in this paper that YOLOv4 transcends both YOLO v3 and SSD MobileNet V2 in sensitivity and precision and thus has a major use case in building AI identification systems. © 2021, Springer Nature Singapore Pte Ltd.