Advanced search in Research products
Research products
arrow_drop_down
Searching FieldsTerms
Any field
arrow_drop_down
includes
arrow_drop_down
Include:
The following results are related to COVID-19. Are you interested to view more results? Visit OpenAIRE - Explore.
1,135 Research products, page 1 of 114

  • COVID-19
  • Publications
  • 2018-2022
  • Conference object
  • WHO Global literature on coronavirus disease
  • Repositorio Digital Universidad Don Bosco
  • COVID-19

10
arrow_drop_down
Relevance
arrow_drop_down
  • Open Access
    Authors: 
    Saksham Tewari; Utkarsh Agrawal; Siddharth Verma; Sunil Kumar; S. Jeevaraj;
    Publisher: IEEE

    Coronavirus is a virus of RNA-type that can infect both humans and animal and causes a wide variety of respiratory infections. In humans, it also causes pneumonia. Since coronavirus has been declared a pandemic, Reverse Transcription Polymerase Chain Reaction (RT-PCR) has been the standard method for detection but is a time consuming operation and due to sudden surge in demand it has a high cost. In this study, coronavirus was detected from X-ray scans of chest using a deep learning model consisting of fuzzy image enhancement, offline data augmentation, image segmentation and classification through Convolutional Neural Network. For training and classification, an ensembeled model consisting of the features of VGG-16, ResNet-50 and MobileNetV2 was built and optimized with bayesian optimization. The proposed model achieved an overall accuracy of 96.34%. The precision, recall and F1-Score for COVID-19 class was 100%, 96% and 98% respectively.

  • Publication . Article . Preprint . Conference object . 2020 . Embargo End Date: 01 Jan 2020
    Open Access
    Authors: 
    Victoria Rayskin;
    Publisher: arXiv

    Utilization of multiple trajectories of a dynamical system model provides us with several benefits in approximation of time series. For short term predictions a high accuracy can be achieved via switches to new trajectory at any time. Different long term trends (tendency to different stationary points) of the phase portrait characterize various scenarios of the process realization influenced by externalities. The dynamical system's phase portrait analysis helps to see if the equations properly describe the reality. We also extend the dynamical systems approach (discussed in \cite{R5}) to the dynamical systems with external control. We illustrate these ideas with the help of new examples of the rental properties HOMES.mil platform data. We also compare the qualitative properties of HOMES.mil and Wikipedia.org platforms' phase portraits and the corresponding differences of the two platforms' users. In our last example with COVID-19 data we discuss the high accuracy of the short term prediction of confirmed infection cases, recovery cases and death cases in various countries. Comment: arXiv admin note: substantial text overlap with arXiv:1912.06939

  • Publication . Article . Preprint . Conference object . 2020
    Open Access
    Authors: 
    Lei Liu; Wentao Lei; Xiang Wan; Li Liu; Yongfang Luo; Cheng Feng;
    Publisher: IEEE

    Ultrasound (US) is a non-invasive yet effective medical diagnostic imaging technique for the COVID-19 global pandemic. However, due to complex feature behaviors and expensive annotations of US images, it is difficult to apply Artificial Intelligence (AI) assisting approaches for lung's multi-symptom (multi-label) classification. To overcome these difficulties, we propose a novel semi-supervised Two-Stream Active Learning (TSAL) method to model complicated features and reduce labeling costs in an iterative procedure. The core component of TSAL is the multi-label learning mechanism, in which label correlations information is used to design multi-label margin (MLM) strategy and confidence validation for automatically selecting informative samples and confident labels. On this basis, a multi-symptom multi-label (MSML) classification network is proposed to learn discriminative features of lung symptoms, and a human-machine interaction is exploited to confirm the final annotations that are used to fine-tune MSML with progressively labeled data. Moreover, a novel lung US dataset named COVID19-LUSMS is built, currently containing 71 clinical patients with 6,836 images sampled from 678 videos. Experimental evaluations show that TSAL using only 20% data can achieve superior performance to the baseline and the state-of-the-art. Qualitatively, visualization of both attention map and sample distribution confirms the good consistency with the clinic knowledge.

  • Open Access English
    Authors: 
    Francesco Benedetto; Gaetano Giunta; Chiara Losquadro; Luca Pallotta;
    Publisher: Institute of Electrical and Electronics Engineers Inc.
    Country: Italy

    Entropy concept is related to uncertainty and predictability of random time series. The estimated trend of such a parameter can provide useful information and possibly predict future behavior of a number of non-stationary noisy signals. The goal of this paper consists of analyzing the Covid19 signal made by the number of registered infections in Italy during the first four months of the pandemic epidemy (March-June 2020). Finally, some considerations are drawn after matching historical dates of some Covid-19 related Acts made by the Italian Government (i.e., lockdown and unlockdowns). Based on the obtained results, we could conjecture that the provisions have inducted people to a common behavior concerning local mobility during the lockdowns and the progressive unlockdowns of the quarantine period in Italy.

  • Open Access English
    Authors: 
    Jie Zhao; Maria Alejandra Rodriguez; Rajkumar Buyya;

    COVID-19 global pandemic is an unprecedented health crisis. Since the outbreak, many researchers around the world have produced an extensive collection of literatures. For the research community and the general public to digest, it is crucial to analyse the text and provide insights in a timely manner, which requires a considerable amount of computational power. Clouding computing has been widely adopted in academia and industry in recent years. In particular, hybrid cloud is gaining popularity since its two-fold benefits: utilising existing resource to save cost and using additional cloud service providers to gain assess to extra computing resources on demand. In this paper, we developed a system utilising the Aneka PaaS middleware with parallel processing and multi-cloud capability to accelerate the ETL and article categorising process using machine learning technology on a hybrid cloud. The result is then persisted for further referencing, searching and visualising. Our performance evaluation shows that the system can help with reducing processing time and achieving linear scalability. Beyond COVID-19, the application might be used directly in broader scholarly article indexing and analysing.

  • Publication . Conference object . 2020
    Open Access
    Authors: 
    Marc Dupuis; Karen Renaud;
    Publisher: ACM

    The COVID-19 pandemic has caused major disruptions across the world; universities have not been exempt. This has included disruptions in not only the delivery of traditional in-person classes, but also research. In this paper, we detail the efforts undertaken to modify the research protocols originally developed for a longitudinal experiment design with two in-person components to it. In particular, we address the challenges and benefits of this conversion, including issues related to compensation, scheduling, technical issues, and attempts to replace the in-person component of the original design.

  • Open Access
    Authors: 
    Abdulrahman Radaideh; Fikri Dweiri; Mohammad S. Obaidat;
    Publisher: IEEE

    At present, each and every part of the globe are facing a COVID crisis, which is affecting an individual physically, mentally and on the other hand, it is affecting the nation economically. Also, the unemployment scenario will be at its peak in the upcoming years as reported by UNGA. To combat this scenario, all the country are working on fostering their fiber network and so the sectors apart from the manufacturing, will tend to work from their home and contribute to the economy. But there are many problems arising to implement this culture practically, since it affects the mindsets of the people who have to endure this transformation within a very short span. Hence, in this research work, it has been decided to focus on this current issue for which the usage of certain apps in UAE such as zoom, totok, botim for internet calling have been identified since this is the only way of connectivity with the outside world. To perform this analysis, the tweets from December to July have been collected by converting the image to text and analyzed using two algorithms such as Naive Bayes Classifier (NBC) and Recurrent Neural Networks (RNN). The sentimental analysis found that 630 tweets were positive and people in UAE feels secured, satisfied and internet calling is very useful for them in the prospect of work, education, etc. Only 48 tweets has negative impact because people feel little bit harder in sudden change of culture with in short period of time and 155 tweets has impact that both positive and negative were view and said to be natural. The study found that NB (84%) is more accurate, user friendly and takes less time than RNN (79%) to perform the analysis. Finally, the sentimental analysis reveals that people in UAE were accepting the new culture of internet calling and it is useful for them in the prospect of work and education.

  • Publication . Conference object . 2020
    Open Access
    Authors: 
    Maha A. Alanezi; Nabil M. Hewahi;
    Publisher: IEEE

    The aim of this paper is to investigate the impact of social distance on people during COVID-19 pandemic using twitter sentiment analysis through a comparison between the k-means clustering and Mini-Batch k-means clustering approaches. To find the most common frequent words, two datasets have been investigated (WHO and Bahrain ministry of health datasets) to be as data preparation and exploration. Another two datasets (English and Arabic datasets) are used in the clustering of k-means. In this paper, a comparison between k-means and Mini-Batch k-means is performed to find a pattern. The word frequency shows that there are several words related to the pandemic. The sentiment analysis result show that in USA, Australia, Nigeria, Canada, and England, most tweets are neutral. However, the majority of tweets are positive tweets from both Italy and India. In addition, the k-means cluster in the English dataset reveals several cluster trends where COVID-19 pandemic procedures are addressed in cluster 1, and health workers are encouraged in cluster 3.

  • Open Access
    Authors: 
    Luxin Zhang; Wei Qi Yan;
    Publisher: IEEE

    The use of deep learning methods for virus identification from digital images is a timely research topic. Given an electron microscopy image, virus recognition utilizing deep learning approaches is critical at present, because virus identification by human experts is relatively slow and time-consuming. In this project, our objective is to develop deep learning methods for automatic virus identification from digital images, there are four viral species taken into consideration, namely, SARS, MERS, HIV, and COVID-19. In this work, we firstly examine virus morphological characteristics and propose a novel loss function which aims at virus identification from the given electron micrographs. We take into account of attention mechanism for virus locating and classification from digital images. In order to generate the most reliable estimate of bounding boxes and classification for a virus as visual object, we train and test five deep learning models: R-CNN, Fast R-CNN, Faster R-CNN, YOLO, and SSD, based on our dataset of virus electron microscopy. Additionally, we explicate the evaluation approaches. The conclusion reveals SSD and Faster R-CNN outperform in the virus identification.

  • Open Access
    Authors: 
    Xinggan Peng; Huiping Zhuang; Guang-Bin Huang; Haizhou Li; Zhiping Lin;
    Publisher: IEEE

    Due to the outbreak of the novel coronavirus (or known as COVID-19), people are advised to wear masks when they stay outdoors in many countries. This could result in difficulty for some public safety surveillance systems involving face detection or tracking. Therefore, the development of face detection and tracking algorithms for people wearing face masks is particularly important. In this paper, a real-time tracking algorithm for people with or without face masks is proposed. This algorithm is trained on public face datasets with faces without masks. Although the training does not involve face images of people wearing face masks, we show that the proposed algorithm is robust as it is able to perform well in face tracking for people wearing face masks. We also discuss the possible scenarios where the algorithm could lose track of the target when experimenting in tracking masked faces. This can motivate future research in this area.