COVID-19 Dataset Clustering based on K-Means and EM Algorithms

In this paper, a COVID-19 dataset is analyzed using a combination of K-Means and Expectation-Maximization (EM) algorithms to cluster the data. The purpose of this method is to gain insight into and interpret the various components of the data. The study focuses on tracking the evolution of confirmed, death, and recovered cases from March to October 2020, using a two-dimensional dataset approach. K-Means is used to group the data into three categories: "Confirmed-Recovered”, "Confirmed-Death”, and "Recovered-Death”, and each category is modeled using a bivariate Gaussian density. The optimal value for k, which represents the number of groups, is determined using the Elbow method. The results indicate that the clusters generated by K-Means provide limited information, whereas the EM algorithm reveals the correlation between "Confirmed-Recovered”, "Confirmed-Death”, and "Recovered-Death”. The advantages of using the EM algorithm include stability in computation and improved clustering through the Gaussian Mixture Model (GMM). © 2023,International Journal of Advanced Computer Science and Applications. All Rights Reserved.

Development of Website for COVID-19 Detection on Chest X-Ray Images

Control of the spread of COVID-19 must be encouraged, even though this is a new normal era. Rapid screening for COVID-19 detection must be carried out to control the spread of COVID-19. This research develops a website for COVID-19 detection based on chest X-Ray images and compares the CNN-BiLSTM model. This study divides X-ray images of the chest into three categories: COVID-19, Normal, and Viral Pneumonia. When compared to other models, the Resnet50-BiLSTM model produces the highest accuracy. The accuracy of the Resnet50-BiLSTM model was 98.51%. Then, in order, the following models were used: Resnet50, VGG19-BiLSTM, VGG19, AlexNet-BiLSTM, and AlexNet. The comparison of Precision, Recall, and F1-Measure findings also demonstrate that Resnet50-BiLSTM has the highest score when compared to other approaches. The website was also developed using the Flask framework for automatic COVID-19 detection. © 2022 IEEE.

Image Processing and Deep Neural Networks for Face Mask Detection

The proper use of a mask is crucial for lowering COVID 19 and transmission. According to the research, transmission is completely decreased when the mask is used appropriately. Factors like sunlight and several items can affect how appropriatel y applied face masks are classified and detected. Cotton masks, sponge masks, scarves, and other options greatly lessen the effect of personal protection in such circumstances. The research suggests a novel modified formula for classifying masks into three categories—a proper mask, a no mask, and an erroneous mask—using deep learning and machine learning. First, we provide a brand-new face mask classification and detection algorithm that combines deep learning, the viola Jones method, and Efficient-Yolov3 Wearing a mask, not wearing a mask, or wearing the wrong mask are the three options. On the dataset with or without mask pictures, the suggested system outperforms and is more accurate when compared to existing techniques. The results of experiments and analysis are also based on the classification knowledge set. In comparison to the present methodology's categorization accuracy of 84%, the anticipated formula boosted it to 97%. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Research on the Spread and Influencing Factors of the COVID-19 Variant in the UK

This paper first establishes a clustering algorithm to cluster the data in the attachment, dividing the data into three categories, and determines the infection rate and transmission time of each virus. On this basis, the cities in four regions are selected for analysis, and a multiple regression fitting model is established to determine their corresponding transmission in different stages and regions. In order to better analyze, this paper takes Aberdeen City as an example. According to the data corresponding to the original three viruses, a grey correlation model is established to analyze the data. Finally, according to the number of confirmed cases of Omicron virus transmission, this paper estimates the duration of Omicron virus transmission by establishing a neural network prediction model. © 2022 IEEE.

Online Trusts, How Media Shaping Student Trust Towards Vaccination News

Indonesian government carries out vaccination program as part of the COVID-19 response. This study aimed to determine student responses to the news of COVID-19 vaccination through online media in August 2021. The media plays an essential role in understanding the importance of vaccines for the community. COVID-19 cases in Indonesia;simultaneously, the government pushed for a vaccination program. This study uses a stimulus-organism-response approach, the SOR approach, that looks at the individual's (organism) perception of the message (stimulus) received. The SOR theory looks at the individual's perception of policies through online media;the elements in SOR analysis look at the stimulus through student responses. The study uses descriptive quantitative methods to describe student responses through purposive sampling. The finding of this study show three categories of aspects;appropriate sources, covering both sides, and verification steps. According to this study, students rate vaccination news differently in three categories: first, aspects of appropriate types of media with assessment (32%), second, cover both sides with assessment (33%), and third, verification with assessment (35%) as a result of news broadcast on online news, pupils can get vaccination programs developed by the government to combat COVID-19. This acceptability is shown by a change in the attitude of the respondents, from being confident to being more confident about carrying out the Covid-19 vaccination. This study classifies the role of online media in shaping students' impressions of government policies and initiatives during the COVID-19 time. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Examination of electric field distribution in a laboratory-built electrospinning device

In 2019, Covid-19 pandemic appeared and affected the health of humanity. The virus can spread between people in various ways, but mostly from infected liquid particles. A fundamental method of defense is the use of a face mask in public, however, the efficiency of wearing a mask can be influenced by a number of factors. Most of the masks have a classification based on its filtration efficiency. There are three categories, the FFP1, FFP2 and FFP3, where FFP means filtering facepiece'. All the 3 types can filter particles down to the size of 0.6 micrometer, but the FFP1's efficiency is 80%, the FFP2's 94%, while the FFP3's reaches 99%. In the USA they use the same categories, but call it KN80, KN95 and KN100. The problem is that the commonly used textile masks do not have a classification, which means that these cannot protect the wearer from being infected. The aim of our research is to improve the filter efficiency of masks, and we have described in this paper the first phase, the construction and testing of the laboratory model. Two cases were considered, with one needle and five needle solutions. During the experiments, the electrode distance was varied. When using more needles, the nanofibers covered a larger area, but there was a greater roughness between the fibers generated. Considering that electrospinning starts after a critical electric field strength, some calculations were performed in COMSOL model. © 2022 IEEE.

Visualization of the Social Atmosphere Using Comments on News Sites

When an emergency such as an infectious disease or natural disaster occurs, a negative atmosphere will usually spread throughout society—increasing people’s dissatisfaction and anxiety. Because of this, it is rather difficult to thoroughly investigate the actual situation. However, people can post sentimental comments on news sites, allowing for their attitudes either for or against the topics to be better observed. This study extracts the positive, negative, and neutral comments by using sentiment analysis. Then, the social atmosphere is visualized by calculating the approval rating of the comments. This methodology is demonstrated in articles regarding COVID-19. The large volume of comments about two topics, Go To campaigns and PCR tests, were analyzed by using ML-Ask to classify the comments into three categories: negative, positive, and neutral. The results indicate that the social atmosphere about the Go To campaigns tended to be negative. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Classification network of Chest X-ray images based on residual network in the context of COVID-19

As COVID-19 spreads across the globe, more cases are being confirmed around the world, making it imperative that we take a better approach to fighting the outbreak. To stop the spread of the disease and better screen for cases, we need a more sensitive and efficient test that can classify images of lung abnormalities in patients. In this paper, residual network is used to classify the collected chest radiographs. Feature extraction and classification were carried out on the original chest X-ray images, which were divided into the following three categories: normal lung, bacterial pneumonia and virus pneumonia. This can quickly rule out normal and routine infections, screen out large numbers of cases, and reduce the burden on health care workers who need to further examine cases. At the same time, our results are also very good, with an accuracy of 94%, which has practical classification significance. © 2022 IEEE.

COVID-19 Detection in Chest X-Rays Using Inception Resnet-v2

Screening for COVID-19 is a vital part of the triage process. The current COVID-19 gold standard, the RT-PCR test, is regarded to be costly and time consuming. Artificial intelligence can be utilized to identify COVID-19 in radiographic pictures to overcome the limitations of existing testing methods. This study describes how the Inception-ResNet-v2 architecture was used to categorize pictures into three categories using transfer learning (Normal, Viral Pneumonia, and COVID-19,). Despite only running for 29 epochs, the resultant model had an accuracy of 0.966. This demonstrates the utility of AI in the diagnosis of illnesses. © 2021 IEEE.

Post COVID-19 Macrotrends in the Pedagogical Practice of Professors

The temporary lockdown of Educational Institutions provoked scenarios of emergency against the Global Crisis of the COVID-19. Which global macrotrends can be applied in the context of a Post COVID-19 pedagogical practices? Three categories were identified: I) Global macrotrends related to the Education Sector;II) The Post COVID-19 pedagogical practice, as a role assumed by the professor involved in the different education spaces (academicist, technological, cultural interpretative, socio-critical and socio-formative);and III) Student Outcomes (SOs), the accreditation model. Global macrotrends were selected to be applied in the post COVID-19 pedagogical practice that contribute to accomplishment of SOs and were consequently classified into three areas: i) Crosscutting Macrotrend (public awareness), ii) the Macrotrend of Post COVID-19 pedagogical practices (Disrupting Education: the assessment of progress, harnessing innovation, multiple senses, co-creation, instant entrepreneurship, the User Experience business-focused model approach for education, and gamification), and iii) the Macrotrend of Support (Networking & Technology). © 2020 for this paper by its authors.

Towards Understanding the Psychological Effects of the COVID-19 Pandemic on the Indian Population

This article explains the preliminary results of the analysis of a public survey carried out in India, assessing the psychological effects on people during the second wave of the COVID-19 pandemic. A survey was designed to categorize the population on the basis of various socio-economic demographics and respondents were then asked to fill out the DASS-21 questionnaire to get their levels of severity of anxiety, depression and stress. The dataset obtained was then further analyzed using various classification machine learning models with the level of severity as the target variable and respondent's attributes as independent variables. A Multinomial Logistic Regression was found to give the best results with an AUC score of 0.94 and was thus, used to predict the severity levels of these three categories, to find various insights from this publicly-sourced dataset. Additionally, the significance of the various socio-demographic attributes asked in the survey was analyzed in order to identify key drivers of mental ailments among the general Indian population. Further, a brief description of segmenting the population using K-Means clustering is provided which attempts to identify population groups that belong to similar socio-economic demographics and suffer from similar mental health issues during the pandemic. Thus, high-risk or high-severity groups can be identified and then could be targeted by the government to provide them relief schemes. This paper applies machine learning on a public dataset to explore the various facets of COVID-induced problems in the Indian Society. © 2021 IEEE.

Using Deep Learning Algorithms in Chest X-ray Image COVID-19 Diagnosis

We are experiencing heavy COVID-19 outbroke globally since January 2020. In Taiwan, because its low infection rate (< 0.01%), there was not enough evidence for diagnosis through medical imaging. At present, chest X-ray is widely used in lung infection diagnoses. This study uses deep learning methods to assist doctors in classifying COVID-19 disease from chest X-ray images. After pre-processing, the images were put into the VGG16 model to automaticallyclassify into three categories to assist the radiologist in the treatment of the disease. The results show that the classification accuracy was 78%. Detail analyses disclosed that this accuracy can be improved by rectifying the unbalanced images problem. In addition, choosing proper image pre-processing algorithms has a high tendency to generate better results. © 2021 ECBIOS 2021. All rights reserved.

Assessing Level of Laboratory Instruction to Engineering Technology Students

This study investigates what amount of assistance (text and hyperlinks) optimize student understanding of instructions in an engineering technology lab. The target course is a 300-level electrical instrumentation class taken technology students. Historically, lab assignments have been lengthy documents that include supporting material and detailed step-by-step instructions. Based on questions received by the instructor, it is obvious that students are not coming to lab having read over the instructions and other supporting material. One possible reason for lack of student pre-reading is the length of the documents. By modifying the presentation of the lab assignments into 3 distinct variations, the authors attempted to determine which variation the students preferred to work through. The authors revised approximately two-thirds of the lab assignments, dividing the assignments into three categories of detail: • High level instruction with extensive hyperlinks for details. • Medium level instruction with a combination of text and hyperlinks for details. • Low level instruction with detailed instructions all in one document (existing format). Students were surveyed on their understanding of the assignments and lab report grades were compared to instruction level. The study was truncated because of the COVID-19 pandemic, so only partial results are presented. These partial results indicate that students prefer a “medium” level of instruction: an assignment that contains all the steps, but with details in hyper-linked documents. © American Society for Engineering Education, 2021