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.

COVID-19 Data Clustering Using K-means and Fuzzy c-means Algorithm

Corona Virus Disease 2019 (COVID-19) is a contagious disease caused by severe acute respiratory symptoms. It has been declared a global pandemic since 2019 by the World Health Organization. Countries are in an authoritarian state of preventing and controlling this pandemic, and the USA is the central hub. The COVID-19 virus has also shown variance. As an outcome of the genetic recombination of genes that arise from coronavirus, their short life span results in mutations that promote new strains. However, the number of individuals who passed their lives is still counted. Additionally, it is crucial to analyze the spread of the virus before it is deferred in the lungs. In this research, the effort has been taken to predict the proliferation of the virus through various chest radiography images by data clustering. In this study, two clustering algorithms, i.e., the K-means algorithm and the Fuzzy c-means algorithm, have been used better to analyze the spread of the virus in the lungs. These algorithms are further being compared and evaluated for the precise result of both models. This study helps to recognize the most suitable clustering model for the COVID-19 prediction and spread of the virus in the lung. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2023.

Research on the Construction Scheme of Wuhan Emergency Logistics System Under the Background of Public Health Emergencies

In order to improve the emergency logistics support capacity of Wuhan city and build a transportation power pilot, based on the background of public health emergencies and on the basis of comprehensively summarizing the experience, practices and prominent problems of emergency logistics support work of COVID-19 in Wuhan City, this paper studies from the aspects of development foundation, overall thinking and main tasks, Put forward the systematic framework and specific implementation path of emergency logistics system construction of "building three guarantee systems of reserve facilities, transportation capacity and command and dispatching, and building an information platform”. At the same time, in the construction of emergency logistics command and coordination information platform, K-means clustering method is adopted to achieve scientific matching and efficient connection between emergency materials transit stations and demand points. For other cities It is of practical significance to improve the regional emergency logistics system. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Contactless non-invasive method to identify abnormal tongue area using K-mean and problem identification in COVID-19 scenario

Due to the spread of COVID-19 all around the world, there is a need of automatic system for primary tongue ulcer cancerous cell detection since everyone do not go to hospital due to the panic and fear of virus spread. These diseases if avoided may spread soon. So, in such a situation, there is global need of improvement in disease sensing through remote devices using non-invasive methods. Automatic tongue analysis supports the examiner to identify the problem which can be finally verified using invasive methods. In automated tongue analysis image quality, segmentation of the affected region plays an important role for disease identification. This paper proposes mobile-based image sensing and sending the image to the examiner, if examiner finds an issue in the image, the examiner may guide the user to go for further treatment. For segmentation of abnormal area, K-mean clustering is used by varying its parameters.Copyright © 2022 Inderscience Enterprises Ltd.

Machine Learning Approach: Consumer Buying Behavior Analysis

The rise of multiple company competitors during the COVID-19 outbreak resulted in fierce competition among competing firms for new clients and the retention of current ones. As a result of the foregoing, exceptional customer service is required, regardless of the size of the organization. Furthermore, any company's ability to know each of its customers' desires will provide it an advantage when it comes to providing specialized customer care and establishing customized marketing plans for them. The term 'Consumer Buying Behavior Analysis' refers to a comprehensive assessment of the company's ideal clients/customers. In this project, we're utilizing the K-Means Algorithm to divide clients into two groups: 'Highly Active Customers' and 'Least Active Customers.' Then, utilizing the Apriori Algorithm, we use Association Rule Mining to recommend the best goods to clients based on their purchasing history and associations. We take one step further and use Logistic Regression to validate our Clustering operation by doing Binary Classification with our clusters as the label, resulting in accuracy and an F1 score of 91%. © 2022 IEEE.

COVID-19 and Arabic Twitter: How can Arab world governments and Public Health Organizations learn from social media?

In March 2020, the World Health Organization announced the COVID-19 outbreak as a pandemic. Most previous social media related research has been on English tweets and COVID-19. In this study, we collect approximately 1 million Arabic tweets from the Twitter streaming API related to COVID-19. Focussing on outcomes that we believe will be useful for Public Health Organizations, we analyse them in three different ways: identifying the topics discussed during the period, detecting rumours, and predicting the source of the tweets. We use the k-means algorithm for the first goal with k=5. The topics discussed can be grouped as follows: COVID-19 statistics, prayers for God, COVID-19 locations, advise and education for prevention, and advertising. We sample 2000 tweets and label them manually for false information, correct information, and unrelated. Then, we apply three different machine learning algorithms, Logistic Regression, Support Vector Classification, and Naïve Bayes with two sets of features, word frequency approach and word embeddings. We find that Machine Learning classifiers are able to correctly identify the rumour related tweets with 84% accuracy. We also try to predict the source of the rumour related tweets depending on our previous model which is about classifying tweets into five categories: academic, media, government, health professional, and public. Around (60%) of the rumour related tweets are classified as written by health professionals and academics. © ACL 2020.All right reserved.

New Approach of Covid-19 Prevention by Implemented Combination of Decision Support System Algorithm

Indonesia and Malaysia from 2020 to 2021 were exposed to COVID-19 pandemic. Both countries implemented a policy of restricting entry areas based on almost the same criteria, In Indonesia namely as PPKM which applying some level of exposure to those infected with covid-19. The determination of this level was all based on the growth in numbers exposed to covid-19, but on pandemic cases, the number of people who do not suffer from COVID-19 disease but have the same symptoms as the symptoms of COVID-19 also need to be considered as the pandemic agent to their environment. We named it as Precaution Covid-19 Pandemic (PCP) Level. The current level of the COVID-19 pandemic has not been fully determined by this idea. So, the idea of this research is to determine the pre-pandemic or precaution level of covid-19 in an area interfere by surrounding area. PCP level was not based on the growth of those infected with the covid-19 disease, but influenced by the number of patients whose have the symptoms similar to the dominant symptoms of the covid-19. The PCP Level determination can be used for precaution policy and support the previous Level Pandemic Methods. To accomplish this idea, three algorithms are used, they are K-Mean algorithm as a pattern clustering and the AHP algorithm as a level determination of the Covid-19 pandemic, While the relationship of candidate symptom pairs to Covid-19 transmission is carried out using the Naïve Bayes algorithm. The results of this study show that the combination of the three proposed algorithms provides and using data symptoms closely to dominant covid-19 symptoms can give an alternative for precaution level of covid-19 pandemic. The model for determining Covid-19 transmission based on four candidate symptoms has 89% precision and 85% accuracy. © 2022 IEEE.

Voting Classification Approach for Covid-19 Prediction with K-mean and PCA

Coronavirus Disease 2019 is occurred as a challenging disease among the scientist worldwide. The disease is developed at an extensive level. Thus, the disease must be detected, reported, isolated, diagnosed and cured at initial phase for mitigating its growth rate. This research paper is conducted on the basisof predicting covid-19 ML algorithms. The methods of predicting this disease consist of diverse stages inwhich data is added as input, pre-processed, attributes are extracted and data is classified. This research work focuses on gathering the authentic dataset which get pre-processed for the classification. In the phase of feature extraction,PCA and k-mean algorithms are applied. The votingclassification method is applied in this work in which GNB, BNB, RF and Support Vector Machine algorithms are integrated. Python is executed to implement the introduced method. Diverse metrics are considered to analyze the outcomes. Using supervised machine learning, we create this model. The branch of ML focuses on implementing intelligent models so that various complicated issues can be tackled. The introduced method offers higher accuracy, precisionand recall in comparison with other classifiers. © 2022 IEEE.

Intrinsic atmospheric circulation patterns associated with high PM2.5 concentration days in South Korea during the cold season.

Based on observation data and a novel K-mean clustering method, we investigated whether intrinsic atmospheric circulation patterns are related with the occurrence of high particulate matter (PM) concentration days (diameters less than or equal to 2.5 µm (PM2.5)), in Seoul, South Korea, during the cold season (December to March). A simple composite map shows that weak horizontal and vertical ventilation over the Korean Peninsula can cause high PM2.5 concentration (High_PM2.5) days. Also, atmospheric circulations are quite different between one day of High_PM2.5 and periods longer than two days. We also found that two intrinsic atmospheric circulation patterns in Asia, which were obtained by adopting K-mean clustering to the daily 850 hPa geopotential height anomalies for 2005-2020, were associated with High_PM2.5 days. These results indicate that High_PM2.5 days in Seoul, South Korea, occur as a result of intrinsic atmospheric circulation patterns, therefore, they are unavoidable unless the anthropogenic emission sources over the Korean Peninsula, East Asia, or both are reduced. In addition, these two intrinsic atmospheric circulation patterns are more prominent for periods longer than two days while there are no favorable intrinsic atmospheric circulation patterns to induce one day of High_PM2.5, which indicates that a single day of High_PM2.5 tends to occur by a stochastic atmospheric circulation rather than the intrinsic atmospheric circulation patterns.

Linguistic Severity Range Fixation of Vital Signs Using Unsupervised Approach in RHM

Automatic abnormality detection in human health status based on the variation in the vital health parameters is a continuous research thrust area. After Covid pandemic the importance of checking the variation in the health status become a part of our regular activities. With the help of artificial intelligence, today many research works have been proposed in abnormality detection. The proposed work is personalized abnormality detection technique based on adaptive unsupervised mechanism and tries to map the health status with the incoming health stream data. The proposed adaptive density-based K-Means fixes the severity range of each vital health parameter of a person and achieved an accuracy rate in fixing the severity range with 91.3% during training and 87.8 % testing respectively. © 2022 IEEE.

The Labour Market Consequences of the COVID-19 Pandemic in the European Union Countries: Selected Issues

The massive lockdowns of economies as a result of the COVID-19 pandemic are unprecedented on a global scale. Such actions have unfortunately had their negative consequences for the labour market. This is expressed, among other things, through the deterioration of labour market indicators. The aim of the presented study is to assess the size of differences in changes in selected labour market indicators across EU countries over the period 2019–2020 and to assess the heterogeneity of EU countries due to the responses of these indicators. Given that EU countries have used isolation strategies and job support with different intensities, and that their labour markets are characterised by quite different elasticities, the response of these markets is characterised by considerable heterogeneity. In the analysis, we consider labour market characteristics such as economic activity, employment level, share of part-time workers, share of temporary workers or share of self-employed. The k-means algorithm is applied as a research tool. In turn, we use the silhouette index to assess the quality of the obtained divisions. The results obtained indicate a diverse response of national labour markets to the restrictions introduced as a result of COVID-19. The largest negative changes we observe in the group includes PIIGS countries (Portugal, Ireland, Italy, Greece and Spain) and Bulgaria, Czech Republic, and Slovakia. The countries in the group in which Luxembourg, Hungary and the Netherlands are classified have done relatively well, where apart from a reduction in the number of temporary workers, changes in other characteristics are positive. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Adoption of Mobile Payment Systems during COVID-19 in India

The digitalization process has been increasing rapidly worldwide today. There is various technologies developed and continue developing tremendously in the world, such as mobile payment systems. Such type of emerging technologies has made a very significant transformation in people lives everywhere. Technologies such as mobile devices facilitate people to finish their work in less time and effort required usually. That is why, these innovations and advancements in technologies led people to be more inclined toward their use. Furthermore, in the current scenario, mobile payments have become an integral part of the daily lives of people due to the impact of the novel coronavirus (COVID-19) disease on society. The presence of mobile payment systems can be considered for years, but the use of mobile payment systems has increased in the current situation of the COVID-19 pandemic, which is the core basis of this research paper. However, the user's acceptance of mobile payment systems is still low due to some pros and cons of this technology which are examined in this paper by applying a hybrid machine learning model. We collected primary data through Google Form from the institute in the Meerut region and other sources from India with a total of 222 respondents. In this study, the data is processed and applied on to the machine learning models. Data analysis and findings of the research showed that the proposed ensemble of classifier algorithms outperforms other exiting machine models in terms of accuracy, precision, recall and F1-score. The research and findings will help the organizations have a clear and correct analysis of the scenario of the adoption of mobile payments in India and also design better mobile payment systems to curb the situation like the COVID-19 pandemic.

Clustering Analysis in the Student Academic Activities on COVID-19 Pandemic in Mexico

The pandemic caused by the COVID-19 disease has affected all aspects of the life of the people in every region of the world. The academic activities at universities in Mexico have been particularly disturbed by two years of confinement;all activities were migrated to an online modality where improvised actions and prolonged isolation have implied a significant threat to the educational institutions. Amid this pandemic, some opportunities to use Artificial Intelligence tools for understanding the associated phenomena have been raised. In this sense, we use the K-means algorithm, a well-known unsupervised machine learning technique, to analyze the data obtained from questionaries applied to students in a Mexican university to understand their perception of how the confinement and online academic activities have affected their lives and their learning. Results indicate that the K-means algorithm has better results when the number of groups is bigger, leading to a lower error in the model. Also, the analysis helps to make evident that the lack of adequate computing equipment, internet connectivity, and suitable study spaces impact the quality of the education that students receive, causing other problems, including communication troubles with teachers and classmates, unproductive classes, and even accentuate psychological issues such as anxiety and depression. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Contactless non-invasive method to identify abnormal tongue area using K-mean and problem identification in COVID-19 scenario

Due to the spread of COVID-19 all around the world, there is a need of automatic system for primary tongue ulcer cancerous cell detection since everyone do not go to hospital due to the panic and fear of virus spread. These diseases if avoided may spread soon. So, in such a situation, there is global need of improvement in disease sensing through remote devices using non-invasive methods. Automatic tongue analysis supports the examiner to identify the problem which can be finally verified using invasive methods. In automated tongue analysis image quality, segmentation of the affected region plays an important role for disease identification. This paper proposes mobile-based image sensing and sending the image to the examiner, if examiner finds an issue in the image, the examiner may guide the user to go for further treatment. For segmentation of abnormal area, K-mean clustering is used by varying its parameters.

Vaccination against COVID-19 in Europe: A Typology Based on Cluster Analysis.

This study aims to identify a general typology for the EU27, and subsequently in Romania, regarding the hesitation, acceptance and refusal of vaccination against COVID-19. The analysis we propose below is based on the information contained in Eurobarometer 94.3, the data of which were collected at the beginning of most of the national vaccination campaigns in Europe. Based on the attitudes and opinions expressed by the respondents of the European states (EU27), we constructed with the help of the cluster k-means (SPSS) statistical analysis a typology with four categories on the subject of vaccination against COVID-19. Our study proposes a matrix with five items/scenarios on a scale from total agreement to total disagreement. We chose a typology with four attitudinal types (clusters). We subsequently compared the results of the general European analysis with the cluster typology resulting from the same Eurobarometer, the same set of questions, only for the case of Romania, to see if this analysis sheds a specific light on the fact that Romania had a very low vaccination rate compared to other EU Member States.

An Improved K-means Clustering Algorithm Towards an Efficient Data-Driven Modeling

K-means algorithm is one of the well-known unsupervised machine learning algorithms. The algorithm typically finds out distinct non-overlapping clusters in which each point is assigned to a group. The minimum squared distance technique distributes each point to the nearest clusters or subgroups. One of the K-means algorithm’s main concerns is to find out the initial optimal centroids of clusters. It is the most challenging task to determine the optimum position of the initial clusters’ centroids at the very first iteration. This paper proposes an approach to find the optimal initial centroids efficiently to reduce the number of iterations and execution time. To analyze the effectiveness of our proposed method, we have utilized different real-world datasets to conduct experiments. We have first analyzed COVID-19 and patient datasets to show our proposed method’s efficiency. A synthetic dataset of 10M instances with 8 dimensions is also used to estimate the performance of the proposed algorithm. Experimental results show that our proposed method outperforms traditional kmeans++ and random centroids initialization methods regarding the computation time and the number of iterations. © 2022, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

Analyzing and Predicting the Deaths and Cases of Covid-19 in Different Countries Using Fuzzy K Means Algorithm and Exponential Method

Covid-19 disease, since it first appearance in the Chinese city of Wuhan, has led to many infections and deaths, not only in China, but also in most countries of the world. The most prominent symptoms of this disease are headache, fever, strong cough, and perhaps the strongest of it is difficulty breathing in the event that the virus reaches the lung, which leads to death in many cases if the patient's condition is late, or he does not have strong immunity. The purpose of this study is to use Fuzzy k Means (FKM) and predictive algorithm representing in Simple Exponential Smoothing Method (SESM) to evaluate confirmed cases and deaths in different countries. This study's findings show that the FKM approach can evaluate data and produce reliable results, in addition to the SESM can give good prediction. According to this study, machine learning technologies and predicting methodologies achieved good results when used together. © 2021 IEEE.

Clustering and Visualizing of Chest X-ray Images for Covid-19 Detection

Corona pandemic showed how artificial intelligence has become a part of our daily lives and is breaking into all fields at a high rate and in different ways. Relying on the conventional techniques to test patients such as RT -PCR has two major drawbacks;a long time to get results and a lack of test kits. Therefore, data mining with machine learning techniques has been suggested to investigate covid-19. In this work, chest x-ray image-based covid-19 detection approach is proposed. Three types of x-ray images Covid-19, Pneumonia, and Normal, are used in two frameworks: image visualization and image segmentation. First, the x-ray samples are visualized using histograms to analyze the pixel-value distributions. The visualization approach helps covid-19 specialists to discover the intensity level of infection by examining the corresponding histograms. Second, a segmentation approach is developed with a k-mean algorithm to provide extra image tuning for infected areas. Three different centroids are used to provide different tuning granularity levels. The suggested frameworks give a fast and reliable methodology to help physicians to decide whether there is a virus or not in the x-ray sample. This is done statistically by histograms and visually by monitoring the segmented infected areas. © 2021 IEEE.

An Analysis on the Weibo Topic Detection Based on K-means Algorithm

Sina Weibo, as a platform for netizens to express their opinions, generates a large amount of public opinion data and constantly generates new topics. How to detect new and hot topics on Weibo is a meaningful studied issue. Document Clustering is a widely studied problem in Text Categorization. K-means is one of the most famous unsupervised learning algorithms, partitions a given dataset into disjoint clusters following a simple and easy way. But the traditional K-means algorithm assigns initial centroids randomly, which cannot guarantee to choose the maximum dissimilar documents as the centroids for the clusters. A modified K-means algorithm is proposed, which uses Jaccard distance measure for assigning the most dissimilar k documents as centroids, and uses Word2vec as the Chinese text vectorization model. The experimental results demonstrate that the proposed K-means algorithm improves the clustering performance, and is able to detect new and hot topics based on Weibo COVID-19 data. © 2022 IEEE.

Predicting Creditworthiness of Smartphone Users in Indonesia during the COVID-19 pandemic using Machine Learning

In this research work, we attempted to predict the creditworthiness of smartphone users in Indonesia during the COVID-19 pandemic using machine learning. Principal Component Analysis (PCA) and Kmeans algorithms are used for the prediction of creditworthiness with the used a dataset of 1050 respondents consisting of twelve questions to smartphone users in Indonesia during the COVID-19 pandemic. The four different classification algorithms (Logistic Regression, Support Vector Machine, Decision Tree, and Naive Bayes) were tested to classify the creditworthiness of smartphone users in Indonesia. The tests carried out included testing for accuracy, precision, recall, F1-score, and Area Under Curve Receiver Operating Characteristics (AUCROC) assesment. Logistic Regression algorithm shows the perfect performances whereas Naïve Bayes (NB) shows the least. The results of this research also provide new knowledge about the influential and non-influential variables based on the twelve questions conducted to the respondents of smartphone users in Indonesia during the COVID-19 pandemic. © 2022 IEEE.