Transfer Learning Model in Deep Neural Network for COVID-19 Prediction from CT Images

Deep learning models are often used to process radi-ological images automatically and can accurately train networks' weights on appropriate datasets. One of the significant benefits of the network is that it is possible to use the weight of a pre-trained network for other applications by fine-tuning the current weight. The primary purpose of this work is to employ a pre-trained deep neural framework known as transfer learning to detect and diagnose COVID-19 in CT images automatically. This paper uses a popular deep neural model, ResNet152, as a neural transfer approach. The presented framework uses the weight obtained from the ImageNet dataset, fine-tuned by the dataset used in the work. The effectiveness of the suggested COVID-19 prediction system is evaluated experimentally and compared with DenseNet, another transfer learning model. The recommended ResNet152 transfer learning model exhibits improved performance and has a 99% accuracy when analogized with the DenseNet201 transfer learning model. © 2022 IEEE.

Forecasting of COVID-19 Pandemic Using ARIMA and Fb-Prophet Models: UK Case Study

This study aims to provide insights into predicting future cases of COVID-19 infection and rates of virus transmission in the UK by critically analyzing and visualizing historical COVID-19 data, so that healthcare providers can prepare ahead of time. In order to achieve this goal, the study invested in the existing studies and selected ARIMA and Fb-Prophet time series models as the methods to predict confirmed and death cases in the following year. In a comparison of both models using values of their evaluation metrics, root-mean-square error, mean absolute error and mean absolute percentage error show that ARIMA performs better than Fb-Prophet. The study also discusses the reasons for the dramatic spike in mortality and the large drop in deaths shown in the results, contributing to the literature on health analytics and COVID-19 by validating the results of related studies. Copyright © 2023 by SCITEPRESS - Science and Technology Publications, Lda. Under CC license (CC BY-NC-ND 4.0)

Deep learning framework for rapid and accurate respiratory COVID-19 prediction using chest X-ray images.

COVID-19 is a contagious disease that affects the human respiratory system. Infected individuals may develop serious illnesses, and complications may result in death. Using medical images to detect COVID-19 from essentially identical thoracic anomalies is challenging because it is time-consuming, laborious, and prone to human error. This study proposes an end-to-end deep-learning framework based on deep feature concatenation and a Multi-head Self-attention network. Feature concatenation involves fine-tuning the pre-trained backbone models of DenseNet, VGG-16, and InceptionV3, which are trained on a large-scale ImageNet, whereas a Multi-head Self-attention network is adopted for performance gain. End-to-end training and evaluation procedures are conducted using the COVID-19_Radiography_Dataset for binary and multi-classification scenarios. The proposed model achieved overall accuracies (96.33% and 98.67%) and F1_scores (92.68% and 98.67%) for multi and binary classification scenarios, respectively. In addition, this study highlights the difference in accuracy (98.0% vs. 96.33%) and F_1 score (97.34% vs. 95.10%) when compared with feature concatenation against the highest individual model performance. Furthermore, a virtual representation of the saliency maps of the employed attention mechanism focusing on the abnormal regions is presented using explainable artificial intelligence (XAI) technology. The proposed framework provided better COVID-19 prediction results outperforming other recent deep learning models using the same dataset.

Transformer-based Deep Learning for COVID-19 Prediction Based on Climate Variables in Indonesia

Recent research on the effect of climate variables on coronavirus (COVID-19) transmission has emerged. Climate change can potentially cause new viral outbreaks, illness, and death. This study contributes to COVID-19 disease prevention efforts. This study makes two contributions: (1) we investigated the impact of climate variables on the number of COVID-19 cases in 34 Indonesian provinces, and (2) we developed a transformer-based deep learning model for time series forecasting for the number of positive COVID-19 cases the following day based on climate variables in 34 Indonesian provinces. We obtained data from March 15, 2020, to July 22, 2021, on the number of positive COVID-19 cases and climate change variables (wind, temperature, humidity) in Indonesia. To examine the effect of climate change on the number of positive COVID-19 cases, we employed 15 scenarios for training. The experiment results of the proposed model show that the combination of wind speed and humidity has a weakly positive correlation with positive COVID-19 incidence;however, the temperature has a considerably negative association with positive COVID-19 incidences. Compared to the other testing scenarios, the transformer-based deep learning model produced the lowest MAE of 175.96 and the lowest RMSE of 375.81. This study demonstrates that the transformer model works well in several provinces, such as Sumatra, Java, Papua, Bali, West Nusa Tenggara, East Nusa Tenggara, East Kalimantan, and Sulawesi, but not in Central Kalimantan, West Sulawesi, South Sulawesi, and North Sulawesi. © IJASEIT is licensed under a Creative Commons Attribution-Share Alike 4.0 International License.

RECENT DEVELOPMENTS IN SOFT COMPUTING BASED TECHNIQUES FOR FEATURE SELECTION AND DISEASE CLASSIFICATION

Computational prediction of diseases is vital in medical research that contributes to computer-aided diagnostics and helps doctors and medical practitioners in critical decision-making for various diseases such as bacterial and viral kinds of disease, including COVID-19 of the current pandemic situation. Feature selection techniques function as a preprocessing phase for classification and prediction algorithms. For disease prediction, these features may be the patient's clinical profiles or genomic features such as gene expression profiles from microarray and read counts from RNA-Seq. The performance of a classifier depends primarily on the selected features. In addition, genomic features are too large in numbers, resulting in the curse of dimensionality problem. In the last few years, several feature selection algorithms have been developed to overcome the existing problems to get rid of eliminating chronic diseases, such as various cancers, Zika virus, Ebola virus, and the COVID-19 pandemic. In this review article, we systematically associate soft computing-based approaches for feature selection and disease prediction by applying three data types: patients' clinical profiles, microarray gene expression profiles, and RNA-Seq sample profiles. According to related work, when the discussion took place, the percentage of medical data types highlighted through pictorial representation and the respective ratio of percentages mentioned were 52%, 27%, 9% and 12% for clinical symptoms, gene expression, MRI-Image and other data types such as signal or text-based utilized, respectively. We also highlight the significant challenges and future directions in this research domain © 2023, Suranaree Journal of Science and Technology.All Rights Reserved.

Model for movement of individuals in society after the corona pandemic using deep learning algorithms

The health crisis that attributed to the rapid spread of the COVID-19 has impacted the globe negatively in terms of economy, education and transport and led to the global lockdown. The risk of the COVID-19 infection has been increased due to a lack of successful cure for the disease. Thus, social distancing is considered as the most appropriate precaution measureto control the viral spread throughout the world. Social distancing means that physical contact between individuals can be prevented to reduce the viral transmission effectively. The purpose of this work is to provide a deep learning model capable of predicting the movement of people in the pandemic to take precautions and control the COVID-19 infection. This model is based on twoLSTMand GRU algorithms. The results show that the GRU is better than LSTM in terms of prediction error rate and duration. © 2023 Author(s).

An Agent-Based Model for Localized COVID-19 Transmission Dynamics and Intervention Impacts

Throughout the COVID-19 pandemic, disease-modeling has guided government health officials in choosing appropriate interventions. However, most current models simulate disease spread on a more generalized scale, lacking specificity for localities such as towns or counties, leading to one-size-fits-all policies being instituted on the country or state-wide-level. However, localities differ in many social determinants of health, which impact disease dynamics therefore necessitating models tailored to individual locations. This research aims to answer this question: What local factors affect COVID-19 outbreak severity and intervention effectiveness? To do this, a novel agent-based disease model was created using NetLogo to simulate contextualized COVID-19 disease dynamics at the local level. Model inputs include population demographic composition, area size, vaccination ratio, interventions (mask, test-and-isolate, or lockdown), and compliance rate. Agents representing the simulated local population are assigned specified traits, and become "susceptible”, "exposed”, "infected”, "recovered”, "quarantined”, or "dead” as they interact with other agents. The model was validated using data from state and local health agencies for Westchester County, NY (84.2% accuracy). A sensitivity analysis demonstrated that a higher elderly population, a lower young population, a lower vaccination rate, and weaker interventions were all factors that increased outbreak severity. A comparison of selective localities representing metric axes of high/low age and high/low vaccination was conducted for four different U.S. counties and showed that 1) any intervention would dramatically reduce locality variations and 2) interventions have higher impact in higher risk localities. This model enables local officials to better focus limited resources when making health related decisions, and a website (www.localcovidmodel.org) has been created for model access. © 2022, Avestia Publishing. All rights reserved.

Covid Wave Prediction using SARIMA Machine Learning Algorithm

A speedy and accurate diagnosis of COVID-19 is made possible by effective SARS-Co V -2 screening, which can also lessen the strain on health care systems. There have been built prediction models that assess the likelihood of infection by combining a number of parameters. These are intended to help medical professionals worldwide prioritize patients, particularly when there are few healthcare resources available. From a dataset of 51,831 tested people, out of which 4,769 were confirmed to have COVID-19 virus, a machine learning method was developed and trained. Records of the following week with 47,401 tested people, of which 3,624 were tested positive was also considered. Our method accurately predicted the COVID-19 test results using eight binary characteristics, including gender, age 60, known contact with an infected person, and the presence of five early clinical signs. © 2023 IEEE.

Cellular Automata in Covid-19 prediction.

At the end of 2019 a new coronavirus emerged, turning into a world pandemic. The new coronavirus is called COVID-19. Different countries handled the pandemic differently and our main focus in this article is on Poland. For better counteracting and managing the situation a model for predicting the dynamics of the pandemic is needed. In this article we present a model for simulating future infections taking into account various preventive measures and locations in Poland. We based the model on a two-dimensional cellular automata, with spatial dependencies between regions, different population and size of simulated regions.

A Staging Prediction Model for COVID-19 Pandemic under Strong Public Health Interventions

With the extensive implementation of the strong public health interventions in China, many models proposed to predict COVID-19 epidemic are no longer applicable to the current epidemic development. In this paper, a COVID-19 prediction method is proposed based on a staging SEITR model with consideration of strong public health interventions in China. The method simulates preventive and control measures such as mass nucleic acid testing and quarantine of close contacts by introducing the role of Isolates and the transformation of Exposed to Isolated. The experimental evaluation uses real epidemic data from six cities including Nanjing, Yangzhou, and etc. The accuracy of prediction for total number of infections reaches 95.8% with the data of the first 15 days of the outbreak. In addition, the prediction accuracy of the end of the pandemic is 95.07%. These show that the proposed method can effectively predict the course of the epidemic and it is practical for relevant departments to formulate reasonable prevention and control measures. © 2022 IEEE.

Multi-weight susceptible-infected model for predicting COVID-19 in China.

The mutant strains of COVID-19 caused a global explosion of infections, including many cities of China. In 2020, a hybrid AI model was proposed by Zheng et al., which accurately predicted the epidemic in Wuhan. As the main part of the hybrid AI model, ISI method makes two important assumptions to avoid over-fitting. However, the assumptions cannot be effectively applied to new mutant strains. In this paper, a more general method, named the multi-weight susceptible-infected model (MSI) is proposed to predict COVID-19 in Chinese Mainland. First, a Gaussian pre-processing method is proposed to solve the problem of data fluctuation based on the quantity consistency of cumulative infection number and the trend consistency of daily infection number. Then, we improve the model from two aspects: changing the grouped multi-parameter strategy to the multi-weight strategy, and removing the restriction of weight distribution of viral infectivity. Experiments on the outbreaks in many places in China from the end of 2021 to May 2022 show that, in China, an individual infected by Delta or Omicron strains of SARS-CoV-2 can infect others within 3-4 days after he/she got infected. Especially, the proposed method effectively predicts the trend of the epidemics in Xi'an, Tianjin, Henan, and Shanghai from December 2021 to May 2022.

Learning effective embedding for automated COVID-19 prediction from chest X-ray images.

The pandemic that the SARS-CoV-2 originated in 2019 is continuing to cause serious havoc on the global population's health, economy, and livelihood. A critical way to suppress and restrain this pandemic is the early detection of COVID-19, which will help to control the virus. Chest X-rays are one of the more straightforward ways to detect the COVID-19 virus compared to the standard methods like CT scans and RT-PCR diagnosis, which are very complex, expensive, and take much time. Our research on various papers shows that the currently researchers are actively working for an efficient Deep Learning model to produce an unbiased detection of COVID-19 through chest X-ray images. In this work, we propose a novel convolution neural network model based on supervised classification that simultaneously computes identification and verification loss. We adopt a transfer learning approach using pretrained models trained on imagenet dataset such as Alex Net and VGG16 as back-bone models and use data augmentation techniques to solve class imbalance and boost the classifier's performance. Finally, our proposed classifier architecture model ensures unbiased and high accuracy results, outperforming existing deep learning models for COVID-19 detection from chest X-ray images producing State of the Art performance. It shows strong and robust performance and proves to be easily deployable and scalable, therefore increasing the efficiency of analyzing chest X-ray images with high accuracy in detection of Coronavirus.

COVID-19 Outbreak Prediction by Using Machine Learning Algorithms

COVID-19 is a contagious disease and its several variants put under stress in all walks of life and economy as well. Early diagnosis of the virus is a crucial task to prevent the spread of the virus as it is a threat to life in the whole world. However, with the advancement of technology, the Internet of Things (IoT) and social IoT (SIoT), the versatile data produced by smart devices helped a lot in overcoming this lethal disease. Data mining is a technique that could be used for extracting useful information from massive data. In this study, we used five supervised ML strategies for creating a model to analyze and forecast the existence of COVID-19 using the Kaggle dataset” COVID-19 Symptoms and Presence.” RapidMiner Studio ML software was used to apply the Decision Tree (DT), Random Forest (RF), K-Nearest Neighbors (K-NNs) and Naive Bayes (NB), Integrated Decision Tree (ID3) algorithms. To develop the model, the performance of each model was tested using 10-fold cross-validation and compared to major accuracy measures, Cohan's kappa statistics, properly or mistakenly categorized cases and root means square error. The results demonstrate that DT outperforms other methods, with an accuracy of 98.42% and a root mean square error of 0.11. In the future, a devised model will be highly recommendable and supportive for early prediction/diagnosis of disease by providing different data sets. © 2023 Tech Science Press. All rights reserved.

A Hybrid Model for Coronavirus Disease 2019 Forecasting Based on Ensemble Empirical Mode Decomposition and Deep Learning.

BACKGROUND: The novel coronavirus pneumonia that began to spread in 2019 is still raging and has placed a burden on medical systems and governments in various countries. For policymaking and medical resource decisions, a good prediction model is necessary to monitor and evaluate the trends of the epidemic. We used a long short-term memory (LSTM) model and the improved hybrid model based on ensemble empirical mode decomposition (EEMD) to predict COVID-19 trends; Methods: The data were collected from the Harvard Dataverse. Epidemic data from 21 January 2020 to 25 April 2021 for California, the most severely affected state in the United States, were used to develop an LSTM model and an EEMD-LSTM hybrid model, which is an LSTM model combined with ensemble empirical mode decomposition. In this study, ninety percent of the data were adopted to fit the models as a training set, while the subsequent 10% were used to test the prediction effect of the models. The mean absolute percentage error, mean absolute error, and root mean square error were used to evaluate the prediction performances of the models; Results: The results indicated that the number of confirmed cases in California was increasing as of 25 April 2021, with no obvious evidence of a sharp decline. On 25 April 2021, the LSTM model predicted 3666418 confirmed cases, whereas the EEMD-LSTM predicted 3681150. The mean absolute percentage errors for the LSTM and EEMD-LSTM models were 0.0151 and 0.0051, respectively. The mean absolute and root mean square errors were 5.58 × 104 and 5.63 × 104 for the LSTM model and 1.9 × 104 and 2.43 × 104 for the EEMD-LSTM model, respectively; Conclusions: The results showed the advantage of an EEMD-LSTM model over a single LSTM model, and the established EEMD-LSTM model may be suitable for monitoring and evaluating the epidemic situation and providing quantitative analysis evidence for epidemic prevention and control.

An efficient lung disease classification from X-ray images using hybrid Mask-RCNN and BiDLSTM

Lung diseases mainly affect the inner lining of the lungs causing complications in breathing, airway obstruction, and exhalation. Identifying lung diseases such as COVID-19, pneumonia, fibrosis, and tuberculosis at the earlier stage is a great challenge due to the availability of insufficient laboratory kits and image modalities. The rapid progression of the lung disease can be easily identified via Chest X-rays and this serves as a major boon for the terminally ill patients admitted to Intensive Care Units (ICU). To enhance the decision-making capability of the clinicians, a novel lung disease prediction framework is proposed using a hybrid bidirectional Long-Short-Term-Memory (BiDLSTM)-Mask Region-Based Convolutional Neural Network (Mask-RCNN) model. The Crystal algorithm is used to optimize the scalability and convergence issues in the Mask-RCNN model by hyperparameter tuning. The long-range dependencies for lung disease prediction are done using the BiDLSTM architecture which is connected to the fully connected layer of the Mask RCNN model. The efficiency of the proposed methodology is evaluated using three publicly accessible lung disease datasets namely the COVID-19 radiography dataset, Tuberculosis (TB) Chest X-ray Database, and National Institute of Health Chest X-ray Dataset which consists of the images of infected lung disease patients. The efficiency of the proposed technique is evaluated using different performance metrics such as Accuracy, Precision, Recall, F-measure, Specificity, confusion matrix, and sensitivity. The high accuracy obtained when comparing the proposed methodology with conventional techniques shows its efficiency of it in improving lung disease diagnosis. Copyright © 2022 Elsevier Ltd

COVID-19 prediction using machine learning based on the patient's vital signs: A case for Saudi Arabia

The world faces a rapidly spreading of COVID19 globally, for several countries around the world mitigating the consequences and spread of the pandemic remains a top priority. Researchers work to find a smart and rational solution to limit the spread of this epidemic and its repercussions. The goal of this research is to produce an early and accurate COVID-19 prediction, as well as a comparative analysis of the performance of several machine learning (ML) models based on patient vital signs, dataset balancing, and feature selection. The cases dataset was provided by King Fahad Hospital University in Al-Khobar, Saudi Arabia. The current study used the WEKA 3.8.5 and Python programming language (SKLEARN) to decide which method generated the highest level of accuracy while using fewer features. Random forest with grid search (RF with grid search), Artificial Neural Networks (ANN), Support Vector Machine (SVM), Random Forest (RF), J48, XGB Classifier, and XGB Classifier with grid search were the techniques that were compared. The highest level of accuracy obtained with seven features was 84% achieved with the RF using grid search technique, while ANN, SVM, RF, J48, XGB Classifier, and XGB Classifier with grid search obtained 82.85%, 79%, 82.93%, 82.5%,82.21%, and 83.4% accuracy, respectively. © 2022 IEEE.

Al-Biruni Earth Radius Optimization for COVID-19 Forecasting

Several instances of pneumonia with no clear etiology were recorded in Wuhan, China, on December 31, 2019. The world health organization (WHO) called it COVID-19 that stands for "Coronavirus Disease 2019," which is the second version of the previously known severe acute respiratory syndrome (SARS) Coronavirus and identified in short as (SARSCoV-2). There have been regular restrictions to avoid the infection spread in all countries, including Saudi Arabia. The prediction of new cases of infections is crucial for authorities to get ready for early handling of the virus spread. Methodology: Analysis and forecasting of epidemic patterns in new SARSCoV-2 positive patients are presented in this research using metaheuristic optimization and long short-term memory (LSTM). The optimization method employed for optimizing the parameters of LSTM is Al-Biruni Earth Radius (BER) algorithm. Results: To evaluate the effectiveness of the proposed methodology, a dataset is collected based on the recorded cases in Saudi Arabia between March 7th, 2020 and July 13th, 2022. In addition, six regression models were included in the conducted experiments to show the effectiveness and superiority of the proposed approach. The achieved results show that the proposed approach could reduce the mean square error (MSE), mean absolute error (MAE), and R2 by 5.92%, 3.66%, and 39.44%, respectively, when compared with the six base models. On the other hand, a statistical analysis is performed to measure the significance of the proposed approach. Conclusions: The achieved results confirm the effectiveness, superiority, and significance of the proposed approach in predicting the infection cases of COVID-19. © 2023 CRL Publishing. All rights reserved.

Analysis and Comparison for Innovative Prediction Technique of COVID-19 using Support Vector Machine over Neural Network algorithm with Improved Accuracy

Aim: The primary purpose of this study is to improve the accuracy of COVID-19 prediction and evaluation. Materials and Methods: This project is based on data extracted from Kaggle's website, which is separated into two categories. According to the total sample size estimated by clinical.com, each group comprises 20 samples (N=20) for both the Support Vector Machine (SVM) and Neural Network methods, by keeping 0.05 alpha error-threshold, 95% confidence interval, enrolment ratio at 0:1, and G power at 80%. In MatLab 2021a, this entails training the data and verifying 20 validations ranging from 5 to 24. Results: The SPSS Software and Independent sample T-test are used to contrast the accuracy, sensitivity, and precision rates. The Neural Network has 94.55 percent accuracy (P<0.001), 93.11 percent sensitivity (P<0.001), and 95.31 percent precision (P<0.001), compared to 91.25 percent accuracy (P<0.001), 93.93 percent sensitivity (P<0.001), and 86.11 percent precision (P<0.001) for the SVM. Conclusion: The Neural Network algorithm outperforms the SVM approach in terms of results.

Analysis and Comparison for Innovative Prediction of COVID-19 using Logistic Regression Algorithm over the Decision Tree Algorithm with Improved Accuracy

Aim: The major goal of this research is to increase the accuracy of innovation prediction and examine the COVID-19. Materials and Method: This study relied on data collected from Kaggle's website and samples are divided into two groups, GROUP 1 (N=20) for Logistic regression and GROUP 2 (N=20) for Decision tree in accordance with the total sample size calculated using clinical.com by keeping 0.05 alpha error-threshold, 95% confidence interval, enrolment ratio as 0:1, and G power at 80%. It involves the software implementation program in MatLab 2021a validating with 20 validations. Results: The accuracy, sensitivity, and precision rates are compared using SPSS software and an Independent sample T-Test. In comparison the Logistic regression 95.98% accuracy with P=0.001, (p<0.05), 94.65% sensitivity (with P=0.001, (p<0.05) and 96.20% precision with P=0.001, (p<0.05) produces a superior outcome than the Decision tree 93.91% accuracy with P=0.001, (p<0.05), 94.33% sensitivity with P=0.001, (p<0.05), 92.00% precision with P=0.001, (p<0.05). Conclusion: The Logistic regression algorithm produces better results compared to the Decision tree.

Analysis and Comparison for Innovative Prediction Technique of COVID-19 using Decision Tree Algorithm over the Support Vector Machine Algorithm with Improved Accuracy

Aim: The primary goal of this research is to increase the accuracy of COVID-19 prediction and its analysis. Materials and Method: This study relied on data collected from Kaggle's website and samples are divided into two groups, GROUP 1 (N=20) for the Decision tree and GROUP 2 (N=20) for the Support Vector Machine (SVM) in accordance with the total sample size calculated using clinical.com by keeping alpha error-threshold value 0.05, 95% confidence interval, enrolment ratio as 0:1, and G power at 80%. It involves the software implementation program in MatLab 2021a validating with 20 validations. Results: The accuracy, sensitivity, and precision rates are compared using Statistical Package for the Social Sciences (SPSS) software and an Independent sample T-Test. In comparison to the two, the Decision tree 93.91% accuracy, 94.33% sensitivity, 92% precision with P=0.001 ((p<0.05) produces a superior outcome to the Support Vector Machine 91.25% accuracy, 93.93% sensitivity, 86.11% precision (P<0.001)). Conclusion: The decision tree algorithm produces better results compared to the Support Vector Machine.