Prediction of the COVID-19 infectivity and the sustainable impact on public health under deep learning algorithm.

The aim is to explore the development trend of COVID-19 (Corona Virus Disease 2019) and predict the infectivity of 2019-nCoV (2019 Novel Coronavirus), as well as its impact on public health. First, the existing data are analyzed through data pre-processing to extract useful feature factors. Then, the LSTM (Long-Short Term Memory) prediction model in the deep learning algorithm is used to predict the epidemic situation in Hubei Province, outside Hubei nationwide, and the whole country, respectively. Meanwhile, the impact of intervention time changes on the epidemic situation is compared. The results show that the prediction results are almost consistent with the actual values. Specifically, Hubei Province abolishes quarantine restrictions after the Spring Festival holiday, and the first COVID-19 peak is reached in late February, while the second COVID-19 peak has been reached in early March. Finally, the cumulative number of diagnoses reaches 85,000 cases, with an increase of 15,000 cases compared with the nationwide cases outside Hubei under the continuous implementation of prevention and control measures. Under the prediction of the proposed LSTM model, if the nationwide implementation of prevention and control interventions is postponed by 5 days, the epidemic will peak in early March, and the cumulative number of diagnoses will be about 200,000; and if the intervention measures are implemented five days earlier, the epidemic will peak in mid-February, with a cumulative number of diagnoses of approximately 40,000. Meanwhile, the proposed LSTM model predicts the RMSE values of the epidemic situation in Hubei Province, outside Hubei nationwide, and the whole country as 34.63, 75.42, and 50.27, respectively. Under model comparison analysis, the prediction error of the proposed LSTM model is small and has better applicability over similar algorithms. The results show that the LSTM model is effective and has high performance in infectious disease prediction, and the research results can provide scientific and effective references for subsequent related research.

Leveraging Deep Learning for Designing Healthcare Analytics Heuristic for Diagnostics.

Healthcare Informatics is a phenomenon being talked about from the early 21st century in the era in which we are living. With evolution of new computing technologies huge amount of data in healthcare is produced opening several research areas. Managing the massiveness of this data is required while extracting knowledge for decision making is the main concern of today. For this task researchers are doing explorations in big data analytics, deep learning (advanced form of machine learning known as deep neural nets), predictive analytics and various other algorithms to bring innovation in healthcare. Through all these innovations happening it is not wrong to establish that disease prediction with anticipation of its cure is no longer unrealistic. First, Dengue Fever (DF) and then Covid-19 likewise are new outbreak in infectious lethal diseases and diagnosing at all stages is crucial to decrease mortality rate. In case of Diabetes, clinicians and experts are finding challenging the timely diagnosis and analyzing the chances of developing underlying diseases. In this paper, Louvain Mani-Hierarchical Fold Learning healthcare analytics, a hybrid deep learning technique is proposed for medical diagnostics and is tested and validated using real-time dataset of 104 instances of patients with dengue fever made available by Holy Family Hospital, Pakistan and 810 instances found for infectious diseases including prognosis of; Covid-19, SARS, ARDS, Pneumocystis, Streptococcus, Chlamydophila, Klebsiella, Legionella, Lipoid, etc. on GitHub. Louvain Mani-Hierarchical Fold Learning healthcare analytics showed maximum 0.952 correlations between two clusters with Spearman when applied on 240 instances extracted from comorbidities diagnostic data model derived from 15696 endocrine records of multiple visits of 100 patients identified by a unique ID. Accuracy for induced rules is evaluated by Laplace (Fig. 8) as 0.727, 0.701 and 0.203 for 41, 18 and 24 rules, respectively. Endocrine diagnostic data is made available by Shifa International Hospital, Islamabad, Pakistan. Our results show that in future this algorithm may be tested for diagnostics on healthcare big data.

GW- CNNDC: Gradient weighted CNN model for diagnosing COVID-19 using radiography X-ray images.

COVID-19 is one of the dangerous viruses that cause death if the patient doesn't identify it in the early stages. Firstly, this virus is identified in China, Wuhan city. This virus spreads very fast compared with other viruses. Many tests are there for detecting this virus, and also side effects may find while testing this disease. Corona-virus tests are now rare; there are restricted COVID-19 testing units and they can't be made quickly enough, causing alarm. Thus, we want to depend on other determination measures. There are three distinct sorts of COVID-19 testing systems: RTPCR, CT, and CXR. There are certain limitations to RTPCR, which is the most time-consuming technique, and CT-scan results in exposure to radiation which may cause further diseases. So, to overcome these limitations, the CXR technique emits comparatively less radiation, and the patient need not be close to the medical staff. COVID-19 detection from CXR images has been tested using a diversity of pre-trained deep-learning algorithms, with the best methods being fine-tuned to maximize detection accuracy. In this work, the model called GW-CNNDC is presented. The Lung Radiography pictures are portioned utilizing the Enhanced CNN model, deployed with RESNET-50 Architecture with an image size of 255*255 pixels. Afterward, the Gradient Weighted model is applied, which shows the specific separation regardless of whether the individual is impacted by Covid-19 affected area. This framework can perform twofold class assignments with exactness and accuracy, precision, recall, F1-score, and Loss value, and the model turns out proficiently for huge datasets with less measure of time.

Detection of COVID-19 from X-RAY Images using Artificial Intelligence (AI)

Corona virus (COVID-19) is an infectious disease. Several millions of people worldwide suffer from this disease. The signs of progress of virus infection are more severe damage to lungs and causes to organs failure, death. X-rays are readily available and an excellent alternative method to x-ray imaging in the diagnosis of covid-19 and very crucial role play to recognizing this disease and recovery with hospitalization. The goal of this revise is to expand a reliable method for detecting COVID-19 from digital chest X-ray pictures using well-before deep-learning algorithms while optimizing detection performance. To train and verify, the transfer learning (TL) approach was utilized with the aid of picture extension. Current would be hugely beneficial in this pandemic because the illness severity and the necessity for prevention methods are at odds with available resources. © 2022 IEEE.

Development of Contactless Individual Management System with Covid - 19 Preemptive Measures

The significance of social distancing and non-contact habits was emphasized by the Covid-19 pandemic. Even after the pandemic, everyone should adhere to the same hygiene procedures. Preventive measures must be implemented prior to the individuals' return. These include identifying people's presence and monitoring their health. This research focuses on using sensor fusion and deep learning technology to create a contactless individual management system. It is capable of carrying out the attendance routine without compromising the precautionary measures. Persons can be identified without removing the mask by employing random Quick Response (QR) code recognition. While recognising the QR, the system will double-verify the individual by identifying the Media Access Control (MAC) address of the user's mobile Bluetooth at the backend. Then the system employs a pre-trained deep learning model to detect masks. The Convolutional Neural Network (CNN) technique produces a deep learning model that can distinguish between Faces with and without masks. The system then monitors the body temperature with an Infrared (IR) temperature sensor followed by dispensing sanitizer. The response for the entire procedure will be updated in both the person's mobile application and the Management Authority. © 2022 IEEE.

Deep learning offering resilience from trending cyber-attacks, a review

During the Covid-19 pandemic world has witnessed the rise of cyber-attacks, especially during the Lockdown time course announced by the countries throughout the world, when almost every aspect of life changed the routine from offline to online. Protecting and securing information resources during pandemics has been a top priority for the modern computing world, with databases, banking, E-commerce and mailing services, etc. being the eye-catching credentials to the attackers. Apart from cryptography, machine learning and deep learning can offer an enormous amount of help in testing, training, and extracting negligible information from the data sets. Deep learning and machine learning have many methods and models in the account to detect and classify the different versions of cyber-attacks occasionally, from the datasets. Some of the most common deep learning methods inspired by the neural networks are Recurrent Neural Networks, Convolutional Neural Networks, Deep Belief Networks, Deep Boltzman Networks, Autoencoders, and Stacked Auto-encoders. Also counting machine learning algorithms into the account, there is a vast variety of algorithms that are meant to perform classification and regression. The survey will provide some of the most important deep learning and machine learning architectures used for Cyber-security and can offer protective services against cyber-attacks. The paper is a survey about various categories of cyber-attacks with a timeline of different attacks that took place in India and some of the other countries in the world. The final section of the report is about what deep learning methods can offer for developing and improving the security policies and examining vulnerabilities of an information system. © 2021 IEEE.

COVID-19 Fake News Detection System

This article deals with the problem of the rapidly increasing COVID-19 infodemic in the world. Thus, there is a need for an effective framework of detecting fake information or misleading news related to COVID-19 virus/disease. To resolve this, we have used a dataset obtained from ConstraintAI'21. The dataset consists of 10,700 tweets and online posts of fake and real news concerning COVID-19. Machine Learning (ML) algorithms compared in this paper to classify the given news or tweet into real or fake are Logistic Regression (LR), K-Nearest Neighbor (KNN), Linear Support Vector Machine (LSVM), Random Forest Classifier (RFC), Decision Tree (DT), Naive Bayes (NB) and Stochastic Gradient Descent (SGD) algorithm. Two feature extraction techniques were used count vectorization and TF-IDF. Deep Learning (DL) algorithms implemented using Adam optimizer are Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM), and Gated Recurrent Unit (GRU). The best testing accuracy was achieved with the LSVM model using TF-IDF feature extraction method followed by Stochastic Gradient Descent classifier with TF-IDF feature extraction technique. LR, DT, and RFC performed better with the Count vectorization feature extraction technique, whereas LSVM, KNN, NB and SGD had better accuracy with TF-IDF feature extraction technique. The LSTM model performed slightly better among the DL algorithms. © 2022 IEEE.

An Introductory Assessment on Computational Algorithm in Initial Finding of COVID-19 Cases

This research discusses how to detect coronavirus patients using various target optimization and deep learning methods. This research utilizes the J48 decision tree methodology to describe the extended attributes of X-ray coronagraphs to identify polluted ill persons rapidly and efficiently. The investigation has found eleven distinct releases of the converting neural network to categorize infected individuals utilizing coronavirus pneumonia employing X-ray imaging (CNN). An emperor penguin and its objectives also indicate the characteristics of the CNN model. In the classified X-ray photos, a comprehensive model analysis displays the proper percentages of the features such as accuracy, precision, recollections, specificities, and F1. Extensive testing has shown that the new strategy outperforms competitors using wellknown performance criteria. The proposed model is therefore suitable for the Covid-19 disease radiation thoroughbred image in real-time. The developed/projected design is unique and will aid in the COVID-19 screening process optimization. © 2021 IEEE.

A Deep Learning Based Face Mask and Social Distance Monitoring Framework for Covid-19

Covid-19 has become one of the most dangerous diseases suddenly which is infecting the people in all over the world. It has created an impact on the lives of thousands of people all over the world. Governments of various countries are trying to control the wide spread of COVID-19 in our society. It is a danger to the human existence, so it is highly important to stop spreading the disease as it is deadly contagious. Spreading of virus can be prevented, by maintaining social distance and hygiene. The major transmission mode of COVID-19 is through saliva and nose discharge.It is highly important to know the necessity of wearing mask in the public. We need an automatic monitoring system for time being to monitor the public so as to avoid the situation of spreading of the disease for not wearing mask and not maintaining social distance. We have applied a deep learning technique to check whether the person is having a face mask or not. This work is aimed to identify the face mask in the public places which helps in the reducing of spread of the virus. CNN is used for the model. The proposed model recognizes the face region in the image given as input and extracts the necessary facial features to identify the face mask region. © 2021 IEEE.

Using artificial intelligence to risk stratify COVID-19 patients based on chest X-ray findings.

BACKGROUND: Deep learning-based radiological image analysis could facilitate use of chest x-rays as a triaging tool for COVID-19 diagnosis in resource-limited settings. This study sought to determine whether a modified commercially available deep learning algorithm (M-qXR) could risk stratify patients with suspected COVID-19 infections. METHODS: A dual track clinical validation study was designed to assess the clinical accuracy of M-qXR. The algorithm evaluated all Chest-X-rays (CXRs) performed during the study period for abnormal findings and assigned a COVID-19 risk score. Four independent radiologists served as radiological ground truth. The M-qXR algorithm output was compared against radiological ground truth and summary statistics for prediction accuracy were calculated. In addition, patients who underwent both PCR testing and CXR for suspected COVID-19 infection were included in a co-occurrence matrix to assess the sensitivity and specificity of the M-qXR algorithm. RESULTS: 625 CXRs were included in the clinical validation study. 98% of total interpretations made by M-qXR agreed with ground truth (p = 0.25). M-qXR correctly identified the presence or absence of pulmonary opacities in 94% of CXR interpretations. M-qXR's sensitivity, specificity, PPV, and NPV for detecting pulmonary opacities were 94%, 95%, 99%, and 88% respectively. M-qXR correctly identified the presence or absence of pulmonary consolidation in 88% of CXR interpretations (p = 0.48). M-qXR's sensitivity, specificity, PPV, and NPV for detecting pulmonary consolidation were 91%, 84%, 89%, and 86% respectively. Furthermore, 113 PCR-confirmed COVID-19 cases were used to create a co-occurrence matrix between M-qXR's COVID-19 risk score and COVID-19 PCR test results. The PPV and NPV of a medium to high COVID-19 risk score assigned by M-qXR yielding a positive COVID-19 PCR test result was estimated to be 89.7% and 80.4% respectively. CONCLUSION: M-qXR was found to have comparable accuracy to radiological ground truth in detecting radiographic abnormalities on CXR suggestive of COVID-19.

Digital Customer Acquisition and Onboarding during the Pandemic

A must for telecom industry in times of social distancing: Digital customer acquisition and onboarding. Digital channels gained more importance as classical sales channels could not work with the expected performance during the pandemic. In this paper, the digital sales paperless project carried out in the telecom industry is handled. The identification scanning with OCR (Optical Character Recognition), the verification with deep learning artificial intelligence algorithms, the management of remote vendors and other stakeholders in extensive software projects is told. © 2021 IEEE.

Clinical Validation of a Deep Learning Algorithm for Detection of Pneumonia on Chest Radiographs in Emergency Department Patients with Acute Febrile Respiratory Illness.

Early identification of pneumonia is essential in patients with acute febrile respiratory illness (FRI). We evaluated the performance and added value of a commercial deep learning (DL) algorithm in detecting pneumonia on chest radiographs (CRs) of patients visiting the emergency department (ED) with acute FRI. This single-centre, retrospective study included 377 consecutive patients who visited the ED and the resulting 387 CRs in August 2018-January 2019. The performance of a DL algorithm in detection of pneumonia on CRs was evaluated based on area under the receiver operating characteristics (AUROC) curves, sensitivity, specificity, negative predictive values (NPVs), and positive predictive values (PPVs). Three ED physicians independently reviewed CRs with observer performance test to detect pneumonia, which was re-evaluated with the algorithm eight weeks later. AUROC, sensitivity, and specificity measurements were compared between "DL algorithm" vs. "physicians-only" and between "physicians-only" vs. "physicians aided with the algorithm". Among 377 patients, 83 (22.0%) had pneumonia. AUROC, sensitivity, specificity, PPV, and NPV of the algorithm for detection of pneumonia on CRs were 0.861, 58.3%, 94.4%, 74.2%, and 89.1%, respectively. For the detection of 'visible pneumonia on CR' (60 CRs from 59 patients), AUROC, sensitivity, specificity, PPV, and NPV were 0.940, 81.7%, 94.4%, 74.2%, and 96.3%, respectively. In the observer performance test, the algorithm performed better than the physicians for pneumonia (AUROC, 0.861 vs. 0.788, p = 0.017; specificity, 94.4% vs. 88.7%, p < 0.0001) and visible pneumonia (AUROC, 0.940 vs. 0.871, p = 0.007; sensitivity, 81.7% vs. 73.9%, p = 0.034; specificity, 94.4% vs. 88.7%, p < 0.0001). Detection of pneumonia (sensitivity, 82.2% vs. 53.2%, p = 0.008; specificity, 98.1% vs. 88.7%; p < 0.0001) and 'visible pneumonia' (sensitivity, 82.2% vs. 73.9%, p = 0.014; specificity, 98.1% vs. 88.7%, p < 0.0001) significantly improved when the algorithm was used by the physicians. Mean reading time for the physicians decreased from 165 to 101 min with the assistance of the algorithm. Thus, the DL algorithm showed a better diagnosis of pneumonia, particularly visible pneumonia on CR, and improved diagnosis by ED physicians in patients with acute FRI.