Impact of Internet of Health Things (IoHT) on COVID-19 Disease Detection and Its Treatment Using Single Hidden Layer Feed Forward Neural Networks (SIFN)

COVID-19 endemic has made the entire world face an extraordinary challenging situation which has made life in this world a fearsome halt and demanding numerous lives. As it has spread across 212 nations and territories and the infected cases and deaths are increased to 5,212,172 and 334,915 (as of May 22 2020). Still, it is a real hazard to human health. Severe Acute Respiratory Syndrome cause vast negative impacts economy and health populations. Professionals involved in COVID test can commit mistakes when testing for identifying the disease. Evaluating and diagnosing the disease by medical experts are the significant key factor. Technologies like machine learning and data mining helps substantially to increase the accuracy of identifying COVID. Artificial Neural Networks (ANN) has been extensively used for diagnosis. Proposed Single Hidden Layer Feedforward Neural Networks (SLFN)-COVID approach is used to detect COVID-19 for disease detection on creating the social impacts and its used for treatment. The experimental results of the proposed method outperforms well when compared to existing methods which achieves 83% of accuracy, 73% of precision, 68% of Recall, 82% of F1-Score. © The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG 2022.

CovMnet-Deep Learning Model for classifying Coronavirus (COVID-19).

Diagnosing COVID-19, current pandemic disease using Chest X-ray images is widely used to evaluate the lung disorders. As the spread of the disease is enormous many medical camps are being conducted to screen the patients and Chest X-ray is a simple imaging modality to detect presence of lung disorders. Manual lung disorder detection using Chest X-ray by radiologist is a tedious process and may lead to inter and intra-rate errors. Various deep convolution neural network techniques were tested for detecting COVID-19 abnormalities in lungs using Chest X-ray images. This paper proposes deep learning model to classify COVID-19 and normal chest X-ray images. Experiments are carried out for deep feature extraction, fine-tuning of convolutional neural networks (CNN) hyper parameters, and end-to-end training of four variants of the CNN model. The proposed CovMnet provide better classification accuracy of 97.4% for COVID-19 /normal than those reported in the previous studies. The proposed CovMnet model has potential to aid radiologist to monitor COVID-19 disease and proves to be an efficient non-invasive COVID-19 diagnostic tool for lung disorders.

Computer-aided diagnosis of COVID-19 from chest X-ray images using histogram-oriented gradient features and Random Forest classifier.

The decision-making process is very crucial in healthcare, which includes quick diagnostic methods to monitor and prevent the COVID-19 pandemic disease from spreading. Computed tomography (CT) is a diagnostic tool used by radiologists to treat COVID patients. COVID x-ray images have inherent texture variations and similarity to other diseases like pneumonia. Manually diagnosing COVID X-ray images is a tedious and challenging process. Extracting the discriminant features and fine-tuning the classifiers using low-resolution images with a limited COVID x-ray dataset is a major challenge in computer aided diagnosis. The present work addresses this issue by proposing and implementing Histogram Oriented Gradient (HOG) features trained with an optimized Random Forest (RF) classifier. The proposed HOG feature extraction method is evaluated with Gray-Level Co-Occurrence Matrix (GLCM) and Hu moments. Results confirm that HOG is found to reflect the local description of edges effectively and provide excellent structural features to discriminate COVID and non-COVID when compared to the other feature extraction techniques. The performance of the RF is compared with other classifiers such as Linear Regression (LR), Linear Discriminant Analysis (LDA), K-nearest neighbor (kNN), Classification and Regression Trees (CART), Random Forest (RF), Support Vector Machine (SVM), and Multi-layer perceptron neural network (MLP). Experimental results show that the highest classification accuracy (99. 73%) is achieved using HOG trained by using the Random Forest (RF) classifier. The proposed work has provided promising results to assist radiologists/physicians in automatic COVID diagnosis using X-ray images.

Doctor's Dilemma: Evaluating an Explainable Subtractive Spatial Lightweight Convolutional Neural Network for Brain Tumor Diagnosis

In Medicine Deep Learning has become an essential tool to achieve outstanding diagnosis on image data. However, one critical problem is that Deep Learning comes with complicated, black-box models so it is not possible to analyze their trust level directly. So, Explainable Artificial Intelligence (XAI) methods are used to build additional interfaces for explaining how the model has reached the outputs by moving from the input data. Of course, that's again another competitive problem to analyze if such methods are successful according to the human view. So, this paper comes with two important research efforts: (1) to build an explainable deep learning model targeting medical image analysis, and (2) to evaluate the trust level of this model via several evaluation works including human contribution. The target problem was selected as the brain tumor classification, which is a remarkable, competitive medical image-based problem for Deep Learning. In the study, MR-based pre-processed brain images were received by the Subtractive Spatial Lightweight Convolutional Neural Network (SSLW-CNN) model, which includes additional operators to reduce the complexity of classification. In order to ensure the explainable background, the model also included Class Activation Mapping (CAM). It is important to evaluate the trust level of a successful model. So, numerical success rates of the SSLW-CNN were evaluated based on the peak signal-to-noise ratio (PSNR), computational time, computational overhead, and brain tumor classification accuracy. The objective of the proposed SSLW-CNN model is to obtain faster and good tumor classification with lesser time. The results illustrate that the SSLW-CNN model provides better performance of PSNR which is enhanced by 8%, classification accuracy is improved by 33%, computation time is reduced by 19%, computation overhead is decreased by 23%, and classification time is minimized by 13%, as compared to state-of-the-art works. Because the model provided good numerical results, it was then evaluated in terms of XAI perspective by including doctor-model based evaluations such as feedback CAM visualizations, usability, expert surveys, comparisons of CAM with other XAI methods, and manual diagnosis comparison. The results show that the SSLW-CNN provides good performance on brain tumor diagnosis and ensures a trustworthy solution for the doctors.

Diagnosis of covid-19 using optimized pca based local binary pattern features

Introduction: COVID-19 is a pandemic disease affecting the global mankind since December 2019. Diagnosing COVID-19 using lung X-ray image is a great challenge faced by the entire world. Early detection helps the doctors to suggest suitable treatment and also helps speedy recovery of the patients. Advancements in the field of computer vision aid medical practitioners to predict and diagnosis disease accurately. Objective: This study aims to analyze the chest X-ray for determining the presence of COVID-19 using machine learning algo-rithm. Methods: Researchers propose various techniques using machine learning algorithms and deep learning approaches to de-tect COVID-19. However, obtaining an accurate solution using these AI techniques is the main challenge still remains open to researchers. Results: This paper proposes a Local Binary Pattern technique to extract discriminant features for distinguishing COVID-19 disease using the X-ray images. The extracted features are given as input to various classifiers namely Random Forest (RF), Linear Discriminant Analysis (LDA), k-Nearest Neighbour (kNN), Classification and Regression Trees (CART), Support Vector Machine (SVM), Linear Regression (LR), and Multi-layer perceptron neural network (MLP). The proposed model has achieved an accuracy of 77.7% from Local Binary Pattern (LBP) features coupled with Random Forest classifier. Conclusion: The proposed algorithm analyzed COVID X-ray images to classify the data in to COVID-19 or not. The features are extracted and are classified using machine learning algorithms. The model achieved high accuracy for linear binary pattern with random forest classifier. © IJCRR.

A report on the impact of information technology and social media on covid-19

The destruction caused by the COVID-19 virus to the human race is beyond the imagination. This article elucidates how COVID-19 is identified as a threat to human life. The statistical report is given for the some of the countries which are highly affected by this pandemic. The medical advancements and the impact of insufficient medical facilities, are available even in the well-developed nations. The role of Information Technology (IT) in the development of various effective algorithms for the diagnosis and prevention of the disease is discussed. This research article also covers the responsibilities of the various social mediaalong with their vulnerable efforts in carrying awareness to society. © 2020 IEEE.

COVID-19 prediction and symptom analysis using wearable sensors and IoT

Purpose The purpose of the research work is to focus on the deployment of wearable sensors in addressing symptom Analysis in the Internet of Things (IoT) environment to reduce human interaction in this epidemic circumstances. Design/methodology/approach COVID-19 pandemic has distracted the world into an unaccustomed situation in the recent past. The pandemic has pulled us toward data harnessing and focused on the digital framework to monitor the COVID-19 cases seriously, as there is an urge to detect the disease, wearable sensors aided in predicting the incidence of COVID-19. This COVID-19 has initiated many technologies like cloud computing, edge computing, IoT devices, artificial intelligence. The deployment of sensor devices has tremendously increased. Similarly, IoT applications have witnessed many innovations in addressing the COVID-19 crisis. State-of-the-art focuses on IoT factors and symptom features deploying wearable sensors for predicting the COVID-19 cases. The working model incorporates wearable devices, clinical therapy, monitoring the symptom, testing suspected cases and elements of IoT. The present research sermonizes on symptom analysis and risk factors that influence the coronavirus by acknowledging the respiration rate and oxygen saturation (SpO(2)). Experiments were proposed to carry out with chi-Square distribution with independent measures t-Test. Findings IoT devices today play a vital role in analyzing COVID-19 cases effectively. The research work incorporates wearable sensors, human interpretation and Web server, statistical analysis with IoT factors, data management and clinical therapy. The research is initiated with data collection from wearable sensors, data retrieval from the cloud server, pre-processing and categorizing based on age and gender information. IoT devices contribute to tracking and monitoring the patients for prerequisites. The suspected cases are tested based on symptom factors such as temperature, oxygen level (SPO2), respiratory rate variation and continuous investigation, and these demographic factors are taken for analyzed based on the gender and age factors of the collected data with the IoT factors thus presenting a cutting edge construction design in clinical trials. Originality/value The contemporary study comprehends 238 data through wearable sensors and transmitted through an IoT gateway to the cloud server. Few data are considered as outliers and discarded for analysis. Only 208 data are contemplated for statistical examination. These filtered data are proclaimed using chi-square distribution with t-test measure correlating the IoT factors. The research also interprets the demographic features that induce IoT factors using alpha and beta parameters showing the equal variance with the degree of freedom (df = 206).