Detecting COVID-19 from Chest X-rays Using Convolutional Neural Network Ensembles

Starting in late 2019, the coronavirus SARS-CoV-2 began spreading around the world and causing disruption in both daily life and healthcare systems. The disease is estimated to have caused more than 6 million deaths worldwide [WHO]. The pandemic and the global reaction to it severely affected the world economy, causing a significant increase in global inflation rates, unemployment, and the cost of energy commodities. To stop the spread of the virus and dampen its global effect, it is imperative to detect infected patients early on. Convolutional neural networks (CNNs) can effectively diagnose a patient's chest X-ray (CXR) to assess whether they have been infected. Previous medical image classification studies have shown exceptional accuracies, and the trained algorithms can be shared and deployed using a computer or a mobile device. CNN-based COVID-19 detection can be employed as a supplement to reverse transcription-polymerase chain reaction (RT-PCR). In this research work, 11 ensemble networks consisting of 6 CNN architectures and a classifier layer are evaluated on their ability to differentiate the CXRs of patients with COVID-19 from those of patients that have not been infected. The performance of ensemble models is then compared to the performance of individual CNN architectures. The best ensemble model COVID-19 detection accuracy was achieved using the logistic regression ensemble model, with an accuracy of 96.29%, which is 1.13% higher than the top-performing individual model. The highest F1-score was achieved by the standard vector classifier ensemble model, with a value of 88.6%, which was 2.06% better than the score achieved by the best-performing individual model. This work demonstrates that combining a set of top-performing COVID-19 detection models could lead to better results if the models are integrated together into an ensemble. The model can be deployed in overworked or remote health centers as an accurate and rapid supplement or back-up method for detecting COVID-19.

A deep learning approach for COVID-19 detection from computed tomography scans

The classification of COVID-19 patients from chest computed tomography (CT) images is a very difficult task due to the similarities observed with other lung diseases. Based on various CT scans of COVID and non-COVID patients, the aim of this chapter is to propose a simple deep learning architecture and compare its diagnostic performance using transfer learning and several machine learning techniques that could extract COVID-19's graphical features and classify them in order to provide a clinical diagnosis ahead of the pathogenic test, thus saving critical time for disease control. We also compare our approach and show that it outperforms various previous state-of-the-art techniques. We propose a deep learning architecture for transfer learning that is just a simple modification of eight new layers on the ImageNet pretrained convolutional neural networks (CNNs) which yielded us the best test accuracy of 98.30%, F1 score of 0.982, area under the receiver operating characteristic (ROC) curve of 0.982, and kappa value of 0.964 after training. Moreover, we use the proposed architecture for feature extraction and study the performance of various classifiers on them and were able to obtain the highest test accuracy of 91.75% with K-nearest neighbors. Also, we compare multiple CNNs and machine learning models for their diagnostic potential in disease detection and suggest a much faster and automated disease detection methodology. We show that smaller and memory efficient architectures are equally good compared to deep and heavy architectures at classifying chest CTs. We also show that visual geometry group (VGG) architectures are overall the best for this task. © 2023 Elsevier Inc. All rights reserved.

Signal Preprocessing Technique With Noise-Tolerant for RF-Based UAV Signal Classification

Since the beginning of the COVID-19 pandemic, the demand for unmanned aerial vehicles (UAVs) has surged owing to an increasing requirement of remote, noncontact, and technologically advanced interactions. However, with the increased demand for drones across a wide range of fields, their malicious use has also increased. Therefore, an anti-UAV system is required to detect unauthorized drone use. In this study, we propose a radio frequency (RF) based solution that uses 15 drone controller signals. The proposed method can solve the problems associated with the RF based detection method, which has poor classification accuracy when the distance between the controller and antenna increases or the signal-to-noise ratio (SNR) decreases owing to the presence of a large amount of noise. For the experiment, we changed the SNR of the controller signal by adding white Gaussian noise to SNRs of -15 to 15 dB at 5 dB intervals. A power-based spectrogram image with an applied threshold value was used for convolution neural network training. The proposed model achieved 98% accuracy at an SNR of -15 dB and 99.17% accuracy in the classification of 105 classes with 15 drone controllers within 7 SNR regions. From these results, it was confirmed that the proposed method is both noise-tolerant and scalable.

Efficient Artificial Intelligence-based Models for COVID-19 Disease Detection and Diagnosis from CT-Scans

COVID-19 is contagious virus that first emerged in China in 2019's last month. It mainly infects the both the lungs and the respiratory system. The virus has severely impacted life and the economy, which exposed threats to governments worldwide to manage it. Early diagnosis of COVID-19 could help with treatment planning and disease prevention strategies. In this study, we use CT-Scanned images of the lungs to show how COVID-19 may be identified using transfer learning model and investigate which model achieved the best and fastest results. Our primary focus was to detect structural anomalies to distinguish among COVID-19 positive, negative, and normal cases with deep learning methods. Every model received training with and without transfer learning and results were compared for various versions of DenseNet and EfficientNet. Optimal results were obtained using DenseNet201 (99.75%). When transfer learning was applied, all models produced almost similar results. © 2022 IEEE.

Human Emotion Prediction Analysis on Post-COVID-19 Crisis in Digital Media Using Deep Learning

The COVID-19 pandemic has produced a significant impact on society. Apart from its deadliest attack on human health and economy, it has also been affecting the mental stability of human being at a larger scale. Though vaccination has been partially successful to prevent further virus outreach, it is leaving behind typical health-related complications even after surviving from the disease. This research work mainly focuses on human emotion prediction analysis in post-COVID-19 period. In this work, a considerable amount of data collection has been performed from various digital sources, viz. Facebook, e-newspapers, and digital news houses. Three distinct classes of emotion, i.e., analytical, depressed, and angry, have been considered. Finally, the predictive analysis is performed using four deep learning models, viz. CNN, RNN, LSTM, and Bi-LSTM, based on digital media responses. Maximum accuracy of 97% is obtained from LSTM model. It has been observed that the post-COVID-19 crisis has mostly depressed the human being. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

An Approach of Dempster-Shafer Decision Fusion to Diagnose COVID-19 in Chest X-ray Imagery by Using Controlled Asymmetric Training of the two CNNs Ensemble

This paper proposes a model of Dempster-Shafer decision fusion based on controlled training of the ensemble of two Convolutional Neural Networks (CNNs) by the asymmetry parameter k, defined as the ratio of the numbers of training data per class assigned to each CNN module. The proposed model is dedicated to COVID-19 diagnose in chest X-ray imagery. We have considered two CNN modules with identical architectures. First CNN module has been trained with 2837 COVID-19 labeled images and (2837/k) NON-COVID images. Second CNN module has been trained with (2837/k) COVID-19 labeled images and 2837 NON-COVID images. We have evaluated the influence of control parameter k on the diagnosis performances. As a result of Dempster-Shafer fusion, for k=2.1, one obtains a maximum Overall Accuracy (OA) of 95.18% The above performance is clearly better than the corresponding OA obtained by a single CNN (92.26%) for the same k, and at the same time it is better than OA obtained by any single CNN module for any considered k. Moreover, one can remark, that by controlled training, for k=20, a CNN module can lead to an incredible low Missing Alarm Rate (MAR) of only 0.63% © 2022 IEEE.

Embedded Implementation of Social Distancing Detector Based on One Stage Convolutional Neural Network Detector

The recent COVID-19 is a very dangerous disease that intimidates humanity. It spreads very fast and many rules must be respected to reduce its prevalence. One of the most important rules is the social distance which means keeping a safe distance between two persons. A safe distance must be one meter or more. Respecting such rules in public spaces is a very challenging task that needs the assistance of artificial intelligence tools. In this paper, we propose a social distance detector using convolutional neural networks. The detector was based on the Yolo model with a custom-made backbone to guarantee real-time processing and embedded implementation. The backbone was optimized to make it suitable for embedded resources. The inference model was evaluated on the Pynq platform. The model was trained and fine-tuned using the MS COCO dataset. The evaluation of the proposed model proved its efficiency with a precision of 87.98% while running in real-time. The achieved results proved the efficiency of the proposed model and the proposed optimization for embedded implementation. © 2022 Lavoisier. All rights reserved.

Deep Learning based Analysis of Covid-19 Mortality Risk

Viral infectious diseases such as Covid-19 present a major threat to public health. Despite extreme research efforts, how, when and where such new outbreaks appear is still a source of substantial uncertainty. Deep learning (DL) is playing an increasingly important role in our lives. This paper presents one of the popular deep learning technique, Long Short Term Memory (LSTM) for prediction of Corona-Virus cases. The handcrafted feature extraction of traditional methods is less scalable on large data-sets, but deep learning algorithms perform extremely well on large data-sets, because of automatic feature extraction. Deep learning has already made a huge impact in areas, such as cancer diagnosis, precision medicine, self-driving cars, predictive forecasting, and speech recognition. This paper highlights the approaches where deep learning can be helpful to tackle the Covid-19 virus and similar outbreaks. This paper also discusses the structure and functioning of Covid-19. The utilization of different deep learning concepts like Convolutional Neural Networks, Transfer Learning for this pandemic is also highlighted. © 2022 University of Bahrain. All rights reserved.

Identification of Non-Vaccinated People Using Face Recognition Based on CNN

Preventive medical care relies on vaccinations to provide significant health benefits. Vaccination is an important and effective preventive health measure. There is no better way to reduce the risk of pandemic spread of SARS-CoV-2/COVID-19 than vaccination. As a preventive measure, the government has begun vaccinating Indians against Corona infection. It is therefore important, in addition to developing and supplying vaccines, that enough people are willing to obtain vaccines. However, of the populations worldwide, there are concerning proportions that are reluctant to get vaccinated. In order to end the pandemic, it is highly essential to deal with another omnipresent issue: outright rejection of vaccinations. To achieve population immunity first we have to find the non-vaccinated population should be detected and to this end, this project proposed an Aadhaar-based facial recognition system is used to find non-vaccinated citizen and alert them using Artificial Intelligence. Deep learning which is in the form of Convolutional Neural Networks (CNNs) are used to carry out the face recognition process and it is also proven to be an efficient method to carry out face recognition due to its high fidelity. A CNN is a Deep Neural Network (DNN), which is designed to perform challenging tasks like image processing, which is crucial for facial recognition. The CNN structure is composed of numerous layers of neurons that connect the neurons: an input layer, an output layer, and layers between these two layers. In the midst of the epidemic coronavirus outbreak (COVID-19), a person's current inoculation status will be updated based on face recognition to safeguard him/her from COVID-19 and it may also serve as proof of vaccination for other purposes. Facial recognition technology (FRT) along with the Aadhaar helps to authenticate people before entering into any types of service. This project provides COVID-19 immunization status, which is determined by observing at their face, and certify that they have been vaccinated. © 2022 IEEE.

An Adaptive Approach to Detect Face Mask in Real Time using Convolutional NeuralNetwork (CNN) Model

The corona virus diseases are sparkling an astonishing level of scientific collaboration around the world. Artificial intelligence (AI) association with machine learning and deep learning could greatly assist in fighting corona virus in a number of paths. Machine learning allows research scholar, researchers and clinicians to make assessment on various amounts of datasets to foresee the spread of corona virus, which serve as an early warning mechanism for potential epidemics. In many countries, people are required by protocol to wear a mask in public. These rules and laws are designed as measures to exponentially increase the number of diseases count and death cases in many regions. However, the procedure of observing many people is becoming increasingly difficult. Here, we present a model for mask face detection based on deep learning and computer vision. The proposed model can be embedded with a surveillance camera to block the spread of corona diseases, detecting people wearing masks but not face masks. This model integrates deep learning and classic machine learning methods using open computer vision, tensor flow and keras.

deepHPI: a comprehensive deep learning platform for accurate prediction and visualization of host-pathogen protein-protein interactions.

Host-pathogen protein interactions (HPPIs) play vital roles in many biological processes and are directly involved in infectious diseases. With the outbreak of more frequent pandemics in the last couple of decades, such as the recent outburst of Covid-19 causing millions of deaths, it has become more critical to develop advanced methods to accurately predict pathogen interactions with their respective hosts. During the last decade, experimental methods to identify HPIs have been used to decipher host-pathogen systems with the caveat that those techniques are labor-intensive, expensive and time-consuming. Alternatively, accurate prediction of HPIs can be performed by the use of data-driven machine learning. To provide a more robust and accurate solution for the HPI prediction problem, we have developed a deepHPI tool based on deep learning. The web server delivers four host-pathogen model types: plant-pathogen, human-bacteria, human-virus and animal-pathogen, leveraging its operability to a wide range of analyses and cases of use. The deepHPI web tool is the first to use convolutional neural network models for HPI prediction. These models have been selected based on a comprehensive evaluation of protein features and neural network architectures. The best prediction models have been tested on independent validation datasets, which achieved an overall Matthews correlation coefficient value of 0.87 for animal-pathogen using the combined pseudo-amino acid composition and conjoint triad (PAAC_CT) features, 0.75 for human-bacteria using the combined pseudo-amino acid composition, conjoint triad and normalized Moreau-Broto feature (PAAC_CT_NMBroto), 0.96 for human-virus using PAAC_CT_NMBroto and 0.94 values for plant-pathogen interactions using the combined pseudo-amino acid composition, composition and transition feature (PAAC_CTDC_CTDT). Our server running deepHPI is deployed on a high-performance computing cluster that enables large and multiple user requests, and it provides more information about interactions discovered. It presents an enriched visualization of the resulting host-pathogen networks that is augmented with external links to various protein annotation resources. We believe that the deepHPI web server will be very useful to researchers, particularly those working on infectious diseases. Additionally, many novel and known host-pathogen systems can be further investigated to significantly advance our understanding of complex disease-causing agents. The developed models are established on a web server, which is freely accessible at http://bioinfo.usu.edu/deepHPI/.

CXR-15: Deep Learning-Based Approach Towards Pneumonia Detection from Chest X-Rays

Pneumonia detection and recognition have been one of the major challenges, and the machine learning community has been trying to tackle. Pneumonia is identified in X-ray images by the virtue of haziness in the lung region created due to the air sacs filled with fluid or pus. As pneumonia affects around 7% of the world’s population and kills over 700,000 children annually, the research in this field has become more prominent. In severe cases of COVID-19, people also get pneumonia. Earlier attempts using CNN, ChexNet, ensembles of transfer learning models have been carried out to solve this problem. However, work in this field has not been keeping up with the advancements in neural network happened in past few years. In this work, a 15-layer CNN architecture called CXR-15 is proposed. The performance of the architecture was tested on a dataset with 5856 images and compared with various existing architectures. CXR-15 outperformed most of the existing architectures used for pneumonia detection like ChexNet, Xception, InceptionResNetV2, VGG16, EfficientNet-B5, CNN as feature extractors and MobileNetV2 by achieving an accuracy of 95.2%. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Real Time Face Mask Detection Using MobileNetV2 and InceptionV3 Models

The widespread outbreak of COVID-19 has resulted in the need for efficient face mask detection. This study is focused on achieving real time face mask detection using methods which are not computationally expensive. A dataset which contains images captured in real time was selected for this application. The subjects in the dataset belonged to three different categories consisting of mask worn correctly, mask worn incorrectly and no mask. Two pretrained Convolutional Neural Network models, MobileNetV2 and InceptionV3 were fine-tuned using the transfer learning approach. This paper presents a simple approach in which the Region of Interest is extracted using a pretrained Multi-task Cascaded Convolutional Neural Network, whose output is fed into the classifier model. It was observed that the InceptionV3 model performs better when compared with MobileNetV2 model. © 2021 IEEE.

COVID-19 classification using deep feature concatenation technique.

Detecting COVID-19 from medical images is a challenging task that has excited scientists around the world. COVID-19 started in China in 2019, and it is still spreading even now. Chest X-ray and Computed Tomography (CT) scan are the most important imaging techniques for diagnosing COVID-19. All researchers are looking for effective solutions and fast treatment methods for this epidemic. To reduce the need for medical experts, fast and accurate automated detection techniques are introduced. Deep learning convolution neural network (DL-CNN) technologies are showing remarkable results for detecting cases of COVID-19. In this paper, deep feature concatenation (DFC) mechanism is utilized in two different ways. In the first one, DFC links deep features extracted from X-ray and CT scan using a simple proposed CNN. The other way depends on DFC to combine features extracted from either X-ray or CT scan using the proposed CNN architecture and two modern pre-trained CNNs: ResNet and GoogleNet. The DFC mechanism is applied to form a definitive classification descriptor. The proposed CNN architecture consists of three deep layers to overcome the problem of large time consumption. For each image type, the proposed CNN performance is studied using different optimization algorithms and different values for the maximum number of epochs, the learning rate (LR), and mini-batch (M-B) size. Experiments have demonstrated the superiority of the proposed approach compared to other modern and state-of-the-art methodologies in terms of accuracy, precision, recall and f_score.