Early detection of COVID-19 using deep learning architectures: CNN and resnet-101

The main purpose of this paper was to classify if subject has a COVID-19 or not base on CT scan. CNN and resNet-101 neural network architectures are used to identify the coronavirus. The experimental results showed that the two models CNN and resNet-101 can identify accurately the patients have COVID-19 from others with an excellent accuracy of 83.97 % and 90.05 % respectively. The results demonstrates the best ability of the used models in the current application domain. © 2022 IEEE.

Predicting COVID-19 from Chest X-ray Images using a New Deep Learning Architecture

The spread of coronavirus disease in late 2019 caused huge damage to human lives and forced a chaos in health care systems around the globe. Early diagnosis of this disease can help separate patients from healthy people. Therefore, precise COVID-19 detection is necessary to prevent the spread of this virus. Many artificial intelligent technologies for example deep learning models have been applied successfully for this task by employing chest X-ray images. In this paper, we propose to classify chest X-ray images using a new end-To-end convolutional neural network model. This new model consists of six convolutional blocks. Each block consists of one convolutional layer, one ReLU layer, and one max-pooling layer. The new model was applied on a challenging imbalanced COVID19 dataset of 5000 images, divided into two classes, COVID and Non-COVID. In experiments, the input image is first resized to 256×256×3 before being fed to the model. Two metrics were used to test our new model: sensitivity and specificity. A sensitivity rate of 97% was achieved along with a specificity rate of 99.32%. These results are promising when compared to other deep learning models applied on the same dataset. © 2022 IEEE.

Deep Learning-Based Model for Face Mask Detection in the Era of COVID-19 Pandemic

Recent advancements in the growth of classification tasks and deep learning have culminated in the worldwide success of numerous practical applications. With the onset of COVID-19 pandemic, it becomes very important to use technology to help us control the infectious nature of the virus. Deep learning and image classification can help us detect face mask from a crowd of people. However, choosing the correct deep learning architecture can be crucial in the success of such an idea. This study presents a model for extracting features from face masks utilizing pre-trained models ConvNet, InceptionV3, MobileNet, DenseNet, ResNet50, and VGG19, as well as stacking a fully connected layer to solve the issue. On the face mask 12 k dataset, the study assesses the effectiveness of the suggested deep learning approaches for the task of facemask detection. The performance metrics used for analysis are loss, accuracy, validation loss, and validation accuracy. The maximum accuracy is achieved by DenseNet and MobileNet. Both the models gave a comparable and good accuracies in terms of training and validation (99.89% and 99.79%), respectively. Further, the paper also demonstrates the deployment of deep learning architecture in the real-world using Raspberry Pi 2B (1 GB RAM). © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Deep Learning-Based Multi-modal COVID-19 Screening by Socially Assistive Robots Using Cough and Breathing Symptoms

In this paper, we present the development of a novel autonomous social robot deep learning architecture capable of real-time COVID-19 screening during human-robot interactions. The architecture allows for autonomous preliminary multi-modal COVID-19 detection of cough and breathing symptoms using a VGG16 deep learning framework. We train and validate our VGG16 network using existing COVID datasets. We then perform real-time non-contact preliminary COVID-19 screening experiments with the Pepper robot. The results for our deep learning architecture demonstrate: 1) an average computation time of 4.57 s for detection, and 2) an accuracy of 84.4% with respect to self-reported COVID symptoms. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

COVID-DenseNet: A Deep Learning Architecture to Detect COVID-19 from Chest Radiology Images

COVID-19 has a severe risk of spreading rapidly, the quick identification of which is essential. In this regard, chest radiology images have proven to be a practical screening approach for COVID-19 affected patients. This study proposes a deep learning-based approach using DenseNet-121 to detect COVID-19 patients effectively. We have trained and tested our model on the COVIDx dataset and performed both two-class and three-class classifications, achieving 96.49% and 93.71% accuracy, respectively. By successfully utilizing transfer learning, we achieve comparable performance to the state-of-the-art method while using 15 × fewer model parameters. Moreover, we performed an interpretability analysis using Grad-CAM to highlight the most significant image regions at test time. Finally, we developed a website that takes chest radiology images as input and detects the presence of COVID-19 or pneumonia and a heatmap highlighting the infected regions. Source code for reproducing results and model weights is available. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Feasibility Study on Browser-Based Federated Machine Learning (FML) Architecture for Medical Application

Traditional approaches to Artificial Intelligence (AI) based medical image classification requires huge amounts of data sets to be stored in a centralized server for analysis and training. In medical applications, data privacy and ownership may pose a challenge. In addition, costs incurred by data transfer and cloud server may pose a challenge to implementing a large dataset. This work studies the feasibility of a decentralized, browser-based Artificial Intelligence (AI) federated machine learning (FML) architecture. The proposed work studies the feasibility of bringing training and inference to the browser, hence removing the need to transfer raw data to a centralized server. If feasible, the system allows practitioners to compress and upload their pre-trained model to the server instead of raw data. This allows medical practitioners to update the model without the need to reveal their raw data. A sandbox system was implemented by applying transfer learning on MobileNet V3 and was tested with chest X-ray image datasets from COVID-19, viral pneumonia, and normal patients to simulate medical usage environment. The training speed, model performance and inference speed were tested on a PC browser and mobile phone with various levels of network throttling and image degradation. © 2022 IEEE.

A Vietnamese Named Entity Recognition System for COVID-19 Articles

This paper presents a named entity recognition system for the specific domain of Vietnamese COVID-19 news articles. By incorporating manually selected and domain-specific features into a simple deep learning architecture, the system can identify a wide range of custom named entities relevant in the context of COVID-19 and future epidemics. Using high-dimensional embedding vectors in combination with part-of-speech tags and additional features, the system achieves an F score of about 90.41%, surpassing or coming close to results by other models that are more complicated or pre-Trained and fine-Tuned. © 2022 IEEE.

Off-Shelf Deep Learning Architectures as Feature Extractor in CT COVID-19 Classification

Recently the chest imaging plays an important role in COVID-19 diagnosis compared to laboratory diagnosis such as RT-PCR. This paper investigates a robust algorithm to detect infected COVID-19 patients using computed tomography scans. The proposed algorithm utilizes a deep learning approach through applying an off shelf pretrained neural network to extract a feature map matrix from the first layer of convolutional neural network, which preserve the basic features related to geometry structures. Later the trained features are classified using a machine learning classifier as support vector machine algorithm to classify the tested images into two classes infected against not infected. The investigated algorithm was trained and tested using two open-source datasets. The results were experimented using five general pretrained off shelf CNN architectures, the performance of the pretrained algorithm was measured and evaluated for the extracted image features with popular five pretrained CNN and classification accuracy 90%. © 2022 IEEE.

A Vietnamese Named Entity Recognition System for COVID-19 Articles

This paper presents a named entity recognition system for the specific domain of Vietnamese COVID-19 news articles. By incorporating manually selected and domain-specific features into a simple deep learning architecture, the system can identify a wide range of custom named entities relevant in the context of COVID-19 and future epidemics. Using high-dimensional embedding vectors in combination with part-of-speech tags and additional features, the system achieves an F score of about 90.41%, surpassing or coming close to results by other models that are more complicated or pre-Trained and fine-Tuned. © 2022 IEEE.

COVID-19 Lung CT Images Recognition with Superscalar Winograd Circuit Based on VGG19

In this paper, we proposed COVID-19 lung CT (computed tomography) images recognition with superscalar winograd circuit based on VGG19. We adopt the VGG-19 machine learning architecture to recognize lung CT images and speed up neural network operations through Superscalar Winograd Circuit. After a series of experiments, our proposed method has a high pneumonia recognition rate and high computational efficiency. © 2022 IEEE.

Computational Deep Learning Models for Detection of COVID-19 Using Chest X-Ray Images

Traditional deep learning architectures after the AlexNet have added more layers to achieve higher accuracy. However, with increasing number of layers, we are likely to encounter vanishing/exploding gradient problems in these architectures which significantly impact the training performance. This was solved by the introduction of residual networks which make use of "skip connections” by adding the output from the previous layer to the layer ahead. ResNets are often combined with the Inception v4 model and was first used by Google researchers as Inception-ResNet. Inception v4 aimed to reduce the complexity of Inception v3 model which gave the state-of-the-art accuracy on ILSVRC 2015 challenge. The initial set of layers before the Inception block in Inception v4, referred to as "stem of the architecture,” was modified to make it more uniform. This model can be trained without partition of replicas unlike the previous versions of inceptions which required different replica in order to fit in memory. This architecture uses memory optimization on back propagation to reduce the memory requirement. In this paper, we propose two approaches for detection of COVID-19 using chest X-ray images by implementing ResNet16 and Inception v4 and providing a comparison of their performances. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Comparison Study Of Deep-Learning Architectures For Classification of Thoracic Pathology

This work aims to study different architectures for the classification of thoracic diseases using pre-trained convolutional neural networks (PCNN) such as VGG-16, ResNet-50, EfficientNetB0, and InceptionV3 which are considered as state-of-the-art deep learning models. Indeed, they are used to detect various thoracic disorders. In this study, the main focus is on COVID-19 and pneumonia to make an optimal diagnosis for these two diseases. Although these diseases are prevalent, the process of detection and diagnosis is challenging. In this work, two unbalanced datasets (COVID-19 and Pneumonia) have been used. After the training phase where hyperparameters of the models have been tuned for best accuracy, a comparison study of these different models is conducted. The EfficientNetB0 model has achieved the highest test accuracy around 96.50% for Pneumonia X-ray images. The same work has been applied to the COVID-19 CT scans dataset, and the highest accuracy is achieved with the ResNet-50 network (99.5%). Therefore, these two models will be used for rapid diagnosis and assist radiologists in the detection process precisely. © 2022 IEEE.

ML and DL Architectures Comparisons for the Classification of COVID-19 Using Chest X-Ray Images

Pandemic COVID-19 ranked as one of the world’s worst pandemics ever witnessed in history. It has affected every country by spreading this disease with an increase in mortality at alarming rates despite the technologically advanced era of medicine. AI/ML is one of the strong wings in the medical field so while fighting the battle to control and diagnose the best medicine for the outbreak COVID-19 disease. Automated and AI-based prediction models for COVID-19 are the main attraction for the scientist hoping to support some good medical decisions at this difficult time. However, mostly classical image processing methods have been implemented to detect COVID-19 cases resultant in low accuracy. In this chapter, multiple naïve machine and deep learning architectures are implied to evaluate the performance of the models for the classification of COVID-19 using a dataset comprising of chest x-ray images of, i.e., COVID-19 patients and normal (non-infected) individuals. The analysis looks at three machine learning architectures including Logistic Regression, Decision Tree (DT) Classifier, and support vector machine (SVM), and four deep learning architectures, namely: Convolutional neural networks (CNNs), VGG19, ResNet50, and AlexNet. The dataset has been divided into train, test and validation set and the same data have been used for the training, testing, and validation of all the architectures. The result analysis shows that AlexNet provides the best performance out of all the architectures. It can be seen that the AlexNet model achieved 98.05% accuracy (ACC), 97.40% recall, 98.03% F1-score, 98.68% precision, and 98.05% area under the curve (AUC) score. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Deep Learning-Based Trend Analysis on Indian Stock Market in COVID-19 Pandemic Scenario and Forecasting Future Financial Drift

This present study has used the long-short-term memory (LSTM) network-based deep learning architecture to analyze the influence of the current widespread COVID-19 on the Indian stock market. The major contribution of this work is as follows: (1) Designing LSTM-based deep neural network is used to study the effect of the COVID-19 outbreak and Lockdown on the Indian stock exchange (Nifty 50), and (2) designing a prediction model to capture the effect of various COVID-19 waves in India on Indian Stock exchange. The outcomes of the analysis show that the increase in daily new confirmed cases, recovered cases, and death cases have a significant adverse impact on the trend of the stock market. Moreover, the results of the work have also analyzed the impact of government policy such as ‘lockdown city’ with a reaction to increased Pandemic cases. This work is briefly summarized as follow: (1) LSTM-based deep neural network is used for this study to analyze the effect of the COVID-19 outbreak on the Indian stock exchange. (2) The Indian Stock exchange affected by the COVID-19 pandemic has been studied. Here, the analysis is based on the impact of COVID-19 including the effect of lockdown. (3) A prediction model has been proposed for the study of the behavior of the Indian stock index (Nifty 50) during the COVID-19 pandemic. (4) Comparison of the efficacy of the suggested approach with other existing baseline regression models. © 2022, The Institution of Engineers (India).

Comparison of deep learning architectures for COVID-19 diagnosis using chest X-ray images

The implementation of architectures based on artificial intelligence and deep learning to support COVID-19 diagnosis has great potential. However, especially in architectures designed at the beginning of the pandemic, they use different databases that do not contain a good amount of chest X-ray images of COVID-19 patients. The present work presents a comparison of three deep learning architectures (COVID-Net, CovXNet and DarkCovidNet) for COVID-19 diagnosis using chest Xray images. First, the architectures were implemented with the databases provided by the authors, to compare the results with those presented in the state of the art. Then, a new database with more than 9000 chest X-ray images of patients with COVID-19, pneumonia and healthy (3305 images for each class), was elaborated using databases from four different institutions around the world. Finally, the database was used to evaluate the original architectures, retrain them and, finally, evaluate the performance of the retrained architectures and compare results. It was identified that the architectures with the best performance and generalizability are DarkCovidNet and CovXNet with a support vector machine stacking algorithm, with an accuracy of 94.04% and 92.02% respectively, for the test data of the new database. 2022 SPIE. © 2022 SPIE. All rights reserved.

Masked Deep Face Recognition using ArcFace and Ensemble Learning

With advancements in technology, human biometrics, especially face recognition, has witnessed a tremendous increase in usage, prominently in the field of security. Face recognition proves to be a convenient, coherent, and efficient way to identify a person uniquely. Face recognition systems are trained generally on human faces sans masks. With the ubiquitous use of face masks due to the ongoing COVID-19 pandemic, face recognition becomes a daunting challenge. In this paper, the deep learning architectures, namely MobileNetV2, DenseNet201, ResNet50V2, and VGG16 with the ArcFace loss function, were trained on the newly created dataset called "MaFaR", which consists of a mixture of masked and unmasked images of 75 distinct individuals, and ensemble learning techniques have been used to improve the performance, achieving an accuracy 93.65%. © 2021 IEEE.

CompDNet-512: Hybrid Deep Learning Architecture for Prediction of COVID-19

With a growing appearance of enormous cases of COVID-19 in people, computational solutions founded on deep learning can play a huge role in performing automated prediction of the corona virus disease. In this article a hybrid deep convolution neural network architecture named as CompDNet-512 is implemented to detect the presence of COVID disease in the chest radiographs of patients. Previously the researchers had only used deep transfer learning technique for train neural network model to detect the syndrome. They have succeeded to some extent, but none were able to developed generalized model which can be predicting various abnormalities present in clinical images. Herein, our model can be applied to range of medical application for abnormalities prediction. The proposed model is a combination of three techniques that is, lossless compression, dense network and progressive resizing, which when applied in a pipeline to the chest X-ray dataset consisting of positive corona virus patient studies and normal studies, outperformed the existing models in detecting COVID-19 and shown an accuracy of 98.3 %. © 2021 IEEE.

Improved Transfer Learning Architecture to Classify Covid-19 Affected Chest X-Rays using Noisy Student Pre-training

During this pandemic situation Chest, X-rays may play a vital role in the diagnosis of COVID-19. The shortage of labeled medical images becomes this diagnosis more challenging. We established an efficient transfer learning method for classifying COVID-19 chest X-rays. We also gathered images from the publicly available chest x-ray datasets. We built an effective classifier for our pre-trained model with the latest state-of-the-art activation function Mish, Batch Normalization, and Dropout Layer. Our classifier efficiently detects Covid-19, Pneumonia, and normal case by differentiating inflammation in the lungs. Furthermore, we used the recent state-of-the-art idea of semi-supervised Noisy Student Training in our EfficientNet Architecture model and compared it with other benchmark models. We found that our proposed model performs well by using benchmark evaluation metrics(accuracy, F1 score, and ROC(AUC)) and our ROC(AUC) score of 98% overall. After that, we visually interpreted our training model with a saliency map to make it more understandable. Contribution: We contributed an improved three-class classifier part using the new state-of-the-art activation function Mish for the EfficientNet Transfer Learning model and improved the accuracy of Covid-19 Classification through Semi-Supervised Noisy Student training. © 2021 IEEE

Efficient Deep Learning Architecture for Facemask Detection

Since COVID-19 pandemic all over the world, wearing mask become mandatory in public space. In order to enforce the new normal behaviour, regulators need to ensure every person is wearing a mask in order to avoid the spreading of the viruses. Before the pandemic, there were a number of closed-circuit televisions (CCTV) installed in public space for security purposes. The research aims to identify algorithms with acceptable classification quality and at the same time low computing complexity. This research aims to identify the algorithm to identify Face Mask. This research uses two public datasets, the first dataset has two labels with and without mask, and the second dataset consists of three labels (facemask, improper use of facemask and proper use of facemask). This research examines some well known deep learning architectures which are VGG, MobileNet, MobileNetV2, EfficientNet B0, NasNetMobile. A modification of VGG to reduce the number of parameters is also examined. An evaluation of the classification performance and execution time in the testing set is carried out on binary and three class dataset. According to the experiments, Modified VGG with 7 layers with 1.6 Million parameters consistently achieves fastest performance. The classification performance for three class dataset is achieved by Modified VGG (CVGG-7) at 100% while for the binary facemask classification is achieved by MobileNetV2 at 99.7% © 2021 IEEE

COVID-CBR: A Deep Learning Architecture Featuring Case-Based Reasoning for Classification of COVID-19 from Chest X-Ray Images

Background and Objectives: This study aims to assist rapid accurate diagnosis of COVID-19 based on chest x-ray (CXR) images to provide supplementary information, leading to screening program for early detection of COVID-19 based on CXR images by developing an interpretable, robust and performant AI system. Methods: A case-based reasoning approach built upon autoencoder deep learning architecture is applied to classify COVID-19 from other non-COVID-19 as well as normal subjects from chest x-ray images. The system integrates the interpretation and decision-making together by producing a set of profiles that in appearance resemble the training samples and hence explain the outcome of classifications. Three classes are studied, which are COVID-19 (n=250), other non-COVID-19 diseases (NCD) (n=384), including TB and ARDS, and normal (n=327). Results: This COVID-CBR system sustains the average sensitivity and specificity of 93.1±3.58% and 96.1±4.10% respectively for classification of these three classes. In comparison with the current state of the art, including COVID-Net, VGG-16 and other explainable AI systems, the developed COVID-CBR system appears to perform similar or better when classifying multi-class categories. Conclusion: This paper presents a case-based reasoning deep learning system for detection of COVID19 from chest x-ray images. Comparison with several state of the art systems is conducted. Although the improvement tends to be marginal, especially for VGG-16, the novelty of this work manifests its interpretable feature building upon case-based reasoning, leading to revealing this viral insight and hence ascertaining more effective treatment and drugs while maintaining being transparent. Furthermore, different from several other current explainable networks that highlight key regions or the points of an input that activate the network, i.e. heat maps, this work is constructed upon whole training images, i.e. case-based, whereby each training image belongs to one of the case clusters. © 2021 IEEE.