Hybrid deep neural network for automatic detection of COVID-19 using chest x-ray images

The 2019 coronavirus (COVID-19), started in China, spreads rapidly around the entire world. In automated medical imagery diagnostic technique, due to presence of noise in medical images and use of single pre-trained model on low quality images, the existing deep network models cannot provide the optimal results with better accuracy. Hence, hybrid deep learning model of Xception model & Resnet50V2 model is proposed in this paper. This study suggests classifying X-ray images into three categories namely, normal, bacterial/viral infections and Covid positive. It utilizes CLAHE & BM3D techniques to improve visual clarity and reduce noise. Transfer learning method with variety of pre-trained models such as ResNet-50, Inception V3, VGG-16, VGG-19, ResNet50V2, and Xception are used for better feature extraction and Chest X-ray image classification. The overfitting issue were resolved using K-fold cross validation. The proposed hybrid deep learning model results high accuracy of 97.8% which is better than existing techniques.

AI-based wavelet and stacked deep learning architecture for detecting coronavirus (COVID-19) from chest X-ray images.

A novel coronavirus (COVID-19), belonging to a family of severe acute respiratory syndrome coronavirus 2 (SARs-CoV-2), was identified in Wuhan city, Hubei, China, in November 2019. The disease had already infected more than 681.529665 million people as of March 13, 2023. Hence, early detection and diagnosis of COVID-19 are essential. For this purpose, radiologists use medical images such as X-ray and computed tomography (CT) images for the diagnosis of COVID-19. It is very difficult for researchers to help radiologists to do automatic diagnoses by using traditional image processing methods. Therefore, a novel artificial intelligence (AI)-based deep learning model to detect COVID-19 from chest X-ray images is proposed. The proposed work uses a wavelet and stacked deep learning architecture (ResNet50, VGG19, Xception, and DarkNet19) named WavStaCovNet-19 to detect COVID-19 from chest X-ray images automatically. The proposed work has been tested on two publicly available datasets and achieved an accuracy of 94.24% and 96.10% on 4 classes and 3 classes, respectively. From the experimental results, we believe that the proposed work can surely be useful in the healthcare domain to detect COVID-19 with less time and cost, and with higher accuracy.

An Integrated Framework for COVID-19 Classification Based on Ensembles of Deep Features and Entropy Coded GLEO Feature Selection

COVID-19 is a challenging worldwide pandemic disease nowadays that spreads from person to person in a very fast manner. It is necessary to develop an automated technique for COVID-19 identification. This work investigates a new framework that predicts COVID-19 based on X-ray images. The suggested methodology contains core phases as preprocessing, feature extraction, selection and categorization. The Guided and 2D Gaussian filters are utilized for image improvement as a preprocessing phase. The outcome is then passed to 2D-superpixel method for region of interest (ROI). The pre-trained models such as Darknet-53 and Densenet-201 are then applied for features extraction from the segmented images. The entropy coded GLEO features selection is based on the extracted and selected features, and ensemble serially to produce a single feature vector. The single vector is finally supplied as an input to the variations of the SVM classifier for the categorization of the normal/abnormal (COVID-19) X-rays images. The presented approach is evaluated with different measures known as accuracy, recall, F1 Score, and precision. The integrated framework for the proposed system achieves the acceptable accuracies on the SVM Classifiers, which authenticate the proposed approach's effectiveness. © World Scientific Publishing Company.

Trust Factors in the Social Figuration of Online Drug Trafficking: A Qualitative Content Analysis on a Darknet Market

The rise in illicit drug trafficking on darknet markets (DNMs) was boosted by those restrictions imposed due to the COVID-19 pandemic. This study aims to put this trend into context by exploring the characteristics of vendors' services and reputations and understand how products are advertised and what customers tend to value. Qualitative content analysis was conducted on a sample (n = 100) randomly selected from 6,357 product descriptions and a sample (n = 500) randomly selected from 34,619 reviews. Both samples are from products found in the drug category of the darknet market Dark0de Reborn. On the supply side, vendors tended to provide basic information on the drugs, a mention of their high quality, the speed and stealth of delivery, their availability for responding to messages, the effects of the drugs, and sometimes even instructions for use. Regarding the demand side, customers usually praised the quality of the product, mentioned the speed and stealth-secure packaging of delivery as essentials, and expressed only a small number of issues. These results support the applicability of Norbert Elias' social figuration theory in which the interdependencies of the actors are fueled by trust. This theoretical frame sheds light on the social value of the community of DNMs. Furthermore, the findings formulate a robust hypothesis for future research about the previously undervalued role of delivery providers. © The Author(s) 2023.

Profiling the vendors of COVID-19 related product on the Darknet: An observational study.

Background: In a time of unprecedented global change, the COVID-19 pandemic has led to a surge in demand of COVID-19 vaccines and related certifications. Mainly due to supply shortages, counterfeit vaccines, fake documentation, and alleged cures to illegal portfolios, have been offered on darkweb marketplaces (DWMs) with important public health consequences. We aimed to profile key DWMs and vendors by presenting some in-depth case studies. Methods: A non-systematic search for COVID-19 products was performed across 118 DWMs. Levels of activity, credibility, content, COVID-19 product listings, privacy protocols were among the features retrieved. Open web fora and other open web sources were also considered for further analysis of both functional and non functional DWMs. Collected data refers to the period between January 2020 and October 2021. Results: A total of 42 relevant listings sold by 24 vendors across eight DWMs were identified. Four of these markets were active and well-established at the time of the study with good levels of credibility. COVID-19 products were listed alongside other marketplace content. Vendors had a trusted profile, communicated in English language and accepted payments in cryptocurrencies (Monero or Bitcoin). Their geographical location included the USA, Asia and Europe. While COVID-19 related goods were mostly available for regional supply, other listings were also shipped worldwide. Interpretation: Findings emerging from this study rise important questions about the health safety of certain DWMs activities and encourage the development of targeted interventions to overcome such new and rapidly expanding public health threats. Funding: CovSaf, National Research centre on Privacy, Harm Reduction and Adversarial Influence Online (REPHRAIN), Commonwealth Fund.

Multiple face mask wearer detection based on YOLOv3 approach

The coronavirus disease 2019 (COVID-19) is a highly infectious disease caused by the SARS-CoV-2 coronavirus. In breaking the transmission chain of SARS-CoV-2, the government has made it compulsory for the people to wear a mask in public places to prevent COVID-19 transmission. Hence, an automated face mask detection is crucial to facilitate the monitoring process in ensuring people to wear a face mask in public. This project aims to develop an automated face and face mask detection for multiple people by applying deep learning-based object detection algorithm you only look once version 3 (YOLOv3). YOLOv3 object detection algorithm was concatenated with different backbones including ResNet-50 and Darknet-53 to develop the face and face mask detection model. Datasets were collected from online resources including Kaggle and Github and the images were filtered and labelled accordingly. The models were trained on 4393 images and evaluated based on precision, recall, mean average precision and the detection time. In conclusion, DarkNet53_YOLOv3 was chosen as the better model compared to ResNet50_YOLOv3 model with its good performance on accuracy with a mAP of 95.94% and a fast detection speed with a detection time of 50 seconds on 776 images.

Optimization of Darknet-19 model for the early diagnosis of Covid-19 based on CXR images

Even after the pandemic, Covid-19 is still threatening lives and causing devastating losses to businesses. Thus, early Covid-19 diagnosis prevents the further spread of this epidemic and helps to quickly treat affected patients of coronavirus. Unlike Polymerase Chain Reaction (PCR) test, screening techniques based on Chest X-Ray (CXR) scan detect Covid-19 early even before the beginning of Covid-19 symptoms, also they are more effective and have higher detection rates. However, the CXR images suffer of some low visual quality which makes the CXR-based screening method time consuming due to the small number of radiologists. Therefore, in this paper, we propose an optimization technique for a recently developed intelligent classification system (Darknet-19) that assists radiologists in diagnosing coronavirus for patients using CXR images. In particular, our proposed optimization scheme consists first in a close-up dataset cleaning followed by advanced image enhancement as a preprocessing phase to the Darknet-19 classification model. Our experiments show that our proposed preprocessing optimization scheme improved the performance of the Darknet-19 model to reach an accuracy of 99.2%. © 2022 IEEE.

Multiple face mask wearer detection based on YOLOv3 approach

The coronavirus disease 2019 (COVID-19) is a highly infectious disease caused by the SARS-CoV-2 coronavirus. In breaking the transmission chain of SARS-CoV-2, the government has made it compulsory for the people to wear a mask in public places to prevent COVID-19 transmission. Hence, an automated face mask detection is crucial to facilitate the monitoring process in ensuring people to wear a face mask in public. This project aims to develop an automated face and face mask detection for multiple people by applying deep learning-based object detection algorithm you only look once version 3 (YOLOv3). YOLOv3 object detection algorithm was concatenated with different backbones including ResNet-50 and Darknet-53 to develop the face and face mask detection model. Datasets were collected from online resources including Kaggle and Github and the images were filtered and labelled accordingly. The models were trained on 4393 images and evaluated based on precision, recall, mean average precision and the detection time. In conclusion, DarkNet53_YOLOv3 was chosen as the better model compared to ResNet50_YOLOv3 model with its good performance on accuracy with a mAP of 95.94% and a fast detection speed with a detection time of 50 seconds on 776 images.

Recognition of violent actions on streets in urban spaces using Machine Learning in the context of the Covid-19 pandemic

Currently, recognition systems based on Artificial Intelligence and Computer Vision have enabled various applications in fields such as Medicine, Industrial Engineering, and in an emerging way in the field of Public Safety as a useful and necessary tool in smart cities that favours the control, management and prevention of criminal acts. Given that violence is a very frequent social problem in Latin American countries. A pilot case has been proposed in the city of Iquitos, Peru, with a tool generated to recognise violent actions from a video or image captured from a mobile phone. This work proposes the application of a mobile tool that facilitates the recognition of high-frequency violent actions on public roads. A bank of 500 images has been generated for each class of violent action prioritised in this work, then a manual labelling tool called "LabelImg" has been used with the extraction of FPS from videos, and the convolutional neural network algorithm YOLO v3 has been used with the Darknet variant. The results of the experiment achieved an accuracy of 94% in the detection of 4 violent actions: punching, kicking, grappling and strangling.

A Crowd Alert System for Pandemic Control using Yolov4

The Covid-19 pandemic in the late 2019 caused the world to shut down. Even though it is recommended to reduce overcrowding it still cannot be avoided. This can cause the pandemic to spread even more, especially since offices, schools and colleges are slowly reopening. With image detection making huge breakthroughs in the last decade, modern image detection technologies can now be combined with the current hardware to combat problems like overcrowding, which massively spreads the pandemic. In this paper, the YOLO v4 algorithm has been used, which greatly speeds up the process of detection and improves the overall accuracy of the system. © 2022 IEEE.

Stacked Dark COVID-Net: A Multi-class Multi-label Classification Approach for Diagnosing COVID-19 Using Chest X-Ray Images

Most challenging yet, the need of the hour is accurate diagnosis of COVID-19, as the Coronavirus cases are increasing drastically day-by-day. Ceaseless efforts by the researchers and innovators have led to the development of several diagnostic models based on Deep Learning for effective diagnosis of COVID-19. However, the Deep Learning techniques that have been developed so far, fail to address major challenges such as overfitting, stability, computation overhead due to the usage of the massive volume of parameters and problems associated with the multi-class classification. Also in the medical perspective, researchers often suffer to identify the infinitesimal difference that exists in the radiographic images among the several lung diseases which makes the decision-making process difficult. Thus, to curb the crisis and to provide promising solutions & expertise for accurate diagnosis, this paper presents a novel lightweight multi-class multi-label COVID-19 detection model to assist physicians with greater ease to fight against this pandemic situation. Radiographic images are pre-processed using Contrast Limited Adaptive Histogram Equalization (CLAHE) and classified using novel Stacked Dark COVID-Net. The proposed model is validated using chest X-ray images and the results confirm the efficacy of the proposed model in terms of classification accuracy, sensitivity, specificity and stability. © 2022, Springer Nature Switzerland AG.

Covid-19 Classification and Detection Model using Deep Learning

One of the deadly diseases in recent years is covid19 which is affecting the lives of peoples. Also leading to severe adverse problems and death. Prevention is done using early diagnosis and medication which in turn helps in early detection of the disease. The basic aim of the paper is to identify and further classify the patients using the chest x-rays. From scratch the Convolutional Neural Network is diagnosed producing a very high accurate and optimum results. In recent years, researchers found out that in the radiological images such as like x-rays, the traces of covid-19 can be found. In few areas, a good accuracy of the covid-19 detection cannot be achieved due to lack of the people who test so the artificial intelligence is combined with the radiological image. In machine learning the models used are deep learning by automatizing the actions and making it certain by swift, skillful and proficient outcome produced by the chest images provided by the patients. There are several layers like convolutional layer, max pooling layer etc. which are initiated and are used with aid of ReLU activation function. These images given as inputs are also classified accordingly. There is a sequence of neurons being given as input to the active dense layer and there is a result to the input by a sigmoidal function. There is a rise in efficiency because the models are trained and there is a decline of loss at the same time. If there is a model where fitting is done earlier to the overfitting and is restricted from implementing in the data augmentation. There is a better and efficient involvement of suggestions to models of deep learning. Further there is a classification of chest images for identifying and analyzing covid19. So, to check the Covid detection, the images are used as raw. In this paper a model is proposed to have good accuracy in the classification between Covid and normal and further it can be classified into three categories like Covid, pneumonia, normal. There is a 98.08% for the first one and 87.02% for the second one. By introducing 17 convolutional layers and using the Darknet model used for classifying you only look once (YOLO) for the live identification of the objects and multiple layers of filters are used. In the model there is an initial screening. © 2022 IEEE.

FaceMask: A New Image Dataset for the Automated Identification of People Wearing Masks in the Wild.

The rapid spread of the COVID-19 pandemic, in early 2020, has radically changed the lives of people. In our daily routine, the use of a face (surgical) mask is necessary, especially in public places, to prevent the spread of this disease. Furthermore, in crowded indoor areas, the automated recognition of people wearing a mask is a requisite for the assurance of public health. In this direction, image processing techniques, in combination with deep learning, provide effective ways to deal with this problem. However, it is a common phenomenon that well-established datasets containing images of people wearing masks are not publicly available. To overcome this obstacle and to assist the research progress in this field, we present a publicly available annotated image database containing images of people with and without a mask on their faces, in different environments and situations. Moreover, we tested the performance of deep learning detectors in images and videos on this dataset. The training and the evaluation were performed on different versions of the YOLO network using Darknet, which is a state-of-the-art real-time object detection system. Finally, different experiments and evaluations were carried out for each version of YOLO, and the results for each detector are presented.

Detection of Face Mask During Pandemic of Covid-19

The global pandemic caused due to COVID-19 has badly affected the entire world in all the different sectors. With the increasing number of cases of coronavirus, it becomes very necessary for the people to wear a mask, maintain social distancing, and maintain proper sanitization of themselves as well as their surroundings. However, some people are not serious about wearing a mask. Thus, it is necessary to develop a system that can detect the people violating this rule of not wearing a mask. Our system gives provision to detect the people who have not worn the mask appropriately or have not at all worn the mask. Face detection is one of the major problems, to overcome this problem various algorithms are being developed using different architectures. The convolutional architecture has made it possible. Our motive is to design a binary classifier that can detect any face in front of the frame and produce accurate output. Our model has shown very good results in detecting the faces without a mask as well as it is also able to detect the multiple facial mask images in a single frame. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.