Comparative Study of VGG-13, AlexNet, MobileNet and Modified-DarkCovidNet for Chest X-Ray Classification

Convolutional neural network (CNN) is the most widely used structure-building technique for deep learning models. In order to classify chest x-ray pictures, this study examines a number of models, including VGG-13, AlexN ct, MobileNet, and Modified-DarkCovidNet, using both segmented image datasets and regular image datasets. Four types of chest X- images: normal chest image, Covid-19, pneumonia, and tuberculosis are used for classification. The experimental results demonstrate that the VGG offers the highest accuracy for segmented pictures and Modified Dark CovidN et performs best for multi class classification on segmented images. © 2023 Bharati Vidyapeeth, New Delhi.

A COVID-19 Detection Model Based on Convolutional Neural Network and Residual Learning

A model that can obtain rapid and accurate detection of coronavirus disease 2019 (COVID-19) plays a significant role in treating and preventing the spread of disease transmission. However, designing such a model that can balance the detection accuracy and weight parameters of memory well to deploy a mobile device is challenging. Taking this point into account, this paper fuses the convolutional neural network and residual learning operations to build a multi-class classification model, which improves COVID-19 pneumonia detection performance and keeps a trade-off between the weight parameters and accuracy. The convolutional neural network can extract the COVID-19 feature information by repeated convolutional operations. The residual learning operations alleviate the gradient problems caused by stacking convolutional layers and enhance the ability of feature extraction. The ability further enables the proposed model to acquire effective feature information at a low cost, which can make our model keep small weight parameters. Extensive validation and comparison with other models of COVID-19 pneumonia detection on the well-known COVIDx dataset show that (1) the sensitivity of COVID-19 pneumonia detection is improved from 88.2% (non-COVID-19) and 77.5% (COVID-19) to 95.3% (non-COVID-19) and 96.5% (COVID-19), respectively. The positive predictive value is also respectively increased from 72.8% (non-COVID-19) and 89.0% (COVID-19) to 88.8% (non-COVID-19) and 95.1% (COVID-19). (2) Compared with the weight parameters of the COVIDNet-small network, the value of the proposed model is 13 M, which is slightly higher than that (11.37 M) of the COVIDNet-small network. But, the corresponding accuracy is improved from 85.2% to 93.0%. The above results illustrate the proposed model can gain an efficient balance between accuracy and weight parameters. © 2023 Tech Science Press. All rights reserved.

Multi-class classification of COVID-19 documents using machine learning algorithms.

In most biomedical research paper corpus, document classification is a crucial task. Even due to the global epidemic, it is a crucial task for researchers across a variety of fields to figure out the relevant scientific research papers accurately and quickly from a flood of biomedical research papers. It can also assist learners or researchers in assigning a research paper to an appropriate category and also help to find the relevant research paper within a very short time. A biomedical document classifier needs to be designed differently to go beyond a "general" text classifier because it's not dependent only on the text itself (i.e. on titles and abstracts) but can also utilize other information like entities extracted using some medical taxonomies or bibliometric data. The main objective of this research was to find out the type of information or features and representation method creates influence the biomedical document classification task. For this reason, we run several experiments on conventional text classification methods with different kinds of features extracted from the titles, abstracts, and bibliometric data. These procedures include data cleaning, feature engineering, and multi-class classification. Eleven different variants of input data tables were created and analyzed using ten machine learning algorithms. We also evaluate the data efficiency and interpretability of these models as essential features of any biomedical research paper classification system for handling specifically the COVID-19 related health crisis. Our major findings are that TF-IDF representations outperform the entity extraction methods and the abstract itself provides sufficient information for correct classification. Out of the used machine learning algorithms, the best performance over various forms of document representation was achieved by Random Forest and Neural Network (BERT). Our results lead to a concrete guideline for practitioners on biomedical document classification.

A Deep Learning Network for Detecting COVID-19 From Chest X-Ray Images

Rapid and accurate detection of COVID-19 plays a significant role in treating and preventing the spread of disease transmission. To this end, we fuse the convolutional neural network and residual learning operation to build a multi-class classification model, which has a few parameters and is more conducive to be deployed on a mobile device. Extensive experiments show that our proposed model gains competitive performance. Compared with the COVIDNet-small network, the sensitivity of COVID-19 pneumonia detection is improved from 88.2% (non-COVID-19) and 77.5% (COVID-19) to 95.3% (non-COVID-19) and 96.5% (COVID-19). Alternatively, the Positive predictive value is increased from 72.8% (non-COVID-19) and 89.0% (COVID-19) to 88.8% (non-COVID-19) and 95.1 % (COVID-19). The accuracy is also improved from 85.2 % to 93.0 %, which is very close to the value (93.3 %) of the COVIDNet-large network. But, the weight parameters (13M) of the proposed model are slightly higher than that (11.37M) of the COVIDNet-small network, but only about one-third of that (37.85M) of the COVIDNet-large network. © 2022 IEEE.

Diagnosis of COVID-19 from CT Images and Respiratory Sound Signals Using Deep Learning Strategies

COVID-19 has been a major issue among various countries, and it has already affected millions of people across the world and caused nearly 4 million deaths. Various precautionary measures should be taken to bring the cases under control, and the easiest way for diagnosing the diseases should also be identified. An accurate analysis of CT has to be done for the treatment of COVID-19 infection, and this process is complex and it needs much attention from the specialist. It is also proved that the covid infection can be identified with the breathing sounds of the patient. A new framework was proposed for diagnosing COVID-19 using CT images and breathing sounds. The entire network is designed to predict the class as normal, COVID-19, bacterial pneumonia, and viral pneumonia using the multiclass classification network MLP. The proposed framework has two modules: (i) respiratory sound analysis framework and (ii) CT image analysis framework. These modules exhibit the workflow for data gathering, data preprocessing, and the development of the deep learning model (deep CNN + MLP). In respiratory sound analysis framework, the gathered audio signals are converted to spectrogram video using FFT analyzer. Features like MFCCs, ZCR, log energies, and Kurtosis are needed to be extracted for identifying dry/wet coughs, variability present in the signal, prevalence of higher amplitudes, and for increasing the performance in audio classification. All these features are extracted with the deep CNN architecture with the series of convolution, pooling, and ReLU (rectified linear unit) layers. Finally, the classification is done with a multilayer perceptron (MLP) classifier. In parallel to this, the diagnosis of the disease is improved by analyzing the CT images. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

MTMC-AUR2CNet: Multi-textural multi-class attention recurrent residual convolutional neural network for COVID-19 classification using chest X-ray images.

Coronavirus disease (COVID-19) has infected over 603 million confirmed cases as of September 2022, and its rapid spread has raised concerns worldwide. More than 6.4 million fatalities in confirmed patients have been reported. According to reports, the COVID-19 virus causes lung damage and rapidly mutates before the patient receives any diagnosis-specific medicine. Daily increasing COVID-19 cases and the limited number of diagnosis tool kits encourage the use of deep learning (DL) models to assist health care practitioners using chest X-ray (CXR) images. The CXR is a low radiation radiography tool available in hospitals to diagnose COVID-19 and combat this spread. We propose a Multi-Textural Multi-Class (MTMC) UNet-based Recurrent Residual Convolutional Neural Network (MTMC-UR2CNet) and MTMC-UR2CNet with attention mechanism (MTMC-AUR2CNet) for multi-class lung lobe segmentation of CXR images. The lung lobe segmentation output of MTMC-UR2CNet and MTMC-AUR2CNet are mapped individually with their input CXRs to generate the region of interest (ROI). The multi-textural features are extracted from the ROI of each proposed MTMC network. The extracted multi-textural features from ROI are fused and are trained to the Whale optimization algorithm (WOA) based DeepCNN classifier on classifying the CXR images into normal (healthy), COVID-19, viral pneumonia, and lung opacity. The experimental result shows that the MTMC-AUR2CNet has superior performance in multi-class lung lobe segmentation of CXR images with an accuracy of 99.47%, followed by MTMC-UR2CNet with an accuracy of 98.39%. Also, MTMC-AUR2CNet improves the multi-textural multi-class classification accuracy of the WOA-based DeepCNN classifier to 97.60% compared to MTMC-UR2CNet.

A multi-class classification framework for disease screening and disease diagnosis of COVID-19 from chest X-ray images.

To accurately diagnose multiple lung diseases from chest X-rays, the critical aspect is to identify lung diseases with high sensitivity and specificity. This study proposed a novel multi-class classification framework that minimises either false positives or false negatives that is useful in computer aided diagnosis or computer aided detection respectively. To minimise false positives or false negatives, we generated respective stacked ensemble from pre-trained models and fully connected layers using selection metric and systematic method. The diversity of base classifiers was based on diverse set of false positives or false negatives generated. The proposed multi-class framework was evaluated on two chest X-ray datasets, and the performance was compared with the existing models and base classifiers. Moreover, we used LIME (Local Interpretable Model-agnostic Explanations) to locate the regions focused by the multi-class classification framework.

Automated multi-class classification of lung diseases from CXR-images using pre-trained convolutional neural networks

According to the World Health Organization (WHO), Pneumonia, COVID-19, Tuberculosis, and Pneumothorax are the leading death causes in the world. Coughing, sneezing, fever, and shortness of breath are common symptoms. To detect them, several tests such as molecular tests (RT-PCR), antigen tests, Monteux tuberculin skin test (TST), and complete blood count (CBC) tests are needed. But these are time-consuming processes and have an error rate of 20% and a sensitivity of 80%. So, radiographic tests like computed tomography (CT) and an X-ray are used to identify lung diseases with the help of a physician. But the risk of these lung diseases' diagnoses overlapping features in chest radiographs is a worry with chest X-ray or CT-scan images. To accurately classify one of four diseases with healthy images demands the automation of such a process. There is no method for identifying and categorizing these lung diseases. As a result, we were encouraged to use eight pre-trained convolutional neural networks (CNN) to classify various lung diseases into COVID-19, pneumonia, pneumothorax, tuberculosis, and normal images from the chest X-ray image dataset. This classification process is divided into two phases. In the training phase, the CNNs are trained with the Adam optimizer with a maximum epoch of 30 and a mini-batch size of 32. In the classification phase, these trained networks are used to classify diseases. In both phases, the dataset is color preprocessed, resized, and undergoes data augmentation. For this, we used eight pre-trained CNNs: Alexnet,Darknet-19, Darknet-53, Densenet-201, Googlenet, InceptionResnetV2, MobilenetV2, and Resnet-18. Finally, we concluded that the best one to classify these diseases. Among these networks, Densenet-201, achieved the highest accuracy of 97.2%, 94.28% of sensitivity, and 97.92% of specificity for K=5. For K=10, it achieved 97.49% of accuracy, 95.57% of sensitivity, and 97.96% of specificity and for K=15, achieved 97.01% of accuracy, 96.71% of sensitivity, and 97.17% of specificity. Hence, the proposed method outperformed the existing state-of-the-art methods. Finally, our proposed research could aid clinicians in making quick conclusions concerning lung problems so that treatment can proceed. © 2022 Elsevier Ltd

Predicting the Pre-release Success of a Web Series' Season

With the onset of COVID-19, OTT platforms have become popular. With this added popularity, many production companies tend to release their content on platforms like Netflix, Amazon Prime, Disney + Hotstar, etc. Through this research work, we tend to check the impact of different classical factors like genre, age certification, time of release, the platform of release, etc. as well as various social factors like the sentiment of the audience around the trailer, songs, and success of the previous season in predicting the success of the pre-release season of an English web series by creating our dataset. This will enhance the business strategies that production houses can use to improve their profits. We have trained different classification models like Decision Tree, Support Vector Machine, Multinomial Naive Bayes, and hyper tuned the parameters of Random Forest and K-Nearest Neighbours. We have also created a Multi-Layer Perceptron model and an ensemble classifier and trained them on our dataset. The best accuracy of 76.66% was achieved by the Hard Voting type ensemble classifier. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Sentiment Analysis Using CatBoost Algorithm on COVID-19 Tweets

Sentimental analysis is a study of emotions or analysis of text as an approach to machine learning. It is the most well-known message characterization device that investigates an approaching message and tells whether the fundamental feeling is positive or negative. Sentimental analysis is best when utilized as an instrument to resolve the predominant difficulties while solving a problem. Our main objective is to identify the emotional tone and classify the tweets on COVID-19 data. This paper represents an approach that is evaluated using an algorithm namely—CatBoost and measures the effectiveness of the model. We have performed a comparative study on various machine learning algorithms and illustrated the performance metrics using a Bar-graph. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Analysis of Covid-19 Literature Evolution via NLP and Machine Learning

The ongoing pandemic has impacted the world order. It has changed people's perceptions and their behaviors towards the seemingly never-ending pandemic of coronavirus. A huge amount of literature is available on SARS-COV2. Research on Covid-19 continues to expand in terms of the involved risk factors, disease prediction, diagnostics, pharmaceutical intervention, disease transmission, vaccine creation, impacts on the economy, education, healthcare, and so forth. This study aims to analyze the current literature trend of domain topics most affected by the pandemic and the regions most impacted. The data is collected from various Journals and the COVID-WHO database from the time-span of Jan 2020 - Sep 2021. For binary classification, the Covid-19 specific literature is filtered using LSTM and several machine learning models. Further Covid-related information can be extracted from Covid-related publications on vaccination and prediction of such cases in various regions. © 2022 IEEE.

Predicting the Pre-release Success of a Web Series' Season

With the onset of COVID-19, OTT platforms have become popular. With this added popularity, many production companies tend to release their content on platforms like Netflix, Amazon Prime, Disney + Hotstar, etc. Through this research work, we tend to check the impact of different classical factors like genre, age certification, time of release, the platform of release, etc. as well as various social factors like the sentiment of the audience around the trailer, songs, and success of the previous season in predicting the success of the pre-release season of an English web series by creating our dataset. This will enhance the business strategies that production houses can use to improve their profits. We have trained different classification models like Decision Tree, Support Vector Machine, Multinomial Naive Bayes, and hyper tuned the parameters of Random Forest and K-Nearest Neighbours. We have also created a Multi-Layer Perceptron model and an ensemble classifier and trained them on our dataset. The best accuracy of 76.66% was achieved by the Hard Voting type ensemble classifier. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Class-Aware Attention Network for infectious keratitis diagnosis using corneal photographs.

Infectious keratitis is one of the common ophthalmic diseases and also one of the main blinding eye diseases in China, hence rapid and accurate diagnosis and treatment for infectious keratitis are urgent to prevent the progression of the disease and limit the degree of corneal injury. Unfortunately, the traditional manual diagnosis accuracy is usually unsatisfactory due to the indistinguishable visual features. In this paper, we propose a novel end-to-end fully convolutional network, named Class-Aware Attention Network (CAA-Net), for automatically diagnosing infectious keratitis (normal, viral keratitis, fungal keratitis, and bacterial keratitis) using corneal photographs. In CAA-Net, a class-aware classification module is first trained to learn class-related discriminative features using separate branches for each class. Then, the learned class-aware discriminative features are fed into the main branch and fused with other feature maps using two attention strategies to assist the final multi-class classification performance. For the experiments, we have built a new corneal photograph dataset with 1886 images from 519 patients and conducted comprehensive experiments to verify the effectiveness of our proposed method. The code is available at https://github.com/SWF-hao/CAA-Net_Pytorch.

Diagnosis of Acute Respiratory Syndromes from X-Rays using Customised CNN Architecture

This work presents the diagnosis of various acute respiratory syndromes using customized CNN architecture from X-ray images. Complications of viral pneumonia results in influenza and COVID-19. The respiratory syndromes occur due to bacterial and fungal infections as well. Hence, the objective was to use customized CNN architecture to perform a multi-class pneumonia classification. VGG16 architecture is carefully trained for pneumonia classification with ReLU activation and categorical cross-entropy loss function. The proposed model is efficient and robust and yielded 97.87% accuracy on the train set and 90% accuracy on the test set. The experimental results suggest that the model efficiently detects all sorts of lung diseases, including COVID 19. © 2022 IEEE.

Multiclass Deep Transfer Learning for Covid-19 Classification

Over 500 million people have been infected with COVID-19 since it first appeared, including more than 6 million cases in Indonesia. Although COVID-19 has the potential to cause pneumonia, COVID is not always the sole cause of the illness, necessitating the need for another rapid and precise approach to disease classification. Additionally, it is not only dependent on the Polymerase Chain Reaction (PCR) technique, which is costly and labor-intensive. The study of chest X-ray images can be one quick and accurate way of helping to confirm the disease. It is necessary to investigate the multiclass classification of diseases with comparable clinical characteristics since COVID-19-related diseases can vary. This investigation chose pneumonia, COVID-19, and Normal as the deep learning model's three target classes. The mobileNet-based deep transfer learning accuracy obtained was 0.95%, while the recall obtained was 0.93%, 0.97%, and 0.96%, respectively, where the targets were three classes (COVID, Pneumonia, and Normal). Additionally, the Covid class precision value received the perfect score, while the Normal and Pneumonia classes received the same for the f1-score. © 2022 IEEE.

Multiclass Classification for Air Quality In Jakarta Using Support Vector Machine and Multi-Layer Perceptron Classifier

Air is one of the necessities of living things. Therefore, it is necessary to have good air quality. Air pollution can cause many negative impacts on life. Therefore, it is important to know the air quality in an area. Jakarta is one of the cities with poor air quality in Indonesia and the world. During the Covid-19 pandemic, the government implemented a large-scale social restriction policy, the impact of this policy was better air quality. But now it has started to back to normal, then it is important to control air quality. There are 5 locations to measure air quality in Jakarta. The results of the independence test between the location of air quality measurements and critical variables on air pollution indicate a relationship between the two variables. Moreover, there are differences in air quality before Covid-19 and during Covid-19 based on the results of the t-test. Air quality classification was carried out in this research using machine learning methods. Because there are several levels of air quality, the classification uses a multiclass classification. Support Vector Machine (SVM) and Multi-Layer Perceptron (MLP) Classifier are used in this research. Because based on the results of literature reviews, both methods produce high accuracy. The results of this research showed a comparison of the two methods. The comparison showed that the SVM method is better than the MLP Classifier. © 2022 IEEE.

Multi-Class Flat Classification of Lung Diseases Utilizing Deep Learning

Early diagnosis of diseases is very critical for recovery. However, this is not always feasible due to the limited available staff or expensive and inadequate tools as we have witnessed in the recent COVID-19 pandemic. Lung diseases are life-threatening, but fortunately, they can be detected from X-ray images, which are cost-effective approaches. However, they need experts who are sometimes unavailable. Thus, using cutting-edge technology to diagnose diseases automatically and fast is the key solution to saving people's lives. In this research, deep learning techniques have been utilized to classify several lung diseases in a cost-saving, time-saving, and efficient manner. Examples of lung diseases studied in this research are COVID-19, Lung Opacity, Pneumonia, and Tuberculosis. Several pre-trained deep learning models have been employed for flat multi-class classification of these lung diseases instead of using binary classification to recognize one disease from normal cases, as most state-of-the-art studies carry out. The models' performance has been evaluated on imbalanced data of X-ray images with various resolutions and types. Finally, multiple measurements metrics have been utilized to evaluate the performance. The best accuracy achieved in this research is 95.643%. © 2022 IEEE.

Improved COVID-19 detection with chest x-ray images using deep learning.

The novel coronavirus disease, which originated in Wuhan, developed into a severe public health problem worldwide. Immense stress in the society and health department was advanced due to the multiplying numbers of COVID carriers and deaths. This stress can be lowered by performing a high-speed diagnosis for the disease, which can be a crucial stride for opposing the deadly virus. A good large amount of time is consumed in the diagnosis. Some applications that use medical images like X-Rays or CT-Scans can pace up the time used in diagnosis. Hence, this paper aims to create a computer-aided-design system that will use the chest X-Ray as input and further classify it into one of the three classes, namely COVID-19, viral Pneumonia, and healthy. Since the COVID-19 positive chest X-Rays dataset was low, we have exploited four pre-trained deep neural networks (DNNs) to find the best for this system. The dataset consisted of 2905 images with 219 COVID-19 cases, 1341 healthy cases, and 1345 viral pneumonia cases. Out of these images, the models were evaluated on 30 images of each class for the testing, while the rest of them were used for training. It is observed that AlexNet attained an accuracy of 97.6% with an average precision, recall, and F1 score of 0.98, 0.97, and 0.98, respectively.

Transfer Learning for COVID-19 and Pneumonia Detection using Chest X-Rays

Chest X-rays (CXR) images are a useful noninvasive diagnostic tool for assessing various lung diseases. In this paper, we propose transfer learning with a fine-tuning-based model to detect and classify COVID-19 and pneumonia using CXR images to assist the radiologist with diagnosis. One of the difficulties with the medical imaging classification is the limited number of available datasets, and hence training a deep Convolutional Neural Network (CNN) model for medical image classification on a small dataset is challenging. We address this issue by exploiting transfer learning via fine-tuning. In this paper, we use a pre-trained deep CNN model and then fine-tune the layers of the neural network to perform multi-class classification using CXR images. The model is trained to perform multi-class classification, such as two-class (COVID-19 vs normal), three-class (COVID-19 vs Bacterial Pneumonia vs normal), four-class (COVID-19 vs Bacterial Pneumonia vs lung opacity vs normal), and five-class (COVID-19 vs Bacterial Pneumonia vs Viral Pneumonia vs lung opacity vs normal) classification. The performance of the model is evaluated in terms of accuracy, precision, recall, and F1-score. © 2022 IEEE.

Resnet Fusion Model for Multi-Class Classification of Chest X-Rays

Lung diseases affect many populations around the world and their symptoms may range from common cough to chronic lung infections caused by unhygienic living conditions, unhealthy habits(smoking) and often inter-species virus/bacterial transmission. Moreover, the death toll and individuals affected by lung infections have skyrocketed after the contagious COVID-19 outbreak in 2019 December in Wuhan China. The Big Data revolution has increased the number of labelled and analyzed x-ray image data in the medical field, which has triggered more solutions for preventive and early diagnostics measures in the area. However contagious nature of COVID-19 makes it unsafe for medical practitioners despite the use of preventive gear and the varying examination skills of radiologists generates a biased result with different x-rays. Employing Deep Neural Network-based methodologies would help overcome the current issue. In this paper, we have compared the performance of pre-trained models Resnet18, Resnet50 and the fusion of the two Resnet models using transfer learning. We have performed cross-validation of 5 folds with 25 epochs for each fold to obtain the optimal metrics performance for all three models. Average accuracy, precision, f1-score and recall of 88.75%, 89.89%, 88.75% and 88.66% was reported for resnet18 respectively while Resnet50 yield 90.25%, 90.26%, 90.25% and 90.24% for the same. The proposed fusion model gave increased performance metrics with an accuracy of 95.75%, precision of 95.89%, recall of 95.75% and an f-1 score of 95.75%. © 2022 IEEE.