Transfer Learning Model in Deep Neural Network for COVID-19 Prediction from CT Images

Deep learning models are often used to process radi-ological images automatically and can accurately train networks' weights on appropriate datasets. One of the significant benefits of the network is that it is possible to use the weight of a pre-trained network for other applications by fine-tuning the current weight. The primary purpose of this work is to employ a pre-trained deep neural framework known as transfer learning to detect and diagnose COVID-19 in CT images automatically. This paper uses a popular deep neural model, ResNet152, as a neural transfer approach. The presented framework uses the weight obtained from the ImageNet dataset, fine-tuned by the dataset used in the work. The effectiveness of the suggested COVID-19 prediction system is evaluated experimentally and compared with DenseNet, another transfer learning model. The recommended ResNet152 transfer learning model exhibits improved performance and has a 99% accuracy when analogized with the DenseNet201 transfer learning model. © 2022 IEEE.

Fine-Tuning ResNet-152V2 for COVID-19 Recognition in Chest Computed Tomography Images

The epidemic Covid-19 has extended to majority of nations. This pandemic is due to a contagious condition 'SARS-CoV-2', was identified by the the International Health association. In order to diagnosis this virus from 2D chest computed tomography (CT) images, we applied three different transfer learning algorithms: $VGG-19, ResNet-152V2$ and a Fine-Tuned version of $ResNet-152V2$. The different transfer learning models are used on three hundred and four exams where 74 are normal cases, 60 are community-acquired pneumonia (CAP) cases and 169 were confirmed corona-virus cases. The best accuracy value is reached by the fine-tuned $ResNet-152v2$ by 75% against 70% for the basic $ResNet-152v2$ and 66% for the $VGG-19$. © 2022 IEEE.

COVID QA Network: A Specific Case of Biomedical Question Answering

COVID-19 crisis has led to an outburst of information that needs to be organized, validated, and made available to the seekers. Despite the rapid growth and success of BERT models in the last 3 years, COVID QA is a difficult task due to the lack of applicable datasets and a relevant language representation. Therefore, this study proposes a transformer-based Question Answering (QA) model for COVID-19 questions from the biomedical domain. Further, explored several datasets, and models required for question type prediction, no-Answer prediction, and answer extraction and transfer learning strategies. It has been demonstrated that the exact match score can be significantly improved with limited amounts of training data from the biomedical domain. Finally, the findings of the study have been summarized as Factoid QA Finetuning Framework (FQFF), which can provide initial direction for domain-specific QA tasks with a limited amount of data. © 2023 IEEE.

A Shuffling Building Block and Augmentation Parameter Tuning Techniques to Handle Small Medical Dataset

The recent COVID-19 outbreak showed us the importance of faster disease diagnosis using medical image processing as it is considered the most reliable and accurate diagnostic tool. In a CNN architecture, performance improves with the increasing number of trainable parameters at the cost of processing time. We have proposed an innovative approach of combining efficient novel architectures like Inception, ResNet, and ResNet-Xt and created a new CNN architecture that benefits Extreme Cardinal dimensions. We have also created four variations of the same base architecture by varying the position of each building block and used X-Ray, Microscopic, MRI, and pathMNIST datasets to train our architecture. For learning curve optimization, we have applied learning rate changing techniques, tuned image augmentation parameters, and chose the best random states value. For a specific dataset, we reduced the validation loss from 0.22 to 0.18 by interchanging the architecture's building block position. Our results indicate that image augmentation parameters can help to decrease the validation loss. We have also shown rearrangement of the building blocks reduces the number of parameters, in our case, from 5,689,008 to 3,876,528. © 2023 IEEE.

Graph data science and machine learning for the detection of COVID-19 infection from symptoms.

Background: COVID-19 is an infectious disease caused by SARS-CoV-2. The symptoms of COVID-19 vary from mild-to-moderate respiratory illnesses, and it sometimes requires urgent medication. Therefore, it is crucial to detect COVID-19 at an early stage through specific clinical tests, testing kits, and medical devices. However, these tests are not always available during the time of the pandemic. Therefore, this study developed an automatic, intelligent, rapid, and real-time diagnostic model for the early detection of COVID-19 based on its symptoms. Methods: The COVID-19 knowledge graph (KG) constructed based on literature from heterogeneous data is imported to understand the COVID-19 different relations. We added human disease ontology to the COVID-19 KG and applied a node-embedding graph algorithm called fast random projection to extract an extra feature from the COVID-19 dataset. Subsequently, experiments were conducted using two machine learning (ML) pipelines to predict COVID-19 infection from its symptoms. Additionally, automatic tuning of the model hyperparameters was adopted. Results: We compared two graph-based ML models, logistic regression (LR) and random forest (RF) models. The proposed graph-based RF model achieved a small error rate = 0.0064 and the best scores on all performance metrics, including specificity = 98.71%, accuracy = 99.36%, precision = 99.65%, recall = 99.53%, and F1-score = 99.59%. Furthermore, the Matthews correlation coefficient achieved by the RF model was higher than that of the LR model. Comparative analysis with other ML algorithms and with studies from the literature showed that the proposed RF model exhibited the best detection accuracy. Conclusion: The graph-based RF model registered high performance in classifying the symptoms of COVID-19 infection, thereby indicating that the graph data science, in conjunction with ML techniques, helps improve performance and accelerate innovations.

Conspiracy Narratives in the Protest Movement Against COVID-19 Restrictions in Germany. A Long-term Content Analysis of Telegram Chat Groups

From the start of the COVID-19 pandemic in Germany, different groups have been protesting measures implemented by different government bodies in Germany to control the pandemic. It was widely claimed that many of the offline and online protests were driven by conspiracy narratives disseminated through groups and channels on the messenger app Telegram. We investigate this claim by measuring the frequency of conspiracy narratives in messages from open Telegram chat groups of the Querdenken movement, set up to organize protests against COVID-19 restrictions in Germany. We furthermore explore the content of these messages using topic modelling. To this end, we collected 822k text messages sent between April 2020 and May 2022 in 34 chat groups. By fine-tuning a Distilbert model, using self-annotated data, we find that 8.24% of the sent messages contain signs of conspiracy narratives. This number is not static, however, as the share of conspiracy messages grew while the overall number of messages shows a downward trend since its peak at the end of 2020. We further find a mix of known conspiracy narratives make up the topics in our topic model. Our findings suggest that the Querdenken movement is getting smaller over time, but its remaining members focus even more on conspiracy narratives. © 2022 Association for Computational Linguistics.

Exploring Language-Interfaced Fine-Tuning for COVID-19 Patient Survival Classification

We present Language-Interfaced Fine-Tuning (LIFT) in application to COVID-19 patient survival classification. LIFT describes translating tabular Electronic Health Records (EHRs) into text inputs for transformer neural networks. We study LIFT with a dataset of 5,371 COVID-19 patients. We focus on the predictive task of survival classification utilizing demographic and medical history features. We begin by presenting information about our dataset. We preface our investigation in text-based transformers by reporting the performances of conventional machine learning models such as Logistic Regression and Random Forest classifiers. We also present the results of a few configurations of tabular input-based Deep Multilayer Perceptron (MLP) networks. 86% of the patients in our database survived in the measured time window. Thus, predictive models are heavily biased to predict that a patient will survive. We emphasize that this problem of Class Imbalance was a major challenge in developing these models. Our balanced sampling strategy from examples in the majority and minority classes is crucial to achieving even reasonable predictive performance. For this reason, we also report performance based on Precision, Recall, and F-score metrics, in addition to Accuracy. Having established baselines with tabular inputs, we then shift our focus to the prompts for translating from tabular to text inputs. We report the performance of 5 prompts. The LIFT model achieves an F-score on the held-out test set of 0.21, slightly behind the Deep MLP with Tabular Features score of 0.23. Both models outperform the Random Forest with Tabular Features at 0.15. We believe that LIFT is a very exciting direction for machine learning in healthcare applications because text-based inputs enables us to take advantage of recent advances in Transfer Learning and Retrieval-Augmented Learning. This study illustrates the effectiveness of converting tabular EHRs to text inputs and utilizing transformer neural networks for prediction. © 2022 IEEE.

Tourism Demand Prediction after COVID-19 with Deep Learning Hybrid CNN–LSTM—Case Study of Vietnam and Provinces

The tourism industry experienced a positive increase after COVID-19 and is the largest segment in the foreign exchange contribution in developing countries, especially in Vietnam, where China has begun reopening its borders and lifted the pandemic limitation on foreign travel. This research proposes a hybrid algorithm, combined convolution neural network (CNN) and long short-term memory (LSTM), to accurately predict the tourism demand in Vietnam and some provinces. The number of new COVID-19 cases worldwide and in Vietnam is considered a promising feature in predicting algorithms, which is novel in this research. The Pearson matrix, which evaluates the correlation between selected features and target variables, is computed to select the most appropriate input parameters. The architecture of the hybrid CNN–LSTM is optimized by utilizing hyperparameter fine-tuning, which improves the prediction accuracy and efficiency of the proposed algorithm. Moreover, the proposed CNN–LSTM outperformed other traditional approaches, including the backpropagation neural network (BPNN), CNN, recurrent neural network (RNN), gated recurrent unit (GRU), and LSTM algorithms, by deploying the K-fold cross-validation methodology. The developed algorithm could be utilized as the baseline strategy for resource planning, which could efficiently maximize and deeply utilize the available resource in Vietnam.

Real Time Mask Detection using Convolutional Neural Network

With the advent of Convolutional Neural Networks, the field of image classification has seen tremendous growth, with various previously impossible applications now being pursued. One such application is face mask detection, which is an important problem to solve, considering recent pandemic. The novelty of this work is the training of YOLO (You Only Look Once) framework for custom object detection, which in this case is face mask, based on some empirical rules for fine-tuning the performance. Also, image classification is proposed to be combined with tracker, in order to implement real world access grant system based on compliance shown by mask wearer. © 2022 IEEE.

Covid-19 cases prediction using SARIMAX Model by tuning hyperparameter through grid search cross-validation approach.

SARS-Coronavirus was first detected in December 2019, later named COVID-19, and declared a pandemic by the World Health Organization (WHO). As prediction models assist policymakers in making decisions based on expected outcomes. Existing models were only used to anticipate a smaller range of data resulting in irrelevant predictions. Our research focuses on predicting COVID-19 confirmed, recovered, and deceased Indian cases for 20 days ahead. Tuning of hyperparameters is performed with a grid search cross-validation approach. The dataset is collected from the Kaggle. Our forecast indicates that the count of confirmed and deceased cases is higher whereas, recovered cases prediction shows a decreasing trend. The R 2 Score achieved is 0.5112 and root-mean-square error (RMSE) is 1251 using optimized SARIMAX. Finally, Monte Carlo simulation has also been performed to justify the prediction accuracy as compared to other models such as linear, polynomial, prophet, and SARIMAX without grid search cross validation.

Transfer learning-based CNN diagnostic framework for diagnosis of COVID-19 from lung CT images

COVID-19 is an infectious disease that affects the respiratory system. To assist the physician in diagnosing lung disorders from chest CT images various systems have been developed and used. Detection of COVID-19 remains a challenging area of research. The objective of the work is to develop an inductive parameter-transfer learning-based approach for the prediction of COVID-19, pneumonia, from lung CT images. Our proposed approach is built on layer wise and convolution block-wise fine-tuning which designs the CNN architecture highly specific to lung CT image. We implemented the DenseNet201, InceptionV3, Xception, VGG19, and ResNet50 as baseline models. The network architectures are developed to learn feature representation of lung CT images. For the experimental analysis, five datasets are used. From the experimental results, it is inferred that the DenseNet201 model yields higher accuracy of 0.94 for Adam optimizer and 0.93 for the RMSprop optimizer compared to other models.

Design of Auto-Tuning Nonlinear PID Tracking Speed Control for Electric Vehicle with Uncertainty Consideration

This study presents a new auto-tuning nonlinear PID controller for a nonlinear electric vehicle (EV) model. The purpose of the proposed control was to achieve two aims. The first aim was to enhance the dynamic performance of the EV regarding internal and external disturbances. The second aim was to minimize the power consumption of the EV. To ensure that these aims were achieved, two famous controllers were implemented. The first was the PID controller based on the COVID-19 optimization. The second was the nonlinear PID (NPID) optimized controller, also using the COVID-19 optimization. Several driving cycles were executed to compare their dynamic performance and the power consumption. The results showed that the auto-tuning NPID had a smooth dynamic response, with a minimum rise and settling time compared to other control techniques (PID and NPID controllers). Moreover, it achieved low continuous power consumption throughout the driving cycles. © 2023 by the author.

A Comparison of COVID-19 Detection using Deep Learning Methods

The recognition of covid-19 is major confront in today's world, specified as sudden increase in spreading of the disease. Hence, identifying this infection in earlier phase facilitates medicinal fields such as doctors, nurses and lab reporters. This article introduces a novel deep learning technique especially Convolutional Neural Network (CNN) by analyzing features in chest input images. Moreover, this proposed Convolutional Neural Network detects the covid-19 disease under several layers and finally performs binary classification that categorizes input images into covid 19 and non-covid patients. Finally, comparisons had made among all models to predict which model diagnose the disease accurately. To evaluate the overall model performance in detection and classification of covid disease, metrics criterias precision, recall and F1-score are evaluated. Validation analysis were completed for quantify the outcomes via performance measures for each model. This proposed comparison attains maximum accuracy of 100% along with least loss as 0.04 that might diminish human inaccuracy in identification procedure. © 2023 IEEE.

Hyperparameter Search for CT-Scan Classification Using Hyperparameter Tuning in Pre-Trained Model CNN With MLP

The common approach to find best hyperparameter in CNN training is grid search, by observing one set to another of hyperparameter for obtaining the best result. However, this approach is considered inefficient, time-consuming, and ineffectively computational. In this study, we are observing 2 hyperparameter tuning algorithms (bayesian optimization and random search) in search of the best hyperparameter for CT-Scan classification case. The used dataset is COVID-19 and non-COVID-19 lung CT-Scans. Several CNN architectures are also used such as: InceptionV4, MobileNetV3, and EfficientnetV2 with additional multi-layer perceptron on top layers. Based on the experiments, model EfficientnetV2-L architecture using hyperparameter from bayesian-optimization can outperform other models, with batch size of 32, learning rate of 0.01, dropout 0.5, Adam optimizer and SoftMax activation, resulting in the accuracy rate of 0.94% and a model training time of 50 minutes 40 seconds. © 2022 IEEE.

Prototyping a VR Sandbox for Scene Customization without 3D Authoring Skills

Virtual Reality (VR) and simulation continue po-sitioning as suitable tools for fine-tuning processes otherwise impossible in real life. Such is the case of Aether, a mobile service robot for elderly care developed during the COVID-19 pandemic. Aether's development was negatively impacted due to restrictions placed on accessing long-term care facilities that impeded testing object tracking, elderly tracking, fall detection, and human-robot interactions. Our efforts to maximize Aether's development led us to create a digital twin where the core functionality is replicated to train the machine learning modules to optimize the robot's responses before real-world deployment. However, the digital twin creation requires significant authoring to ensure the virtual environment matches the real one by employing 3D technical artistry skills, which demands a professional knowledgeable in this domain. This paper presents a sandbox prototype for scene customization that allows importing, positioning, scaling, and saving changes for mobile robot simulation. Our preliminary testing of the sandbox has focused on usability to understand how the setting up of the environment is perceived. Preliminary results indicate that the sandbox is usable with improvements pertaining to improving the manipulation of the objects. © 2022 IEEE.

Identifying Similar Questions in the Medical Domain Using a Fine-tuned Siamese-BERT Model

A large number of people search about their health related problems on the web. However, the number of sites with qualified and verified people answering their queries is quite low in comparison to the number of questions being put up. The rate of queries being searched on such sites has further increased due to the COVID-19 pandemic. The main reason people find it difficult to find solutions to their queries is due to ineffective identification of semantically similar questions in the medical domain. For most cases, answers to the queries people ask would be present, the only caveat being the question may be present in a different form than the one asked by the particular user. In this research, we propose a Siamese-based BERT model to detect similar questions using a fine-tuning approach. The network is fine-tuned with medical question-answer pairs and then with question-question pairs to get a better question similarity prediction. © 2022 IEEE.

Transfer learning-based CNN diagnostic framework for diagnosis of COVID-19 from lung CT images

COVID-19 is an infectious disease that affects the respiratory system. To assist the physician in diagnosing lung disorders from chest CT images various systems have been developed and used. Detection of COVID-19 remains a challenging area of research. The objective of the work is to develop an inductive parameter-transfer learning-based approach for the prediction of COVID-19, pneumonia, from lung CT images. Our proposed approach is built on layer wise and convolution block-wise fine-tuning which designs the CNN architecture highly specific to lung CT image. We implemented the DenseNet201, InceptionV3, Xception, VGG19, and ResNet50 as baseline models. The network architectures are developed to learn feature representation of lung CT images. For the experimental analysis, five datasets are used. From the experimental results, it is inferred that the DenseNet201 model yields higher accuracy of 0.94 for Adam optimizer and 0.93 for the RMSprop optimizer compared to other models. © 2023 The Royal Photographic Society.

A Transfer Learning Approach for Diagnosis of COVID-19 Cases from Chest Radiography Images

The new coronavirus disease 2019 (COVID-19) pandemic completely changed individuals' daily lives and created economic disruption across the world. Many countries are using movement restrictions and physical distancing as their measures to slow down this transmission. Effective screening of COVID-19 cases is needed to stop the spreading of these diseases. In the first phases of clinical assessment, it was seen that patients with deformities in chest X-ray images show the signs of COVID-19 infection. Inspired from this, in this study, a novel framework is designed to detect the COVID-19 cases from chest radiography images. Here, a pre-trained deep convolutional neural network VGG-16 is used to extract discriminating features from the radiography images. These extracted features are given as an input to the Logistic regression classifier for automatic detection of COVID-19 cases. The suggested framework obtained a remarkable accuracy of 99.1% with a 100% sensitivity rate in comparison with other state-of-the-art classifier. © 2022 IEEE.

IMPLEMENTATION OF MACHINE LEARNING ALGORITHM FOR COVID19 DETECTION USING X-RAY AND VOICE DATASET

Ever since the deadly corona virus came into existence the life of the people has been shattered both in terms of health and economic crisis. Even today its various variants are creating havoc among the people. The traditional way of testing the disease is time consuming and is also not cost efficient due to the requirement of PEP kits. In this paper various Machine Learning (ML) techniques have been implemented based on the cough samples and chest x-ray images of the individuals. A hybrid model with GUI interface is designed to predict covid-19 and to perform the comparative analysis of sequential model and ResNet50 for image dataset, CNN with hyper parameter tuning and CNN for voice dataset. From the experimental analysis, ResNet50 performed better when compared to sequential model for image dataset and CNN with hyper parameter tuning performed better when compared with CNN model for voice dataset. © 2022 IEEE.

An integrative systems biology view of host-pathogen interactions: The regulation of immunity and homeostasis is concomitant, flexible, and smart.

The systemic bio-organization of humans and other mammals is essentially "preprogrammed", and the basic interacting units, the cells, can be crudely mapped into discrete sets of developmental lineages and maturation states. Over several decades, however, and focusing on the immune system, we and others invoked evidence - now overwhelming - suggesting dynamic acquisition of cellular properties and functions, through tuning, re-networking, chromatin remodeling, and adaptive differentiation. The genetically encoded "algorithms" that govern the integration of signals and the computation of new states are not fully understood but are believed to be "smart", designed to enable the cells and the system to discriminate meaningful perturbations from each other and from "noise". Cellular sensory and response properties are shaped in part by recurring temporal patterns, or features, of the signaling environment. We compared this phenomenon to associative brain learning. We proposed that interactive cell learning is subject to selective pressures geared to performance, allowing the response of immune cells to injury or infection to be progressively coordinated with that of other cell types across tissues and organs. This in turn is comparable to supervised brain learning. Guided by feedback from both the tissue itself and the neural system, resident or recruited antigen-specific and innate immune cells can eradicate a pathogen while simultaneously sustaining functional homeostasis. As informative memories of immune responses are imprinted both systemically and within the targeted tissues, it is desirable to enhance tissue preparedness by incorporating attenuated-pathogen vaccines and informed choice of tissue-centered immunomodulators in vaccination schemes. Fortunately, much of the "training" that a living system requires to survive and function in the face of disturbances from outside or within is already incorporated into its design, so it does not need to deep-learn how to face a new challenge each time from scratch. Instead, the system learns from experience how to efficiently select a built-in strategy, or a combination of those, and can then use tuning to refine its organization and responses. Efforts to identify and therapeutically augment such strategies can take advantage of existing integrative modeling approaches. One recently explored strategy is boosting the flux of uninfected cells into and throughout an infected tissue to rinse and replace the infected cells.