Centralized CNN-GRU Model by Federated Learning for COVID-19 Prediction in India

In 2019, the corona virus was found in Wuhan, China. The corona virus has traveled several countries in the world from the beginning of 2020. The early estimation of COVID-19 cases is one of the efficient approaches to control the pandemic. Many researchers had proposed the deep learning model for the efficient estimation of COVID-19 cases for different provinces in the world. The research work had not focused on the discussion of robustness in the model. In this study, centralized federated-convolutional neural network–gated recurrent unit (Fed-CNN–GRU) model is proposed for the estimation of active cases per day in different provinces of India. In India, the uneven transmission of COVID-19 virus was seen in 36 provinces due to the different geographical areas and population densities. So, the methodology of this study had focused on the development of single deep learning algorithm, which is robust and reliable to estimate the active cases of COVID-19 in different provinces of India. The concept of transfer and federated learning is involved to enhance the estimation of active cases of COVID-19 by the CNN–GRU model. The study had considered the active cases per day dataset for 36 provinces in India from 12 March, 2020 to 17 January, 2022. Based on the study, it is proven that the centralized CNN–GRU model by federated learning had captured the transmission dynamics of COVID-19 in different provinces with an enhanced result. IEEE

Initial Stage Identification of COVID-19 Using Capsule Networks

Coronavirus is a pandemic that has kept us in great grief for the past few months. These days have created a devastating effect all through the world. As coronavirus has lot of similarities with other lung diseases, it becomes a challenging task for medical practitioners to identify the virus. A fast and robust system to identify the disease has been the need of the hour. In this chapter, we have used convolutional CapsNet for detecting COVID-19 disease using chest X-ray images. This design aims at obtaining fast and accurate diagnostic results. The proposed technique with less trainable parameters, COVID-CAPS, produced an accuracy of 87.5%, a sensitivity of 90%, a specificity of 95.8%, and an area under the curve (AUC) of 0.97. The main advantage of using CapsNet is that it can capture affine transformation in data that is a common scenario while dealing with real-world X-ray images. The CapsNet model is trained with normal data and tested with affine transformed data. The accuracy level obtained in the proposed method is comparatively much better along with having less learnable parameters and computational speed as compared to standard architectures such as ResNet, MobileNet, etc. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Biological Sequence Classification Using Deep Learning Architectures

Finding similar biological sequences to categorize into respective families is an important task. The present works attempt to use machine learning-based approaches to find the family of a given sequence. The first task in this direction is to convert the sequences to vector representations and then train a model using a suitable machine learning architecture. The second task is to find which family the sequence belongs to. In this work, deep learning-based architectures are proposed to do the task. A comparative study on how effective various deep learning architectures for this problem is also discussed in this work. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Deep Learning Based NLP Embedding Approach for Biosequence Classification

Biological sequence analysis involves the study of structural characteristics and chemical composition of a sequence. From a computational perspective, the goal is to represent sequences using vectors which bring out the essential features of the virus and enable efficient classification. Methods such as one-hot encoding, Word2Vec models, etc. have been explored for embedding sequences into the Euclidean plane. But these methods either fail to capture similarity information between k-mers or face the challenge of handling Out-of-Vocabulary (OOV) k-mers. In order to overcome these challenges, in this paper we aim explore the possibility of embedding Biosequences of MERS, SARS and SARS-CoV-2 using Global Vectors (GloVe) model and FastText n-gram representation. We conduct an extensive study to evaluate their performance using classical Machine Learning algorithms and Deep Learning methods. We compare our results with dna2vec, which is an existing Word2Vec approach. Experimental results show that FastText n-gram based sequence embeddings enable deeper insights into understanding the composition of each virus and thus give a classification accuracy close to 1. We also provide a study regarding the patterns in the viruses and support our results using various visualization techniques. © 2022, Springer Nature Switzerland AG.

Biological Sequence Classification Using Deep Learning Architectures

Finding similar biological sequences to categorize into respective families is an important task. The present works attempt to use machine learning-based approaches to find the family of a given sequence. The first task in this direction is to convert the sequences to vector representations and then train a model using a suitable machine learning architecture. The second task is to find which family the sequence belongs to. In this work, deep learning-based architectures are proposed to do the task. A comparative study on how effective various deep learning architectures for this problem is also discussed in this work.

CT Image Enhancement Using Variational Mode Decomposition for AI-Enabled COVID Classification

SARS-COV-2, also known as COVID-19 pandemic, has escalated calamity in the entire world. Due to its contagious properties, the disease spreads swiftly from person to person via direct contact. More than 210 million people got infected worldwide with more than 18 million active patients as of August 29, 2021. In numerous places, the test process for COVID-19 detection takes longer than 2 days. Once the patient is affected by COVID-19, the obstruction in lungs causes difficulty in analyzing the presence of other lung diseases, such as variants of pneumonia. In this paper, we propose an enhancement technique via the acclaimed signal processing method called variational mode decomposition (VMD) aiding any X-ray image classification method for the detection of pneumonia using convolutional neural networks (CNN). The experiments were conducted on VGG-16 model loaded with ImageNet weights followed by numerous configurations of dense layers. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Early Warning Indicators for Financial Crisis During Covid-19

The impact of covid-19 on the financial market is considered a ‘black swan event’, i.e., the occurrence of a highly unpredictable event with far-reaching consequences. Prediction of such events in prior is essential due to the financial risk associated. In this paper, we study critical slowing down as an early warning signal to forewarn such unpredictable and sudden transitions concerning the Indian stock market for the covid-19 period. This is the first study to predict covid-19 financial crisis based on critical slowing down theory. We analyze the evolution of first-order autocorrelation and standard deviation using the sliding window approach to predict any impending transition. We found that both the early warning measures could forewarn an impending transition for almost all the stock indices considered for the analysis. © 2022, Springer Nature Switzerland AG.

Explainable AI Framework for COVID-19 Prediction in Different Provinces of India (preprint)

In 2020, covid-19 virus had reached more than 200 countries. Till December 20th 2021, 221 nations in the world had collectively reported 275M confirmed cases of covid-19 & total death toll of 5.37M. Many countries which include United States, India, Brazil, United Kingdom, Russia etc were badly affected by covid-19 pandemic due to the large population. The total confirmed cases reported in this country are 51.7M, 34.7M, 22.2M, 11.3M, 10.2M respectively till December 20, 2021. This pandemic can be controlled with the help of precautionary steps by government & civilians of the country. The early prediction of covid-19 cases helps to track the transmission dynamics & alert the government to take the necessary precautions. Recurrent Deep learning algorithms is a data driven model which plays a key role to capture the patterns present in time series data. In many literatures, the Recurrent Neural Network (RNN) based model are proposed for the efficient prediction of COVID-19 cases for different provinces. The study in the literature doesnt involve the interpretation of the model behavior & robustness. In this study, The LSTM model is proposed for the efficient prediction of active cases in each provinces of India. The active cases dataset for each province in India is taken from John Hopkins publicly available dataset for the duration from 10th June, 2020 to 4th August, 2021. The proposed LSTM model is trained on one state i.e., Maharashtra and tested for rest of the provinces in India. The concept of Explainable AI is involved in this study for the better interpretation & understanding of the model behavior. The proposed model is used to forecast the active cases in India from 16th December, 2021 to 5th March, 2022. It is notated that there will be a emergence of third wave on January, 2022 in India.

Modified VGG deep-learning architecture for COVID-19 classification using chest radiography images

Background: The world faced a deadly disease encounter by the starting of 2020, known as coronavirus disease 2019 (COVID-19). Due to the rapid increase in the counts of COVID cases, the WHO declared the COVID-19 as a pandemic on March 11, 2020. Among the different screening techniques available for COVID-19, radiography of the chest is one of the efficient way for disease detection. While other disease detection techniques take time, radiography takes less time to identify because of the abnormalities caused by the disease in the lungs. Methods: In the rapid development era of artificial intelligence and deep-learning techniques, various models are being developed for COVID disease detection. COVID-19 can be easily detected from Chest X-ray images and the pretrained models yield high accuracy with small dataset. Results: In this paper, one of the standard deep-learning architectures, VGGNet, is modified for classifying chest X-ray images under four categories. The proposed model uses open source dataset that contains 231, 2503, 1345, and 1341 images of four classes such as COVID, bacterial, normal, and viral chest radiography images, respectively. Conclusion: The performance matrices of the proposed work were compared with the five benchmark deep-learning architectures namely VGGNet, AlexNet, GoogLeNET, Inception-v4, and DenseNet-201. © This is an open access journal, and articles are distributed under the terms of the Creative Commons Attribution-NonCommercial-ShareAlike 4.0 License.

Prediction of number of cases expected and estimation of the final size of coronavirus epidemic in India using the logistic model and genetic algorithm (preprint)

In this paper, we have applied the logistic growth regression model and genetic algorithm to predict the number of coronavirus infected cases that can be expected in upcoming days in India and also estimated the final size and its peak time of the coronavirus epidemic in India.