COVID-19 Classification from X-Ray Images: An Approach to Implement Federated Learning on Decentralized Dataset

The COVID-19 pandemic has devastated our daily lives, leaving horrific repercussions in its aftermath. Due to its rapid spread, it was quite difficult for medical personnel to diagnose it in such a big quantity. Patients who test positive for Covid-19 are diagnosed via a nasal PCR test. In comparison, polymerase chain reaction (PCR) findings take a few hours to a few days. The PCR test is expensive, although the government may bear expenses in certain places. Furthermore, subsets of the population resist invasive testing like swabs. Therefore, chest X-rays or Computerized Vomography (CT) scans are preferred in most cases, and more importantly, they are non-invasive, inexpensive, and provide a faster response time. Recent advances in Artificial Intelligence (AI), in combination with state-of-the-art methods, have allowed for the diagnosis of COVID-19 using chest x-rays. This article proposes a method for classifying COVID-19 as positive or negative on a decentralized dataset that is based on the Federated learning scheme. In order to build a progressive global COVID-19 classification model, two edge devices are employed to train the model on their respective localized dataset, and a 3-layered custom Convolutional Neural Network (CNN) model is used in the process of training the model, which can be deployed from the server. These two edge devices then communicate their learned parameter and weight to the server, where it aggregates and updates the global model. The proposed model is trained using an image dataset that can be found on Kaggle. There are more than 13,000 X-ray images in Kaggle Database collection, from that collection 9000 images of Normal and COVID-19 positive images are used. Each edge node possesses a different number of images;edge node 1 has 3200 images, while edge node 2 has 5800. There is no association between the datasets of the various nodes that are included in the network. By doing it in this manner, each of the nodes will have access to a separate image collection that has no correlation with each other. The diagnosis of COVID-19 has become considerably more efficient with the installation of the suggested algorithm and dataset, and the findings that we have obtained are quite encouraging. © 2023 Tech Science Press. All rights reserved.

A New Approach for Forecasting Crude Oil Prices Based on Stochastic and Deterministic Influences of LMD Using ARIMA and LSTM Models

Crude oil is one of the non-renewable power sources and is the lifeblood of the contemporary industry. Every significant change in the price of crude oil (CO) will have an effect on how the global economy, including COVID-19, develops. This study developed a novel hybrid prediction technique that depends on local mean decomposition, Autoregressive Integrated Moving Average (ARIMA), and Long Short-term Memory (LSTM) models to increase crude oil price prediction accuracy. The original data is decomposed by local mean decomposition (LMD), and the decomposed components are reconstructed into stochastic and deterministic (SD) components by average mutual information to reduce the computation cost and enhance forecasting accuracy, predict each individual reconstructed component by ARIMA, and integrate the residuals with LSTM to capture the nonlinearity in residuals and help to find the final prediction result. The new hybrid model LMD-SD-ARIMA-LSTM has reduced the volatility and solved the issue of the overfitting problem of neural networks. The proposed hybrid technique is validated using publicly accessible data from the West Texas Intermediate (WTI), and forecast accuracy are compared using accuracy measures. The value of Mean Absolute Error (MAE) and Mean Absolute Percentage Error (MAPE) for ARIMA, LSTM, LMD-ARIMA, LMD-SD-ARIMA, LMD-ARIMA-LSTM, LMD-SD-ARIMA-LSTM, and Naïve are 1.00, 1.539, 5.289, 0.873, 0.359, 0.106, 4.014 and 2.165, 1.832, 9.165, 1.359, 1.139, 1.124 and 3.821 respectively. From these results, it is concluded that the proposed model LMD-SD-ARIMA-LSTM has minimum values for MAE and MAPE which assured the superiority of the proposed model in One-step ahead forecasting. Moreover, forecasting performance is also compared up to five steps ahead. The findings demonstrate that the suggested approach is a helpful tool for predicting CO prices both in the short and long term. Furthermore, the current study reduces labor costs by combing the stationary and non-stationary Product Functions (PFs) into stochastic and deterministic components with improved accuracy. Meanwhile, the traditional econometric model can strengthen the prediction behavior of CO prices after decomposition and reconstruction, and the new hybrid forecasting method has better performance in medium and long-term forecasting of the CO price. Moreover, accurate predictions can provide reasonable advice for relevant departments to make correct decisions. © 2013 IEEE.

Soft computing techniques for forecasting of COVID-19 in Pakistan

Novel Pandemic COVID-19 led globally to severe health barriers and financial issues in different parts of the world. The forecast on COVID-19 infections is significant. Demeanor vital data will help in executing policies to reduce the number of cases efficiently. Filtering techniques are appropriate for dynamic model structures as it provide reasonable estimates over the recursive Bayesian updates. Kalman Filters, used for controlling epidemics, are valuable in knowing contagious infections. Artificial Neural Networks (ANN) have generally been used for classification and forecasting problems. ANN models show an essential role in several successful applications of neural networks and are commonly used in economic and business studies. Long short-term memory (LSTM) model is one of the most popular technique used in time series analysis. This paper aims to forecast COVID-19 on the basis of ANN, KF, LSTM and SVM methods. We applied ANN, KF, LSTM and SVM for the COVID-19 data in Pakistan to find the number of deaths, confirm cases, and cases of recovery. The three methods were used for prediction, and the results showed the performance of LSTM to be better than that of ANN and KF method. ANN, KF, LSTM and SVM endorsed the COVID-19 data in closely all three scenarios. LSTM, ANN and KF followed the fluctuations of the original data and made close COVID-19 predictions. The results of the three methods helped significantly in the decision-making direction for short term strategies and in the control of the COVID-19 outbreak. © 2022 Faculty of Engineering, Alexandria University

Assessment of Pattern of Drug Abuse from Different Clinical Settings in a Reference Laboratory of Pakistan During the COVID-19 Pandemic

Objective: To determine the pattern of drug abuse from different clinical settings in a reference laboratory of Pakistan during the COVID-19 pandemic and assess any change from the previous trend. Study Design: Comparative cross-sectional study. Place and Duration of Study: Department of Chemical Pathology and Endocrinology, Armed Forces Institute of Pathology (AFIP), Rawalpindi Pakistan from Mar to Dec 2020. Methodology: Out of 6902 subjects tested for drug abuse, 672 subjects with positive results were included in the study. The study population was divided into three main Groups. i.e., Psychiatry, ITC/Emergency and Workplace testing. A pattern of drug abuse was compared in the pre (Mar-Dec 2019) and post-COVID (Mar-Dec 2020) periods. Results: Out of 672 study subjects, 338(50%) were psychiatry patients. Around 629(94%) subjects were males. Mainly young individuals (306, 46%) were affected. Cannabis was the most frequent drug of abuse detected (357, 53%), followed by Benzodiazepines (BZD) (236, 35%) individuals and Opiates (47, 7%). Compared with pre-COVID data, an overall increase of 3% in the total frequency of drug abuse from 392(7%) to 672(10%) was found in 2020. About 14% decrease, from the frequency of 81(21%) to 47(7%) in Opiates usage, while 8% increase in frequency, from 106(27%) to 236(35%) in Benzodiazepines, was observed. There was significant mean difference (p<0.001) between Psychiatric and ITC patients. Conclusion: Most frequent drug abuse in our settings is Cannabis, followed by Benzodiazepines and Opiates. An overall increase in drug abuse frequency while a decrease in the frequency of Opiates users has been observed, a finding different from previous studies. © 2022, Army Medical College. All rights reserved.

Digital Twinning remote laboratories for online practical learning

The COVID19 pandemic has demonstrated a need for remote learning and virtual learning applications such as virtual reality (VR) and tablet-based solutions. Creating complex learning scenarios by developers is highly time-consuming and can take over a year. It is also costly to employ teams of system analysts, developers and 3D artists. There is a requirement to provide a simple method to enable lecturers to create their own content for their laboratory tutorials. Research has been undertaken into developing generic models to enable the semi-automatic creation of virtual learning tools for subjects that require practical interactions with the lab resources. In addition to the system for creating digital twins, a case study describing the creation of a virtual learning application for an electrical laboratory tutorial is presented, demonstrating the feasibility of this approach. © 2022 The Author(s). Published by Informa UK Limited, trading as Taylor & Francis Group.

To evaluate the cardiovascular changes associated with covid-19

Aim: To evaluate the cardiovascular changes associated with covid-19 Methods: One hundred consecutive patients diagnosed with COVID-19 infection underwent complete echocardiographic evaluation within 24 hours of admission and were compared with reference values. Echocardiographic studies included left ventricular (LV) systolic and diastolic function and valve hemodynamics and right ventricular (RV) assessment, as well as lung ultrasound. A second examination was performed in case of clinical deterioration. Results: Clinical data were collected in 120 consecutive patients hospitalized with COVID-19 infection. A total of 20 patients were excluded because they did not undergo echocardiographic assessment. The reasons for not performing the echocardiogram were as follows: hospital discharge within 24 hours of admission (8 patients), patient refusal (2 patient), and death shortly after hospitalisation (8 patients, all >80 years of age and with a “do not resuscitate” status). Conclusions: patients presenting with clinical deterioration at follow-up, acute RV dysfunction, with or without deep vein thrombosis, is more common, but acute LV systolic dysfunction was noted in ≈20%.

The Implications of COVID-19 Pandemic on Dollar Exchange Rate of Pakistan

The Coronavirus disease (COVID-19) most likely began in an animal species and subsequently transmitted to humans in Wuhan, China, a city of 11 million people, on December 29, 2019, when the first case was recorded. The Coronavirus then transmitted from person to person by infected droplets from a sick person's coughing, sneezing, or contaminated hands. Hence, the purpose of the study is to see the impact of the outbreak of COVID-19 daily tests on the Pakistani rupee against the US dollar exchange rate using Vector Autoregressive approach. The data is gathered from February 26, 2020 to March, 2021. This period was selected, because the pandemic expanded, and the first case was observed in Pakistan on Feb 26th 2020. To verify this effect, a Vector Autoregressive Model was developed. A generalized version of the Autoregressive Model is a Vector Autoregressive (VAR) model. As a result of the COVID-19 pandemic, the Pakistani rupee devalued against the US dollar throughout the abovementioned period. When analyzing the Pakistani rupee vs. the US dollar exchange rate using a Vector Autoregressive Model, the values of the lags (1, 4, 6, and 7) of the explanatory variable have a significant impact. Besides, under the VAR model, the IRF (Impulse Response Function) asserted the actual impact of the daily COVID-19 tests, as well as Decomposition of Variance was shown to provide for the daily COVID-19 tests just a small part in understanding the volatility of the Pakistani rupee against the US dollar exchange rate. The Granger Causality suggests that the short-term and long-term changes in the Pakistani rupee against the US dollar exchange rate are caused by daily COVID-19 tests. Copyright © 2022 Akhtar, Abiad, Mashwani, Aamir, Naeem and Khan.

PREVALENCE OF MORTALITY AND ITS DISTRIBUTION BY SEX AND AGE GROUPS IN INDOOR COVID-19 PATIENTS IN D.I.KHAN DIVISION, PAKISTAN

Background: COVID-19 has become one of the leading causes of morbidity and mortality. The objectives of this study were to determine the prevalence of mortality and its distribution by sex and age groups in indoor COVID-19 patients in D.I.Khan Division, Pakistan. Materials & Methods: This cross-sectional study was conducted in the Department of Medicine, Gomal Medical College, D.I.Khan, Pakistan. A sample of 438 patients with positive SARS-CoV-2 RT-PCR was selected. Sex & age groups were two demographic and presence of mortality was a research variable. The data type for all variables was nominal, except ordinal age groups. Prevalence & distribution were described by count and percentage with 95%CI. The hypotheses were tested by chi-square goodness of fit test. Results: Out of 438 COVID-19 patients, mortality was 43 (9.82%), including 34 (7.76%) men and nine (2.06%) women. The mortality was 0% for 0-19 years, four (0.92%) for 20-39 years, 12 (2.74%) for 40-59 years and 27 (6.16%) >= 60 years. Our mortality 9.82% was lower than expected 20.95% (p=<.001). It was higher in men than women (p=<.001). It was highest in age group >= 60 years, while 0% in 0-19 years. It was similar to expected by sex (p=.070) and age group (p=<.207). Conclusion: Our study showed 9.82% mortality in indoor COVID-19 patients. The mortality was lower than expected. The mortality was higher in men than women. It was highest in elderly, while zero in children and adolescents. It was similar to expected by sex and age group.

Threat of covid-19 and perceived stress: The mediating role of challenge, uncontrollability and stressfulness

Objective: To find out the mediating role of challenge, uncontrollability, and stressfulness in predicting perceived stress from threat during COVID-19 pandemic in the general public. Study Design: Cross-sectional survey. Place and Duration of Study: Bahawalpur City, from Mar to May 2020. Methodology: A total of 360 participants (men=154, women=206) were recruited from different cities of Punjab province. The stress appraisal measure, perceived stress scale, and coping scale were administered through Google forms using social media platforms. The participation in the online survey implied signing the written informed consent available in the survey. Results: The primary and secondary appraisals of challenge (IE=0.84, SE=0.27, 95% LL=0.31, 95% UL=1.40), uncontrollability (IE=1.03, SE=0.36, 95% LL=0.34, 95% UL=1.76), and stressfulness (IE=-0.28, SE=0.12, 95% LL=-0.56, 95% UL=-0.08) fully mediated the relationship between threat of COVID-19 and perceived stress. Additionally, there was statistically significant positive relationship between threat of COVID-19 and use of coping strategies (r=0.14, p<0.01). The statistics of women regarding appraisals of threat, uncontrollability, stressfulness and perceived stress (2.94 ± 0.88);(2.49 ± 0.84);(2.87 ± 0.73);(19.92 ± 6.08), were found to be slightly higher on as compared to men (2.76 ± 0.82);(2.25 ± 0.81);(2.58 ± 0.76);(18.41 ± 5.37) respectively with p=0.01, Cohen’s d=0.21);p=0.001, Cohen’s d=0.29);p=0.001, Cohen’s d=0.38);(p=0.01, Cohen’s d=0.26). Conclusion: The threat of COVID-19 significantly led to the experience of perceived stress through the mediating role of primary and secondary appraisals of challenge, uncontrollability, and stressfulness. © 2021, Army Medical College. All rights reserved.

Analysis and Forecast of the Number of Deaths, Recovered Cases, and Confirmed Cases From COVID-19 for the Top Four Affected Countries Using Kalman Filter

COVID-19 is a virus that spread globally, causing severe health complications and substantial economic impact in various parts of the world. The COVID-19 forecast on infections is significant and crucial information that will help in executing policies and effectively reducing the daily cases. Filtering techniques are important ways to model dynamic structures because they provide good valuations over the recursive Bayesian updates. Kalman filters, one of the filtering techniques, are useful in the studying of contagious infections. Kalman filter algorithm performs an important role in the development of actual and comprehensive approaches to inhibit, learn, react, and reduce spreadable disorder outbreaks in people. The purpose of this paper is to forecast COVID-19 infections using the Kalman filter method. The Kalman filter (KF) was applied for the four most affected countries, namely the United States, India, Brazil, and Russia. Based on the results obtained, the KF method is capable of keeping track of the real COVID-19 data in nearly all scenarios. Kalman filters in the archetype background implement and produce decent COVID-19 predictions. The results of the KF method support the decision-making process for short-term strategies in handling the COVID-19 outbreak. © Copyright © 2021 Ahmadini, Naeem, Aamir, Dewan, Alshqaq and Mashwani.