DEEP LEARNING BASED AN EFFICIENT HYBRID PREDICTION MODEL FOR COVID-19 CROSS-COUNTRY SPREAD AMONG E7 AND G7 COUNTRIES

The COVID-19 pandemic has caused the death of many people around the world and has also caused economic problems for all countries in the world. In the literature, there are many studies to analyze and predict the spread of COVID-19 in cities and countries. However, there is no study to predict and analyze the cross-country spread in the world. In this study, a deep learning based hybrid model was developed to predict and analysis of COVID-19 cross-country spread and a case study was carried out for Emerging Seven (E7) and Group of Seven (G7) countries. It is aimed to reduce the workload of healthcare professionals and to make health plans by predicting the daily number of COVID-19 cases and deaths. Developed model was tested extensively using Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE) and R Squared (R2). The experimental results showed that the developed model was more successful to predict and analysis of COVID-19 cross-country spread in E7 and G7 countries than Linear Regression (LR), Random Forest (RF), Support Vector Machine (SVM), Multilayer Perceptron (MLP), Convolutional Neural Network (CNN), Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM). The developed model has R2 value close to 0.9 in predicting the number of daily cases and deaths in the majority of E7 and G7 countries. © 2023 by the authors.

Deep-learning models for Covid-19 Detection Using Chest X-Ray Images

Deep Convolutional Neural Networks are a form of neural network that can categorize, recognize, or separate images. The problem of COVID-19 detection has become the world's most complex challenge since 2019. In this research work, Chest X-Ray images are used to detect patients' Covid Positive or Negative with the help of pre-trained models: VGG16, InceptionV3, ResNet50, and InceptionResNetV2. In this paper, 821 samples are used for training, 186 samples for validation, and 184 samples are used for testing. Hybrid model InceptionResNetV2 has achieved overall maximum accuracy of 94.56% with a Recall value of 96% for normal CXR images, and a precision of 95.12% for Covid Positive images. The lowest accuracy was achieved by the ResNet50 model of 92.93% on the testing dataset, and a Recall of 93.93% was achieved for the normal images. Throughout the implementation process, it was discovered that factors like epoch had a considerable impact on the model's accuracy. Consequently, it is advised that the model be trained with a sufficient number of epochs to provide reliable classification results. The study's findings suggest that deep learning models have an excellent potential for correctly identifying the covid positive or covid negative using CXR images. © 2023 IEEE.

A Hybrid Model of Deep Learning Features and Clinical Features for Severe Cases Predication of COVID-19

COVID-19 has spread around the world since 2019. Approximately 6.5% of COVID-19 a risk of developing severe disease with high mortality rate. To reduce the mortality rate and provide appropriate treatment, this research established an integrated models with to predict the clinical outcome of COVID-19 patients with clinical, deep learning and radiomics features. To obtain the optimal feature combination for prediction, 9 clinical features combination was selected from all available clinical factors after using LASSO, 18 deep learning features from U-Net architecture, and 9 radiomics features from segmentation result. A total of 213 COVID-19 patients and 335 non-COVID-19 patients from 5 hospitals were enrolled and used as training and test sample in this research. The proposed model obtained an accuracy, precision, recall, specificity, F1-score and ROC curve of 0.971, 0.943, 0.937, 0.974, 0.941 and 0.979, respectively, which exceeds the related work using only clinical, deep learning or radiomics factors. © 2023 SPIE.

Machine Learning-Based Hybrid Ensemble Model Achieving Precision Education for Online Education Amid the Lockdown Period of COVID-19 Pandemic in Pakistan

Institutions of higher learning have made persistent efforts to provide students with a high-quality education. Educational data mining (EDM) enables academic institutions to gain insight into student data in order to extract information for making predictions. COVID-19 represents the most catastrophic pandemic in human history. As a result of the global pandemic, all educational systems were shifted to online learning (OL). Due to issues with accessing the internet, disinterest, and a lack of available tools, online education has proven challenging for many students. Acquiring accurate education has emerged as a major goal for the future of this popular medium of education. Therefore, the focus of this research was to identifying attributes that could help in students' performance prediction through a generalizable model achieving precision education in online education. The dataset used in this research was compiled from a survey taken primarily during the academic year of COVID-19, which was taken from the perspective of Pakistani university students. Five machine learning (ML) regressors were used in order to train the model, and its results were then analyzed. Comparatively, SVM has outperformed the other methods, yielding 87.5% accuracy, which was the highest of all the models tested. After that, an efficient hybrid ensemble model of machine learning was used to predict student performance using NB, KNN, SVM, decision tree, and logical regression during the COVID-19 period, yielding outclass results. Finally, the accuracy obtained through the hybrid ensemble model was obtained as 98.6%, which demonstrated that the hybrid ensemble learning model has performed better than any other model for predicting the performance of students.

A Hybrid Model for Covid-19 Detection using CT-Scans

Although some believe it has been wiped out, the coronavirus is striking again. Controlling this epidemic necessitates early detection of coronavirus disease. Computed tomography (CT) scan images allow fast and accurate screening for COVID-19. This study seeks to develop the most precise model for identifying and classifying COVID-19 by developing an automated approach using transfer-learning CNN models as a base. Transfer learning models like VGG16, Resnet50, and Xception are employed in this study. The VGG16 has a 98.39% accuracy, the Resnet50 has a 97.27% accuracy, and the Xception has a 96.6% accuracy;after that, a hybrid model made using the stacking ensemble method has an accuracy of 98.71%. According to the findings, hybrid architecture offers greater accuracy than a single architecture. © 2023,International Journal of Advanced Computer Science and Applications. All Rights Reserved.

Residential Load Forecasting based on Deep Neural Network

This paper presents residential load forecasting using multivariate multi-step Deep Neural Networks (DNN) such as LSTM, CNN, Stacked LSTM, and Hybrid CNN-LSTM. A preliminary Exploratory Data Analysis (EDA) is conducted, and the decision variables are identified. An elbowing method is used to determine the number of clusters. Data is categorized based on weekdays, weekends, vacations, and Covid-Lockdown. Dimensionality-reduction using principal component analysis (PCA) is conducted. Seasonality-based clustering is found to improve the DNN model prediction accuracy further. A comparative analysis employs error metrics such as RMSE, MSE, MAPE, and MAE. The multivariate LSTM model with feedback is found to be the best fit model with the better performance indices. © 2023 IEEE.

Demographic differences in services utilization across in-person (2019), telehealth (2020), and hybrid (2021) outpatient substance use services in New York.

OBJECTIVES: Many outpatient substance use programs have experienced in-person, remote/telehealth, and hybrid models of care since the 2020 Covid-19 Pandemic. Changes in treatment models naturally affect service utilization and may affect treatment trajectories. Currently, limited research examines the implications of different health care models on service utilization and patient outcomes in substance use treatment. Here, we reflect on the implications of each model from a patient-centered care approach and review the implications on service utilization and outcomes. METHODS: We employed a retrospective, observational, longitudinal, cohort design to explore differences in demographic characteristics and service utilization among patients receiving in-person, remote, or hybrid services across four substance use clinics in New York. We reviewed admission (N = 2238) and discharge (N = 2044) data from four outpatient SUD clinics within the same health care system across three cohorts (2019, in-person; 2020, remote; 2021, hybrid). RESULTS: Patients discharged in 2021 (hybrid) had significantly more median total treatment visits (M = 26, p ≤ 0.0005), a longer course of treatment (M = 154.5 days, p ≤ 0.0001), and more individual counseling sessions (M = 9, p ≤ 0.0001) compared to the other two cohorts. Demographic analyses indicate more ethnoracial diversity (p = 0.0006) among patients admitted in 2021, compared to the other two cohorts. Over time, the proportion of individuals being admitted with a co-existing psychiatric disorder (2019, 49 %; 2020; 55.4 %, 2021, 54.9 %) and no prior mental health treatment (2019, 49.4 %; 2020, 46.0 %; 2021, 69.3 %) increased (p = 0.0001). Admissions in 2021 were more likely to be self-referred (32.5 %, p < 0.0001), employed full-time (39.5 %, p = 0.01), and have higher educational attainment (p = 0.0008). CONCLUSION: During hybrid treatment in 2021, patients from a wider range of ethnoracial backgrounds were admitted and retained in care, patients with higher socioeconomic status (who were previously less likely to enter treatment) were admitted, and fewer individuals left against clinical advice (compared to the remote 2020 cohort). More patients successfully completed treatment in 2021. Service utilization, demographic, and outcome trends support a hybrid model of care.

Maternity care during a pandemic: Can a hybrid telehealth model comprising group interdisciplinary education support maternal psychological health?

BACKGROUND: The transition to parenthood is one of the most challenging across the life course, with profound changes that can impact psychological health. In response to the coronavirus disease 2019 (COVID-19), came the rapid implementation of remote antenatal care, i.e., telehealth, with fewer in-person consultations. A change in service delivery in addition to the cancellation of antenatal education represented a potential threat to a woman's experience - with likely adverse effects on mental health and wellbeing. AIM: To explore a hybrid model of pregnancy care, i.e., telehealth and fewer in-person health assessments, coupled with concurrent small group interdisciplinary education delivered via video conferencing, extending into the postnatal period. METHODS: Using a quasi-experimental design with an interrupted time series and a control group, this population-based study recruited low-risk women booking for maternity care at one community health site affiliated with a large public hospital in Victoria, Australia. FINDINGS: Whilst there was no difference in stress and anxiety scores, a significant interactive effect of the hybrid model of care with time was seen in the DASS depression score (-1.17, 95% CI: -1.81, -0.53) and the EPDS (-0.83, 95% CI: -1.5, -0.15). DISCUSSION: The analyses provide important exploratory findings regarding the positive effects of a hybrid model of care with interdisciplinary education in supporting mental health of first-time mothers. CONCLUSION: This study demonstrates that small group online education scheduled in conjunction with individual pregnancy health assessments can be executed within a busy antenatal clinic with promising results and modest but dedicated staff support.

Hybrid Artificial Intelligence-Based Models for Prediction of Death Rate in India Due to COVID-19 Transmission

COVID-19 prediction models are highly welcome and necessary for authorities to make informed decisions. Traditional models, which were used in the past, were unable to reliably estimate death rates due to procedural flaws. The genetic algorithm in association with an artificial neural network (GA-ANN) is one of the suitable blended AI strategies that can foretell more correctly by resolving this difficult COVID-19 phenomena. The genetic algorithm is used to simultaneously optimise all of the ANN parameters. In this work, GA-ANN and ANN models were performed by applying historical daily data from sick, recovered, and dead people in India. The performance of the designed hybrid GA-ANN model is validated by comparing it to the standard ANN and MLR approach. It was determined that the GA-ANN model outperformed the ANN model. When compared to previous examined models for predicting mortality rates in India, the hypothesized hybrid GA-ANN model is the most competent. This hybrid AI (GA-ANN) model is suggested for the prediction due to reasonably better performance and ease of implementation.

CNS: Hybrid Explainable Artificial Intelligence-Based Sentiment Analysis on COVID-19 Lockdown Using Twitter Data

COVID-19 preventive measures have been a hindrance to millions of people over the globe not only affecting their daily routine but also affecting the mental stability. Among several preventive measures for COVID-19 spread, the lockdown is an important measure which helps considerably reduce the number of cases. The updated news about the COVID-19 is drastically spread in social media. Particularly, Twitter is widely used to share posts and opinions about the COVID-19 pandemic. Sentiment analysis (SA) on tweets can be used to determine different emotions such as anger, disgust, sadness, joy, and trust. But transparence is needed to understand how a given sentiment is evaluated with the black-box machine learning models. With this motivation, this paper presents a new explainable artificial intelligence (XAI)-based hybrid approach to analyze the sentiments of the tweets during different COVID-19 lockdowns. The proposed model attempted to understand the public's emotions during the first, second, and third lockdowns in India by analyzing tweets on social media, and demonstrates the novelty of the work. A new hybrid model is derived by integrating surrogate model and local interpretable model-agnostic explanation (LIME) model to categorize and predict different human emotions. At the same time, the Topj Similarity evaluation metric is employed to determine the similarity between the original and surrogate models. Furthermore, top words using the feature importance are identified. Finally, the overall emotions during the first, second, and third lockdowns are also estimated. For validating the enhanced outcomes of the proposed method, a series of experimental analysis was performed on the IEEE port and Twitter API dataset. The simulation results highlighted the supremacy of the proposed model with higher average precision, recall, F-score, and accuracy of 95.69%, 96.80%, 95.04%, and 96.76%, respectively. The outcome of the study reported that the public initially had a negative feeling and then started experiencing positive emotions during the third lockdown. © 2022 World Scientific Publishing Company.

Research and Design of an Emergency Supply Assurance Monitoring System in the Post-epidemic Context

At present, the COVID-19 epidemic is still ravaging the world, and the domestic epidemic is still recurring and continues to affect people's life and work. The research and design of an emergency supply assurance monitoring system in response to the epidemic and other emergencies, which provides the competent authorities with monitoring alert and trend data of supply, demand and price of essential goods market, is of great significance to stabilize people's basic essential goods materials. Based on the data of essential goods under epidemic, the system carries out the construction and application of monitoring and warning model and RNN-SARIMA hybrid model. Through the research and design of the system, monitoring and warning of abnormal fluctuations of essential goods and predicting price trends are realized. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Transformation of the post-covid media ecosystem. Teleworking and the hybrid model as organisational innovation in newsrooms

The covid-19 pandemic accelerated the media's efforts to survive in an unprecedented crisis. In this context, teleworking, despite having existed for decades, stood out as an efficient solution to sustain organisational processes. This exploratory study analyses the impact of teleworking and the introduction of hybrid formulas in two newspaper companies in the Spanish market (eldiario.es and Heraldo de Aragón), once the toughest stage of the pandemic was overcome. Through participant observation and in-depth interviews with experts and media professionals, we investigate whether the new teleworking formulas are innovative and if they could be adopted in the future. The results reveal that the impact of telework on news organisations has been decisive, especially to reshape the way in which ideas are shared and workflows are established. The adaptability of the case studies to the new organisational models has been found to be high;however, there are some factors limiting their full adoption. The hybrid telework model has brought unprecedented organisational change to many newsrooms and has accelerated digital transformation. However, there is still some uncertainty, because even in those newspapers that are committed to the model, implementation is still being developed. © 2023, CEU Ediciones. All rights reserved.

DEVS Model Design for Simulation Web App Deployment

The discrete-event system specification (DEVS) formalism has been recognized to be able to enable a formal and complete description of the components and subsystems of hybrid models. What is missing for accelerated adoption of DEVS-based methodology is to offer a way to design web apps to interact with a simulation model and to automatically deploy it on an online server which is remotely accessible from web app. The deployment of DEVS simulation models is the process of making models available in production where web applications, enterprise software, and APIs can consume the simulation by providing new inputs and generating outputs. This paper proposes a framework allowing one to simplify the DEVS simulation model building and deployment on the web by the modeling and simulation engineers with minimal web development knowledge. A case study on the management of COVID-19 epidemic surveillance is presented. © 2022 IEEE.

MepoGNN: Metapopulation Epidemic Forecasting with Graph Neural Networks

Epidemic prediction is a fundamental task for epidemic control and prevention. Many mechanistic models and deep learning models are built for this task. However, most mechanistic models have difficulty estimating the time/region-varying epidemiological parameters, while most deep learning models lack the guidance of epidemiological domain knowledge and interpretability of prediction results. In this study, we propose a novel hybrid model called MepoGNN for multi-step multi-region epidemic forecasting by incorporating Graph Neural Networks (GNNs) and graph learning mechanisms into Metapopulation SIR model. Our model can not only predict the number of confirmed cases but also explicitly learn the epidemiological parameters and the underlying epidemic propagation graph from heterogeneous data in an end-to-end manner. Experiment results demonstrate our model outperforms the existing mechanistic models and deep learning models by a large margin. Furthermore, the analysis on the learned parameters demonstrates the high reliability and interpretability of our model and helps better understanding of epidemic spread. Our model and data have already been public on GitHub https://github.com/deepkashiwa20/MepoGNN.git. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

A System Dynamics Model for Studying the Resiliency of Supply Chains and Informing Mitigation Policies for Responding to Disruptions

Economic shocks are unanticipated events that have widespread impact on an economy and can lead to supply chain disruptions that propagate from one region to another. The COVID-19 pandemic is a recent example. Simulations have been applied to study the impact of COVID-19 shocks on supply chains at the macro level using various approaches. This research has developed a hybrid System Dynamics and Input/Output simulation to model the economic impact of various types of supply chain disruptions. The hybrid model provides results that match historical performance of the U.S. economy under COVID-19 shocks and provides reasonable results when applied to investigate U.S. dependence on foreign trade. Its graphical nature also supports a decision support tool that will allow policymakers to explore the costs and benefits of various policy decisions designed to mitigate the impact of a broad set of potential supply chain disruptions. © 2022 IEEE.

Hybrid Model of Teaching-Learning is Total Chaos: An effect of Reverse Halo

Although the COVID-19 outbreak has had a disruptive impact on the education industry;the academicians have moulded themselves according to changing situations. They have evolved to an entirely different level during the last two years. This longitudinal study is conducted on faculty members from all over India and aimed to explore some individual and organizational factors affecting the "Hybrid” model of the teaching-learning process, which is the future of the education and training industry [1] [2] creating a Reverse Halo Effect [3]. More than 1000 faculty members from all over India have contacted over WhatsApp and a self-report questionnaire in the form of Google Form measuring various student-related factors, institute-related issues, faculty-related issues, technology-related issues, perceived learning, and perceived employability was circulated. A path analysis showed that the student-related issues, faculty-related issues, institute-related issues, and technology-related issues affect perceived learning which will eventually affect the perceived employability of students. The findings of this study provide a theoretical contribution toward the effectiveness of the hybrid model in the teaching-learning process and its effect on the perceived learning and employability of students. © 2022, Rajarambapu Institute Of Technology. All rights reserved.

Using a hybrid simulation model to assess the impacts of combined COVID-19 containment measures in a high-speed train station

In this study, we present a hybrid agent-based model (ABM) and discrete event simulation (DES) framework where ABM captures the spread dynamics of COVID-19 via asymptomatic passengers and DES captures the impacts of environmental variables, such as service process capacity, on the results of different containment measures in a typical high-speed train station in China. The containment and control measures simulated include as-is (nothing changed) passenger flow control, enforcing social distancing, adherence level in face mask-wearing, and adding capacity to current service stations. These measures are evaluated individually and then jointly under a different initial number of asymptomatic passengers. The results show how some measures can consolidate the outcomes for each other, while combinations of certain measures could compromise the outcomes for one or the other due to unbalanced service process configurations. The hybrid ABM and DES models offer a useful multi-function simulation tool to help inform decision/policy makers of intervention designs and implementations for addressing issues like public health emergencies and emergency evacuations. Challenges still exist for the hybrid model due to the limited availability of simulation platforms, extensive consumption of computing resources, and difficulties in validation and optimisation. © 2023 The Operational Research Society.

A Hybrid Approach for Detection of Fake News in Sinhala Text

The impact of technology on people's lives has grown continuously. The consumption of online news is one of the important trends as the share of population with internet access grows rapidly over time. Global statistics have shown that the internet and social media usage has an increasing trend. Recent developments like the Covid 19 pandemic have amplified this trend even more. However, the credibility of online news is a very critical issue to consider since it directly impacts the society and the people's mindsets. Majority of users tend to instinctively believe what they encounter and come into conclusions based upon them. It is essential that the consumers have an understanding or prior knowledge regarding the news and its source before coming into conclusions. This research proposes a hybrid model to predict the accuracy of a particular news article in Sinhala text. The model combines the general news content based analysis techniques using machine learning/ deep learning classifiers with social network related features of the news source to make predictions. A scoring mechanism is utilized to provide an overall score to a given news item where two independent scores- Accuracy Score (by analyzing the news content) and Credibility Score (by a scoring mechanism on social network features of the news source) are combined. The hybrid model containing the Passive Aggressive Classifier has shown the highest accuracy of 88%. Also, the models containing deep neural netWorks has shown accuracy around 75-80%. These results highlight that the proposed method could efficiently serve as a Fake News Detection mechanism for news content in Sinhala Language. Also, since there's no publicly available dataset for Fake News detection in Sinhala, the datasets produced in this work could also be considered as a contribution from this research. © 2022 IEEE.

The impact of the COVID-19 pandemic on instructor perspectives about online teaching in higher education from a small private university

The COVID-19 pandemic had caused major changes in many aspects of our lives when it spread worldwide at the beginning of 2020. Hence, higher education was affected when the face-to-face classes were suspended and moved completely online. The aim of this study was to investigate the impact of COVID-19 on faculty perspectives about online teaching in general. Also, the study focused on challenges that faculty encountered during the transition and highlighted major skills that instructors learned. The mixed methodologies were developed and grounded in a transformative learning theory (TLT) framework, relying on an online questionnaire and semi-structured interviews. After analyzing data of 178 participants (N = 178, 61% response rate), and interviewing instructors, the results show that faculty have different perspectives about online teaching in general. The descriptive statistics indicated that COVID-19 had a significant impact on faculty attitudes in various areas, including familiarity with online teaching, comparison of online learning to traditional learning, and output quality. Faculty showed familiarity with online teaching and a positive attitude when comparing online environments to face-to-face learning, but negative attitude toward output quality. The data also revealed that the online synchronous strategy was used the most (n = 78, 46%), followed by the hybrid model (n = 77, 45%). Additionally, the qualitative data revealed a mash-up of themes, including obstacles and abilities. The most common problems encountered throughout the pandemic were student engagement, academic integrity and practical skills. During the pandemic, however, the top abilities were determined to be student engagement, delivering feedback, managing with classroom technologies, flexibility and confidence. (PsycInfo Database Record (c) 2023 APA, all rights reserved)

Adaptive Collaborative Learning Process in a Hybrid Model

Technological progress has led to the integration of technology into the practices of the learning process. The aim of this integration is to overcome the deficiencies of traditional methods to ensure greater efficiency. Despite the technology revolution, the adoption of e-learning has always been a choice in the educational process. The COVID 19 crisis has shown the need for a total transition to e-learning during the period of lockdown. According to several studies that have assessed the impact of COVID 19 on their education systems and the solutions adopted, hybrid learning represents an adequate solution to benefit from the advantages of both modes: face-to-face and distance learning. For this purpose, we propose in this paper a hybrid learning model based on an adaptive collaborative work through an intelligent assignment of the group member's roles by using Naïve Bayes algorithm and Belbin theory. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.