Forecasting COVID-19 Pandemic using Prophet, LSTM, hybrid GRU-LSTM, CNN-LSTM, Bi-LSTM and Stacked-LSTM for India

The COVID-19 Pandemic has been around for four years and remains a health concern for everyone. Although things are somewhat returning to normal, increased incidence of COVID-19 cases in some regions of the world (such as China, Japan, France, South Korea, etc.) has bred worry and anxiety in world, including India. The scientific community, which includes governmental organizations and healthcare facilities, was eager to learn how the COVID-19 Pandemic would develop. The current work makes an attempt to address this question by employing cutting-edge machine learning and Deep Learning algorithms to anticipate the daily incidence of COVID-19 for India over the course of the next six months. For the purpose famous timeseries algorithms were implemented including LSTM, Bi-Directional LSTM and Stacked LSTM and Prophet. Owing to success of hybrid algorithms in specific problem domains- the present study also focuses on such algorithms like GRU-LSTM, CNN-LSTM and LSTM with Attention. All these models have been trained on timeseries dataset of COVID-19 for India and performance metrics are recorded. Of all the models, the simplistic algorithms have performed better than complex and hybrid ones. Owing to this best result was obtained with Prophet, Bidirectional LSTM and Vanilla LSTM. The forecast reveals flat nature of COVID-19 case load for India in future six months. . © 2023 IEEE.

Work in Progress: A Virtual Educational Robotics Coding Club Framework to Improve K-6 Students Emotional Engagement in STEM

Educational robots allow students deepen their knowledge of mathematics and scientific concepts. Educational Robotic coding clubs provide a learning environment for K-6 students that promotes coding through STEM digital literacy. Students in educationally disadvantaged families may not have the educational and financial capital to engage in STEM learning. Closures of schools and afterschool services during the COVID-19 pandemic increased this digital divide. This research proposes a framework for delivering a virtual robotic coding club in an educationally disadvantaged community. The framework develops young people's emotional engagement in STEM through robotic coding. Synchronous online classes were delivered into family homes using Zoom. Results demonstrate that children achieved emotional engagement as reported through high levels of enjoyment and increased interest after participating in the programme. The research shows promise in increasing children's STEM skills and knowledge, and in improving positive attitudes towards STEM for children and parents. © 2023 IEEE.

Predicting COVID-19 Fourth Wave Incidence in India Using Machine Learning Algorithms and SEIR Model

The world is witnessing COVID - 19 Pandemic for quite some time now. India has seen three waves of COVID-19 in the last 700 days. The curiosity still lies in the occurrence and timing of the fourth wave. The current study tries to solve this and predicts the COVID-19 daily incidence in India in the future. State-of-the-art methodologies both from Machine learning (LSTM, KNN, SVR, Random Forest, and Multi Linear Regressor) and Mathematical models (SEIR) have been tried out to train and predict the Daily New Cases of COVID19 in India. Further prediction for the next 200 days has been tried out using the trained models. As per the forecast from most of the models, it is evident that no fourth wave is going to be witnessed in India in the next 200 days. © 2022 IEEE.

A Framework for Managing the Transition from Second Level to Higher Education in Response to the COVID19 Emergency Restrictions

This Research-to-Practice Full Paper looks at the transition from second level education to higher education and the challenges this presents in terms of students getting to know a new learning environment, identifying supports to assist with their learning and even getting to know new friends. This challenge is even more complicated with the move to an online learning environment in response to the COVID19 emergency restrictions. This research introduces a higher education transition framework (called S³F) that provides support and intervention activities to manage students transition from second level education to higher education, to reduce the impact of the online environment on students learning experience and to help to improve student mental health. The S³F framework uses ongoing student Feedback to inform activities across three pillars: Learning Environment Support, Academic Subject Support and Social Support. The research presented in this paper was conducted over the 2020/2021 academic year when 1st year undergraduate Computing students from National College of Ireland, School of Computing participated in an innovative induction programme that consisted of a number of activities and support actions for the entire duration of the academic year that were part of the S³F framework. Students were surveyed during each induction session for live feedback to adapt the activities for the following sessions and to inform staff of other interventions required. Students initially have expressed feelings of nervousness at the start of the first semester however this changed to feelings of excitement midway through the induction programme. Results of the case study demonstrates that the activities and innovative actions introduced as part of S³F framework had a positive impact on student's transition to higher education, especially around mental health, seen in the retention figures for those students. This paper discusses the results only in terms of students mental health This research is of benefit to higher education management and course directors involved in first year orientation that would like to reduce the impact of the online environment on student's transition from second level to higher education. © 2022 IEEE.

Reserve system design for allocation of scarce medical resources in a pandemic: some perspectives from the field

Reserve systems are a tool to allocate scarce resources when stakeholders do not have a single objective. This paper introduces some basic concepts about reserve systems for pandemic medical resource allocation. At the onset of the Covid-19 pandemic, we proposed that reserve systems can help practitioners arrive at compromises between competing stakeholders. More than a dozen states and local jurisdictions adopted reserve systems in initial phases of vaccine distribution. We highlight several design issues arising in some of these implementations. We also offer suggestions about ways practitioners can take advantage of the flexibility offered by reserve systems.

Evolving robotic process automation (RPA) & artificial intelligence (AI) in response to Covid-19 and its future

The recent outbreak of COVID-19 across the globe has been a challenge not just to the health & well-being of people. However, it has also led to a downturn in the economy throughout the world. The purpose of this study is to thoroughly investigate the possible use of emerging technologies such as robotic process automation (RPA) and artificial intelligence (AI) in order to find ways to tackle corona virus, its impact on the economy, and the people. The other technology involved is RPA which is a type of process that can easily and efficiently make it convenient for any machine to handle a repetitive task. When these two technologies are coupled, they can be used in a wide range of applications. This paper explains how RPA and AI can separately, used in various industries and sectors to tackle and effectively reduce the corona virus pandemic's negative impact. © 2022 Author(s).

A Dashboard for Mitigating the COVID-19 Misinfodemic

This paper describes the current milestones achieved in our ongoing project that aims to understand the surveillance of, impact of, and effective interventions against the COVID-19 misinfodemic on Twitter. Specifically, it introduces a public dashboard which, in addition to displaying case counts in an interactive map and a navigational panel, also provides some unique features not found in other places. Particularly, the dashboard uses a curated catalog of COVID-19 related facts and debunks of misinformation, and it displays the most prevalent information from the catalog among Twitter users in user-selected U.S. geographic regions. The paper explains how to use BERT-based models to match tweets with the facts and misinformation and to detect their stance towards such information. The paper also discusses the results of preliminary experiments on analyzing the spatiotemporal spread of misinformation.

A Process Model for transitioning to alternative assessment and authentication in response to the COVID19 emergency restrictions

Terminal exams moved to online in response to the COVID19 emergency restrictions. Moving to alternative forms of assessment in a short timescale presents challenges for academic integrity. Academic integrity revolves around determining that work submitted is by the enrolled learner. This research proposes a Terminal Assignment Based Assessment Process Model that provides faculty with structured guidance to address academic integrity issues. The process model describes the roles and responsibilities of Academic and Administrative staff in the creation of assessments that are valid and reliable. Guidance revolves around assessment variability and information use. Assessment variability involves introducing variability into the question so that each student works on a unique problem. Information use revolves around the application of knowledge rather than knowledge recall. The process model was applied successfully over four semesters. This research discusses the process model and guidance with an applied examples of assessment variability and information use.

Blockchain and IoT in developing Fintech Ecosystem- An assistance to Insurance Industry

PURPOSE- The Covid Pandemic has coerced the insurers to determine how best to meet the demands of their customers, provide service with minimal effort, and achieve their cost efficiency objective. The cost-efficiency objective of the insurance industry should also be aimed at freeing up funds to invest in new technologies and not lose sight of the transformation imperative. The insurance business, despite its size, is underrepresented in the literature. As a result, this paper explains how blockchain technology and IoT might benefit the insurance business. We go over the fundamentals of blockchain and IoT, the most prominent platforms already in use, and a short theoretical description of the insurance sub-processes that both the technologies can positively alter. We also go over the roadblocks that must be overcome in order to properly utilize blockchain technology in the insurance industry.RESEARCH METHODOLOGY- This study provides a qualitative assessment and analysis of journals, articles, and white papers on the implementation of Blockchain and IoT in the Insurance industry, as well as research trends. In addition, the study attempts to identify potential opportunities in the insurance business. The systematic review aims to bring together findings from several fields of study. The goal of this review article is to analyze both the literature sources to comprehend the actual levels of implementation and use cases, as well as to determine the direction in which the insurance industry is now heading in terms of technological adoption.ORIGINALITY- It also covers a wide range of study topics, as well as the most significant articles from the best journals. This paper also covers book chapters, conference papers, journal articles, review papers, white papers, and reports from various organizations.IMPLICATION- The research can prove to be a useful beginning point for new researchers looking for interesting and relevant research on the application and implementation of blockchain and IoT in general insurance. © 2022 IEEE.

The trade-off between prioritization and vaccination speed depends on mitigation measures

Calls for eliminating prioritization for SARS-CoV-2 vaccines are growing amid concerns that prioritization reduces vaccination speed. We use an SEIR model to study the effects of vaccination distribution on public health, comparing prioritization policy and speed under mitigation measures that are either eased during the vaccine rollout or sustained through the end of the pandemic period. NASEM's recommended prioritization results in fewer deaths than no prioritization, but does not minimize total deaths. If mitigation measures are eased, abandoning NASEM will result in about 134,000 more deaths at 30 million vaccinations per month. Vaccination speed must be at least 53% higher under no prioritization to avoid increasing deaths. With sustained mitigation, discarding NASEM prioritization will result in 42,000 more deaths, requiring only a 26% increase in speed to hold deaths constant. Therefore, abandoning NASEM's prioritization to increase vaccination speed without substantially increasing deaths may require sustained mitigation.

Covid under the sheets, a STI clinic survives lockdown!

Background Our aim principally was to assess our readiness to remain open as we provide an essential public health service namely the treatment of infectious diseases. Facing this pandemic with limited preparation time, the journey of our sexual health clinic had to evolve multiple times in order in to provide optimal care for our patient population. Method A retrospective study was conducted of all consultations during March - June 2020, which was Ireland's first lockdown period and was compared to the same period in 2019. Results 251 symptomatic people attended the clinic in 2019 compared to 129 attendees in 2020. We assume;this was due to our national lockdown due to a global pandemic. Of note, a doubling of Herpes Simplex Virus (HSV) rates was noted from 4% in 2019 to 8% in 2020. Non- sexually transmitted infections increased from 11% in 2019 to 53% in 2020, These included genital dermatoses, non-specific urethritis, and testicular pathologies such as epididymitis. Conclusion Our sexual health clinic adapted overnight to the challenges of Covid-19 with virtual consults being one of many new techniques that were employed. The high number of symptomatic patients certainly surprised us but also helped us in understanding human nature and their craving for social interaction..

Natural Language Processing (NLP) and Its Impact across Industries - Unlocking the True Potential of Digital Healthcare (A Case Study Approach)

During the advent of the 21st century, technical breakthroughs and developments took place. Natural Language Processing or NLP is one of their promising disciplines that has been increasingly dynamic via groundbreaking findings on most computer networks. Because of the digital revolution the amounts of data generated by M2M communication across devices and platforms such as Amazon Alexa, Apple Siri, Microsoft Cortana, etc. were significantly increased. This causes a great deal of unstructured data to be processed that does not fit in with standard computational models. In addition, the increasing problems of language complexity, data variability and voice ambiguity make implementing models increasingly harder. The current study provides an overview of the potential and breadth of the NLP market and its acceptance in industry-wide, in particular after Covid-19. It also gives a macroscopic picture of progress in natural language processing research, development and implementation.

Developing and implementing a weighted lottery to equitably allocate scarce COVID-19 medications

RATIONALE: The burdens of the COVID-19 pandemic have fallen disproportionately on disadvantaged groups, including the poor and Black, Latinx, and Indigenous communities. We sought to develop and implement a weighted lottery to more equitably allocate scarce COVID-19 medications in a large U.S. health system. METHODS: We convened a multi-institution consortium of experts in bioethics, economics, health disparities, medicine, pharmacy, and health law to develop the weighted lottery. The UPMC Patient and Family Advisory Council and the Commonwealth of Pennsylvania's Ethical Allocation Committee reviewed and endorsed the framework. We implemented the weighted lottery during periods when there was inadequate remdesivir to treat all patients in need. We used administrative data to ascertain the number and characteristics of patients who, on days of drug shortage: 1) were eligible for remdesivir;2) were offered remdesivir;and 3) accepted remdesivir. RESULTS: We implemented the weighted lottery across 23 hospitals in the UPMC health system during periods of drug shortage in May-July 2020. We proactively identified eligible patients using an EHR-and telephone-based screening system. To determine the general population chances in the lottery, each week we divided the number of available treatment courses by the predicted number of patients who would be eligible that week, based on the number of eligible patients in the prior week. The table contains the weighting factors in the remdesivir lottery. An allocation team met daily to apply the weighting system that determined each eligible patient's chance, then used a random number generator to run the lottery. Overall, 93 patients met the clinical eligibility criteria outlined in the FDA's emergency use authorization;44% were from disadvantaged neighborhoods, 20% were essential workers, and 9% had an underlying end-stage medical condition. During the periods of drug shortage, the general population chances to receive treatment ranged from 28%-88%. 59% of eligible patients (55 of 93) were allocated remdesivir, 13% of whom (7 of 55) refused the treatment. Overall 61% of drug was allocated to patients who were from disadvantaged neighborhoods and/or were essential workers, who made up 56% of the population. >CONCLUSIONS: We developed and implemented a weighted lottery to promote equity in the allocation of scarce COVID-19 therapeutics. The lottery resulted in heightened access to treatment among groups that have been disproportionately impacted by the pandemic, though larger weightings may be needed to substantially mitigate disparities. (Table Presented).

Design of mass burial sites for safe and dignified disposal of pandemic fatalities

The huge number of fatalities due to the coronavirus disease 2019 pandemic has imposed an unprecedented pressure on existing burial facilities. Thus, mass burial is being used in different parts of the world to cope with this unusual situation. As a dead body might be contagious for at least hours, if not days, there is a need to manage/design/construct the mass burial considering the safe handling of coffins and other environmental, social, economical and ethical/dignity aspects. However, the guidelines of the World Health Organization do not thoroughly address the potential risk associated with groundwater pollution due to mass burial construction. Hence, the present study discusses the potential risk of groundwater pollution in mass burial sites and sheds light on the factors that control the survival/retention of bacteria and viruses in porous media. Furthermore, using the available knowledge on designing/monitoring of municipal/industrial waste disposal sites, a cost-effective and simple construction method of mass burial is proposed to mitigate its potential environmental impact. © 2021 ICE Publishing: All rights reserved.

Leaving no ethical value behind: triage protocol design for pandemic rationing

Rationing of medical resources is a critical issue in the COVID-19 pandemic. Most existing triage protocols are based on a priority point system, in which a formula specifies the order in which the supply of a resource, such as a ventilator, is to be rationed for patients. A priority point system generates an identical priority ranking specifying claims on all units. Triage protocols in some states (e.g. Michigan) prioritize frontline health workers giving heavier weight to the ethical principle of instrumental value. Others (e.g. New York) do not, reasoning that if frontline workers obtain high enough priority, there is a risk that they obtain all units and none remain for the general community. This debate is pressing given substantial COVID-19 health risks for frontline workers. In this paper, we analyze the consequences of rationing medical resources through a reserve system. In a reserve system, resources are placed into multiple categories. Priorities guiding allocation of units can reflect different ethical values between these categories. A reserve system provides additional flexibility over a priority point system because it does not dictate a single priority order for the allocation of all units. It offers a middle-ground approach that balances competing objectives, such as in the medical worker debate. This flexibility requires attention to implementation, especially the processing order of reserve categories. We describe our model of a reserve system, characterize its potential outcomes, and examine distributional implications of particular reserve systems. We also discuss several practical considerations with triage protocol design.

A comparative study of machine learning models for COVID-19 prediction in India

Machine learning is commonly being used in every field. Forecasting systems based on machine learning (ML) have shown their importance in interpreting perioperative effects to accelerate decision-making on the potential course of action. In several technology domains, ML models have been used long to define and prioritize adverse threat variables. To manage forecasting challenges, many prediction approaches are widely used. The paper shows the ability of ML models to estimate the amount of forthcoming COVID-19-affected patients that is now considered a serious threat to civilization. In paper this, we have performed a comparative study of five machine learning standard models like Linear regression (LR), decision tree, least absolute shrinkage and selection operator (LASSO), random forest and support vector machine (SVM) to forecast the threatening variables of COVID-19. Each of the models makes three forms of forecasts, i.e. the total active cases, the total deaths, and the total recoveries in the next five days. The findings provided by the paper suggest that the use of these techniques for the current COVID-19 the pandemic scenario is a promising strategy. For better accuracy, we have used a six-degree polynomial. Experiment results illustrate that poly LR and poly LASSO gives the best results followed by LR, LASSO, random forest, and decision tree. SVM shows the poor result in the prediction of COVID-19. © 2020 IEEE.