Optimisation of Non-Pharmaceutical Measures in COVID-19 Growth via Neural Networks

PaCAR: COVID-19 Pandemic Control Decision Making via Large-Scale Agent-Based Modeling and Deep Reinforcement Learning

BACKGROUND

Policy makers are facing more complicated challenges to balance saving lives and economic development in the post-vaccination era during a pandemic. Epidemic simulation models and pandemic control methods are designed to tackle this problem. However, most of the existing approaches cannot be applied to real-world cases due to the lack of adaptability to new scenarios and micro representational ability (especially for system dynamics models), the huge computation demand, and the inefficient use of historical information.

METHODS

We propose a novel Pandemic Control decision making framework via large-scale Agent-based modeling and deep Reinforcement learning (PaCAR) to search optimal control policies that can simultaneously minimize the spread of infection and the government restrictions. In the framework, we develop a new large-scale agent-based simulator with vaccine settings implemented to be calibrated and serve as a realistic environment for a city or a state. We also design a novel reinforcement learning architecture applicable to the pandemic control problem, with a reward carefully designed by the net monetary benefit framework and a sequence learning network to extract information from the sequential epidemiological observations, such as number of cases, vaccination, and so forth.

RESULTS

Our approach outperforms the baselines designed by experts or adopted by real-world governments and is flexible in dealing with different variants, such as Alpha and Delta in COVID-19. PaCAR succeeds in controlling the pandemic with the lowest economic costs and relatively short epidemic duration and few cases. We further conduct extensive experiments to analyze the reasoning behind the resulting policy sequence and try to conclude this as an informative reference for policy makers in the post-vaccination era of COVID-19 and beyond.

LIMITATIONS

The modeling of economic costs, which are directly estimated by the level of government restrictions, is rather simple. This article mainly focuses on several specific control methods and single-wave pandemic control.

CONCLUSIONS

The proposed framework PaCAR can offer adaptive pandemic control recommendations on different variants and population sizes. Intelligent pandemic control empowered by artificial intelligence may help us make it through the current COVID-19 and other possible pandemics in the future with less cost both of lives and economy.

HIGHLIGHTS

We introduce a new efficient, large-scale agent-based epidemic simulator in our framework PaCAR, which can be applied to train reinforcement learning networks in a real-world scenario with a population of more than 10,000,000.We develop a novel learning mechanism in PaCAR, which augments reinforcement learning with sequence learning, to learn the tradeoff policy decision of saving lives and economic development in the post-vaccination era.We demonstrate that the policy learned by PaCAR outperforms different benchmark policies under various reality conditions during COVID-19.We analyze the resulting policy given by PaCAR, and the lessons may shed light on better pandemic preparedness plans in the future.

Social distance capacity to control the COVID-19 pandemic: A systematic review on time series analysis

BACKGROUND

Reducing interpersonal contact has been one of the least expensive and most widely used COVID-19 control strategies.

OBJECTIVE

This systematic review has been conducted with the aim of identifying social distancing strategies and policies and their impact on the COVID-19 pandemic.

METHODS

In order to compile this systematic review, Google Scholar, PubMed, Scopus, Web of Science, Science Direct, Magiran, SID, and Irandoc databases were searched from the COVID-19 outbreak until March 2021. Keywords included "social", "physical", "distance", "outbreak", "incidence", "prevalence", "spread", "new case", "death*", "mortality*", "morbidity*" , "covid-19", "coronavirus", "sars-cov-2" and "time series*". The articles were qualitatively evaluated by two researchers using the STROBE tool. Finally, the study data were divided into three conceptual categories by three researchers, who then agreed on one category. The practical suggestions were also categorized in the same way.

RESULTS

The policies and strategies adopted to implement social distancing were included in five categories of restrictions, prohibitions, closures, incentives, and punishments. Transportation and travel restrictions, crowded places and schools closure, use of telecommunications and virtual communications, and financial and psychological support to society members were the main policies in this area.

CONCLUSION

Rapid and complete vaccination of all people around the world is out of reach, therefore social distancing and the implementation of physical restraints, especially in crowded and densely populated environments, should be done extensively until COVID-19 is eradicated.

Accountancy as a Meaningful Work. Main Determinants from a Job Quality and Optimization Algorithm Approach

The primary purpose of the accounting profession is to provide quality information to the market that facilitates the allocation of resources. The context in which it operates must attend to some stressors that can affect the professional’s meaning of the work. Meaningful work (MW) is based on the concept of valuable work and work well done, so it is directly related to the concept of quality at work, which is a constant concern in the accounting profession. The method used to determine meaningful work identifies the set of job quality indexes, as defined by the European Working Conditions Survey (EWCS), related to the MW. This paper has used an integer programming genetic algorithm (GA) to determine the JQIs and the statistically significant combinations. The findings showed that JQIs, skills development and discretion (SD), and physical environment (PE) positively and intensely relate to MW. Likewise, reduction of the work intensity (WI) and improvement of the social environment (SE) are related in the same direction as the MW. On the other hand, the results showed different indicator weightings depending on the age of the accountants. This paper shows the importance that accountants attribute to professional competence and how, throughout their careers, the JQI that most relate to MW is changing, from a social vision to preferences where the care of personal time also prevails.

Identifying Key Variables on the Way to Wellbeing in the Transition from Face-to-Face to Online Higher Education due to COVID-19: Evidence from the Q-Sort Technique

This paper reports perceptions of higher education lecturers who switched from classical face-to-face teaching to online teaching due to the unexpected circumstances caused by the COVID-19 pandemic. Based on a validated theoretical model about the roles of instructors in online settings, the authors document the perceptions of experienced face-to-face lecturers regarding their performance in online roles and the perceived importance of the formal and informal support they received during the process of adapting to a sudden online context. The study was based on the Q-sort methodology. Among other conclusions, our research reveals that the best performance we elicited pertained to the technical role, followed by the managerial role and the support received through informal channels. Worryingly, the worst performance pertained to promoting life skills. This finding is especially alarming considering both the UNESCO humanistic vision of universities as promoters of university community development and wellbeing and SDG 4.7 of Agenda 2030, which states that education should ensure that all learners acquire the knowledge and skills needed to promote sustainable development through education on sustainable development and lifestyles. This article is meant to provide guidelines to traditional universities to help them overcome weaknesses and enhance strengths when switching to online learning.

Applications of artificial intelligence in battling against covid-19: A literature review

Colloquially known as coronavirus, the Severe Acute Respiratory Syndrome CoronaVirus 2 (SARS-CoV-2), that causes CoronaVirus Disease 2019 (COVID-19), has become a matter of grave concern for every country around the world. The rapid growth of the pandemic has wreaked havoc and prompted the need for immediate reactions to curb the effects. To manage the problems, many research in a variety of area of science have started studying the issue. Artificial Intelligence is among the area of science that has found great applications in tackling the problem in many aspects. Here, we perform an overview on the applications of AI in a variety of fields including diagnosis of the disease via different types of tests and symptoms, monitoring patients, identifying severity of a patient, processing covid-19 related imaging tests, epidemiology, pharmaceutical studies, etc. The aim of this paper is to perform a comprehensive survey on the applications of AI in battling against the difficulties the outbreak has caused. Thus we cover every way that AI approaches have been employed and to cover all the research until the writing of this paper. We try organize the works in a way that overall picture is comprehensible. Such a picture, although full of details, is very helpful in understand where AI sits in current pandemonium. We also tried to conclude the paper with ideas on how the problems can be tackled in a better way and provide some suggestions for future works.