Gradient-based grey wolf optimizer with Gaussian walk: Application in modelling and prediction of the COVID-19 pandemic

A robust optimization model for multi-objective blood supply chain network considering scenario analysis under uncertainty: a multi-objective approach

Annually, different regions of the world are affected by natural disasters such as floods and earthquakes, resulting in significant loss of lives and financial resources. These events necessitate rescue operations, including the provision and distribution of relief items like food and clothing. One of the most critical challenges in such crises is meeting the blood requirement, as an efficient and reliable blood supply chain is indispensable. The perishable nature of blood precludes the establishment of a reserve stock, making it essential to minimize shortages through effective approaches and designs. In this study, we develop a mathematical programming model to optimize supply chains in post-crisis scenarios using multiple objectives. Presented model allocates blood to various demand facilities based on their quantity and location, considering potential situations. We employ real data from a case study in Iran and a robust optimization approach to address the issue. The study identifies blood donation centers and medical facilities, as well as the number and locations of new facilities needed. We also conduct scenario analysis to enhance the realism of presented approach. Presented research demonstrates that with proper management, crises of this nature can be handled with minimal expense and deficiency.

A deterministic transmission model for analytics-driven optimization of COVID-19 post-pandemic vaccination and quarantine strategies

This study developed a deterministic transmission model for the coronavirus disease of 2019 (COVID-19), considering various factors such as vaccination, awareness, quarantine, and treatment resource limitations for infected individuals in quarantine facilities. The proposed model comprised five compartments: susceptible, vaccinated, quarantined, infected, and recovery. It also considered awareness and limited resources by using a saturated function. Dynamic analyses, including equilibrium points, control reproduction numbers, and bifurcation analyses, were conducted in this research, employing analytics to derive insights. Our results indicated the possibility of an endemic equilibrium even if the reproduction number for control was less than one. Using incidence data from West Java, Indonesia, we estimated our model parameter values to calibrate them with the real situation in the field. Elasticity analysis highlighted the crucial role of contact restrictions in reducing the spread of COVID-19, especially when combined with community awareness. This emphasized the analytics-driven nature of our approach. We transformed our model into an optimal control framework due to budget constraints. Leveraging Pontriagin's maximum principle, we meticulously formulated and solved our optimal control problem using the forward-backward sweep method. Our experiments underscored the pivotal role of vaccination in infection containment. Vaccination effectively reduces the risk of infection among vaccinated individuals, leading to a lower overall infection rate. However, combining vaccination and quarantine measures yields even more promising results than vaccination alone. A second crucial finding emphasized the need for early intervention during outbreaks rather than delayed responses. Early interventions significantly reduce the number of preventable infections, underscoring their importance.

Resilient and social health service network design to reduce the effect of COVID-19 outbreak

With the severe outbreak of the novel coronavirus (COVID-19), researchers are motivated to develop efficient methods to face related issues. The present study aims to design a resilient health system to offer medical services to COVID-19 patients and prevent further disease outbreaks by social distancing, resiliency, cost, and commuting distance as decisive factors. It incorporated three novel resiliency measures (i.e., health facility criticality, patient dissatisfaction level, and dispersion of suspicious people) to promote the designed health network against potential infectious disease threats. Also, it introduced a novel hybrid uncertainty programming to resolve a mixed degree of the inherent uncertainty in the multi-objective problem, and it adopted an interactive fuzzy approach to address it. The actual data obtained from a case study in Tehran province in Iran proved the strong performance of the presented model. The findings show that the optimum use of medical centers' potential and the corresponding decisions result in a more resilient health system and cost reduction. A further outbreak of the COVID-19 pandemic is also prevented by shortening the commuting distance for patients and avoiding the increasing congestion in the medical centers. Also, the managerial insights show that establishing and evenly distributing camps and quarantine stations within the community and designing an efficient network for patients with different symptoms result in the optimum use of the potential capacity of medical centers and a decrease in the rate of bed shortage in the hospitals. Another insight drawn is that an efficient allocation of the suspect and definite cases to the nearest screening and care centers makes it possible to prevent the disease carriers from commuting within the community and increase the coronavirus transmission rate.

An Improved Grey Wolf Optimizer and Its Application in Robot Path Planning

This paper discusses a hybrid grey wolf optimizer utilizing a clone selection algorithm (pGWO-CSA) to overcome the disadvantages of a standard grey wolf optimizer (GWO), such as slow convergence speed, low accuracy in the single-peak function, and easily falling into local optimum in the multi-peak function and complex problems. The modifications of the proposed pGWO-CSA could be classified into the following three aspects. Firstly, a nonlinear function is used instead of a linear function for adjusting the iterative attenuation of the convergence factor to balance exploitation and exploration automatically. Then, an optimal α wolf is designed which will not be affected by the wolves β and δ with poor fitness in the position updating strategy; the second-best β wolf is designed, which will be affected by the low fitness value of the δ wolf. Finally, the cloning and super-mutation of the clonal selection algorithm (CSA) are introduced into GWO to enhance the ability to jump out of the local optimum. In the experimental part, 15 benchmark functions are selected to perform the function optimization tasks to reveal the performance of pGWO-CSA further. Due to the statistical analysis of the obtained experimental data, the pGWO-CSA is superior to these classical swarm intelligence algorithms, GWO, and related variants. Furthermore, in order to verify the applicability of the algorithm, it was applied to the robot path-planning problem and obtained excellent results.

An Improved Gradient-Based Optimization Algorithm for Solving Complex Optimization Problems

In this paper, an improved gradient-based optimizer (IGBO) is proposed with the target of improving the performance and accuracy of the algorithm for solving complex optimization and engineering problems. The proposed IGBO has the added features of adjusting the best solution by adding inertia weight, fast convergence rate with modified parameters, as well as avoiding the local optima using a novel functional operator (G). These features make it feasible for solving the majority of the nonlinear optimization problems which is quite hard to achieve with the original version of GBO. The effectiveness and scalability of IGBO are evaluated using well-known benchmark functions. Moreover, the performance of the proposed algorithm is statistically analyzed using ANOVA analysis, and Holm–Bonferroni test. In addition, IGBO was assessed by solving well-known real-world problems. The results of benchmark functions show that the IGBO is very competitive, and superior compared to its competitors in finding the optimal solutions with high convergence and coverage. The results of the studied real optimization problems prove the superiority of the proposed algorithm in solving real optimization problems with difficult and indefinite search domains.

Viable supply chain with vendor-managed inventory approach by considering blockchain, risk and robustness

This research shows a Viable Supply Chain with Vendor Managed Inventory approach by considering Blockchain, Risk, and Robustness. We embedded Blockchain Technology (BCT) to improve SC agility. To tackle risk and robustness, we suggest a new objective function with the weighted expected value, worst case, and Entropic Value at Risk for considering risk and robustness under different scenarios. This model is Mixed-Integer Linear Programming, and GAMS-Bonmin is utilized to solve it. The case study of this research is on the Pharmacy industry. We compare problems in the situation with BCT and without BCT. The results show that the cost function of the main problem without BCT is greater than the same problem with BCT, and its gaps are 0.61%. Finally, the cost function increase by increasing the conservative coefficient and decreasing the resiliency coefficient. The cost function reduces by increasing the confidence level. We change the scale of the problem and define problems. By increasing the scale of the problem, the solution time increased.

A possibilistic-robust-fuzzy programming model for designing a game theory based blood supply chain network

This paper presents a bi-level blood supply chain network under uncertainty during the COVID-19 pandemic outbreak using a Stackelberg game theory technique. A new two-phase bi-level mixed-integer linear programming model is developed in which the total costs are minimized and the utility of donors is maximized. To cope with the uncertain nature of some of the input parameters, a novel mixed possibilistic-robust-fuzzy programming approach is developed. The data from a real case study is utilized to show the applicability and efficiency of the proposed model. Finally, some sensitivity analyses are performed on the important parameters and some managerial insights are suggested.

Understanding systemic disruption from the Covid-19-induced semiconductor shortage for the auto industry

Covid-19 has allowed us to study systemic disruptions that impact entire industries. This paper explores how disruptions start, propagate, and continue over time by examining the semiconductor chip shortage faced by the auto industry during the years following Covid-19 in 2020. First, we carried out a thematic analysis of 209 pertinent newspaper articles. The analysis resulted in a thematic model of such disruptions with the interplay of various factors leading to the prolonged disruption to the auto sector. Second, we present the results from a stylized supply chain planning model run at different times to show how disruptions propagate to the auto and other sectors, causing systemic shortages. Overall, we contribute to the supply chain risk literature by focusing on system disruptions impacting entire industries versus normal disruptions affecting a particular company's supply chain.

Probabilistic graphical model for the evaluation of the emotional and dramatic personality disorders

Personality disorders are psychological ailments with a major negative impact on patients, their families, and society in general, especially those of the dramatic and emotional type. Despite all the research, there is still no consensus on the best way to assess and treat them. Traditional assessment of personality disorders has focused on a limited number of psychological constructs or behaviors using structured interviews and questionnaires, without an integrated and holistic approach. We present a novel methodology for the study and assessment of personality disorders consisting in the development of a Bayesian network, whose parameters have been obtained by the Delphi method of consensus from a group of experts in the diagnosis and treatment of personality disorders. The result is a probabilistic graphical model that represents the psychological variables related to the personality disorders along with their relations and conditional probabilities, which allow identifying the symptoms with the highest diagnostic potential. This model can be used, among other applications, as a decision support system for the assessment and treatment of personality disorders of the dramatic or emotional cluster. In this paper, we discuss the need to validate this model in the clinical population along with its strengths and limitations.

Comparison of hospital service performances under COVID-19 pandemics for pilot regions with low vaccination rates

It is essential to measure the quality and performance of health centers and propose policies in order for health services to continue without interruption during the pandemic period and for the continuous and proper implementation of new procedures in hospitals with COVID-19.The measurement of service quality and performance in hospitals should be provided not only for the smooth flow of health services that are vital for individuals but also for the elimination of hesitations in the treatment and vaccination processes related to COVID-19. Previously, models have been proposed by introducing some criteria to measure and evaluate hospital service performance in some extraordinary conditions, but such a study has not yet been put forward under pandemic conditions. Starting from this point, we aim to fill the gap in the literature by conducting a measurement study for hospitals in the pilot region, where COVID-19 cases are common but vaccination is observed at low rates. For this aim, the evaluation criteria are gathered under basic dimensions as in SERVPERF (Service Performance), which is a widely used tool for measuring service quality and a fuzzy multi-criteria decision analysis is proposed to measure the service performance of state hospitals for a pilot region. In the proposed methodology, the integrated methods consisting of CRITIC-TOPSIS have been extended with fermatean fuzzy sets. Expert opinions are taken via questionaries to determine hospital service performances. Based on the results obtained from the hospitals in the pilot region, the policies and strategies to be adopted by the hospitals serving under pandemic conditions worldwide to increase the service quality have been put forward. Additionally, the sensitivity of the parameters in the problem is measured, and then the validity of the obtained results is also validated. According to the results, assurance is determined as the most important main service performance factor during the pandemic period. So, the managers should develop strategies to address people's concerns about vaccines and increase people's trust in hospitals.

National IoMT platform strategy portfolio decision model under the COVID-19 environment: based on the financial and non-financial value view

The Internet of Medical Things (IoMT) is an emerging technology in the healthcare revolution which provides real-time healthcare information communication and reasonable medical resource allocation. The COVID-19 pandemic has had a significant effect on people's lives and has affected healthcare capacities. It is important for integrated IoMT platform development to overcome the global pandemic challenges. This study proposed the national IoMT platform strategy portfolio decision-making model from the non-financial (technology, organization, environment) and financial perspectives. As a solution to the decision problem, initially, the decision-making trial and evaluation laboratory (DEMATEL) technology were employed to capture the cause-effect relationship based on the perspectives and criteria obtained from the insight of an expert team. The analytic network process (ANP) and pairwise comparisons were then used to determine the weights for the strategy. Simultaneously, this study incorporated IoMT platform resource limitations into the zero-one goal programming (ZOGP) method to obtain an optimal portfolio selection for IoMT platform strategy planning. The results showed that the integrated MCDM method produced reasonable results for selecting the most appropriate IoMT platform strategy portfolio when considering resource constraints such as system installation costs, consultant fees, infrastructure costs, reduction of medical staff demand, and improvement rates for diagnosis efficiency. The decision-making model of the IoMT platform in this study was conclusive and significantly compelling to aid government decision makers in concentrating their efforts on planning IoMT strategies in response to various pandemic and medical resource allocations.

Viable healthcare supply chain network design for a pandemic

The recent COVID-19 pandemic revealed that healthcare networks must have a flexible and effective structure. In this study, we develop a viable healthcare network design for a pandemic using a multi-stage stochastic approach. We propose a multi-level network that includes health centers, computed tomography scan centers, hospitals, and clinics. Patients have conditions to returning to normal life or quarantining at home. Three objectives are defined: maximizing the probability of patient recovery, minimizing the costs of all centers in the network, and minimizing the Coronavirus death rate. We investigate a real case study in Iran to demonstrate the model's applicability. Finally, we compare the healthcare supply chain network design in a pandemic with a normal situation to advise how the network can continue to remain viable.

Ladybug Beetle Optimization algorithm: application for real-world problems

In this paper, a novel optimization algorithm is proposed, called the Ladybug Beetle Optimization (LBO) algorithm, which is inspired by the behavior of ladybugs in nature when they search for a warm place in winter. The new proposed algorithm consists of three main parts: (1) determine the heat value in the position of each ladybug, (2) update the position of ladybugs, and (3) ignore the annihilated ladybug(s). The main innovations of LBO are related to both updating the position of the population, which is done in two separate ways, and ignoring the worst members, which leads to an increase in the search speed. Also, LBO algorithm is performed to optimize 78 well-known benchmark functions. The proposed algorithm has reached the optimal values of 73.3% of the benchmark functions and is the only algorithm that achieved the best solution of 20.5% of them. These results prove that LBO is substantially the best algorithm among other well-known optimization methods. In addition, two fundamentally different real-world optimization problems include the Economic-Environmental Dispatch Problem (EEDP) as an engineering problem and the Covid-19 pandemic modeling problem as an estimation and forecasting problem. The EEDP results illustrate that the proposed algorithm has obtained the best values in either the cost of production or the emission or even both, and the use of LBO for Covid-19 pandemic modeling problem leads to the least error compared to others.

Interval type-3 fuzzy aggregators for ensembles of neural networks in COVID-19 time series prediction

In this work we are presenting an approach for fuzzy aggregation in ensembles of neural networks for forecasting. The aggregator is used in an ensemble to combine the outputs of the networks forming the ensemble. This is done in such a way that the total output of the ensemble is better than the outputs of the individual modules. In our approach a fuzzy system is used to estimate the weights that will be assigned to the outputs in the process of combining them in a weighted average calculation. The uncertainty in the process of aggregation is modeled with interval type-3 fuzzy, which in theory can outperform type-2 and type-1. Publicly available data sets of COVID-19 cases for several countries in the world were utilized to test the proposed approach. Simulation results of the COVID-19 data show the potential of the approach to outperform other aggregators in the literature.

Feature Selection Based on Adaptive Particle Swarm Optimization with Leadership Learning

With the rapid development of the Internet of Things (IoT), the curse of dimensionality becomes increasingly common. Feature selection (FS) is to eliminate irrelevant and redundant features in the datasets. Particle swarm optimization (PSO) is an efficient metaheuristic algorithm that has been successfully applied to obtain the optimal feature subset with essential information in an acceptable time. However, it is easy to fall into the local optima when dealing with high-dimensional datasets due to constant parameter values and insufficient population diversity. In the paper, an FS method is proposed by utilizing adaptive PSO with leadership learning (APSOLL). An adaptive updating strategy for parameters is used to replace the constant parameters, and the leadership learning strategy is utilized to provide valid population diversity. Experimental results on 10 UCI datasets show that APSOLL has better exploration and exploitation capabilities through comparison with PSO, grey wolf optimizer (GWO), Harris hawks optimization (HHO), flower pollination algorithm (FPA), salp swarm algorithm (SSA), linear PSO (LPSO), and hybrid PSO and differential evolution (HPSO-DE). Moreover, less than 8% of features in the original datasets are selected on average, and the feature subsets are more effective in most cases compared to those generated by 6 traditional FS methods (analysis of variance (ANOVA), Chi-Squared (CHI2), Pearson, Spearman, Kendall, and Mutual Information (MI)).

A framework for the estimation of treatment costs of cardiovascular conditions in the presence of disease transition

The current research aims to aid policymakers and healthcare service providers in estimating expected long-term costs of medical treatment, particularly for chronic conditions characterized by disease transition. The study comprised two phases (qualitative and quantitative), in which we developed linear optimization-based mathematical frameworks to ascertain the expected long-term treatment cost per patient considering the integration of various related dimensions such as the progression of the medical condition, the accuracy of medical treatment, treatment decisions at respective severity levels of the medical condition, and randomized/deterministic policies. At the qualitative research stage, we conducted the data collection and validation of various cogent hypotheses acting as inputs to the prescriptive modeling stage. We relied on data collected from 115 different cardio-vascular clinicians to understand the nuances of disease transition and related medical dimensions. The framework developed was implemented in the context of a multi-specialty hospital chain headquartered in the capital city of a state in Eastern India, the results of which have led to some interesting insights. For instance, at the prescriptive modeling stage, though one of our contributions related to the development of a novel medical decision-making framework, we illustrated that the randomized versus deterministic policy seemed more cost-competitive. We also identified that the expected treatment cost was most sensitive to variations in steady-state probability at the "major" as opposed to the "severe" stage of a medical condition, even though the steady-state probability of the "severe" state was less than that of the "major" state.

Adapting supply chain operations in anticipation of and during the COVID-19 pandemic

This article investigates the impacts of the COVID-19 pandemic and their proactive mediation by adaptive operational decisions in different network design structures in anticipation of and during the pandemic. In generalized terms, we contribute to the understanding of the effect of preparedness and recovery decisions in a pandemic setting on supply chain operations and performance. In particular, we examine the impact of inventory pre-positioning in anticipation of a pandemic and the adaptation of production-ordering policy during the pandemic. Our model combines three levels, which is not often seen jointly in operations management literature, i.e., pandemic dynamics, supply chain design, and operational production-inventory control policies. The analysis is performed for both two- and three-stage supply chains and different scenarios for pandemic dynamics (i.e., uncontrolled propagation or controlled dispersal with lockdowns). Our findings suggest that two-stage supply chains exhibit a higher vulnerability in disruption cases. However, they are exposed to a lower system inertia and show positive effects at the recovery stage. Supply chain adaptation ahead of a pandemic is more advantageous than during the pandemic when specific operational recovery policies are deployed. We show that it is instructive to avoid simultaneous changes in structural network design and operational policies since that can destabilize the production-inventory system and result in higher product shortages.

A multi-objective location-routing model for dental waste considering environmental factors

Nowadays, the amounts of infectious medical waste (IMW) have surged considerably so waste management has become a critical emergency in many developing countries. However, most large medical waste generation centers (MWGC) are equipped with treatment facilities, small MWGC faces the waste management problem. It reveals the significance of having a proper program for small health centers. This is an indisputable difficulty that governments bordered because it imposes great costs on societies, also the environmental problems caused by improper treatment are irreparable. To attend to all the essential aspects of the problem, this paper recommended a location-routing model with four objective functions to minimize the total costs, environmental pollution, the risk imposed on the population around disposal sites, and the total violation from the expected arrival time. Considering a multi-period problem with a maximum acceptable delay plays a key role to connect the assumptions to the real-world problem. In addition, for solving mathematical models based on case studies, the role of uncertainty is undeniable. The demand for dental waste treatment is not definite and is changed based on the different conditions thus fuzzy chance-constrained programming is proposed for this problem to tackle the uncertainty. The revised multi-choice goal programming method is considered to solve the model and a real case study for dental clinics in Babol city of Iran is investigated to illustrate the validation of the proposed model. The results indicate that the solution method can create a balance between four objective functions. Finally, sensitivity analyses are performed for some parameters to analyze the behavior of the objective functions.

Interval Type-3 Fuzzy Aggregation of Neural Networks for Multiple Time Series Prediction: The Case of Financial Forecasting

In this work, we present an approach for fuzzy aggregation of neural networks for forecasting. The interval type-3 aggregator is used to combine the outputs of the networks to improve the quality of the prediction. This is carried out in such a way that the final output is better than the outputs of the individual modules. In our approach, a fuzzy system is used to estimate the prediction increments that will be assigned to the output in the process of combining them with a set of fuzzy rules. The uncertainty in the process of aggregation is modeled with an interval type-3 fuzzy system, which, in theory, can outperform type-2 and type-1 fuzzy systems. Publicly available data sets of COVID-19 cases and the Dow Jones index were utilized to test the proposed approach, as it has been stated that a pandemic wave can have an effect on the economies of countries. The simulation results show that the COVID-19 data does have, in fact, an influence on the Dow Jones time series and its use in the proposed model improves the forecast of the Dow Jones future values.

A goal programming model for two-stage COVID19 test sampling centers location-allocation problem

The COVID19 virus, which first appeared in Wuhan, China, and has become a pandemic in a short time, has threatened the health system in many countries and put it into a bottleneck. Simultaneously, the second wave's expectation spread it necessary to plan the health services correctly. In this study, a location-allocation problem in the two-echelon system, which considers different test sampling alternatives, is examined to obtain test sampling centers' location-allocation. The problem is modeled as a goal programming model to create a network that tests samples at a minimum total distance, establishes a minimum number of test sampling centers, and reaches the distance of PCR test laboratories at minimum total distances. The proposed model is applied as a case study for the two cities located in Turkey, and the obtained locations and inventory levels of each location are presented. Besides, different scenarios are examined to understand the structure of the model. As a result, only testing in hospitals will increase the risk of contamination. Since testing at all points will not be possible administratively, it will be ensured that the most appropriate location-allocation decisions are taken by considering all the proposed model's objectives.

Gradient-based elephant herding optimization for cluster analysis

Clustering analysis is essential for obtaining valuable information from a predetermined dataset. However, traditional clustering methods suffer from falling into local optima and an overdependence on the quality of the initial solution. Given these defects, a novel clustering method called gradient-based elephant herding optimization for cluster analysis (GBEHO) is proposed. A well-defined set of heuristics is introduced to select the initial centroids instead of selecting random initial points. Specifically, the elephant optimization algorithm (EHO) is combined with the gradient-based algorithm GBO for assigning initial cluster centers across the search space. Second, to overcome the imbalance between the original EHO exploration and exploitation, the initialized population is improved by introducing Gaussian chaos mapping. In addition, two operators, i.e., random wandering and variation operators, are set to adjust the location update strategy of the agents. Nine datasets from synthetic and real-world datasets are adopted to evaluate the effectiveness of the proposed algorithm and the other metaheuristic algorithms. The results show that the proposed algorithm ranks first among the 10 algorithms. It is also extensively compared with state-of-the-art techniques, and four evaluation criteria of accuracy rate, specificity, detection rate, and F-measure are used. The obtained results clearly indicate the excellent performance of GBEHO, while the stability is also more prominent.

An extended robust mathematical model to project the course of COVID-19 epidemic in Iran

This research develops a regression-based Robust Optimization (RO) approach to efficiently predict the number of patients with confirmed infection caused by the recent Coronavirus Disease (COVID-19). The main idea is to study the dynamics of the COVID-19 outbreak at the first stage and then provide efficient insights to estimate the necessary resources accordingly. The convex RO with Mean Absolute Deviation (MAD) objective function is utilized to project the course of COVID-19 epidemic in Iran. To validate the performance of the suggested model, a real-case study is investigated and compared to several well-known forecasting models including Simple Moving Average, Exponential Moving Average, Weighted Moving Average and Exponential Smoothing with Trend Adjustment models. Furthermore, the effect of parameter uncertainties is examined using a set of sensitivity analyses. The results demonstrate that by increasing the degree (coefficient) of regression up to 8, MAD value decreases to 1378.12, and consequently, the corresponding equation becomes more accurate. On the other hand, from the 8th degree onwards, MAD value follows an upward trend. Furthermore, by increasing the level of regression uncertainty, MAD value follows a downward trend to reach 1309.28 and the estimation accuracy of the model increases accordingly. Finally, our proposed model achieves the least MAD and the greatest correlation coefficient against the other models.

Investigation of robustness of hybrid artificial neural network with artificial bee colony and firefly algorithm in predicting COVID-19 new cases: case study of Iran

As an ongoing public health menace, the novel coronavirus pandemic has challenged the world. With several mutations and a high transmission rate, the virus is able to infect individuals in an exponential manner. At the same time, Iran is confronted with multiple wave peaks and the health care system is facing a major challenge. In consequence, developing a robust forecasting methodology can assist health authorities for effective planning. In that regard, with the help of Artificial Neural Network-Artificial Bee Colony (ANN-ABC) and Artificial Neural Network- Firefly Algorithm (ANN-FA) as two robust hybrid artificial intelligence-based models, the current study intends to select the optimal model with the maximum accuracy rate. To do so, first a sample of COVID-19 confirmed cases in Iran ranging from 19 February 2020 to 25 July 2021 is compiled. 75% (25%) of total observation is randomly allocated as training (testing) data. Afterwards, an ANN model is trained with Levenberg-Marquardt algorithm. Accordingly, based on R-squared and root-mean-square error criteria, the optimal number of hidden neurons is computed as 17. The proposed ANN model is employed to develop ANN-ABC and ANN-FA models for achieving the maximum accuracy rate. According to ANN-ABC, the R- squared values of the optimal model are 0.9884 and 0.9885 at train and test stages. In respect to ANN-FA, the R-squared ranged from 0.9954 to 0.9940 at the train and test phases, which indicates the outperformance of ANN-FA for predicting COVID-19 new cases in Iran. Finally, the proposed ANN-ABC and ANN-FA are applied for simulating the COVID-19 new cases data in different countries. The results revealed that both models can be used as a robust predictor of COVID-19 data and in a majority of cases ANN-FA outperforms the ANN-ABC.

Optimization in the Context of COVID-19 Prediction and Control: A Literature Review

This paper presents an overview of some key results from a body of optimization studies that are specifically related to COVID-19, as reported in the literature during 2020-2021. As shown in this paper, optimization studies in the context of COVID-19 have been used for many aspects of the pandemic. From these studies, it is observed that since COVID-19 is a multifaceted problem, it cannot be studied from a single perspective or framework, and neither can the related optimization models. Four new and different frameworks are proposed that capture the essence of analyzing COVID-19 (or any pandemic for that matter) and the relevant optimization models. These are: (i) microscale vs. macroscale perspective; (ii) early stages vs. later stages perspective; (iii) aspects with direct vs. indirect relationship to COVID-19; and (iv) compartmentalized perspective. To limit the scope of the review, only optimization studies related to the prediction and control of COVID-19 are considered (public health focused), and which utilize formal optimization techniques or machine learning approaches. In this context and to the best of our knowledge, this survey paper is the first in the literature with a focus on the prediction and control related optimization studies. These studies include optimization of screening testing strategies, prediction, prevention and control, resource management, vaccination prioritization, and decision support tools. Upon reviewing the literature, this paper identifies current gaps and major challenges that hinder the closure of these gaps and provides some insights into future research directions.