A decision-making framework for COVID-19 infodemic management strategies evaluation in spherical fuzzy environment.

100 years after the Spanish flu, the COVID-19 crisis showed that large-scale epidemics and pandemics do not belong to the past. On the report of the World Health Organization, COVID-19 is the most significant public health problem of the twenty-first century. Like previous epidemics, the current crisis is accompanied by uncertainty, mistrust, doubt and fear, and this has led to an infodemic connection to the epidemic. So not only are we fighting an epidemic, but also, we are brawling an infodemic. To reduce the social and economic consequences and harmful effects of infodemic health, and to overcome it, we need to implement strategies against infodemic. Evaluating strategies based on multiple characteristics can be considered multi-criteria decision-making (MCDM) problem. According to the literature, there is no study that aims on proposing an integrated approach to evaluate infodemic management strategies under uncertain environment. Therefore, in this paper, an integrated framework based on the extended version of best-worst method (BWM) and Combined Compromise Solution (CoCoSo) methods under a spherical fuzzy set (SFS) is developed for the first time to address the COVID-19 infodemic management strategies selection. Initially, the criteria are weighted using the developed SFS BWM which reduces uncertainty in pairwise comparisons. In the next step, the 15 selected strategies are analyzed and ranked using SFS CoCoSo. The outputs of this paper illustrate that online tools for fact checking COVID-19 information and engage and empower communities are placed in the first and second priorities, respectively. The comparison of ranking results SFS-CoCoSo with other MCDM methods demonstrates the performance of the proposed approach and its ranking stability.

Brain tumor segmentation of MRI images: A comprehensive review on the application of artificial intelligence tools.

BACKGROUND: Brain cancer is a destructive and life-threatening disease that imposes immense negative effects on patients' lives. Therefore, the detection of brain tumors at an early stage improves the impact of treatments and increases the patients survival rates. However, detecting brain tumors in their initial stages is a demanding task and an unmet need. METHODS: The present study presents a comprehensive review of the recent Artificial Intelligence (AI) methods of diagnosing brain tumors using MRI images. These AI techniques can be divided into Supervised, Unsupervised, and Deep Learning (DL) methods. RESULTS: Diagnosing and segmenting brain tumors usually begin with Magnetic Resonance Imaging (MRI) on the brain since MRI is a noninvasive imaging technique. Another existing challenge is that the growth of technology is faster than the rate of increase in the number of medical staff who can employ these technologies. It has resulted in an increased risk of diagnostic misinterpretation. Therefore, developing robust automated brain tumor detection techniques has been studied widely over the past years. CONCLUSION: The current review provides an analysis of the performance of modern methods in this area. Moreover, various image segmentation methods in addition to the recent efforts of researchers are summarized. Finally, the paper discusses open questions and suggests directions for future research.

Breast tumor localization and segmentation using machine learning techniques: Overview of datasets, findings, and methods.

The Global Cancer Statistics 2020 reported breast cancer (BC) as the most common diagnosis of cancer type. Therefore, early detection of such type of cancer would reduce the risk of death from it. Breast imaging techniques are one of the most frequently used techniques to detect the position of cancerous cells or suspicious lesions. Computer-aided diagnosis (CAD) is a particular generation of computer systems that assist experts in detecting medical image abnormalities. In the last decades, CAD has applied deep learning (DL) and machine learning approaches to perform complex medical tasks in the computer vision area and improve the ability to make decisions for doctors and radiologists. The most popular and widely used technique of image processing in CAD systems is segmentation which consists of extracting the region of interest (ROI) through various techniques. This research provides a detailed description of the main categories of segmentation procedures which are classified into three classes: supervised, unsupervised, and DL. The main aim of this work is to provide an overview of each of these techniques and discuss their pros and cons. This will help researchers better understand these techniques and assist them in choosing the appropriate method for a given use case.

Road safety assessment and risks prioritization using an integrated SWARA and MARCOS approach under spherical fuzzy environment.

There are a lot of elements that make road safety assessment situations unpredictable and hard to understand. This could put people's lives in danger, hurt the mental health of a society, and cause permanent financial and human losses. Due to the ambiguity and uncertainty of the risk assessment process, a multi-criteria decision-making technique for dealing with complex systems that involves choosing one of many options is an important strategy of assessing road safety. In this study, an integrated stepwise weight assessment ratio analysis (SWARA) with measurement of alternatives and ranking according to compromise solution (MARCOS) approach under a spherical fuzzy (SF) set was considered. Then, the proposed methodology was applied to develop the approach of failure mode and effect analysis (FMEA) for rural roads in Cosenza, southern Italy. Also, the results of modified FMEA by SF-SWARA-MARCOS were compared with the results of conventional FMEA. The risk score results demonstrated that the source of risk (human) plays a significant role in crashes compared to other sources of risk. The two risks, including landslides and floods, had the lowest values among the factors affecting rural road safety in Calabria, respectively. The correlation between scenario outcomes and main ranking orders in weight values was also investigated. This study was done in line with the goals of sustainable development and the goal of sustainable mobility, which was to find risks and lower the number of accidents on the road. As a result, it is thus essential to reconsider laws and measures necessary to reduce human risks on the regional road network of Calabria to improve road safety.

A robust fuzzy multi-objective location-routing problem for hazardous waste under uncertain conditions.

Industrialization and population growth have been accompanied by many problems such as waste management worldwide. Waste management and reduction have a vital role in national management. The presents study represents a multi-objective location-routing problem for hazardous wastes. The model was solved using Non dominated Sorting Genetic Algorithm-II, Multi-Objective Particle Swarm Optimization, Multi-Objective Invasive Weed Optimization, Pareto Envelope-based Selection Algorithm, Multi-Objective Evolutionary Algorithm Based on Decomposition and Multi-Objective Grey Wolf Optimizer algorithms. The findings revealed that the Multi-Objective Invasive Weed Optimization algorithm was the best and the most efficient among the algorithms used in this study. Obtaining income from the incineration of the wastes and reducing the risk of COVID-19 infection are the first innovation of the present study, which considered in the presented model. The second innovation is that uncertainty was considered for some of the crucial parameters of the model while the robust fuzzy optimization model was applied. Besides, the model was solved using several meta-heuristic algorithms such as Multi-Objective Invasive Weed Optimization, Multi-Objective Evolutionary Algorithm Based on Decomposition and Multi-Objective Grey Wolf Optimizer, which were rarely used in literature. Eventually, the most efficient algorithm was identified by comparing the considered algorithms.

Barriers to circular economy implementation in designing of sustainable medical waste management systems using a new extended decision-making and FMEA models.

The idea of the circular economy (CE) has gained prominence in the policies of the European Union (EU), commerce, and academic studies. Basically, CE is capable of achieving the best value and resolving many of the systemic challenges in the society and commerce of a country, thus leading to sustainable development and preventing irreparable damage to the environment. Medical waste management has proved a daunting challenge with the increase in the global population and the demand for medical services. Fuzzy multi-criteria decision-making approaches try to cover the different and uncertain views of decision-makers (DMs). The present study suggests a novel strategy based on multi-objective optimization using the ratio analysis (MOORA) in the area of spherical fuzzy sets (SFSs) to counterbalance the disadvantages of the failure modes and effects analysis (FMEA) method, such as the lack of weight assignment for risk factors and consideration of uncertainty. In the proposed method, first, the barriers are identified using the FMEA method, and the risk factors are given values. Then, the barriers identified using MOORA are prioritized in the spherical fuzzy (SF) area. The computational procedure of the proposed methodology is established through a case study of the barriers to circular economy implementation in designing sustainable medical waste management systems problems under an SF environment. The proposed approach was compared with IF-MOORA and was found that the results are more reliable using the proposed method, also the ranking in the MOORA method was compared with the TOPSIS method in terms of degree of correlation.

Presentation of a Segmentation Method for a Diabetic Retinopathy Patient's Fundus Region Detection Using a Convolutional Neural Network.

Diabetic retinopathy is characteristic of a local distribution that involves early-stage risk factors and can forecast the evolution of the illness or morphological lesions related to the abnormality of retinal blood flows. Regional variations in retinal blood flow and modulation of retinal capillary width in the macular area and the retinal environment are also linked to the course of diabetic retinopathy. Despite the fact that diabetic retinopathy is frequent nowadays, it is hard to avoid. An ophthalmologist generally determines the seriousness of the retinopathy of the eye by directly examining color photos and evaluating them by visually inspecting the fundus. It is an expensive process because of the vast number of diabetic patients around the globe. We used the IDRiD data set that contains both typical diabetic retinopathic lesions and normal retinal structures. We provided a CNN architecture for the detection of the target region of 80 patients' fundus imagery. Results demonstrate that the approach described here can nearly detect 83.84% of target locations. This result can potentially be utilized to monitor and regulate patients.

Experimental and numerical diagnosis of fatigue foot using convolutional neural network.

Fatigue is an essential criterion for physiotherapy in injured athletes. Muscle fatigue mechanism also is a crucial matter in designing a workout program. It is mainly related to physical injury, cerebrovascular accident, spinal cord injury, and rheumatologic disease. The leg is one of the organs in the body where fatigue is visible, and usually, the first fatigue traces in the human body are shown. The main objective of the article is to diagnosis tired and untired feet base on digital footprint images. Therefore, the foot images of students in the age group of 20-30 were examined. The device is a digital footprint scanner. This device includes a plate screen equipped with pressure sensors and footprints in the image. A treadmill is used for 8 min to tire our test individuals. Therefore, six methods of k-nearest-neighbor classifier, multilayer perceptron, support vector machine, naïve Bayesian learning, decision tree, and convolutional neural network (CNN) architecture are presented to achieve the goal. First, the images are grayscale and divide into four regions, and the mean and variance of pressure in each of the four areas are extracted as features. Finally, the classification is accomplished using machine learning methods. Then, the results are compared with a proposed CNN architecture. The presented CNN method is outperforming other approaches and can be used for future fatigue diagnosis systems.

Lung Infection Segmentation for COVID-19 Pneumonia Based on a Cascade Convolutional Network from CT Images.

The COVID-19 pandemic is a global, national, and local public health concern which has caused a significant outbreak in all countries and regions for both males and females around the world. Automated detection of lung infections and their boundaries from medical images offers a great potential to augment the patient treatment healthcare strategies for tackling COVID-19 and its impacts. Detecting this disease from lung CT scan images is perhaps one of the fastest ways to diagnose patients. However, finding the presence of infected tissues and segment them from CT slices faces numerous challenges, including similar adjacent tissues, vague boundary, and erratic infections. To eliminate these obstacles, we propose a two-route convolutional neural network (CNN) by extracting global and local features for detecting and classifying COVID-19 infection from CT images. Each pixel from the image is classified into the normal and infected tissues. For improving the classification accuracy, we used two different strategies including fuzzy c-means clustering and local directional pattern (LDN) encoding methods to represent the input image differently. This allows us to find more complex pattern from the image. To overcome the overfitting problems due to small samples, an augmentation approach is utilized. The results demonstrated that the proposed framework achieved precision 96%, recall 97%, F score, average surface distance (ASD) of 2.8 ± 0.3 mm, and volume overlap error (VOE) of 5.6 ± 1.2%.

Brain tumor segmentation based on deep learning and an attention mechanism using MRI multi-modalities brain images.

Brain tumor localization and segmentation from magnetic resonance imaging (MRI) are hard and important tasks for several applications in the field of medical analysis. As each brain imaging modality gives unique and key details related to each part of the tumor, many recent approaches used four modalities T1, T1c, T2, and FLAIR. Although many of them obtained a promising segmentation result on the BRATS 2018 dataset, they suffer from a complex structure that needs more time to train and test. So, in this paper, to obtain a flexible and effective brain tumor segmentation system, first, we propose a preprocessing approach to work only on a small part of the image rather than the whole part of the image. This method leads to a decrease in computing time and overcomes the overfitting problems in a Cascade Deep Learning model. In the second step, as we are dealing with a smaller part of brain images in each slice, a simple and efficient Cascade Convolutional Neural Network (C-ConvNet/C-CNN) is proposed. This C-CNN model mines both local and global features in two different routes. Also, to improve the brain tumor segmentation accuracy compared with the state-of-the-art models, a novel Distance-Wise Attention (DWA) mechanism is introduced. The DWA mechanism considers the effect of the center location of the tumor and the brain inside the model. Comprehensive experiments are conducted on the BRATS 2018 dataset and show that the proposed model obtains competitive results: the proposed method achieves a mean whole tumor, enhancing tumor, and tumor core dice scores of 0.9203, 0.9113 and 0.8726 respectively. Other quantitative and qualitative assessments are presented and discussed.

Theory-Based Failure Modes and Effect Analysis for Medication Errors.

Medication Errors (MEs) are still significant challenges, especially in nonautomated health systems. Qualitative studies are mostly used to identify the parameters involved in MEs. Failing to provide accurate information in expert-based decisions can provoke unrealistic results and inappropriate corrective actions eventually. However, mostly, some levels of uncertainty accompany the decisions in real practice. This study tries to present a hybrid decision-making approach to assigning different weights to risk factors and considering the uncertainty in the ranking process in the Failure Modes and Effect Analysis (FMEA) technique. Initially, significant MEs are identified by three groups of qualified experts (doctors, nurses, and pharmacists). Afterward, for assigning weights to the risk factors, Z-number couples with the Stepwise Weight Assessment Ratio Analysis (SWARA) method, named Z-SWARA, to add reliability concept in the decision-making process. Finally, the identified MEs are ranked through the developed Weighted Aggregated Sum Product Assessment (WASPAS) method, namely, Z-WASPAS. To demonstrate the applicability of the proposed approach, the ranking results compare with typical methods, such as fuzzy-WASPAS and FMEA. The findings of the present study highlight improper medication administration as the main failure mode, which can result in a fatality or patient injury. Moreover, the utilization of multiple-criteria decision-making methods in combination with Z-number can be a useful tool in the healthcare management field since it can address the problems by considering reliability and uncertainty simultaneously.

Revealing the relationship between solar activity and COVID-19 and forecasting of possible future viruses using multi-step autoregression (MSAR).

The number of sunspots shows the solar activity level. During the high solar activity, emissions of matter and electromagnetic fields from the Sun make it difficult for cosmic rays to penetrate the Earth. When solar energy is high, cosmic ray intensity is lower, so that the solar magnetic field and solar winds affect the Earth externally and originate new viruses. In this paper, we assess the possible effects of sunspot numbers on the world virus appearance. The literature has no sufficient results about these phenomena. Therefore, we try to relate solar ray extremum to virus generation and the history of pandemics. First, wavelet decomposition is used for smoothing the sunspot cycle to predict past pandemics and forecast the future time of possible virus generation. Finally, we investigate the geographical appearance of the virus in the world to show vulnerable places in the world. The result of the analysis of pandemics that occurred from 1750 to 2020 shows that world's great viral pandemics like COVID-19 coincide with the relative extrema of sunspot number. Based on our result, 27 pandemic (from 36) incidences are on sunspot extrema. Then, we forecast future pandemics in the world for about 110 years or 10 cycles using presented multi-step autoregression (MSAR). To confirm these phenomena and the generation of new viruses because of solar activity, researchers should carry out experimental studies.

Investigation of effective climatology parameters on COVID-19 outbreak in Iran.

SARS CoV-2 (COVID-19) Coronavirus cases are confirmed throughout the world and millions of people are being put into quarantine. A better understanding of the effective parameters in infection spreading can bring about a logical measurement toward COVID-19. The effect of climatic factors on spreading of COVID-19 can play an important role in the new Coronavirus outbreak. In this study, the main parameters, including the number of infected people with COVID-19, population density, intra-provincial movement, and infection days to end of the study period, average temperature, average precipitation, humidity, wind speed, and average solar radiation investigated to understand how can these parameters effects on COVID-19 spreading in Iran? The Partial correlation coefficient (PCC) and Sobol'-Jansen methods are used for analyzing the effect and correlation of variables with the COVID-19 spreading rate. The result of sensitivity analysis shows that the population density, intra-provincial movement have a direct relationship with the infection outbreak. Conversely, areas with low values of wind speed, humidity, and solar radiation exposure to a high rate of infection that support the virus's survival. The provinces such as Tehran, Mazandaran, Alborz, Gilan, and Qom are more susceptible to infection because of high population density, intra-provincial movements and high humidity rate in comparison with Southern provinces.