PSTCNN: Explainable COVID-19 diagnosis using PSO-guided self-tuning CNN

Since 2019, the coronavirus disease-19 (COVID-19) has been spreading rapidly worldwide, posing an unignorable threat to the global economy and human health. It is a disease caused by severe acute respiratory syndrome coronavirus 2, a single-stranded RNA virus of the genus Betacoronavirus. This virus is highly infectious and relies on its angiotensin-converting enzyme 2-receptor to enter cells. With the increase in the number of confirmed COVID-19 diagnoses, the difficulty of diagnosis due to the lack of global healthcare resources becomes increasingly apparent. Deep learning-based computer-aided diagnosis models with high generalisability can effectively alleviate this pressure. Hyperparameter tuning is essential in training such models and significantly impacts their final performance and training speed. However, traditional hyperparameter tuning methods are usually time-consuming and unstable. To solve this issue, we introduce Particle Swarm Optimisation to build a PSO-guided Self-Tuning Convolution Neural Network (PSTCNN), allowing the model to tune hyperparameters automatically. Therefore, the proposed approach can reduce human involvement. Also, the optimisation algorithm can select the combination of hyperparameters in a targeted manner, thus stably achieving a solution closer to the global optimum. Experimentally, the PSTCNN can obtain quite excellent results, with a sensitivity of 93.65% ± 1.86%, a specificity of 94.32% ± 2.07%, a precision of 94.30% ± 2.04%, an accuracy of 93.99% ± 1.78%, an F1-score of 93.97% ± 1.78%, Matthews Correlation Coefficient of 87.99% ± 3.56%, and Fowlkes-Mallows Index of 93.97% ± 1.78%. Our experiments demonstrate that compared to traditional methods, hyperparameter tuning of the model using an optimisation algorithm is faster and more effective. © 2023 Centro Regional de Invest. Cientif. y Tecn.. All rights reserved.

Adverse Effects of COVID-19 Vaccination: Machine Learning and Statistical Approach to Identify and Classify Incidences of Morbidity and Postvaccination Reactogenicity.

Good vaccine safety and reliability are essential for successfully countering infectious disease spread. A small but significant number of adverse reactions to COVID-19 vaccines have been reported. Here, we aim to identify possible common factors in such adverse reactions to enable strategies that reduce the incidence of such reactions by using patient data to classify and characterise those at risk. We examined patient medical histories and data documenting postvaccination effects and outcomes. The data analyses were conducted using a range of statistical approaches followed by a series of machine learning classification algorithms. In most cases, a group of similar features was significantly associated with poor patient reactions. These included patient prior illnesses, admission to hospitals and SARS-CoV-2 reinfection. The analyses indicated that patient age, gender, taking other medications, type-2 diabetes, hypertension, allergic history and heart disease are the most significant pre-existing factors associated with the risk of poor outcome. In addition, long duration of hospital treatments, dyspnoea, various kinds of pain, headache, cough, asthenia, and physical disability were the most significant clinical predictors. The machine learning classifiers that are trained with medical history were also able to predict patients with complication-free vaccination and have an accuracy score above 90%. Our study identifies profiles of individuals that may need extra monitoring and care (e.g., vaccination at a location with access to comprehensive clinical support) to reduce negative outcomes through classification approaches.

Demystifying the effectiveness of emergency remote teaching during global pandemic: Evidence from India

Given the adverse impacts of the global pandemic COVID-19 on higher educational institutions worldwide, this study aims to examine the effectiveness of emergency remote teaching (ERT), especially in the developing country context, India. In addition, this study investigates the antecedents and consequences of academic performance and explores social media use as a moderator in these relationships. A carefully crafted survey instrument was distributed. Data was collected from 719 respondents from the affiliated arts and science college of a renowned university in southern India. After checking the psychometric properties of the constructs using the Smart Partial Least Squares (Smart-PLS) of structural equation modelling, and hierarchical regression was used to test the hypothesized relationships. The results of this research indicate that course content, instructor-learner interaction, and student expectation are positively associated with academic performance;social media use moderate the relationship between (i) course content and academic performance, (ii) student expectation and academic performance, and (iii) learning platforms and academic performance. The results also support the positive relationship between academic performance and students' satisfaction with ERT. https//doi.org/10.34105/j.kmel.2022.14.022

Examining ecological strategies adopted by agricultural exporting firms in an emerging country

PurposeThe rising food demand around the globe goes hand in hand with the rapid development of the agriculture industry. However, this development at the same time has detrimental effects on the natural environment. Hence, promoting ecological strategies in agriculture is essential for environmental sustainability. This study aims to investigate the institutional determinants of ecological strategies adopted by agricultural exporting firms and how these strategies enhance the firms' competitive advantage and financial performance.Design/methodology/approachA survey was conducted to collect data from 218 managers of agricultural exporting companies in Vietnam, which is a major exporter of agricultural products. The data were analyzed using different techniques including partial least squares structural equation modeling (PLS-SEM).FindingsThe results reveal that market pressure, regulatory pressure and competitive pressure motivate the adoption of ecological strategies among the surveyed agricultural exporting firms. Furthermore, such strategies help these firms obtain competitive advantage, which in turn increases their export financial performance. In addition, larger firms, compared to smaller firms, are more likely to adopt ecological strategies.Originality/valueThis study contributes to the literature by developing and validating a unique model examining the institutional pressures of ecological strategies and their outcomes in export markets. The study extends current knowledge about ecological exporting strategies for agricultural products, and its findings have several managerial and policy implications for promoting these strategies among agricultural exporting firms in emerging countries like Vietnam.

A systematic hybrid machine learning approach for stress prediction

Stress is becoming an increasingly prevalent health issue, seriously affecting people and putting their health and lives at risk. Frustration, nervousness, and anxiety are the symptoms of stress and these symptoms are becoming common (40%) in younger people. It creates a negative impact on human lives and damages the performance of each individual. Early prediction of stress and the level of stress can help to reduce its impact and different serious health issues related to this mental state. For this, automated systems are required so they can accurately predict stress levels. This study proposed an approach that can detect stress accurately and efficiently using machine learning techniques. We proposed a hybrid model (HB) which is a combination of gradient boosting machine (GBM) and random forest (RF). These models are combined using soft voting criteria in which each model's prediction probability will be used for the final prediction. The proposed model is significant with 100% accuracy in comparison with the state-of-the-art approaches. To show the significance of the proposed approach we have also done 10-fold cross-validation using the proposed model and the proposed HB model outperforms with 1.00 mean accuracy and +/−0.00 standard deviation. In the end, a statistical T-test we have done to show the significance of the proposed approach in comparison with other approaches.

Antecedents of obesity among Indian youth: from consumer psychological and lifestyle perspective

PurposeThe purpose of this study is to determine the antecedents of obesity among the younger generation of Indians (Generation Y) from a psychological and lifestyle consumer perspective. The study also investigates the moderating role of demography on the body mass index (BMI) of Indian youths.Design/methodology/approachThe study initially develops a conceptual model, stemming from an extensive theoretical research, and subsequently validates this using structural equation modeling (SEM) technique with a sample size of 1,242 Indian youths.FindingsThe study concludes that consumers' food habits (FH) and physical activity (PA) positively impact consumers' physical health (PH), which influences their BMI levels (BLs). Anxiety (AX), depression (DE), stress (ST), peer pressure (PP) and work pressure (WP) impact individuals' mental health (MH), which also influences their BLs. Finally, there is a significant moderating impact of demographic factors, such as age (AG), gender (GE) and income levels (ILs) on the relationship between individuals' physical and MH and individuals' BLs.Research limitations/implicationsThis study proposes a new model which highlights the issue of youth consumer obesity from the psychological and lifestyle perspectives. The model is effective as it has a high explanative power of 73%. The study investigates consumer obesity from emerging market like India perspective, but the study does not examine consumer food consumption behavior and obesity from developed market perspective.Practical implicationsYouth obesity could be considered a global pandemic, and obesity rates among the Indian youth are also increasing. This study provides valuable inputs and understanding of consumer markets to policy makers, consumer protection institutions, organizations related to the food and beverage industry, healthcare workers and consumers themselves regarding the antecedents of youth obesity (BL) in developing and emerging markets.Originality/valueThe study adds value to the body of literature related to consumer obesity, FH, consumer psychology and lifestyle through findings that are new in terms of findings' specificity, contextual focus and explication. Moreover, the study extends the cognitive theory of DE and the theory of planned behavior (TPB). The research effectively offers significant theoretical and practicable market knowledge to both scholars and marketing practitioners, as well as policy makers and institutions dealing with youth obesity, particularly in emerging markets.

Experience of Tocilizumab in Hospital Patients with Moderate Covid-19

Severe form of COVID 19 has been linked to the phenomenon of dysregulated inflammation with excessive cytokine release and elevated interleukin 6 (IL6) levels. Suppressive agents enabling specific inhibition of cytokines, notably monoclonal antibodies to IL6 and its receptors, have been applied as a rescue therapy in COVID 19 despite the underexplored clinical scope for these biologic medications. This study aimed to evaluate the clinical utility of IL6 receptor antagonist tocilizumab in moderate symptomatic COVID 19 prone to aggravation. The retrospective cohort study enrolled two groups of hospitalized patients (a total of n = 72) diagnosed with moderate COVID-19. The main group received a single 400 mg dose of tocilizumab (TCZ) on top of standard therapy. The comparative analysis included statistical evaluation for a number of clinical and laboratory parameters at reference time points and disease outcomes with regard to treatment strategy. Overall, TCZ administration provided no advantages in terms of oxygen supplementation status, disease progression, or survival. Lethal cases constituted 19.2% (10 pts) and 5% (1 pt) in TCZ and comparison groups, respectively. The results indicate that administration of monoclonal antibody drugs in hospital patients with COVID-19 must follow differential schemes with regard to the disease severity and comorbidities, as well as proper commencement schedules. Copyright © 2022 Pirogov Russian National Research Medical University. All rights reserved.

Lockdown Effects on Air Quality in Megacities During the First and Second Waves of COVID-19 Pandemic

Air pollution is among the highest contributors to mortality worldwide, especially in urban areas. During spring 2020, many countries enacted social distancing measures in order to slow down the ongoing COVID-19 pandemic. A particularly drastic measure, the "lockdown”, urged people to stay at home and thereby prevent new COVID-19 infections during the first (2020) and second wave (2021) of the pandemic. In turn, it also reduced traffic and industrial activities. But how much did these lockdown measures improve air quality in large cities, and are there differences in how air quality was affected? Here, we analyse data from two megacities: London as an example for Europe and Delhi as an example for Asia. We consider data during first and second-wave lockdowns and compare them to 2019 values. Overall, we find a reduction in almost all air pollutants with intriguing differences between the two cities except Delhi in 2021. In London, despite smaller average concentrations, we still observe high-pollutant states and an increased tendency towards extreme events (a higher kurtosis of the probability density during lockdown) during 2020 and low pollution levels during 2021. For Delhi, we observe a much stronger decrease in pollution concentrations, including high pollution states during 2020 and higher pollution levels in 2021. These results could help to design policies to improve long-term air quality in megacities.

Experts? opinions about lasting innovative technologies in City Logistics

The COVID-19 pandemic has highlighted the relevance of goods delivery in urban areas. However, this activity often generates negative environmental impact and several technologies have been proposed in recent years to reduce it, thus forming a complex innovation landscape characterized by different levels of maturity and effects on the City Logistics (CL) system. This complexity causes a deep uncertainty over the future of CL. This paper aims to tackle this uncertainty by forecasting the future of a set of CL technologies. A Delphi survey has been submitted to experts of this field to achieve a stable consensus over 33 projections related to 7 CL technologies for the year 2030. Results show that real-time data collection will help the coordination process between stake-holders, engendering an increased awareness over the value of using logistics data as well as its potential drawbacks. Moreover, experts share a positive attitude towards the expansion of Parcel Lockers, which should be monitored by public authorities to avoid a negative impact on land use. Finally, technologies such as drones and crowd-logistics have drawn the lowest level of consensus due to their lower level of maturity, which arouse the necessity to further explore several issues such as legal and technical barriers.

META-ANALYSIS: A SOUND BASE FOR STATISTICAL ANALYSIS OF PANDEMIC DISEASE

The paper provides the basic concept of meta-analysis and its literature. We demonstrate how the meta-analysis is used in a practical approach and especially tends to the human dimension research technique. In the present scenario, social scientists have dared to improve how they access summarize and convey a reference to the health indicator used in health policy. Meta-analysis provides a systematic review of existing research using data from different field studies. Dynamic meta-analysis would ensure the policymaker uses the information and perform the best approximate analysis relevant to the context of new policy used for public health research, social science and life science. Especially in this paper, we analyze the definition of meta-analysis and discuss the various steps used in meta-analysis for analysis and use this interpretation to improve the health policy. We discussed the merits of meta-analysis and did the statistical analysis of the five countries of the pandemic Covid-19 from the total data for 2020 and 2021. © 2022 DAV College. All rights reserved.

Financial Disruption and Microentrepreneurs: Empirical Study on Adoption of E-Wallet Among Micro-Entrepreneurs in India

The COVID-19 pandemic is expeditiously stirring the global economy. The impact of this pandemic has implications on the sustenance of industries worldwide. This study investigates the influence of various endogenous and exogenous factors affecting e-wallet adoption among micro entrepreneurs in India. A sample of 287 micro enterprises were identified in NCR (National Capital Region) region on the basis of random sampling. Structured questionnaires were administered to the respondents. Structural equation modelling was used to analyse the data with the help of Smart PLS 3. The main findings of the study show that self-belief, personal innovativeness, and satisfaction are the key indicators affecting the e-wallet adoption among the microentrepreneurs. Microentrepreneurs contribute greatly to economic development in developed and developing nations. Digitalisation of this segment of industry can turn India into a cashless country, thereby reducing the cash burden of the economy. Microentrepreneurs can also act as a catalyst for financial inclusion.

Employee associations with R&D investment, firm performance, disruption risk, and supply chain performance during the COVID-19 pandemic: A multiple mediational model

Purpose: Scholars have concentrated their efforts on COVID-19's impact on industries worldwide in order to manage timely supply chain disruptions. Epidemic outbursts are a unique supply chain risk that is distinguished by prolonged disruption propagation, disruption existence, and high uncertainty. The purpose of this study was to investigate the role of R&D investment and firm performance in mediating the relationship between disruption risk and supply chain performance in Pakistani manufacturing industries and supply chain employees during the recovery phase of the COVID-19 pandemic via application of dynamic capability theory. Methodology: From July 21 to August 23, 2020, three hundred and eighteen employees from supply chains of manufacturing industries in Rawalpindi and Islamabad, Pakistan, participated in this cross-sectional online web-based survey. The four standard research scales were used to examine the research and development, disruption risk, firm, and supply chain performance. The response link was distributed to respondents via Facebook, WhatsApp, and email. The data was analyzed using structural equation modelling and a partial least squares technique in the study. Results: The study's findings suggest that disruption risk, research and development investment, and firm performance all improve supply chain performance, but the mediation effect is unsupported by the data. These measures help to plan a better supply chain in the face of disruption risk, and they provide one of the timely empirical conclusions on the role of R&D investment in mitigating risk disruptions and improving supply chain performance

Principals' Perceptions of Online Teaching and Learning in School After the Outbreak of the Pandemic

The current study aims to analyse school leaders' understanding and expectation of, and support for, online teaching and learning during and after the outbreak of the COVID-19 pandemic. Based on the theory of reasoned action (TRA) framework, the authors designed a questionnaire and collected 319 responses from school principals about their views on online teaching and learning. Structural equation modelling revealed that principals' understanding was significantly associated with their expectations and support. Together with a thematic analysis, this study indicated that school principals understood online teaching and learning. The most expected item was students' ownership and access to a suitable device for online learning. Principals were willing to support students' self-regulated learning through online teaching. They appealed for more support for the infrastructure needed to ensure teachers' and students' privacy and security in online teaching and learning. They had suggestions for teacher development to tackle learner diversity in the online mode.

Influence of psychological safety and social presence on knowledge sharing behavior in higher education online learning environment: Very Informal Newsletter on Library Automation

Purpose>The absence of physical interactions in online learning environment brings psychological influences on learning participants in interacting and sharing knowledge with others, such as ignorance of other member's presence and insecurity to share something in online environment. The purpose of this research was to examine the knowledge sharing behavior (KSB) by online learning community members in terms of their psychological safety (PS) and social presence (SP) perceptions. In addition, this research also identified the influence of PS to promote SP and the mediation impact of SP in the relationships between PS and KSB.Design/methodology/approach>The data were gathered through self-administered questionnaire distributed to 133 online class members at a university in Indonesia where online learning has created a new learning experience. To represent key behavioral attributes, 12 items were used to represent PS, SP and KSB. The relationships among the variables were analyzed using the structural equation modelling method.Findings>The result showed that PS positively influenced SP and KSB. SP also brought a positive impact on promoting KSB and fully mediated the relationship between PS and KSB.Research limitations/implications>The result may not have fully captured the reflection of the influencing factors of KSB, as this research focused only on two psychological factors, namely, PS and SP. The research may be further enriched by including additional factors and expanding the data collection to include more online learning institutions.Practical implications>The results implied the importance of PS and SP perception to promoting KSB in online learning environments. The results highlighted an important message to universities and schools to be more concerned on students' feeling safe personally and students' awareness of others' presence to maximize knowledge sharing activities in online class environment.Originality/value>This paper revealed the importance of PS and SP to promote KSB in the higher education online learning community. To the best of the researchers' knowledge, this is the first study to link PS and SP to KSB and identify the importance of the mediation effect of SP on the relationship between PS and KSB specifically in higher education online learning environment.

Preliminary Results on the Online Lessons of IDPE Department of University of West Attica 2019-2020

During the pandemic outbreak of COVID-19 in Greece that coincided with the spring semester of the year 2020, conventional face-to-face lessons presented a threat to public health. As a result, house confinement measures were taken. Universities, due to their offering either directly or via their lifelong education centers, were partially prepared to offer distant learning solutions for their students during the pandemic. The lessons, in the general case, were delivered in an ad hoc manner utilizing teachers' personal experiences and preferences creating some pressure on existing infrastructures. In the case of the Department of Industrial Design & Production Engineering at the University of West Attica, things were more organized than in the general case: there was a, more or less, uniform practice of preferring synchronous lessons and some monitoring was planned in order to evaluate the application for future reference. While data collected in the process are still going through statistical analysis there are some preliminary results that can be reported here.

Statistical modelling of the impact of online courses in higher education on sustainable development

Purpose>The concept of sustainable development (SD) is a popular response to society's need to preserve and extend the life span of natural resources. One of the 17 goals of the SD is "education quality” (Fourth Goal of Sustainable Development [SDG-4]). Education quality is an important goal because education is a powerful force that can influence social policies and social change. The SDG-4 must be measured in different contexts, and the tools to quantify its effects require exploration. So, this study aims to propose a statistical model to measure the impact of higher education online courses on SD and a structural equation model (SEM) to find constructs or factors that help us explain a sustainability benefits rate. These proposed models integrate the three areas of sustainability: social, economic and environmental.Design/methodology/approach>A beta regression model suggests features that include the academic and economic opportunities offered by the institution, the involvement in research activities and the quality of the online courses. A structural equation modelling (SEM) analysis allowed selecting the key variables and constructs that are strongly linked to the SD.Findings>One of the key findings showed that the benefit provided by online courses in terms of SD is 62.99% higher than that of offline courses in aspects such as transportation, photocopies, printouts, books, food, clothing, enrolment fees and connectivity.Research limitations/implications>The SEM model needs large sample sizes to have consistent estimations. Thus, despite the obtained estimations in the proposed SEM model being reliable, the authors consider that a limitation of this study was the required time to collect data corresponding to the estimated sample size.Originality/value>This study proposes two novel and different ways to estimate the sustainability benefits rate focused on SDG-4, and machine learning tools are implemented to validate and gain robustness in the estimations of the beta model. Additionally, the SEM model allows us to identify new constructs associated with SDG-4.

Touchless Interfaces in the Operating Room: A Study in Gesture Preferences

Touchless interfaces allow surgeons to control medical imaging systems autonomously while maintaining total asepsis in the Operating Room. This is specially relevant as it applies to the recent outbreak of COVID-19 disease. The choice of best gestures/commands for such interfaces is a critical step that determines the overall efficiency of surgeon-computer interaction. In this regard, usability metrics such as task completion time, memorability and error rate have a long-standing as potential entities in determining the best gestures. In addition, previous works concerned with this problem utilized qualitative measures to identify the best gestures. In this work, we hypothesize that there is a correlation between gestures' qualitative properties and their usability metrics. In this regard, we conducted a user experiment with language experts to quantify gestures' properties (v). Next, we developed a gesture-based system that facilitates surgeons to control the medical imaging software in a touchless manner. Next, a usability study was conducted with neurosurgeons and the standard usability metrics (u) were measured in a systematic manner. Lastly, multi-variate correlation analysis was used to find the relations between u and v. Statistical analysis showed that the v scores were significantly correlated with the usability metrics with an and p < 0.05. Once the correlation is established, we can utilize either gestures' qualitative properties or usability metrics to identify the best set of gestures.

Using the extended parallel process model (EPPM) to explore US consumers' dining behaviors during COVID-19

PurposeThe purpose of this study was to examine consumers' dining behaviors and explore their decision-making process when dining out during the COVID-19 pandemic.Design/methodology/approachBased on the extended parallel process model (EPPM) and the related literature, a conceptual model was developed and tested. This study conducted an online survey with 351 responses. In addition, a series of statistical analyses, including descriptive analyses and path analyses, were conducted to analyze the associations among key constructs in the proposed model.FindingsThe findings of this study confirmed the pragmatic utility of applying EPPM in a hospitality management context. The findings of this study also outline the different nature between the participants' enactment of self-protective measures and dining out activities. Lastly, while consumers are hesitant about dining out, the results showed that consumers' dining behaviors are directly related to their personality trait of sensation-seeking.Research limitations/implicationsThis study was delimited to a cross-sectional design and self-reported data. Such information may provide insights into individuals' decision-making and behaviors related to dining in a COVID-19 context. In addition, this study only includes US samples, while future studies can extend this study by including samples from different countries and cultural backgrounds.Originality/valueThis study adopts an interdisciplinary approach, which derives from tourism and hospitality management and public health. As a result, the findings of this study not only identify the major influencers affecting consumers' dining behavior but also help contextualize a public health model and contribute to the tourism and hospitality management literature.

Factors Influencing Students' Continuous Willingness to Use E-Learning Platforms in Higher Education

The COVID-19 pandemic has imposed significant challenges on education worldwide, particularly in areas with limited online teaching experience. The research design is based on constructivism learning theory and the technology acceptance model. A questionnaire was also distributed to a university of finance and economics in China. Structural equation model was used to test the influence mechanism of social media interaction on college students' willingness to use e-learning platform continuously. The positive moderating effect of online teaching context on this mechanism is further analyzed. Therefore, the use of social media in the online teaching process in higher education institutions should be encouraged, and a good online teaching context should be fostered.

Optimization of ultrasonication-assisted extraction conditions using RSM-I-Optimal experimental design to recover vitamin D2 and K1 from selected green leafy vegetable samples

This study employed the response surface methodology to optimize the extraction conditions for recovering vitamins D2 and K1 from green leafy vegetables using ultrasonication-assisted extraction. The vitamin content was determined using an Accucore C18 column and a UPLC-Q-ToF/MS method. An RSM-I-Optimal design was used for designing the experiment to find the best combination of solvent level (mL), sonication time (min), sonication frequency (kHz), and temperature (°C). The experimental data from a 25-sample set were fitted to a second-order polynomial equation using multiple regression analysis. The extraction models had R2 values of 0.895 and 0.896, respectively, and the probability values (p < 0.0001) indicated that the regression model was highly significant. The optimal extraction conditions were: solvent level of 65 mL, sonication time of 45 min, sonication frequency of 70 kHz, and temperature of 45 °C. Under these conditions, the predicted recovery (%) values for vitamins D2 and K1 were 90.7% and 90.4%, respectively. This study has the potential to use the reported extraction method for routine quantification of vitamins D2 and K1 in the laboratory using UPLC-Q-ToF/MS.