ABSTRACT
A mortality prediction model can be a great tool to assist physicians in decision making in the intensive care unit (ICU) in order to ensure optimal allocation of ICU resources according to the patient's health conditions. The entire world witnessed a severe ICU patient capacity crisis a few years ago during the COVID-19 pandemic. Various widely utilized machine learning (ML) models in this research field can provide poor performance due to a lack of proper feature selection. Despite the fact that nature-based algorithms in other sectors perform well for feature selection, no comparative study on the performance of nature-based algorithms in feature selection has been conducted in the ICU mortality prediction field. Therefore, in this research, a comparison of the performance of ML models with and without feature selection was performed. In addition, explainable artificial intelligence (AI) was used to examine the contribution of features to the decision-making process. Explainable AI focuses on establishing transparency and traceability for statistical black-box machine learning techniques. Explainable AI is essential in the medical industry to foster public confidence and trust in machine learning model predictions. Three nature-based algorithms, namely the flower pollination algorithm (FPA), particle swarm algorithm (PSO), and genetic algorithm (GA), were used in this study. For the classification job, the most widely used and diversified classifiers from the literature were used, including logistic regression (LR), decision tree (DT) classifier, the gradient boosting (GB) algorithm, and the random forest (RF) algorithm. The Medical Information Mart for Intensive Care III (MIMIC-III) dataset was used to collect data on heart failure patients. On the MIMIC-III dataset, it was discovered that feature selection significantly improved the performance of the described ML models. Without applying any feature selection process on the MIMIC-III heart failure patient dataset, the accuracy of the four mentioned ML models, namely LR, DT, RF, and GB was 69.9%, 82.5%, 90.6%, and 91.0%, respectively, whereas with feature selection in combination with the FPA, the accuracy increased to 71.6%, 84.8%, 92.8%, and 91.1%, respectively, for the same dataset. Again, the FPA showed the highest area under the receiver operating characteristic (AUROC) value of 83.0% with the RF algorithm among all other algorithms utilized in this study. Thus, it can be concluded that the use of feature selection with FPA has a profound impact on the outcome of ML models. Shapley additive explanation (SHAP) was used in this study to interpret the ML models. SHAP was used in this study because it offers mathematical assurances for the precision and consistency of explanations. It is trustworthy and suitable for both local and global explanations. It was found that the features that were selected by SHAP as most important were also most common with the features selected by the FPA. Therefore, we hope that this study will help physicians to predict ICU mortality for heart failure patients with a limited number of features and with high accuracy.
ABSTRACT
The scientific community has observed several issues as a result of COVID-19, both directly and indirectly. The use of face mask for health protection is crucial in the current COVID-19 scenario. Besides, ensuring the security of all people, from individuals to the state system, financial resources, diverse establishments, government, and non-government entities, is an essential component of contemporary life. Face recognition system is one of the most widely used security technology in modern life. In the presence of face masks, the performance of the current face recognition systems is not satisfactory. In this paper, we investigate a flexible solution that could be employed to recognize masked faces effectively. To do this, we develop a unique dataset to recognize the masked face, consisting of a frontal and lateral face with a mask. We propose an extended VGG19 deep model to improve the accuracy of the masked face recognition system. Then, we compare the accuracy of the proposed framework to that of well-known deep learning techniques, such as the standard Convolutional Neural Network (CNN) and the original VGG19. The experimental results demonstrate that the proposed extended VGG19 outperforms the investigated approaches. Quantitatively, the proposed model recognizes the frontal face with the mask with high accuracy of 96%. © 2022 IEEE.
ABSTRACT
Vulnerability of small-scale fisheries (SSF) results from complex interactions amongst various threats and stressors, including biophysical risks, environmental variability, unstable political situations, and weak governance, to name a few. SSF vulnerability has become more evident, with increased severity, during the COVID-19 pandemic. Knowledge about what makes SSF vulnerable is limited, which impedes appropriate policy responses and intervention. As a first step to rectifying the situation, a classification approach is proposed to better describe and differentiate types of vulnerability to SSF and to guide data collection and dissemination about SSF vulnerability. The classification system is developed based on a narrative review of case studies worldwide, published in scientific journals in the past 20 years. The case studies cover SSF in diverse aquatic environments, including river, floodplain, reservoir, river delta, lake, atoll, estuaries, lagoon mangrove, coral reefs, seagrass ecosystem, islands, coastal and marine environment. Similar to the five pillars of sustainability, SSF vulnerability is associated with five main factors, i.e., biophysical, social, economic, technological, and governance. Knowledge about SSF vulnerability helps inform tailored management strategies and policies to reduce SSF marginalization and promote viability, aligning, therefore, with the goal of the Voluntary Guidelines for Securing Sustainable Small-Scale Fisheries.Copyright © 2022 Elsevier Ltd
ABSTRACT
The objective of this research paper is to investigate the impact of COVID-19 on the factors influencing on-time software project delivery in different Software Development Life Cycle (SDLC) models such as Agile, Incremental, Waterfall, and Prototype models. Also to identify the change of crucial factors with respect to different demographic information that influences on-time software project delivery. This study has been conducted using a quantitative approach. We surveyed Software Developers, Project Managers, Software Architect, QA Engineer and other roles using a Google form. Python has been used for data analysis purposes. We received 72 responses from 11 different software companies of Bangladesh, based on that we find that Attentional Focus, Team Stability, Communication, Team Maturity, and User Involvement are the most important factors for on-time software project delivery in different SDLC models during COVID-19. On the contrary, before COVID-19 Team Capabilities, Infrastructure, Team Commitment, Team Stability and Team Maturity are found as the most crucial factors. Team Maturity and Team Stability are found as common important factors for both before and during the COVID-19 scenario. We also identified the change in the impact level of factors with respect to demographic information such as experience, company size, and different SDLC models used by participants. Attentional focus is the most important factor for experienced developers while for freshers all factors are almost equally important. This study finds that there is a significant change among factors for on-time software project delivery before and during the COVID-19 scenario. Copyright © 2023 by SCITEPRESS - Science and Technology Publications, Lda. Under CC license (CC BY-NC-ND 4.0)
ABSTRACT
This study aims to evaluate the impacts of the COVID-19 lockdown on traffic volume of national highways connecting Dhaka with other divisional cities considering pre, during and post-lockdown periods during COVID-19. Bangladesh Government imposed countrywide lockdown at different steps in different timeline, based on the dissemination rate of COVID-19 virus. As a part of controlling measures, the first lockdown was imposed on March 2020 and vehicular movement on highways connecting capital Dhaka with other divisional cities got banned. Thus, the vehicular traffic contributing to Dhaka using different highways got lessened over period. Before imposing every movement ban, people migrated and left cities. Considering all these scenarios, traffic volume has been studied for the eight National Highways (N1-N8). Along with this, the change in road crash rate over these periods has also been studied. Although it seems that, with the reduction of vehicular movements on road the crash rate would also be lessened, but the observed scenario is opposite. For example, on N1 from March 9 to March 25, 2019, the crash number was 3 and the fatality rate was 4, however in 2020, the numbers were 4 and 18. Moreover, the crash number on N5 was 6 during the shutdown period from March 26 to May 29, 2020, and it was 5 in 2019. The fatality rates were the same in both times, indicating that the travel restrictions did not reduce the number of crashes. The main causes of these collisions during the lockdown were mostly irresponsible driving and high speeds due to comparatively low traffic volume. On the other hand, the crash number on N7 was 17 after shutdown from 30 May 2020 to 28 November 2020, and it was 15 in 2019. It appears that, because passenger vehicle movement was restricted for a long period, vehicular mobility was exegeted, resulting in a rise in ADT values on national highways, as well as an increase in crash counts. Each year, many unexpected crashes occur on these national highways due to uncontrolled driving, overtaking, and high speeds. The study findings can help policy makers to understand the factors behind roadway crashes on the highways during the COVID-19 period. It would eventually govern reliable, efficient roadway system ensuring mobility with safety. © 2023 Author(s).
ABSTRACT
Educational technological tools are now an integral part of the education industry. Various platforms used for educational purposes were analyzed to find the perception of the learner;however, the major analyzing trends revolve around Zoom, Google meet, Google Classroom, and Institutional LMS, overlooking the evaluation of the perception of Teachly: an Ed-tech application developed by Harvard Kennedy School. The objective of this study is to determine the perception of students at Stamford University (n = 36) who enrolled and completed a semester at Teachly using descriptive statistics. For precision, a slider scale was used to collect data using the Google form in a semi-structured questionnaire. The data were then analyzed using the mean and standard deviation to find the central tendency and the measure of variability. The analysis confirms that the student has a positive perception towards using Teachly covering Walgito's three components of perception, and it also points out some limitations identified by the student which hampers its future implementation. © 2023, North American Business Press. All rights reserved.
ABSTRACT
This study investigates engagement activities higher education institutions have been providing to develop a learning culture as well as entrepreneurship skills for undergraduate entrepreneurship education learners in Australia. This research is intended to explore changes and adjustments made in the curriculum of undergraduate entrepreneurship education programmes in selected higher education institutions in Australia due to uncertainties caused by COVID-19. We focused on six Australian universities offering undergraduate entrepreneurship programmes, which were purposefully chosen. Data and information were gathered from the universities' websites, documents available from the same source, the universities' structure of engagement activities, and their curriculum. Previous literature was referred to for models already proposed and executed. By considering the COVID-19 crisis as well as similar types of future uncertainties, the study has identified the necessity of implementing open innovation and experiential learning models in a blended environment and having strong IT infrastructure for sustainable industry-university collaboration to facilitate a learning culture and develop entrepreneurship skills in undergraduate entrepreneurship education learners in Australia. © 2023 by the authors.
ABSTRACT
PurposeThis study aims to propose and examine a research model where work engagement mediates the impacts of high-involvement work practices (HIWPs) on bank employees' turnover intentions. Specifically, the paper assesses: (a) the effects of empowerment, information sharing, rewards and training on work engagement and turnover intention, (b) work engagement as a mediator of the effects of these HIWPs on turnover intention (c) and functional competence as a moderator of the effects of these HIWPs on work engagement.Design/methodology/approachAn online survey was employed to gather data from 343 employees working in commercial banks in Bangladesh. The authors applied partial least squares structural equation modeling to assess the aforesaid linkages.FindingsEmpowerment and information sharing increase bank employees' work engagement, while training and rewards reduce their proclivity to leave. Work engagement partly mediates the relationships of empowerment and information sharing to turnover intention. Functional competence moderates the relationship between three HIWPs (empowerment, information sharing and rewards) on work engagement.Originality/valueThe paper examines the association between HIWPs and turnover intention, which has been subjected to little empirical inquiry among bank employees during a crisis (e.g. Covid-19 pandemic). The paper provides new insights into the underlying mechanism linking HIWPs and turnover intention and highlights the moderating effect of functional competence. Additionally, the study offers new knowledge on the impact of the pandemic on bank employees' HIWPs. Finally, this paper used data gathered from bank employees in Bangladesh, which is an underrepresented Asian country in the extant service research.
ABSTRACT
India-one of the world's most densely populated countries is severely affected by the COVID-19 pandemic and has the second largest number of confirmed cases followed by the USA as on September 15, 2020. This chapter analyzes the overall features of the outbreak within the country as well as the micro social impacts caused by the coronavirus in India. Based on thematic content of various newspapers, magazines, and other media reports qualitative analyses, it is possible to understand the country features and social impact of the novel coronavirus pandemic. The first part of the chapter gives a general overview of the outbreak and government responses, and the second section scrutinizes the social impact in relation to micro level socio-economic consequences and epidemiological concerns. In mainstream reports, the impact of COVID-19 outbreak in India has been presented through the macro-economic indicators and emphasis on the negative economic impacts such as decline of growth rate, shrinking Gross Domestic Product (GDP), etc. However, the micro level socio-economic impacts of the outbreak, which are largely caused by the government interventions i.e., lock down, social distancing, etc., persist beyond the statistical number and have spread to every corner of the society. Although statistics revealed that the case fatality rate and death per hundred thousand is relatively low in India compared to other severely affected countries there are reasons beyond the standard epidemiological claims for this trend, reasons which are not properly addressed. This chapter concludes that while, from an epidemiological point of view, India has, thus far, been successful in handing the crisis brought by the global outbreak;however, the social consequences are much larger and need to be taken in consideration before claiming any success. © The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2021.
ABSTRACT
Vaccine uptake and coverage in susceptible populations are needed through effective vaccination campaigns to address the COVID-19 pandemic in South Asian countries. We aimed to measure the pooled proportion of COVID-19 vaccine hesitancy in this regard. Research articles published between January 1, 2020, to December 31, 2021, were searched through Medline, PubMed, Cochrane, Google Scholar, and the WHO COVID-19 database. The Joanna Briggs Institute (2014) tool for prevalence studies was used to assess data quality. We performed a meta-regression test and a sensitive analysis among the studies and used the DerSimonian and Laird random-effects model to measure the pooled effect estimates. Subgroup analyses were performed concerning vaccine hesitancy, countries, study population, study level, and the time since the first outbreak of the pandemic. A total of 43 studies out of 598 published articles across the eight countries in South Asia were included. The pooled proportion of COVID-19 vaccine hesitancy was 26.5% (95% CI [22, 31], I2 = 99.59%). Vaccine hesitancy was higher in Afghanistan (37%), Pakistan (33%), and Bangladesh (28.9%);among the general population (29%);at community levels (27.9%);and the duration of time of 1–12 months since the first outbreak in each country (27.5%). Vaccine hesitancy exists in South Asia with different rates among countries, population sub-groups, communities, study-levels, duration of time since the first outbreak, and study population. Therefore, enhancing public awareness of vaccination and vaccine hesitancy is required to prevent future pandemics. © 2023,Journal of Population and Social Studies. All Rights Reserved.
ABSTRACT
An appointment system is going to be popular nowadays. The necessity of these types of systems is increasing day by day specially in education sector. Worldwide COVID-19 pandemic provoke the demand of these types of application. In this research paper, an Android-based appointment is built for booking an appointment and communicating with the teacher. To use this system both student and teacher have to an android device with connection of the internet. A single android application will be used for both types of users. Students can get the information of all teachers and book an appointment with teachers and teachers can accept or decline this appointment. Java programming language is used for this system and Google's Firebase is used for the database. In addition, the modern coding Architecture pattern MVVM (Model- View-View Model) followed to build this system. Hopefully, this system saves valuable time and makes the teacher-student interaction journey easier. © 2023 IEEE.
ABSTRACT
Background The COVID-19 pandemic has disrupted routine HbA1c testing. This has led to difficulties in monitoring glycaemic control and identifying people with suboptimal glycaemia. Delayed diagnosis of diabetes and suboptimal glycaemic control over extended periods can increase the risk of developing long-term complications of diabetes. The self-collection of capillary blood remotely (at home) for routine HbA1c testing can facilitate monitoring of glycaemic control whilst supporting virtual consultations. The aimof this study was to assess the clinical performance and user acceptance of capillary blood samples prepared remotely using the MiniCollect capillary blood collection device as an alternative to standard venous blood collection for HbA1c analysis. Methods Adult men and women with any type of diabetes were recruited. Following informed written consent, eligible participants provided a venous blood sample at their routine clinic appointment and subsequently prepared a capillary blood sample remotely. Participants also completed a bespoke usability questionnaire. Results Of 84 participants recruited, 62 capillary samples returned to the laboratory, with 41 having a paired venous sample for HbA1c analysis. HbA1c results using both collection methods demonstrated good agreement;Passing-Bablok Regression analysis, y=0 + 1x;R=0.986, Bland-Altman Difference Plot providing a mean difference of 0.3 mmol/mol. Conclusions Over half of participants found the MiniCollect device easy to use. The majority were in favour of the remote capillary blood collection service and would use it if routinely available. The remote self-collection of capillary blood for HbA1c is a convenient alternative for people with diabetes living and working in rural or urban settings ensuring optimal continuance of care.
ABSTRACT
The Internet of Things revolution is transforming current healthcare practices by combining technological, economic, and social aspects. Since December 2019, the global spread of COVID19 has influenced the global economy. The COVID19 epidemic has forced governments all around the world to implement lockdowns to prevent viral infections. Wearing a face mask in a public location, according to survey results, greatly minimizes the risk of infection. The suggested robotics design includes an IoT solution for facemask detection, body temperature detection, an automatic dispenser for hand sanitizing, and a social distance monitoring system that can be used in any public space as a single IoT solution. Our goal was to use IoT-enabled technology to help prevent the spread of COVID19, with encouraging results and a future Smart Robot that Aids in COVID19 Prevention. Arduino NANO, MCU unit, ultrasonic sensor, IR sensor, temperature sensor, and buzzer are all part of our suggested implementation system. Our system's processing components, the Arduino UNO and MCU modules are all employed to process and output data. Countries with large populations, such as India and Bangladesh, as well as any other developing country, will benefit from using our cost-effective, trustworthy, and portable smart robots to effectively reduce COVID-19 viral transmission. © 2022 IEEE.
ABSTRACT
Introduction and aim. We aimed to investigate whether systemic immune inflammatory index (SII) and prognostic nutritional index (PNI) were associated with short-term mortality in geriatric patients with SARS-CoV-2. Material and methods. Our study was designed retrospectively. The data of patients that presented to a single center. The primary outcome of the study was the diagnostic value of SII and PNI in predicting 28-day mortality in geriatric patients with SARS-CoV-2 pneumonia. Results. 272 geriatric patients with SARS-CoV-2 included. The median PNI was 42.5, and the median SII was 687.6 (430–1404.2). In univariant analysis, PNI and SII has a significant relationship with mortality (p<0.001 and p=0.008, Mann-Whitney U test). PNI had an area under the curve (AUC) value of 0.680, which was significantly higher than that of SII (AUC: 0.6). The odds ratio of PNI (>40.1) and SII (<1.267) for 30-day mortality were determined as 1.12, and 1. Conclusion. In conclusion, the blood tests used to calculate PNI and SII are routinely included in complete blood count and biochemistry tests that can be performed in every hospital. According to the results of the current study, the mortality group had significantly higher SII values and significantly lower. © 2022 Publishing Office of the University of Rzeszow. All Rights Reserved.
ABSTRACT
Background: Telemedicine system enables doctors and patients to communicate while staying afar which can be helpful for areas with lesser health facilities and at times of natural or health disasters. In developing countries like Bangladesh, telemedicine service offers the potential for wider health access and equity if effectively implemented. Therefore, the response and acceptance of care receivers who are the main beneficiaries of the service should be explored. As Dhaka University Telemedicine Programme (DUTP) is a non-profit University project-induced successful telemedicine service in Bangladesh, our study was conducted on the DUTP hotline-based telemedicine programme aimed to explore patients' prior knowledge and response (experience, satisfaction and acceptance) about the service. Method(s): The cross-sectional study was conducted by interviewing 200 participants over the phone with a structured questionnaire to analyze their knowledge and response. Participants were selected by randomization from the patient pool of hotline-based DUTP telemedicine service. The data was analyzed using SPSSv20. Results and discussion: Among the participants, 41% of total participants knew about telemedicine services before COVID-19. Average patient satisfaction was well above moderate level (p-value< 0.01;mean 3.88). 16.5% respondents mentioned about having any problem while availing the service where 'treatment or service related problem' was the most common. Significant association was found between people's 'occupation' and 'knowledge before COVID-19' (p = 0.002) indicating to the probable role of profession or occupation in molding people's health-service related knowledge. Patient-doctor communication ['perception about doctor's adequate evaluation (Q3)' and 'understanding doctor's advice properly (Q4)'] was found to be significantly associated with 'age' and 'location (division)' while most respondents (around 90%) perceived the communication as effective. 'Age' had also an association with 'treatment or service related problem'. 80.5% were willing to take the service in the future even by paying fees. All participants appreciated telemedicine service in general when they were asked about its possible inclusion in mainstream primary healthcare. Conclusion(s): The overall response of patients toward DUTP hotline-based telemedicine, in general, came out to be positive. Concerned authorities and policymakers may exploit this accepting attitude of people toward developing effective telemedicine services in order to ensure wider health and well-being of population.Copyright © 2023 The Authors
ABSTRACT
This paper aims at investigating the issues and challenges experienced by remote learning among students of higher education in the Swedish context, during COVID-19. The pandemic influenced the emergence of a new learning context, and the effectiveness of the computer-mediated remote learning from the sudden transition of traditional approaches caused many interesting issues. The empirical part of the study was based on a web-based survey conducted in the middle of 2020, during the pandemic, among 1,767 anonymous students who studied at 30 higher educational institutions in Sweden. The results are presented in line with Zimmerman's (2000) triadic (personal, environmental and behavioral) forms of self-regulation. The survey indicated that the perceived worries students experienced were oriented towards the students' own personal situations and future possibilities, rather than the general state and welfare of global society. The fast transition to online classes and seminars led to many students being worried about their abilities to maintain efficiency in their studies. The findings of this study could provide refined insights on the issues that should be in mind when formulating strategies for effective remote learning in such a changing environment during a crisis period, not only in Sweden but also in some international contexts. © 2023 Author(s). This is an open access article distributed under the terms of the Creative Commons CC-BY 4.0
ABSTRACT
Counterfeit and falsified medicines have become a threat to public health around the world. The objective of this review study is to analyze all the relevant studies on preventing or reducing falsified and counterfeit medicines through digital intervention following a Systematic Literature Review (SLR) approach. A total of 51 articles were reviewed from an initial set of 1253 articles following an inclusion-exclusion criterion. As an outcome, this review study found that falsified and counterfeit medicines have become a crucial issue for research and investigation over time. Various advanced technologies (like Blockchain, IoT, RFID, image processing, pattern recognition, etc.) are being used to fight against this issue efficiently. The review also reveals future research opportunities to facilitate the existing initiatives for preventing medicine counterfeit that includes: exploring the implications of emerging technologies;discovering the contaminated point over the medicine supply chain;investigating the less emphasized concern of counterfeit and falsified medicines;exploring all possible use-cases or features of any digital solution to reduce falsified and counterfeit medicines;and the development of counterfeit/ falsified incidents reporting system. Thus, the implication of this study is to discover the research gaps and provide future research directions focusing on the prevention of usage of falsified and counterfeit medicines through the effective use of Information and Communication Technology (ICT). (c) 2022 The Authors. Published by Elsevier B.V. on behalf of King Saud University. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).
ABSTRACT
The coronavirus disease (COVID-19) adversely impacted the fisheries sector of Bangladesh, particularly affecting the outcomes for women workers of the fish and shellfish processing plants (FSPPs). This study aimed to assess the impacts of COVID-19 on the women workers of the FSPPs by collecting data through 151 questionnaire surveys and two focus group discussions (FGDs) from September to December 2021. During COVID-19, 32.1 % of respondents' food consumption decreased slightly, and 16.6 % reduced drastically. Children of 18.2 % of the respondents had no access, and 16.9 % had insufficient access to online class facilities. Increased livelihood costs and decreased household income posed adverse economic impacts on women. Formal paid hours and overtime job opportunities were reduced because foreign buyers cancelled orders during the pandemic. Gender-based violence and social insecurity increased. Respondents (13.2 %) reported increased mistreatment by their husbands during the pandemic. Women workers' mental health deteriorated as their anxiety and insecurity about life increased during the pandemic. This study recommends overcoming the adverse effect of COVID-19 or COVID-like pandemics in the future. To ensure proper food consumption and reduce adverse economic impacts, the government should offer a special relief package, financial incentives and flexible low-interest loans. Related authorities should ensure that every child has the opportunity and access to participate in online classes during COVID-19 or COVID, like pandemics in the future. © Asian Fisheries Society.