Impact Prediction of Online Education During COVID-19 Using Machine Learning: A Case Study

The transition from traditional to online education is challenging and has many obstacles in various situations. Due to the Covid-19 situation, we use digital blended education from the traditional system. However, in some cases, it can harm our student's academic performance. In this research, we aim to identify the factors that impact the student's academic performance in online education. On the other hand, this study also finds the student Cumulative Grade Point Average (CGPA) fluctuation using machine learning classifiers. To achieve this, we survey to gather data perspective of Bangladesh private university, and this data allows us to analyze and classify using machine learning techniques such as Logistic Regression (LR), K-Nearest Neighbor (KNN), Support Vector Machine (SVM), Gaussian Naive Bayes (GNB), Decision Tree (DT), and Random Forest (RF). This study finds Random Forest (RF) outperforms the other state-of-art classifiers. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Forecasting domestic waste generation during successive COVID-19 lockdowns by Bidirectional LSTM super learner neural network

Accurate prediction of domestic waste generation is a challenging task for municipalities to implement sustainable waste management strategies. In the present study, domestic waste generation in the Kingdom of Bahrain, representing a Small Island Developing State (SIDS) case study, has been investigated during successive COVID-19 lockdowns due to the pandemic in 2020. Temporal trends of daily domestic waste generation between 2019 and 2020 and their statistical analyses exhibited remarkable variations highlighting the impact of consecutive COVID-19 lockdowns on domestic waste generation. Machine learning has great potential for predicting solid waste generation rates, but only a few studies utilized deep learning approaches. The state-of-the-art Bidirectional Long Short-Term Memory (BiLSTM) network model as a deep learning method is applied to forecast daily domestic waste data in 2020. Bayesian optimization algorithm (BOA) was hybridized with BiLSTM to generate a super learner approach. The performance of the BOA-BiLSTM super learner model was further compared with the statistical ARIMA model. Performance indicators of the developed models using ARIMA and BiLSTM showed that the latter yielded superior performance for short-term forecasts of domestic waste generation. The MAE, RMSE, MAPE, and R2 were 47.38, 60.73, 256.43, and 0.46, respectively, for the ARIMA model, compared to 3.67, 12.57, 0.24, and 0.96, respectively, for the BiLSTM model. Additionally, the relative errors for the BiLSTM model were lower than those of the ARIMA model. This study highlights that the BiLSTM can be a reliable forecasting tool for solid waste management policymakers during public health emergencies. © 2022 Elsevier B.V.

Forecasting domestic waste generation during successive COVID - 19 lockdowns by Bidirectional LSTM super learner neural network

Accurate prediction of domestic waste generation is a challenging task for municipalities to implement sustainable waste management strategies. In the present study, domestic waste generation in the Kingdom of Bahrain, representing a Small Island Developing State (SIDS) case study, has been investigated during successive COVID-19 lockdowns due to the pandemic in 2020. Temporal trends of daily domestic waste generation between 2019 and 2020 and their statistical analyses exhibited remarkable variations highlighting the impact of consecutive COVID-19 lockdowns on domestic waste generation. Machine learning has great potential for predicting solid waste generation rates, but only a few studies utilized deep learning approaches. The state-of-the-art Bidirectional Long Short-Term Memory (BiLSTM) network model as a deep learning method is applied to forecast daily domestic waste data in 2020. Bayesian optimization algorithm (BOA) was hybridized with BiLSTM to generate a super learner approach. The performance of the BOA-BiLSTM super learner model was further compared with the statistical ARIMA model. Performance indicators of the developed models using ARIMA and BiLSTM showed that the latter yielded superior performance for short-term forecasts of domestic waste generation. The MAE, RMSE, MAPE, and R2 were 47.38, 60.73, 256.43, and 0.46, respectively, for the ARIMA model, compared to 3.67, 12.57, 0.24, and 0.96, respectively, for the BiLSTM model. Additionally, the relative errors for the BiLSTM model were lower than those of the ARIMA model. This study highlights that the BiLSTM can be a reliable forecasting tool for solid waste management policymakers during public health emergencies.

Evaluation of dedicated COVID-19 hospitals in the pandemic response in Iraq: pandemic preparation within a recovering healthcare infrastructure.

The purpose of this study is to evaluate Iraq's health facility preparedness for the surge of hospitalised cases associated with the ongoing COVID-19 pandemic. In this article, we review pandemic preparedness at both general and tertiary hospitals throughout all districts of Iraq. COVID-19 pandemic preparedness, for the purpose of this review, is defined as: (1) staff to patient ratio, (2) personal protective equipment (PPE) to staff ratio, (3) infection control measures training and compliance and (4) laboratory and surveillance capacity. Despite the designation of facilities as COVID-19 referral hospitals, we did not find any increased preparedness with regard to staffing and PPE allocation. COVID-19 designated hospital reported an increased mean number of respiratory therapists as well as sufficient intensive care unit staff, but this did not reach significant levels. Non-COVID-19 facilities tended to have higher mean numbers of registered nurses, cleaning staff and laboratory staff, whereas the COVID-19 facilities were allocated additional N-95 masks (554.54 vs 147.76), gowns (226.72 vs 104.14) and boot coverings (170.48 vs 86.8) per 10 staff, but none of these differences were statistically significant. Though COVID-19 facilities were able to make increased requisitions for PPE supplies, all facility types reported unfulfilled requisitions, which is more likely a reflection of global storage rather than Iraq's preparedness for the pandemic. Incorporating future pandemic preparedness into health system strengthening efforts across facilities, including supplies, staffing and training acquisition, retention and training, are critical to Iraq's future success in mitigating the ongoing impact of the ongoing COVID-19 pandemic.

Detecting Public Outlook Towards Vaccination Using Machine Learning Approaches: A Systematic Review

Vaccination is an effective measure to prevent the spread of harmful diseases. The prevalence towards vaccine hesitancy, however, has been growing throughout the years and expressed openly in various social media platforms. Research works on automating the detection of public’s opinion towards vaccination in social media has recently gained significant popularity with the rise of the COVID-19 pandemic. This paper presents a systematic review on the machine learning approaches used by researchers to detect the inclination of the public towards vaccination. We analyzed the research work conducted within the past five years and summarized their findings. Our systematic review reveals that Support Vector Machine is the most widely used machine learning technique in identifying public sentiment towards vaccination producing the best performance with an F1-score of 97.3, while Twitter is found to be the most popular platform for extracting source of data. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Knowledge on covid-19 among nursing students of a selected nursing institute of dhaka city, bangladesh

Background: Bangladesh is trying to shape out coronavirus disease of 2019 (COVID-19) pandemic with limited frontiers resources science March 2020. Among all frontier, Bangladeshi nurses are also playing a dynamic role to control infection through direct contact with COVID patients. Objective: This research aims to identify the level and predictors of poor knowledge of nursing students toward the COVID-19. Method: This study was a quantitative type of cross-sectional study with 150 participants randomly selected from 226 students of the Armed Forces Medical Institute located in Dhaka Cantonment of Dhaka city of Bangladesh. Data were collected by using a pre-tested questionnaire through a telephonic interview by trained and experienced interviewers. Analysis was done by using univariate, multivariate techniques followed by regression modeling. Result: Overall level of knowledge was observed poor (67.3%) among more than half of BSc nursing students. A greater part of nursing students got poor knowledge on the preventive measures to reduce transmission of COVID 19 (98.7%;40.20±12.39) & management of COVID 19 (94.7%;40.20±12.39). In terms of predicting the causes of poor knowledge, this study found that BSc nursing students of the second year (AOR= 2.53, p < 0.01) are more likely to have poor knowledge on COVID-19 compared to another educational group. Conclusion: Nurses are the frontiers to mitigate COVID-19 and manage the affected people effectively. Therefore, knowledge of them needs to be perfect to ensure the proper practice to prevent COVID-19. Thus, an enthusiastic and demonstrative learning system is required to make them knowledgeable enough against COVID-19.

SARCOIDOSIS WITH SUPERIMPOSED SARS-COV-2 LEADING TO HIGHER PREVALENCE OF CAPA?

TOPIC: Chest Infections TYPE: Fellow Case Reports INTRODUCTION: The recent SARS-CoV-2 pandemic has immensely affected individuals worldwide leading to a serious global emergency. It has the capability to end in post-infection complications and critical outcomes due to significant pro-inflammatory conditions. The role of SARS-CoV-2 in patients with immune disorders, such as sarcoidosis, and the specific interaction between these two diseases remains unclear. Here we present a case of a 65-year-old female with sarcoidosis who got infected with SARS-CoV-2 complicated by pulmonary embolism (PE) and COVID associated pulmonary aspergillosis (CAPA) CASE PRESENTATION: A 60-year-old African American female with a PMH of Sarcoidosis, Chronic thromboembolic pulmonary hypertension (CTEPH) on Riociguat, Macitentan, and Warfarin presented with cough, SOB, and fever for 1-week duration. Upon arrival to the ED, vital signs were significant for tachypnea and hypoxemia. COVID-19 PCR was positive. Initial chest CT revealed bilateral ground-glass opacities (GGOs) with multilobar chronic airspace disease. She was treated with Remdesivir and dexamethasone. During the hospital course, warfarin was held due to supratherapeutic INR. However, before discharge her respiratory parameters decompensated and she required HFNC to maintain her saturation. CT pulmonary angiogram revealed PE in the right distal segmental branch with significant bilateral patchy infiltrates more severe in the distribution of lower lobe suggestive of multilobar pneumonia with bilateral GGOs with crazy paving. Beta galactomannan came back positive and Voriconazole was started empirically with significant improvement in respiratory symptoms. Later fungal culture from sputum confirmed aspergillosis. DISCUSSION: SARS-CoV-2 activates the immune system which results in a release of inflammatory cytokines and leads to cytokine storms. But it remains unknown how the interaction differs in patients with an altered immune system, especially in cases of impairment of the T-cell immunity and granuloma formation, such as sarcoidosis. Some authors suggested that constitutional defects of the regulation of macroautophagy in sarcoidosis could lead to a more severe outcome from the novel SARS-CoV-2 infection. literature review showed that alveolar damage, dysfunctional mucociliary clearance, and altered immune system further facilitates fungal invasion. We, therefore, hypothesize that SARS-CoV-2 in a patient with underlying sarcoidosis may lead to increased risk for pulmonary aspergillosis. CONCLUSIONS: The role of infection from the novel coronavirus in patients having sarcoidosis is still largely unknown however clinicians should be aware that it has the risk of serious complications and clinical deterioration including further destruction of lung architecture, hypervascular response, hypercoagulability, and superinfection like CAPA. REFERENCE #1: https://www.lung.org/lung-health-diseases/lung-disease-lookup/sarcoidosis/learn-about-sarcoidosis REFERENCE #2: https://www.hopkinsmedicine.org/health/conditions-and-diseases/pulmonary-sarcoidosis REFERENCE #3: https://www.nature.com/articles/s41379-020-00661-1#citeas DISCLOSURES: No relevant relationships by Danilo Enriquez, source=Web Response No relevant relationships by SM Hossain, source=Web Response No relevant relationships by Tahmina Jahir, source=Web Response No relevant relationships by Ruby Risal, source=Web Response No relevant relationships by Marie Frances Schmidt, source=Web Response No relevant relationships by Binav Shrestha, source=Web Response No relevant relationships by Sabbena Uppal, source=Web Response

Evaluation of sleep quality, psychological states and subsequent self-medication practice among the Bangladeshi population during Covid-19 pandemic.

INTRODUCTION: Due to the extended lockdown imposed for SARS-CoV-2 pandemic, many people have experienced problematic sleep patterns and associated health issues worldwide. This study was conducted to assess the sleep quality and psychological states of the Bangladeshi population during the COVID-19 pandemic, respondent's behavioral traits as well as psychological or sleep-related problems induced self-medication practice among the respondents, along with the probability of development of drug dependency. METHODS: The survey was conducted among 2941 respondents from 25th November 2020 to 4th December 2020 where the responses were analyzed by SPSS V22. RESULTS: 10-29.5% experienced a significant degree of sleep problems whereas some experienced severe anxiety and depression. The associations between the behavioral traits and parameters concerning sleep quality, anxiety and depression showed 5% level of significance in all cases. Self-medication practice of sleep aids during this pandemic was reported by 7.14% of the respondents, with a greater percentage belonging to the female or senior age group. Tendency to repeatedly self-medication was observed in 18.86% of this self-medicating populace, and a greater number of male (10.26%) respondents displayed such tendency as opposed to their female (8.6%) equivalents. However, 48.10% of the respondents reported perceptions of improved physical and/or psychological health following self-medication, and this trait was predominant in men (52.14%). CONCLUSION: Results showed a significant number of Bangladeshi populaces were suffering from psychological issues during this COVID-19 which also influenced a certain number of people towards self-medication practice where signs of drug dependency were observed in a significant number of respondents.

Hygiene behavior among female garment workers: A pre-covid-19 cross-sectional study in bangladesh

This cross-sectional study was undertaken to delineate the hygiene behavior among the female garment workers in Bangladesh during pre-COVID-19 period. 500 female garments workers were selected for the study. Data were collected by face-to-face interview method using semi-structured questionnaire which include the information on socio-demography, different components of personal hygiene such as bathing, brushing teeth, washing feet, washing/ changing cloth, washing hair by soap/ shampoo, trimming nail and washing hand. The majority of the participants (>75%) had ideal knowledge and practiceon every considered hygiene behavior. Regarding hand-washing behavior, only 3% had appropriate knowledge and ideally practiced by 60.2%. Knowledge of the respondents was significantly associated with ideal practice of all components (p=0.01). Predictors identified according to age, BMI, education and marital status of respondents, were significantly associated with hygiene related to bathing, washing feet, clothing, hair and hand.

A Fuzzy Time Series Prediction Model of the COVID-19 Epidemic

In our study, a number of time series analysis techniques are applied to the COVID-19 epidemic data. The result of the analysis is used to develop three single variable fuzzy time series models from the dataset of day to day newly confirmed cases of the virus in certain countries. Those developed models are later applied on infected cases of the countries that are not used before in model development. This helps in appropriate model selection for prediction of cases for unseen countries. The forecasted results are then compared and analyzed in detail with different performance metric. The time series analysis process described in this article can be used to better understand the epidemic trend of a particular country and help the government plan better intervention policies. © 2021, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Assessment of knowledge, attitudes and practices towards prevention of coronavirus disease (COVID-19) among Bangladeshi population

Background: Cornonavirus disease (COVID-19) has been declared pandemic by the World Health Organization on the 11th March 2020. The knowledge, attitudes and practices of the population towards the COVID-19, play an integral role in determining community’s readiness to engage themselves in government measures including behavioural change in prevention and control of the disease. Objectives: The study was aimed to determine the knowledge levels, attitudes and practices towards the COVID-19 among the Bangladeshi population. Methods: A cross sectional study was conducted among 1549 adult population across Bangladesh including Dhaka city and rural areas during March-April 2020. Data were collected using a structured and pretested questionnaire through online, self-administered and face to face interview. The study instrument consisted of 7 items on socio-demographic characteristics, 12 items on knowledge, 4 items on attitudes and 5 items on practices related to COVID-19. Independent sample t-tests, chi-square tests, one-way analysis of variance (ANOVA) and binary logistic regression were performed to assess the attitudes and practices in relation to knowledge. Results: Of the total 1549 study population, 1249 were interviewed online, 194 were self-administered and 106 were through face to face interview. The lowest level of knowledge prevailed among the above 50 years’ age group regarding the disease, which was higher among female (p=0.03), and more among the respondents having education level below graduation (p=0.000;OR=1.6, χ2=17.6). Of the total respondents, 73.5% having negative attitude towards use of face mask, though 69.8% having the appropriate knowledge on mode of transmission of the virus (p=0.000). Though, 51.6% of the study population, having adequate knowledge, but only 52.1% using face mask (p>0.05) and 51.8% practicing hand washing (p>0.05). More than 70.0% respondents having knowledge on social distancing, but only 50.0% was practicing it. Male respondents had 1.5 times more knowledge about the social distancing than the female counterpart (p=0.000). Conclusion: Public awareness campaign should be enhanced critically focusing the target audience covering the knowledge gaps, motivation for appropriate practices and further improvement of attitudes towards prevention and control of COVID-19 in Bangladesh thus suggested. © 2020 Bangladesh Medical Research Council. All rights reserved.