An Ensemble Learning Model for COVID-19 Detection from Blood Test Samples.

Current research endeavors in the application of artificial intelligence (AI) methods in the diagnosis of the COVID-19 disease has proven indispensable with very promising results. Despite these promising results, there are still limitations in real-time detection of COVID-19 using reverse transcription polymerase chain reaction (RT-PCR) test data, such as limited datasets, imbalance classes, a high misclassification rate of models, and the need for specialized research in identifying the best features and thus improving prediction rates. This study aims to investigate and apply the ensemble learning approach to develop prediction models for effective detection of COVID-19 using routine laboratory blood test results. Hence, an ensemble machine learning-based COVID-19 detection system is presented, aiming to aid clinicians to diagnose this virus effectively. The experiment was conducted using custom convolutional neural network (CNN) models as a first-stage classifier and 15 supervised machine learning algorithms as a second-stage classifier: K-Nearest Neighbors, Support Vector Machine (Linear and RBF), Naive Bayes, Decision Tree, Random Forest, MultiLayer Perceptron, AdaBoost, ExtraTrees, Logistic Regression, Linear and Quadratic Discriminant Analysis (LDA/QDA), Passive, Ridge, and Stochastic Gradient Descent Classifier. Our findings show that an ensemble learning model based on DNN and ExtraTrees achieved a mean accuracy of 99.28% and area under curve (AUC) of 99.4%, while AdaBoost gave a mean accuracy of 99.28% and AUC of 98.8% on the San Raffaele Hospital dataset, respectively. The comparison of the proposed COVID-19 detection approach with other state-of-the-art approaches using the same dataset shows that the proposed method outperforms several other COVID-19 diagnostics methods.

Gender differences in information and communication technology use & skills: a systematic review and meta-analysis.

Even though information and communication technology (ICT) is essential for everyday life and has gained considerable attention in education and other sectors, it also carries individual differences in its use and relevant skills. This systematic review aims to examine the gender differences in ICT use and skills for learning through technology. A comprehensive search of eight journal databases and a specific selection criterion was carried out to exclude articles that match our stated exclusion criteria. We included 42 peer-reviewed empirical publications and conference proceedings published between 2006 and 2020. For a subsample of studies, we performed a small-scale meta-analysis to quantify possible gender differences in ICT use and skills. A random-effects model uncovered a small and positive, yet not significant, effect size in favor of boys (g = 0.17, 95% CI [-0.01, 0.36]). However, this finding needs to be further backed by large-scale meta-analyses, including more study samples and a broader set of ICT use and skills measures. We highlight several concerns that should be addressed and more thoroughly in collaboration with one another to better IT skills and inspire new policies to increase the quality of ICT use. The findings from this review further suggest implications and present existing research challenges and point to future research directions.

Adaption of distance learning to continue the academic year amid COVID-19 lockdown.

This work investigates the use of distance learning in saving students' academic year amid COVID-19 lockdown. It assesses the adoption of distance learning using various online application tools that have gained widespread attention during the coronavirus infectious disease 2019 (COVID-19) pandemic. Distance learning thrives as a legitimate alternative to classroom instructions, as major cities around the globe are locked down amid the COVID-19 pandemic. To save the academic year, educational institutions have reacted to the situation impulsively and adopted distance learning platforms using online resources. This study surveyed random undergraduate students to identify the impact of trust in formal and informal information sources, awareness and the readiness to adopt distance learning. In this study, we have hypothesized that adopting distance learning is an outcome of situational awareness and readiness, which is achieved by the trust in the information sources related to distance learning. The findings indicate that trust in information sources such as institute and media information or interpersonal communication related to distance learning programs is correlated with awareness (ß = 0.423, t = 12.296, p = 0.000) and contribute to readiness (ß = 0.593, t = 28.762, p = 0.001). The structural model path coefficient indicates that readiness strongly influences the adoption of distance learning (ß = 0.660, t = 12.798, p = 0.000) amid the COVID-19 pandemic. Our proposed model recorded a predictive relevance (Q2) of 0.377 for awareness, 0.559 for readiness, and 0.309 for the adoption of distance learning, which explains how well the model and its parameter estimates reconstruct the values. This study concludes with implications for further research in this area.