Student performance prediction in e-learning system and evaluating effectiveness of online courses

In recent years, the number of online courses in India has skyrocketed especially due to the Covid pandemic. The most significant increments have happened in degree colleges, where 85% concur that internet based courses are important for their drawn-out procedure when contrasted with 60% in 2015. The distribution of online courses has evolved dramatically as technology has advanced. Web-based platform provides new challenges for both teachers and students. Teachers should be clear about the effectiveness of online learning in teaching students. For that, the possibilities of online learning should be compared with traditional learning. Students are evaluated based on their focus on online learning. This study aims to determine the efficacy of online courses by predicting student performance in an e-learning system. These research findings evaluate modern learning methods, highlight students' potential and help teachers understand how to assess and lead students on online platforms. © 2023 IEEE.

Web architecture for URL-based phishing detection based on Random Forest, Classification Trees, and Support Vector Machine

Nowadays phishing is as serious a problem as any other, but it has intensified a lot in the current coronavirus pandemic, a time when more than ever we all use the Internet even to make payments daily. In this context, tools have been developed to detect phishing, there are quite complex tools in a computational calculation, and they are not so easy to use for any user. Therefore, in this work, we propose a web architecture based on 3 machine learning models to predict whether a web address has phishing or not based mainly on Random Forest, Classification Trees, and Support Vector Machine. Therefore, 3 different models are developed with each of the indicated techniques and 2 models based on the models, which are applied to web addresses previously processed by a feature retrieval module. All this is deployed in an API that is consumed by a Frontend so that any user can use it and choose which type of model he/she wants to predict with. The results reveal that the best performing model when predicting both results is the Classification Trees model obtaining precision and accuracy of 80%. © IBERAMIA and the authors.

Impact of COVID-19 on electricity demand of Latin America and the Caribbean countries

Governments worldwide have adopted different public health measures in order to slow down the spread of COVID-19. As a result, the electricity demand has been impacted by the changes in human activity. Many of the Latin America and the Caribbean (LAC) countries have adopted different approaches to control the COVID-19 pandemic, including severe shutdown of most social and economic activities. This paper analyzes how this pandemic has influenced, from its appearance until the fall of 2020, the demand of ten LAC countries (Peru, Bolivia, Costa Rica, Brazil, Guatemala, Mexico, Dominican Republic, Argentina, Chile and Uruguay). The approach is based on the concepts of size and shape impacts, which have been proposed in order to decompose the problem for a better understanding of the impact. The size impact accounts for the observed variations on the daily demand, whereas the shape impact focuses on the variations observed on the standardized hourly demand profiles for each day. To calculate both impacts, the observed demand is compared to the expected one if the COVID-19 crisis had not happened. To obtain reliable estimations in the scenario without COVID19, machine learning techniques have been used. Peru and Bolivia are the two countries where the pandemic has had the greatest impact during 2020, with a size impact in April 2020 of around -30%. At the opposite extreme would be Chile and Uruguay, with a maximum monthly size impact of -6%. The other considered countries have maximum monthly impacts in the range of -11% to -17%. (c) 2022 Elsevier Ltd. All rights reserved.

INTENTION of PARTICIPATING in E-LEARNING UNIVERSITY PROGRAMS for SENIOR CITIZENS. PROFILE IDENTIFICATION USING SEGMENTATION ANALYSIS

The University Programmes for Older Adults (PUM) provide organised spaces for training, interaction and social relations. The international emergency situation caused by the COVID19 pandemic has meant the almost total closure of this type of programme, limiting contact and personal relations in face-to-face conditions. This situation, together with a powerful and increasingly accessible technological scenario, leads to the assessment of new areas of online training and learning, also for older people. This study aims to explore the intention to participate in a university programme for older people in an online format. This intention can be predicted on the basis of certain socio-demographic and contextual factors or variables. A total of 1633 older adults with an average age of 68.2 years participated in the study, all of them attending 17 PUM sites in the Community of Castilla y León. The non-parametric technique of classification trees was used to process the data. Three criterion variables were considered (<<Intention to participate in e-PUM>>;<<Attitude towards TD>>;and <<Frequency of technological use>>) around which profiles of subjects are configured according to a series of individual sociodemographic, psychographic and behavioural characteristics, all of them considered as predictor variables. The results offer keys to understanding why the elderly accept (or do not accept) this form of participation, identifying profiles or traits that characterise each of the profiles or subgroups of subjects with a greater or lesser predisposition to this type of socio-educational participation, which can serve as a basis for making social and/or educational policy decisions. © 2015 SIPS. Licencia Creative Commons Attribution-Non Commercial (by-nc) Spain 3.0

Predicting COVID-19 mortality risk in Toronto, Canada: a comparison of tree-based and regression-based machine learning methods.

BACKGROUND: Coronavirus disease (COVID-19) presents an unprecedented threat to global health worldwide. Accurately predicting the mortality risk among the infected individuals is crucial for prioritizing medical care and mitigating the healthcare system's burden. The present study aimed to assess the predictive accuracy of machine learning methods to predict the COVID-19 mortality risk. METHODS: We compared the performance of classification tree, random forest (RF), extreme gradient boosting (XGBoost), logistic regression, generalized additive model (GAM) and linear discriminant analysis (LDA) to predict the mortality risk among 49,216 COVID-19 positive cases in Toronto, Canada, reported from March 1 to December 10, 2020. We used repeated split-sample validation and k-steps-ahead forecasting validation. Predictive models were estimated using training samples, and predictive accuracy of the methods for the testing samples was assessed using the area under the receiver operating characteristic curve, Brier's score, calibration intercept and calibration slope. RESULTS: We found XGBoost is highly discriminative, with an AUC of 0.9669 and has superior performance over conventional tree-based methods, i.e., classification tree or RF methods for predicting COVID-19 mortality risk. Regression-based methods (logistic, GAM and LASSO) had comparable performance to the XGBoost with slightly lower AUCs and higher Brier's scores. CONCLUSIONS: XGBoost offers superior performance over conventional tree-based methods and minor improvement over regression-based methods for predicting COVID-19 mortality risk in the study population.

Proposed clinical indicators for efficient screening and testing for COVID-19 infection using Classification and Regression Trees (CART) analysis.

The introduction and rapid transmission of SARS-CoV-2 in the United States resulted in methods to assess, mitigate, and contain the resulting COVID-19 disease derived from limited knowledge. Screening for testing has been based on symptoms typically observed in inpatients, yet outpatient symptoms may differ. Classification and regression trees recursive partitioning created a decision tree classifying participants into laboratory-confirmed cases and non-cases. Demographic and symptom data from patients ages 18-87 years enrolled from March 29-June 8, 2020 were included. Presence or absence of SARS-CoV-2 was the target variable. Of 832 tested, 77 (9.3%) tested positive. Cases significantly more often reported diarrhea (12 percentage points (PP)), fever (15 PP), nausea/vomiting (9 PP), loss of taste/smell (52 PP), and contact with a COVID-19 case (54 PP), but less frequently reported sore throat (-27 PP). The 4-terminal node optimal tree had sensitivity of 69%, specificity of 78%, positive predictive value of 20%, negative predictive value of 97%, and AUC of 76%. Among those referred for testing, negative responses to two questions could classify about half (49%) of tested persons with low risk for SARS-CoV-2 and would save limited testing resources. Outpatient symptoms of COVID-19 appear to be broader than the inpatient syndrome.Initial supplies of anticipated COVID-19 vaccines may be limited and administration of first such available vaccines may need to be prioritized for essential workers, the most vulnerable, or those likely to have a robust response to vaccine. Another priority group could be those not previously infected. Those who screen out of testing may be less likely to have been infected by SARS-CoV-2 virus thus may be prioritized for vaccination when supplies are limited.