No abstract

No abstract

To avoid the spread of the COVID-19 crisis, many countries worldwide have temporarily shut down their academic organizations. National and international closures affect over 91% of the education community of the world. E-learning is the only effective manner for educational institutions to coordinate the learning process during the global lockdown and quarantine period. Many educational institutions have instructed their students through remote learning technologies to face the effect of local closures and promote the continuity of the education process. This study examines the expected benefits of e-learning during the COVID-19 pandemic by providing a new model to investigate this issue using a survey collected from the students at Imam Abdulrahman Bin Faisal University. Partial Least Squares Structural Equation Modeling (PLS-SEM) was employed on 179 useable responses. This study applied Push-Pull-Mooring theory and examined how push, pull, and mooring variables impact learners to switch to virtual and remote educational laboratories. The Protection Motivation theory was employed to explain how the potential health risk and environmental threat can influence the expected benefits from e-learning services. The findings revealed that the push factor (environmental threat) is significantly related to perceived benefits. The pull factors (e-learning motivation, perceived information sharing, and social distancing) significantly impact learners' benefits. The mooring factor, namely perceived security, significantly impacts learners’ benefits.

Articles you may be interested inFinger vein identification using fuzzy-based k-nearest centroid neighbor classifier AIP Conf. Proc. 1643, 649 (2015); 10.1063/1.4907507Breast cancer classification using cluster k-nearest neighbor AIP Conf.A generalized K-nearest neighbor decision rule for isolated word recognition Abstract. In this paper, a new classification method for enhancing the performance of K-Nearest Neighbor is proposed which uses robust neighbors in training data. The robust neighbors are detected using a vahdation process. This method is more robust than traditional equivalent methods. This new classification method is called Modified K-Nearest Neighbor. Inspired the traditional KNN algorithm, the main idea is classifying the test samples according to their neighbor tags. This method is a kind of weighted KNN so that these weights are determined using a different procedure. The procedure computes the fraction of the same labeled neighbors to the total number of neighbors. The proposed method is evaluated on a variety of several standard UCI data sets. Experiments show the excellent improvement in accuracy in comparison with KNN method.

Abstract. This paper presents an approach for classifying students in order to predict their final grade based on features extracted from logged data in an education web-based system. A combination of multiple classifiers leads to a significant improvement in classification performance. Through weighting the feature vectors using a Genetic Algorithm we can optimize the prediction accuracy and get a marked improvement over raw classification. It further shows that when the number of features is few; feature weighting is works better than just feature selection.