ABSTRACT
Olympic game is a prestigious ceremony that occurs after every four years. However, due to the spread of coronavirus in 2020, the game was held in 2021, which is post-Covid. The main aim of this research is to find out if there was a difference in the performance of nations in Rio 2016 Olympics (pre-Covid) and Tokyo 2020 Olympics (post-Covid). Statistical analysis is carried out to find the correlation between the different variables. One of the highly correlated variables (Gold Tally) is removed while performing the classification analysis. The idea is to see if the classifiers are able to do the comparative analysis without it or not. The classification algorithms utilized in this research are Decision Table, Decision Tree, Naïve Bayes, and Random Forest. The datasets used in this research are imbalanced sets, which were later transformed to balance sets through under-sampling. Random Forest was able to give 100% accuracy in both datasets whereas the True Positive Rate (TPR) was also 100%. After doing the comparative analysis it was found that irrespective of pre and post-Covid, the performance of athletes did not change. This paves the way for other researchers to investigate if Covid had any impact on the performance of the athletes or not. In the future, more vast variables will be investigated to do a more detailed comparative analysis. © 2022 IEEE.
ABSTRACT
COVID-19 has caused major changes in every aspect of human endeavor, including efforts in the higher education sector. A sudden shift from face-to-face and blended settings to a completely online delivery mode has introduced changes to conventional teaching methods, and made learning rely heavily on technology and the Internet. Hence, students' online engagement with these tools has become even more important for their academic success. Therefore, there is a need to investigate the effects of various indicators of students' online presence on their academic performance. This paper explores the effectiveness of online presence in Higher Education Institutes, where COVID-19 has shifted the deliveries to online mode. The chosen indicator is frequency that will be adequately used to quantify the effectiveness of online presence on student performance in online mathematics courses. Statistical methods are used to measure the correlation and association between students' online presence indicators and their performance. As such, it would allow to build models to predict future outcomes or occurrences and student performances, with a major focus on mathematics and statistics courses. The results show that there is an increase in student online interaction in courses during COVID-19 era;however, it is consistent with the Online Measureable Presence Model (OMPM) model where frequency was the dominant indicator of student performance.
ABSTRACT
The Higher Education Institute (HEI) are experiencing a major paradigm shift due to recent global pandemic. A sudden shift from face-to-face (F2F) and blended modes of study to completely online mode of delivery has introduced hidden challenges to facilitators and students alike. Student's online engagement has become even more important for their academic success as F2F component is not there in most cases. Therefore, there is a need to investigate the effects of the various indicators of students' online presence towards their academic performance. This paper explores the effectiveness of online presence in HEI where Covid-19 has shifted the course deliveries to fully online mode. Previously, Online Measurable Presence Model (OMPM) was used to find students effectiveness in a blended learning environment where two indicators used were Frequency and Duration. The chosen indicator in this research is frequency, which will be adequately used to quantify the effectiveness of the online presence in two mathematics courses in the Pacific. Clustering technique is used to create clusters of Frequency and see their relation to OMPM model. Prediction is made using neural network to see the accuracy based on model. The clusters would allow to build predictive models to predict future outcomes or occurrences and student performances, with a major focus on mathematics courses. © 2020 IEEE.