Personalized learning
We evaluate the performance of our proposed protocol using three benchmark datasets. Each dataset is composed of 25 percent of the local data forming the test dataset and 75 percent of the local data forming the training dataset.
MNIST: The dataset is made up of gray pictures that are digits which are written by hand containing ten different classes which provides 60000 training samples in total.
- Categories:
111 Views
The dataset used in this study was derived from data collected from two courses offered on the University of Jordan's E-learning Portal during the second semester of 2020, namely "Computer Skills for Humanities Students" (CSHS) and "Computer Skills for Medical Students" (CSMS). Over the sixteen-week duration of each course, students participated in various activities such as reading materials, video lectures, assignments, and quizzes. To preserve student privacy, the log activity of each student was anonymized.
- Categories:
1901 Views