AI in Higher Education: Insights from Student Surveys and Predictive Analytics using PSO-Guided WOA and Linear Regression | ||||
| Journal of Artificial Intelligence in Engineering Practice | ||||
| Volume 1, Issue 1, April 2024, Page 1-17 PDF (1.95 MB) | ||||
| Document Type: Original Article | ||||
| DOI: 10.21608/jaiep.2024.354003 | ||||
 View on SCiNiTO | ||||
| Authors | ||||
S.K. Towfek  1; Nima Khodadadi2; Laith Abualigah3, 4, 5, 6, 7, 8; Faris H. Rizk1
| ||||
| 1Computer Science and Intelligent Systems Research Center, Blacksburg 24060, Virginia, USA | ||||
| 2Department of Civil and Architectural Engineering, University of Miami, Coral Gables, FL, USA | ||||
| 3Hourani Center for Applied Scientific Research, Al-Ahliyya Amman University, Amman 19328, Jordan | ||||
| 4Computer Science Department, Al al-Bayt University, Mafraq 25113, Jordan | ||||
| 5Artificial Intelligence and Sensing Technologies (AIST) Research Center, University of Tabuk, Tabuk 71491, Saudi Arabia | ||||
| 6MEU Research Unit, Middle East University, Amman 11831, Jordan | ||||
| 7School of Engineering and Technology, Sunway University Malaysia, Petaling Jaya 27500, Malaysia | ||||
| 8Applied science research center, Applied science private university, Amman 11931, Jordan | ||||
| Abstract | ||||
| Artificial intelligence (AI) and machine learning (ML) prediction can change education in a drastic way, where there can be both improvements and regressions concerning the way learning is approached. With individualized learning experiences, being able to spot the students who are falling behind, and customizing the course materials and tests that are fully customized, educators will help students achieve their individualized needs. We at Grand Canyon University conducted our study among 250 students in order to find out how they are interacting with AI in their academic journey. Using the binary Particle Swarm Optimization - Whale Optimization Algorithm for feature selection and the predictive modeling Linear Regression, we came up with vivid findings. For example, the bPSO-Guided WOA algorithm was characterized by a typical Average error of 0.25934, signifying the feat it was in feature selection, and the Linear Regression model particularly stood out in its sustainably low mean squared error (MSE), with a really admirable result of 1.39069E-31. Such evidence indicates the remarkable ability of AI and ML methods to develop true and relevant forecasts by providing teachers with possible and efficient decisions, thus improving the standards and effectiveness of education. | ||||
| Keywords | ||||
| Artificial Intelligence; Higher Education; Student Surveys; Predictive Analytics; PSO-Guided WOA; Linear Regression | ||||
|
Statistics Article View: 179 PDF Download: 113 |
||||
