SACM - United States of America
Permanent URI for this collectionhttps://drepo.sdl.edu.sa/handle/20.500.14154/9668
Browse
3 results
Search Results
Item Restricted AN EXPERIMENTAL STUDY OF SUPERVISED MACHINE LEARNING TECHNIQUES FOR MINOR CLASS PREDICTION UTILIZING KERNEL DENSITY ESTIMATION: FACTORS IMPACTING MODEL PERFORMANCE(Western Michigan University, 2024-06-29) Alfarwan, Abdullah; Applegate, BrooksThis dissertation examined classification outcome differences among four popular individual supervised machine learning (ISML) models (logistic regression, decision tree, support vector machine, and multilayer perceptron) when predicting minor class membership within imbalanced datasets. The study context and the theoretical population sampled focus on one aspect of the larger problem of student retention and dropout prediction in higher education (HE): identification. This study differs from current literature by implementing an experimental design approach with simulated student data that closely mirrors HE situational and student data. Specifically, this study tested the predictive ability of the four ISML classification models (CLS) under experimentally manipulated conditions. These included total sample size (TS), minor class proportion (MCP), training-to-testing sample size ratios (TTSS), and the application of bagging techniques during model training (BAG). Using this 4-between, 1-within mixed design, five different outcome measures (precision, recall/sensitivity, specificity, F1-score and AUC) were examined and analyzed individually. For each outcome measure, findings revealed multiple statistically significant interactions among classifier models and design variables. Simple effect analyses of these interactions highlighted how TS, MCP, TTSS, and BAG differentially affect different measures of classification performance such as precision, recall/sensitivity, specificity, F1-score, and AUC. For instance, the presence of interactions involving MCP underscores the importance of informed modeling of class distribution for enhancing overall model predictive capability and performance. Such insights regarding how the experimental variables can critically affect different measures of classification success advances our understanding of how these four ISML models might be optimized for the prediction of student-at-risk status within imbalanced datasets. This dissertation provides a framework for using these or similar ISML models more effectively in HE. It points toward the development of predictive modeling methods that are more useful and perhaps equitable by demonstrating empirically the impact of one of the most challenging aspects of implementing machine learning in HE: maximizing the accurate identification of the minority class. This work contributes to the use of machine learning in HE and will help inform its use in smaller and larger educational research communities by providing strategies for improving the prediction of student dropout.16 0Item Restricted Predicting The Academic Success of The Deaf and Hard of Hearing University Students: A Multilevel Analysis(Saudi Digital Library, 2023-08-18) Zaino, Zeyad; Schwartz, Ilene; Hudson, RoxanneSecond Language (L2) learners and Deaf and Hard of Hearing (Deaf/HH) students share some commonalities. Both groups are required to obtain a minimum score on Language Proficiency Tests (LPT) to gain acceptance into university level institutions. However, even with accommodations, language proficiency testing becomes more complicated for Deaf/HH students because LPTs were created for hearing people and there is no specific test for Deaf/HH individuals. In Arabic countries, the only LPT for Deaf/HH students is at King Saud University (KSU). This dissertation used multilevel logistic modeling to 1) investigate whether the LPT uniquely predicted academic success for Deaf/HH students at KSU after controlling for individual characteristics, and 2) to Evaluate certain the student characteristics that moderate the relationship between the LPT and passing the Qualifying Year Program (QYP). A total of 619 Deaf/HH students participated in the study across 12 regions in the Kingdom of Saudi Arabia. The results indicated that, within region, the LPT scores significantly predicted the likelihood of passing the QYP. However, LPT was not significantly predictive of the likelihood of passing the QYP in the aggregate, region level. The results also showed that students who were female, HH, and had higher high school GPAs were more likely to pass the QYP. The current context for Deaf/HH students in Arabic universities, including assessment protocols and test shortcomings along with the results of the analysis, are discussed.18 0Item Restricted Transformational Leadership in The Adoption and Implementation of The Internet of Things (IOT) In Higher Education: A Case Study of Saudi Arabian Universities(2023-05-12) Abdo, khalid; Baaden, BeaThe IoT is a growing phenomenon that is pervasive in many areas of society. IoT refers to the interconnection of devices through the internet. Organizations adopting IoT can obtain exciting and valuable outcomes, and higher education is not exempt. Universities are timidly incorporating IoT, therefore not taking advantage of the great benefits that IoT can bring to these institutions. However, adopting IoT in higher education implies a significant change in the usual behavior of the people attending these places. A natural resistance to the adoption of IoT is not a surprise, given that people are reluctant to modify their traditional ways of operating. It is believed that transformational leadership can promote the adoption and implementation of the IoT; a transformational leader can alleviate rejection attitudes and use transformational leadership characteristics to inform the people attending higher education institutions about the benefits of IoT. This study used a mixed-method approach to examine how the leadership qualities of university leaders affect the level of adoption and implementation of the IoT in Saudi Arabian universities. Survey and semi-structured interviews were used to collect data. Evidently, the finding reveals a profile of leadership that is transformational in style suggesting that university executives intellectually excite, inspire, ideally influence their subordinates, and examine their concerns. Second, the leaders have a moderate level of attitude toward teamwork, can motivate, and are open-minded. Third, the extent to which infrastructure enables the implementation of the IoT is not adequate. The institution lacks IoT infrastructures, as seen by the absence of an IoT department. This has made providing IoT help to students and staff problematic. Finally, IoT enables more efficient and effective systems for teaching and learning. keyword: Internet of things (IOT), leadership, Transformational leadership, IOT adoption and implementation, Higher education, Saudi Arabia28 0