Theses and Dissertations

ORCID

https://orcid.org/0000-0001-9784-1196

Issuing Body

Mississippi State University

Advisor

Ma, Junfeng

Committee Member

Marufuzzaman, Mohammad

Committee Member

Babski-Reeves, Kari

Committee Member

Tian, Wenmeng

Committee Member

Faqir, Mustapha

Date of Degree

8-8-2023

Document Type

Dissertation - Open Access

Major

Industrial and Systems Engineering

Degree Name

Doctor of Philosophy (Ph.D)

College

James Worth Bagley College of Engineering

Department

Department of Industrial and Systems Engineering

Abstract

The 21st century is marked by a technological revolution that features digital implementation and high interconnectivity between systems across different domains, such as transportation, agriculture, education, and health. Although these technological changes resulted in modern systems capable of easing individuals’ lives, these systems are increasingly complex, and that increased complexity is only expected to continue. The increased system complexity is due to the rapid exchange of information between subsystems, which creates high interconnectivity and interdependence between the subsystems and their elements. Workforce skill sets, as a result, must be modified appropriately to ensure the systems’ success. Systems Thinking is an approach that helps individuals better understand and effectively solve modern complex systems problems by encouraging holistic thinking. Systems thinking consists of two approaches holistic and reductionist views. This dissertation aims to study college engineering and non-engineering students’ preference for holistic thinking versus reductionist thinking, their ranking to the systems thinking dimensions, and whether this preference varies depending on demographics and general factors. Additionally, this study investigates the possibility of predicting the students’ preference for holistic thinking. The study uses the multi-criteria decision-making method, the Analytic Hierarchy Process and Fuzzy Analytic Hierarchy Process to determine the student’s preferences, and uses statistical analysis such as independent sample t-test and ANOVA to evaluate the factors. Also, the study uses machine learning classification models such as Logistic Regression, Support Vector Machine, Naïve Bayes, Decision Trees, voting classifiers, Bagging, and Random Forest to predict and evaluate the most predicting model. The results of the dissertation conclude that overall students prefer the reductionist approach and report the students’ preference towards dimensions of complexity, independence, uncertainty, systems worldview, and flexibility and the ranking difference based on some factors. Lastly, the results show that the students’ preference for holistic thinking can be predicted with a 77% accuracy using the Random Forest classifier.

Download

Share

COinS