Design and evaluation of the impact of a multi-agent control system (framework) applied to a social setting
Abstract
The objective of this research is to design and analyze the performance of a new mechanism to improve the advising of students in a nontraditional environment. This nontraditional environment includes: a minority serving, commuter campus with a high percentage of transfer students. Specifically, these demographics are unable to keep a tightly controlled cohort of students flowing through to the completion of the curriculum. Students in these circumstances usually have varied course loads and competing priorities due to family and financial needs or other societal responsibilities. Therefore, there is a need for an individualized approach to advising. University administrations face challenges scheduling courses and allocating diminishing resources needed to satisfy the increasing student demand. In addition, the school administrations need to assess the efficacy of the advising program in place in regards to the students’ progress in completing the curriculum in a program. Collecting this type of longitudinal student data can be difficult. A web application system (mobile compatible) using a multi-agent distributed control approach has been developed to allow the students (agents) to gain more control over their individualized advising. In this context, the student becomes an agent, and the school provides the environment with a desirable behavior for the system. This research will identify the school’s administrators, as the academic control element and will be referred as the "Operator". This study focuses on the newly designed agent system built with a dashboard tool that collects each individual student’s information in a web-based program as they progress through the curriculum and generates advising recommendations specific to each student. The agent logic employs principles used in project management tools designed as a resource for schedule optimization. It provides a visualization map of course sequences that are customized for each student based on their history of courses completed. It makes advising adjustments that will optimize the length of time required to obtain the degree under a constrained set of parameters. At the same time, the agent system provides real-time feedback to the Operators. The tool helps students optimize their resources to complete their degree sooner. The second tool is the Operator dashboard that consolidates the collected data from the agents through several semesters (historical data) and the predicted effects of the recommended plans. This enables a better resource allocation utilizing real time data.
Subject Area
Electrical engineering|Educational technology|Computer science
Recommended Citation
Perez Solis, Oscar Antonio, "Design and evaluation of the impact of a multi-agent control system (framework) applied to a social setting" (2016). ETD Collection for University of Texas, El Paso. AAI10118170.
https://scholarworks.utep.edu/dissertations/AAI10118170