ORCID

0009-0003-4470-8772

Keywords

Micro-credentialing, Generative AI in education, STEM learning analytics, FPGA text classification, Agent-based modeling, Workforce alignment

Abstract

The growing demand for a skilled STEM workforce calls for adaptive, data-driven education that personalizes learning while aligning competencies with industry needs. This work introduces a multi-layered framework that integrates artificial intelligence (AI), data mining and hardware-aware optimization to support this goal. At its core, the AchieveUp system applies generative AI-assisted skill tagging to digitized assessments, enabling multi-semester tracking of student progress. Analysis across 14 semesters shows that underperforming students were found to benefit most from attending score clarification sessions, a relationship validated by an R² value of 0.83, indicating strong predictive validity between attendance and skill acquisition. To remediate knowledge gaps to facilitate attainment of a micro-credentials, the Academic Vigilance Environment employs generative AI and data mining to deliver tailored multimedia resources. Hardware acceleration further improves efficiency through a text classification pipeline combining lossless compression with k-Nearest Neighbors clustering, achieving a 3.41× speedup over CPU-based gzip when deployed on field programmable gate arrays (FPGAs) via high-level synthesis. The framework also extends to workforce alignment via micro-recruiting, where generative AI (GenAI) models link micro-credentials to job opportunities through job search APIs. Locally hosted large language models validate automated skill-to-job mapping, while agent-based models simulate student outcomes and instructional strategies. This work contributes a scalable pipeline from learner analytics to hardware deployment, advancing AI-driven education and bridging academic achievement with workforce readiness. While developing AI-driven approaches to address these goals, the Compression Based Feature Clustering (CBFC) hardware-based acceleration method developed improves scalability to large-scale application as well as addressing energy consumption demands.

Completion Date

2026

Semester

Spring

Committee Chair

Ronald F. DeMara

Degree

Doctor of Philosophy (Ph.D.)

College

College of Engineering and Computer Science

Department

Electrical and Computer Engineering

Document Type

Dissertation/Thesis

Identifier

DP0053187

Download

Share

COinS
 

Accessibility Statement

This item was created or digitized prior to April 24, 2027, or is a reproduction of legacy media created before that date. It is preserved in its original, unmodified state specifically for research, reference, or historical recordkeeping. In accordance with the ADA Title II Final Rule, the University Libraries provides accessible versions of archival materials upon request. To request an accommodation for this item, please submit an accessibility request form.