Applied Research

Applied research spanning computational modeling, artificial intelligence, and software engineering education, with sustained real-world impact.

Research Focus Areas

  • Computational modeling and inverse problems
  • Machine learning and data mining
  • Generative AI and Large Language Models (LLMs)
  • Agentic AI systems and multi-step reasoning workflows
  • AI-augmented software engineering practices
  • Curriculum transformation in response to generative AI

Foundational Research: Computational Modeling & Inversion

My early research, including doctoral work in the 1990s, focused on large-scale computational modeling and automated interpretation of geophysical data—approaches that closely align with modern optimization, machine learning, and AI-based inference systems.

  • Forward and inverse modeling of borehole geophysical logs, using nonlinear regression with the Levenberg–Marquardt algorithm
  • Automation of resistivity log interpretation for formation evaluation
  • Numerical solution of large linear systems (thousands of equations) derived from partial differential equations
  • High-performance scientific computing implemented from first principles without external numerical libraries

▶ Interactive Forward Modeling Demo (Web Version)
(Modern JavaScript reimplementation of original research code)

This work emphasized model-based reasoning, numerical stability, and computational efficiency—principles that continue to inform current applied AI research.

Current Applied Research Projects Updated 2026

Current projects build on earlier work in computational modeling, optimization, and data-driven systems, extended today through generative and agentic AI technologies.

Many of these projects are developed in collaboration with senior students through course projects, applied research initiatives, and supervised independent study, providing hands-on experience with real-world AI and software engineering systems.

  • AI Tutors for Enhanced Learning
    Agentic and retrieval-augmented AI systems for personalized, explainable learning.
  • Knowledge-Graph-Driven Curriculum Design
    Modeling curricula, prerequisites, and learning pathways using structured knowledge representations.
  • Agentic AI for Academic and Administrative Support
    AI systems capable of reasoning, retrieval, reflection, and follow-up generation in educational contexts.

Selected Earlier Applied Research Projects

  • Using Institutional Data to Predict Student Performance and Improve Retention
    Applied machine learning and data mining to support evidence-based academic decision-making.
  • Predicting Students at Risk
    Predictive analytics for early intervention and academic success.
  • AI-Enabled GPS Tracking Device for Locating Missing Children
    Prototype development and testing; presented at ARIES Symposium.
  • Online Focus Group Software Platform
    Student-friendly platform integrating qualitative and quantitative research tools.
  • Capstone Projects Website
    Centralized platform for showcasing applied student projects.
  • Educational Career Development Mobile Game
    Co-investigator on a mobile application supporting student engagement and career exploration.
  • Center of Excellence for Data Analytics (CEDA)
    Contributed to the NSERC application supporting institutional data analytics research capacity.