The High-performance Artificial Intelligence Laboratory (HAIL) focuses on real-time big data analytics and machine learning to improve human performance, decision-making, and training. HAIL’s research is supported by a team of data scientists, software engineers, and statisticians, whose work is dedicated to forging innovations in digital twin modeling, deep reinforcement learning, and simulations.

Data analytics, machine learning, and simulations are at the core of HAIL’s research endeavors. To facilitate its research, HAIL relies on its computing capabilities. First, HAIL has its own dedicated machine-learning cluster for data model development and rapid prototyping. For more complex calculations, the lab uses UCF’s Advanced Research Computing Center (ARCC), which has two high-performance computing clusters: Stokes for general computing and Newton for GPU-based deep learning. Pooling these resources and other technologies, HAIL generates high-fidelity models, training platforms, and simulations.

Recent projects include digital twinning for semiconductor fabrication and planning, data mining for nuclear reactor operator training, predictive analytics for student performance and education, and developing automated attacking and defending agents for cybersecurity resiliency and training.

People

• Tori Wright, Data Analyst
• Louis Alvarez, Simulation Engineer
• Austin Starken, Modeling and Simulation Doctoral Student
• William Moulton, Undergraduate Researcher
• Tyler Crawford, Undergraduate Researcher
• Connor Hatfield, Graduate Researcher

Highlights

Publications

• Thomas Schiller and Sean Mondesire, “Human-out-of-the-Loop Swarm-based IoT Network Penetration Testing by IoT Devices,” presented at the Annual Modeling and Simulation Conference 2023 (ANNSIM 2023), Hamilton, Ontario, Canada: Society for Modeling and Simulation International (SCS), May 2023, p. 2.
• Thomas Schiller and Sean Mondesire, “Swarm-based IoT Network Penetration Testing by IoT Devices,” presented at the 21st International Conference on Applied Cryptography and Network Security (ACNS 2023), Kyoto, Japan: Springer (LNCS Series), Jun. 2023, p. 5.
• Sean Mondesire and R. Paul Wiegand, “Mitigating Catastrophic Forgetting with Complementary Layered Learning,” Journal Electronics – Special Issue: Modeling and Simulation Methods: Recent Advances and Applications, Vol. 1, Issue 1, 2023.
• Jordan Dauble and Sean Mondesire, “Prioritizing Improvements in Cyber Defender Knowledge, Skills, and Abilities using Cyber Simulation,” In Proceedings of the Simulation Innovation Workshop (SIW), Orlando, FL., 2023.
• Austin Starken, Bruce Caulkins, Annie S. Wu, Sean C. Mondesire, “Trends in Machine Learning for Adaptive Automated Forces,” In Proceedings of the Interservice/Industry Training, Simulation and Education Conference (IT/TSEC ’22), December 2022.
• Enzo Novi Migliano, Kelly M. Rivera, William Frazee, Louis Alvarez, Sean C. Mondesire, “Evaluating the Consistency of Student Performance Models for Individuals,” The 21st Int’l Conf on e-Learning, e-Business, Enterprise Information Systems, and e-Government (EEE ‘22), July 2022.

Research Areas:

• Artificial Intelligence and Machine Learning
• Digital Twins
• Big Data Analytics
• Data Model Development
• Systems Engineering
• High-performance Computing

---

Capabilities & Advanced Technologies:

• Data Mining
• GPU-based Deep Learning
• High-fidelity Models
• High-performance Computing
• Machine Learning
• Rapid Prototyping
• Simulations
• Training Platforms

---

Application Areas:

• Microelectronics and Semiconductor Fabrication
• Defense
• Cybersecurity
• Education
• Nuclear Reactor Safety