Selected Software Projects
-
Milo: Magnitude-Invariant Learning Optimizer
A group-wise gradient normalization optimizer designed to reduce magnitude distortion in learning dynamics, tested across image classification, CNNs, and reinforcement learning tasks.
github.com/Logan-Cole-Luna/Milo -
SensorWF: A FAIR Generalizable Workflow Framework for Scientific Time-Series Analysis
A FAIR, generalizable workflow framework for scientific time-series analysis (Accepted, ReWorDS Workshop @ IEEE eScience 2026).
github.com/Logan-Cole-Luna/SensorWF -
Learning Causal Structures from Aviation Accident Narratives
Compares rule-based NLP, transformer (DistilBERT), and few-shot LLM (Mistral-7B) approaches for extracting causal relationships from NTSB aviation accident narratives into knowledge graphs.
github.com/Logan-Cole-Luna/CausalStructuresFromAviation -
Energy-Efficient Avionics Security
Research on energy-efficient security mechanisms for avionics systems.
github.com/Logan-Cole-Luna/energy-efficient-avionics-security -
Satellite Trajectory Projection and Collision Avoidance
RL-based satellite collision avoidance environment and PPO pipeline.
github.com/Logan-Cole-Luna/sat-trajectory-avoidance -
Hierarchical Q-Learning for Threat Hunting (Dueling DQN)
A multi-stage RL agent performing hierarchical intrusion detection over network traffic, including binary classification and attack-type prediction.
github.com/Logan-Cole-Luna/Hierarchical-Q-Learning-Threat-Hunting