Computational Sensing for Intelligent Inspection
We develop physics-informed AI systems that see what the human eye cannot — detecting hidden damage in critical structures through advanced sensing, signal processing, and machine learning.
Research Focus
Physics-Based Sensing
Terahertz imaging, electromagnetic methods, and multi-modal data acquisition for subsurface characterization.
AI for Inverse Problems
Deep learning architectures trained on physics-informed features to localize and quantify material degradation.
Intelligent Inspection Systems
End-to-end pipelines from raw sensor data to automated damage assessment — bridging lab research and field deployment.
Where Our Research Applies
✈
Aerospace Composites
🏗
Civil Infrastructure
⚡
Energy Systems
⚙
Advanced Manufacturing
Featured Projects
Multi-Modal Damage Quantification
Physics-informed feature extraction from terahertz, ultrasonic, and electromagnetic sensing data for automated impact damage assessment in composite structures.
Weakly Supervised Defect Localization
Training object detectors without manual annotation using Grad-CAM pseudo-labels — enabling scalable inspection across X-ray, THz, and ultrasonic imaging modalities.
AI-Driven Inspection Pipelines
End-to-end systems combining classification, detection, and quantification — with X-ray ground truth validation for cross-modal benchmarking.
Join the Lab
We welcome motivated graduate and undergraduate researchers interested in computational sensing, machine learning for NDE, signal processing, and multi-modal inspection systems. Our work spans terahertz, ultrasonic, X-ray, and electromagnetic modalities. Reach out to start a conversation.