SPIN GROUP

Research

Our Research Vision

The SPIN Group develops computational methods that transform raw sensor data into actionable knowledge about material health. Our research sits at the intersection of physics-based sensing, signal processing, and machine learning, enabling intelligent, automated inspection systems that scale across modalities and applications.

Research Themes

Three interconnected pillars that define our approach to computational NDE

Physics-Based Sensing & Signal Processing

We acquire and process data from terahertz, ultrasonic, electromagnetic, and X-ray modalities. Our focus is on extracting physics-informed features, time-of-flight, spectral content, attenuation maps, that capture the signatures of subsurface damage.

Machine Learning for NDE

We develop weakly supervised and self-supervised learning frameworks that reduce reliance on manual annotation. Our pipelines combine classification, localization, and quantification, from Grad-CAM pseudo-labels to physics-informed feature maps.

Cross-Modal Validation & Deployment

We benchmark AI-driven inspection across modalities using X-ray ground truth, and build end-to-end pipelines designed for real-world deployment, from laboratory prototyping to field-ready systems.

Sensing Modalities

Multi-modal data acquisition and cross-validation for robust damage characterization

Terahertz (THz)

Time-domain spectroscopy & imaging

Ultrasonics

Phased-array & guided wave inspection

X-Ray

Radiographic ground truth & validation

Electromagnetic

FDTD simulation & EM characterization

Featured Projects

Selected ongoing and recent research

THz · ML · Composites

Multi-Modal Damage Quantification

Physics-informed feature extraction from terahertz, ultrasonic, and electromagnetic sensing data for automated impact damage assessment in composite structures.


Random Forest r = 0.96–0.99

Grad-CAM · YOLO · Weak Supervision

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.


99% classification · 0.67 mAP

X-Ray · ResNet · YOLOv8

AI-Driven Inspection Pipelines

End-to-end systems combining classification, detection, and quantification, with X-ray ground truth validation for cross-modal benchmarking.


mAP@0.5 = 0.99 · mAP@0.5:0.95 = 0.79