{"id":15,"date":"2025-07-15T12:34:19","date_gmt":"2025-07-15T12:34:19","guid":{"rendered":"https:\/\/groupebm.net\/niyem.bawana\/?page_id=15"},"modified":"2026-04-27T05:38:54","modified_gmt":"2026-04-27T05:38:54","slug":"research","status":"publish","type":"page","link":"https:\/\/groupebm.net\/niyem.bawana\/research\/","title":{"rendered":"RESEARCH"},"content":{"rendered":"\t\t
\n\t\t\t\t
\n\t\t\t\t\t
\n\t\t
\n\t\t\t\t
\n\t\t\t\t\t

Research<\/h2>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t
\n\t\t\t\t
\n\t\t\t\t\t

Our Research Vision<\/h2>\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t

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

\n\t\t\t\t
\n\t\t\t\t\t

Research Themes<\/h2>\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t

Three interconnected pillars that define our approach to computational NDE<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t

\n\t\t
\n\t\t\t\t
\n\t\t\t\t\t

Physics-Based Sensing & Signal Processing<\/h2>\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t

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.<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t

\n\t\t\t\t
\n\t\t\t\t\t

Machine Learning for NDE<\/h2>\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t

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.<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t

\n\t\t\t\t
\n\t\t\t\t\t

Cross-Modal Validation & Deployment<\/h2>\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t

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.<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t

\n\t\t\t\t
\n\t\t\t\t\t

Sensing Modalities<\/h2>\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t

Multi-modal data acquisition and cross-validation for robust damage characterization<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t

\n\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t
<\/i><\/div>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t\t

Terahertz (THz)<\/h2>\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t

Time-domain spectroscopy & imaging<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t

\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t
<\/i><\/div>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t\t

Ultrasonics<\/h2>\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t

Phased-array & guided wave inspection<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t

\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t
<\/i><\/div>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t\t

X-Ray<\/h2>\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t

Radiographic ground truth & validation<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t

\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t
<\/i><\/div>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t\t

Electromagnetic<\/h2>\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t

FDTD simulation & EM characterization<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t

\n\t\t\t\t
\n\t\t\t\t\t

Featured Projects<\/h2>\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t

Selected ongoing and recent research<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t

\n\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t
<\/div>
THz \u00b7 ML \u00b7 Composites<\/span>

Multi-Modal Damage Quantification<\/h3>

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

\u25a0<\/span>Random Forest r = 0.96\u20130.99<\/p><\/div>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t

\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t
<\/div>
Grad-CAM \u00b7 YOLO \u00b7 Weak Supervision<\/span>

Weakly Supervised Defect Localization<\/h3>

Training object detectors without manual annotation using Grad-CAM pseudo-labels, enabling scalable inspection across X-ray, THz, and ultrasonic imaging modalities.<\/p>

\u25a0<\/span>99% classification \u00b7 0.67 mAP<\/p><\/div>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t

\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t
<\/div>
X-Ray \u00b7 ResNet \u00b7 YOLOv8<\/span>

AI-Driven Inspection Pipelines<\/h3>

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

\u25a0<\/span>mAP@0.5 = 0.99 \u00b7 mAP@0.5:0.95 = 0.79<\/p><\/div>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t

\n\t\t\t\t
\n\t\t\t\t\t

Useful Links<\/h2>\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t

Resources, tools, and references for our research community<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t

\n\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t<\/i><\/span>PI Google Scholar Profile<\/span><\/a>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t<\/i><\/span>Giving a Talk<\/span><\/a>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t<\/i><\/span>How to Read an Engineering Research Paper<\/span><\/a>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t<\/i><\/span>How to Write a Technical Paper or a Research Paper<\/span><\/a>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t<\/i><\/span>You and Your Research<\/span><\/a>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t<\/i><\/span>How to Write a PhD Thesis<\/span><\/a>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t","protected":false},"excerpt":{"rendered":"

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 […]<\/p>\n","protected":false},"author":1,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-15","page","type-page","status-publish","hentry"],"blocksy_meta":[],"_links":{"self":[{"href":"https:\/\/groupebm.net\/niyem.bawana\/wp-json\/wp\/v2\/pages\/15","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/groupebm.net\/niyem.bawana\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/groupebm.net\/niyem.bawana\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/groupebm.net\/niyem.bawana\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/groupebm.net\/niyem.bawana\/wp-json\/wp\/v2\/comments?post=15"}],"version-history":[{"count":3,"href":"https:\/\/groupebm.net\/niyem.bawana\/wp-json\/wp\/v2\/pages\/15\/revisions"}],"predecessor-version":[{"id":4061,"href":"https:\/\/groupebm.net\/niyem.bawana\/wp-json\/wp\/v2\/pages\/15\/revisions\/4061"}],"wp:attachment":[{"href":"https:\/\/groupebm.net\/niyem.bawana\/wp-json\/wp\/v2\/media?parent=15"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}