MétaCan
Menu
Back to cohort

Real-Time Leak Localization in N95 Respirators Using Infrared Imaging and Deep Learning with Optimal ROI Signal Correlation

2025· article· en· W4414406115 on OpenAlex

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldEngineering
TopicFire Detection and Safety Systems
Canadian institutionsUniversité LavalÉcole de Technologie SupérieureInstitut de recherche Robert-Sauvé en santé et en sécurité du travailUniversité du Québec à Rimouski
Fundersnot available
KeywordsLeakSIGNAL (programming language)RespiratorDeep learningTracking (education)BreathingLeak detectionPattern recognition (psychology)

Abstract

fetched live from OpenAlex

A secure seal in N95 respirators is critical for preventing airborne contaminants, yet minor leaks significantly compromise protective efficiency. This paper presents an integrated framework leveraging infrared imaging and deep learning for real-time, non-contact leak localization. A custom U-Net model extracts the mask region from thermal images, while the Segment Anything Model 2 (SAM2) dynamically tracks contour variations under changing conditions. Thermal signals along the mask boundary are transformed into the frequency domain and correlated with a reference breathing signal to identify leak locations. The proposed method systematically evaluates optimal central region selection to enhance correlation-based leak detection. Experimental validation using pixel-wise Breathing Cycle Optical Flow Tracking demonstrates the effectiveness of this approach in accurately detecting and localizing leaks in real-world conditions, offering a robust alternative to conventional contact-based fit-testing methods.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.000
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.681
Threshold uncertainty score0.444

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.004
GPT teacher head0.194
Teacher spread0.190 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Quick stats

Citations0
Published2025
Admission routes1
Has abstractyes

Explore more

Same topicFire Detection and Safety SystemsFrench-language works237,207