MétaCan
Menu
Back to cohort
Record W4411665802 · doi:10.1016/j.geits.2025.100332

Toward smart railway maintenance: AI-enhanced Non-Destructive Evaluation using Vision Transformers and CNNs for fastener defect detection

2025· article· en· W4411665802 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.
fundA Canadian funder is recorded on the work.

Bibliographic record

VenueGreen Energy and Intelligent Transportation · 2025
Typearticle
Languageen
FieldEngineering
TopicInfrastructure Maintenance and Monitoring
Canadian institutionsUniversité du Québec à Trois-RivièresCentre intégré de santé et de services sociaux de Chaudière-AppalachesUniversité du Québec à Rimouski
FundersScience and Engineering Research CouncilNatural Sciences and Engineering Research Council of Canada
KeywordsArtificial intelligenceComputer scienceDeep learning

Abstract

fetched live from OpenAlex

Predictive health management and maintenance of transport infrastructure are critical for preventing accidents and service disruptions. Applying Non-Destructive Evaluation (NDE) and imaging techniques is essential for identifying irregularities without causing harm. This research utilizes pre-trained models and incorporates transfer learning concepts to overcome dataset constraints. This study assesses the effectiveness of various machine learning models, including the Vision Transformer (ViT), Data-efficient Image Transformer (DeiT), VGG19, VGG16, and ResNet50, in enhancing NDE for railway track fasteners. ViT and DeiT, both transformer-based models, emerged as the top performers due to their superior learning efficiencies and generalization capabilities, augmented by precise hyperparameter tuning. VGG models are a reliable alternative, while ResNet50 is better suited for applications prioritizing computational efficiency over accuracy. • Transformers (ViT/DeiT) outperform CNNs in railway fastener defect detection, showing higher accuracy and robustness. • Leveraging transfer learning and pre-trained ViT/DeiT models helps overcome data scarcity in rail defect datasets. • DeiT achieved 95.04% accuracy, ViT 94.14%, both beating VGG16's 91.54% and showing lower validation loss values. • Results highlight transformers' promise in railway NDE, enabling future hybrid models and larger dataset use.

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: Other design · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.813
Threshold uncertainty score0.846

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 head0.010
GPT teacher head0.251
Teacher spread0.240 · 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