Matches in SemOpenAlex for { <https://semopenalex.org/work/W4283789791> ?p ?o ?g. }
- W4283789791 endingPage "117946" @default.
- W4283789791 startingPage "117946" @default.
- W4283789791 abstract "Increasing demands on railway structures have led to a need for new cost-effective maintenance strategies in recent years. Current dynamic railway track monitoring systems are usually based on the analysis of axle-box accelerations to automatically detect track singularities and defects. These methods rely on hand-crafted feature extraction and classifiers for different tasks. However, the low performance shown in previous literature makes it necessary to complement these analyses with in-situ inspections. Very recent works have proposed the use of deep learning systems that allow extracting more generalizable features from time–frequency spectrograms. However, the lack of specific public domain datasets and the finite number of track singularities in a railway structure have limited the development of deep learning based systems. In this paper, we propose a method capable of outstanding in low-data scenarios. In particular, we explore the use of supervised contrastive learning to cluster class embeddings nearly in the encoder latent space, which is used during inference for prototypical distance-based class assignment. We provide comprehensive experiments demonstrating the performance of our method in comparison to previous literature for detecting worn-out crossings." @default.
- W4283789791 created "2022-07-05" @default.
- W4283789791 creator A5024176997 @default.
- W4283789791 creator A5043316752 @default.
- W4283789791 creator A5066442595 @default.
- W4283789791 creator A5069816579 @default.
- W4283789791 date "2022-11-01" @default.
- W4283789791 modified "2023-09-24" @default.
- W4283789791 title "Supervised contrastive learning-guided prototypes on axle-box accelerations for railway crossing inspections" @default.
- W4283789791 cites W1847343635 @default.
- W4283789791 cites W1942337233 @default.
- W4283789791 cites W2072131106 @default.
- W4283789791 cites W2091738130 @default.
- W4283789791 cites W2194775991 @default.
- W4283789791 cites W2227176820 @default.
- W4283789791 cites W2406523001 @default.
- W4283789791 cites W2540062733 @default.
- W4283789791 cites W2555875178 @default.
- W4283789791 cites W2757352536 @default.
- W4283789791 cites W2794807743 @default.
- W4283789791 cites W2800989301 @default.
- W4283789791 cites W2801287471 @default.
- W4283789791 cites W2890733150 @default.
- W4283789791 cites W2897809320 @default.
- W4283789791 cites W2912475127 @default.
- W4283789791 cites W2945550644 @default.
- W4283789791 cites W2964105864 @default.
- W4283789791 cites W2966749320 @default.
- W4283789791 cites W2972248988 @default.
- W4283789791 cites W2981731882 @default.
- W4283789791 cites W2983285351 @default.
- W4283789791 cites W2989656504 @default.
- W4283789791 cites W3002997085 @default.
- W4283789791 cites W3082027266 @default.
- W4283789791 cites W3090775044 @default.
- W4283789791 cites W3102564565 @default.
- W4283789791 cites W3105031677 @default.
- W4283789791 cites W3111094774 @default.
- W4283789791 cites W3133701504 @default.
- W4283789791 cites W3148337205 @default.
- W4283789791 cites W3155630026 @default.
- W4283789791 cites W3176977755 @default.
- W4283789791 cites W3182874523 @default.
- W4283789791 cites W3183017707 @default.
- W4283789791 cites W3184824399 @default.
- W4283789791 cites W4284991980 @default.
- W4283789791 doi "https://doi.org/10.1016/j.eswa.2022.117946" @default.
- W4283789791 hasPublicationYear "2022" @default.
- W4283789791 type Work @default.
- W4283789791 citedByCount "2" @default.
- W4283789791 countsByYear W42837897912023 @default.
- W4283789791 crossrefType "journal-article" @default.
- W4283789791 hasAuthorship W4283789791A5024176997 @default.
- W4283789791 hasAuthorship W4283789791A5043316752 @default.
- W4283789791 hasAuthorship W4283789791A5066442595 @default.
- W4283789791 hasAuthorship W4283789791A5069816579 @default.
- W4283789791 hasBestOaLocation W42837897911 @default.
- W4283789791 hasConcept C101738243 @default.
- W4283789791 hasConcept C104317684 @default.
- W4283789791 hasConcept C108583219 @default.
- W4283789791 hasConcept C111919701 @default.
- W4283789791 hasConcept C112313634 @default.
- W4283789791 hasConcept C119857082 @default.
- W4283789791 hasConcept C127413603 @default.
- W4283789791 hasConcept C127716648 @default.
- W4283789791 hasConcept C129727815 @default.
- W4283789791 hasConcept C134306372 @default.
- W4283789791 hasConcept C138885662 @default.
- W4283789791 hasConcept C154945302 @default.
- W4283789791 hasConcept C177148314 @default.
- W4283789791 hasConcept C185592680 @default.
- W4283789791 hasConcept C188082640 @default.
- W4283789791 hasConcept C2776214188 @default.
- W4283789791 hasConcept C2776401178 @default.
- W4283789791 hasConcept C33923547 @default.
- W4283789791 hasConcept C41008148 @default.
- W4283789791 hasConcept C41895202 @default.
- W4283789791 hasConcept C55493867 @default.
- W4283789791 hasConcept C78519656 @default.
- W4283789791 hasConcept C89992363 @default.
- W4283789791 hasConceptScore W4283789791C101738243 @default.
- W4283789791 hasConceptScore W4283789791C104317684 @default.
- W4283789791 hasConceptScore W4283789791C108583219 @default.
- W4283789791 hasConceptScore W4283789791C111919701 @default.
- W4283789791 hasConceptScore W4283789791C112313634 @default.
- W4283789791 hasConceptScore W4283789791C119857082 @default.
- W4283789791 hasConceptScore W4283789791C127413603 @default.
- W4283789791 hasConceptScore W4283789791C127716648 @default.
- W4283789791 hasConceptScore W4283789791C129727815 @default.
- W4283789791 hasConceptScore W4283789791C134306372 @default.
- W4283789791 hasConceptScore W4283789791C138885662 @default.
- W4283789791 hasConceptScore W4283789791C154945302 @default.
- W4283789791 hasConceptScore W4283789791C177148314 @default.
- W4283789791 hasConceptScore W4283789791C185592680 @default.
- W4283789791 hasConceptScore W4283789791C188082640 @default.
- W4283789791 hasConceptScore W4283789791C2776214188 @default.
- W4283789791 hasConceptScore W4283789791C2776401178 @default.
- W4283789791 hasConceptScore W4283789791C33923547 @default.