FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4311005463> ?p ?o ?g. }

• W4311005463 endingPage "6048" @default.
• W4311005463 startingPage "6048" @default.
• W4311005463 abstract "A rip current is a strong, localized current of water which moves along and away from the shore. Recent studies have suggested that drownings due to rip currents are still a major threat to beach safety. Identification of rip currents is important for lifeguards when making decisions on where to designate patrolled areas. The public also require information while deciding where to swim when lifeguards are not on patrol. In the present study we present an artificial intelligence (AI) algorithm that both identifies whether a rip current exists in images/video, and also localizes where that rip current occurs. While there have been some significant advances in AI for rip current detection and localization, there is a lack of research ensuring that an AI algorithm can generalize well to a diverse range of coastal environments and marine conditions. The present study made use of an interpretable AI method, gradient-weighted class-activation maps (Grad-CAM), which is a novel approach for amorphous rip current detection. The training data/images were diverse and encompass rip currents in a wide variety of environmental settings, ensuring model generalization. An open-access aerial catalogue of rip currents were used for model training. Here, the aerial imagery was also augmented by applying a wide variety of randomized image transformations (e.g., perspective, rotational transforms, and additive noise), which dramatically improves model performance through generalization. To account for diverse environmental settings, a synthetically generated training set, containing fog, shadows, and rain, was also added to the rip current images, thus increased the training dataset approximately 10-fold. Interpretable AI has dramatically improved the accuracy of unbounded rip current detection, which can correctly classify and localize rip currents about 89% of the time when validated on independent videos from surf-cameras at oblique angles. The novelty also lies in the ability to capture some shape characteristics of the amorphous rip current structure without the need of a predefined bounding box, therefore enabling the use of remote technology like drones. A comparison with well-established coastal image processing techniques is also presented via a short discussion and easy reference table. The strengths and weaknesses of both methods are highlighted and discussed." @default.
• W4311005463 created "2022-12-22" @default.
• W4311005463 creator A5056680752 @default.
• W4311005463 creator A5062691593 @default.
• W4311005463 creator A5063212222 @default.
• W4311005463 creator A5069053250 @default.
• W4311005463 date "2022-11-29" @default.
• W4311005463 modified "2023-10-01" @default.
• W4311005463 title "Interpretable Deep Learning Applied to Rip Current Detection and Localization" @default.
• W4311005463 cites W2017963104 @default.
• W4311005463 cites W2064888423 @default.
• W4311005463 cites W2076965998 @default.
• W4311005463 cites W2092461001 @default.
• W4311005463 cites W2102881289 @default.
• W4311005463 cites W2104970949 @default.
• W4311005463 cites W2117539524 @default.
• W4311005463 cites W2124660862 @default.
• W4311005463 cites W2146486154 @default.
• W4311005463 cites W2152385124 @default.
• W4311005463 cites W2153636305 @default.
• W4311005463 cites W2163923250 @default.
• W4311005463 cites W2330787514 @default.
• W4311005463 cites W2395579298 @default.
• W4311005463 cites W2508457857 @default.
• W4311005463 cites W2527992810 @default.
• W4311005463 cites W2558580397 @default.
• W4311005463 cites W2726556863 @default.
• W4311005463 cites W2743176826 @default.
• W4311005463 cites W2750794296 @default.
• W4311005463 cites W2793357704 @default.
• W4311005463 cites W2913788362 @default.
• W4311005463 cites W2962858109 @default.
• W4311005463 cites W2963037989 @default.
• W4311005463 cites W2963150697 @default.
• W4311005463 cites W2963973518 @default.
• W4311005463 cites W2969723582 @default.
• W4311005463 cites W2975495759 @default.
• W4311005463 cites W3083840715 @default.
• W4311005463 cites W3099319035 @default.
• W4311005463 cites W3104887532 @default.
• W4311005463 cites W3106850242 @default.
• W4311005463 cites W3116286104 @default.
• W4311005463 cites W3128487972 @default.
• W4311005463 cites W3131708156 @default.
• W4311005463 cites W3161025840 @default.
• W4311005463 cites W3171602206 @default.
• W4311005463 cites W3204298030 @default.
• W4311005463 cites W3212623172 @default.
• W4311005463 cites W4205361917 @default.
• W4311005463 cites W4244164532 @default.
• W4311005463 cites W4281563923 @default.
• W4311005463 cites W4308540792 @default.
• W4311005463 cites W3084745089 @default.
• W4311005463 doi "https://doi.org/10.3390/rs14236048" @default.
• W4311005463 hasPublicationYear "2022" @default.
• W4311005463 type Work @default.
• W4311005463 citedByCount "0" @default.
• W4311005463 crossrefType "journal-article" @default.
• W4311005463 hasAuthorship W4311005463A5056680752 @default.
• W4311005463 hasAuthorship W4311005463A5062691593 @default.
• W4311005463 hasAuthorship W4311005463A5063212222 @default.
• W4311005463 hasAuthorship W4311005463A5069053250 @default.
• W4311005463 hasBestOaLocation W43110054631 @default.
• W4311005463 hasConcept C111368507 @default.
• W4311005463 hasConcept C115961682 @default.
• W4311005463 hasConcept C119599485 @default.
• W4311005463 hasConcept C119857082 @default.
• W4311005463 hasConcept C127313418 @default.
• W4311005463 hasConcept C127413603 @default.
• W4311005463 hasConcept C134306372 @default.
• W4311005463 hasConcept C136197465 @default.
• W4311005463 hasConcept C148043351 @default.
• W4311005463 hasConcept C152382732 @default.
• W4311005463 hasConcept C154945302 @default.
• W4311005463 hasConcept C166482635 @default.
• W4311005463 hasConcept C177148314 @default.
• W4311005463 hasConcept C33923547 @default.
• W4311005463 hasConcept C41008148 @default.
• W4311005463 hasConcept C99498987 @default.
• W4311005463 hasConceptScore W4311005463C111368507 @default.
• W4311005463 hasConceptScore W4311005463C115961682 @default.
• W4311005463 hasConceptScore W4311005463C119599485 @default.
• W4311005463 hasConceptScore W4311005463C119857082 @default.
• W4311005463 hasConceptScore W4311005463C127313418 @default.
• W4311005463 hasConceptScore W4311005463C127413603 @default.
• W4311005463 hasConceptScore W4311005463C134306372 @default.
• W4311005463 hasConceptScore W4311005463C136197465 @default.
• W4311005463 hasConceptScore W4311005463C148043351 @default.
• W4311005463 hasConceptScore W4311005463C152382732 @default.
• W4311005463 hasConceptScore W4311005463C154945302 @default.
• W4311005463 hasConceptScore W4311005463C166482635 @default.
• W4311005463 hasConceptScore W4311005463C177148314 @default.
• W4311005463 hasConceptScore W4311005463C33923547 @default.
• W4311005463 hasConceptScore W4311005463C41008148 @default.
• W4311005463 hasConceptScore W4311005463C99498987 @default.
• W4311005463 hasFunder F4320310376 @default.
• W4311005463 hasIssue "23" @default.
• W4311005463 hasLocation W43110054631 @default.

• next