Matches in SemOpenAlex for { <https://semopenalex.org/work/W3085367988> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W3085367988 abstract "Deep learning has many successful real-world applications including traffic signal recognition, which are used in driver assistance systems and autonomous vehicles. Accurate detection of traffic signal indications is critical to ensure safety under autonomous driving. Many past studies have been completed on traffic signal recognition including detection, classification and tracking with datasets which are typically highly imbalanced due to the nature of traffic signal displays. However, most studies simply ignored the minority classes and did not consider cost-sensitive information inherent to traffic signal indications. This paper evaluated several cost-sensitive techniques applicable to deep learning models in traffic signal classification. A convolutional neural network (CNN) was used in the evaluation as the baseline model. Cost-sensitive techniques including cost-proportionate rejection sampling and the use of cost-sensitive loss function was then applied to the baseline CNN model to evaluate and compare the effects of using cost information in traffic signal classification. Arbitrary cost information was assumed in this evaluation, but the resulting models did not improve accuracy in prediction. Future studies may consider more carefully crafted cost information and/or other cost-sensitive techniques." @default.
- W3085367988 created "2020-09-21" @default.
- W3085367988 creator A5002085328 @default.
- W3085367988 creator A5056300209 @default.
- W3085367988 date "2020-08-01" @default.
- W3085367988 modified "2023-09-30" @default.
- W3085367988 title "Traffic Signal Classification with Cost-Sensitive Deep Learning Models" @default.
- W3085367988 cites W1562810981 @default.
- W3085367988 cites W2021383150 @default.
- W3085367988 cites W2139505542 @default.
- W3085367988 cites W2142261479 @default.
- W3085367988 cites W2512944926 @default.
- W3085367988 cites W2551429935 @default.
- W3085367988 cites W2578209314 @default.
- W3085367988 cites W2600072788 @default.
- W3085367988 cites W2603436287 @default.
- W3085367988 cites W2615277952 @default.
- W3085367988 cites W2737202447 @default.
- W3085367988 cites W2789832744 @default.
- W3085367988 cites W2792492025 @default.
- W3085367988 cites W2883223908 @default.
- W3085367988 cites W2887955655 @default.
- W3085367988 cites W2953711573 @default.
- W3085367988 cites W2962829130 @default.
- W3085367988 cites W2963923206 @default.
- W3085367988 doi "https://doi.org/10.1109/icbk50248.2020.00088" @default.
- W3085367988 hasPublicationYear "2020" @default.
- W3085367988 type Work @default.
- W3085367988 sameAs 3085367988 @default.
- W3085367988 citedByCount "3" @default.
- W3085367988 countsByYear W30853679882021 @default.
- W3085367988 countsByYear W30853679882022 @default.
- W3085367988 countsByYear W30853679882023 @default.
- W3085367988 crossrefType "proceedings-article" @default.
- W3085367988 hasAuthorship W3085367988A5002085328 @default.
- W3085367988 hasAuthorship W3085367988A5056300209 @default.
- W3085367988 hasConcept C108583219 @default.
- W3085367988 hasConcept C111368507 @default.
- W3085367988 hasConcept C119857082 @default.
- W3085367988 hasConcept C124101348 @default.
- W3085367988 hasConcept C12725497 @default.
- W3085367988 hasConcept C127313418 @default.
- W3085367988 hasConcept C153180895 @default.
- W3085367988 hasConcept C154945302 @default.
- W3085367988 hasConcept C158379750 @default.
- W3085367988 hasConcept C169988225 @default.
- W3085367988 hasConcept C199360897 @default.
- W3085367988 hasConcept C2779843651 @default.
- W3085367988 hasConcept C38652104 @default.
- W3085367988 hasConcept C41008148 @default.
- W3085367988 hasConcept C81363708 @default.
- W3085367988 hasConceptScore W3085367988C108583219 @default.
- W3085367988 hasConceptScore W3085367988C111368507 @default.
- W3085367988 hasConceptScore W3085367988C119857082 @default.
- W3085367988 hasConceptScore W3085367988C124101348 @default.
- W3085367988 hasConceptScore W3085367988C12725497 @default.
- W3085367988 hasConceptScore W3085367988C127313418 @default.
- W3085367988 hasConceptScore W3085367988C153180895 @default.
- W3085367988 hasConceptScore W3085367988C154945302 @default.
- W3085367988 hasConceptScore W3085367988C158379750 @default.
- W3085367988 hasConceptScore W3085367988C169988225 @default.
- W3085367988 hasConceptScore W3085367988C199360897 @default.
- W3085367988 hasConceptScore W3085367988C2779843651 @default.
- W3085367988 hasConceptScore W3085367988C38652104 @default.
- W3085367988 hasConceptScore W3085367988C41008148 @default.
- W3085367988 hasConceptScore W3085367988C81363708 @default.
- W3085367988 hasLocation W30853679881 @default.
- W3085367988 hasOpenAccess W3085367988 @default.
- W3085367988 hasPrimaryLocation W30853679881 @default.
- W3085367988 hasRelatedWork W2731899572 @default.
- W3085367988 hasRelatedWork W2999805992 @default.
- W3085367988 hasRelatedWork W3116150086 @default.
- W3085367988 hasRelatedWork W3133861977 @default.
- W3085367988 hasRelatedWork W4200173597 @default.
- W3085367988 hasRelatedWork W4223943233 @default.
- W3085367988 hasRelatedWork W4291897433 @default.
- W3085367988 hasRelatedWork W4312417841 @default.
- W3085367988 hasRelatedWork W4321369474 @default.
- W3085367988 hasRelatedWork W4380075502 @default.
- W3085367988 isParatext "false" @default.
- W3085367988 isRetracted "false" @default.
- W3085367988 magId "3085367988" @default.
- W3085367988 workType "article" @default.