Matches in SemOpenAlex for { <https://semopenalex.org/work/W4210904477> ?p ?o ?g. }
Showing items 1 to 84 of
84
with 100 items per page.
- W4210904477 endingPage "1031" @default.
- W4210904477 startingPage "1027" @default.
- W4210904477 abstract "Blind modulation classification is widely used in various military and civilian applications. Characterized by its exemption from likelihood calculation and the ability of using well-trained models, feature-based (FB) classifiers are popular with their high computational efficiency. In recent years, Deep Neural Networks based methods have shown significant improvement in the classification accuracy. However, the performance of FB methods decreases rapidly under low signal-to-noise ratios. To overcome this shortcoming, this letter proposes a joint denoising and modulation classification method based on Multitask Learning, where a denoising network and a classification network are simultaneoulsy trained in an end-to-end manner. In addition, the focal loss function is adopted to highlight the importance of hard-to-classify samples during training. Our numerical experiments show that the proposed method can effectively improve the classification accuracy, and outperform state-of-the-art methods. For example, under the 0dB SNR condition, the performance of our proposed Multitask CNN method is 20% higher than that of the traditional CNN method." @default.
- W4210904477 created "2022-02-09" @default.
- W4210904477 creator A5005215808 @default.
- W4210904477 creator A5023806511 @default.
- W4210904477 creator A5051244203 @default.
- W4210904477 creator A5085286494 @default.
- W4210904477 date "2022-05-01" @default.
- W4210904477 modified "2023-10-17" @default.
- W4210904477 title "Blind Modulation Classification Under Uncertain Noise Conditions: A Multitask Learning Approach" @default.
- W4210904477 cites W1666202160 @default.
- W4210904477 cites W2283470457 @default.
- W4210904477 cites W2755335499 @default.
- W4210904477 cites W2963809753 @default.
- W4210904477 cites W2994812667 @default.
- W4210904477 cites W3104028856 @default.
- W4210904477 cites W3123268700 @default.
- W4210904477 cites W4248350653 @default.
- W4210904477 doi "https://doi.org/10.1109/lcomm.2022.3149284" @default.
- W4210904477 hasPublicationYear "2022" @default.
- W4210904477 type Work @default.
- W4210904477 citedByCount "5" @default.
- W4210904477 countsByYear W42109044772022 @default.
- W4210904477 countsByYear W42109044772023 @default.
- W4210904477 crossrefType "journal-article" @default.
- W4210904477 hasAuthorship W4210904477A5005215808 @default.
- W4210904477 hasAuthorship W4210904477A5023806511 @default.
- W4210904477 hasAuthorship W4210904477A5051244203 @default.
- W4210904477 hasAuthorship W4210904477A5085286494 @default.
- W4210904477 hasConcept C107038049 @default.
- W4210904477 hasConcept C108583219 @default.
- W4210904477 hasConcept C115961682 @default.
- W4210904477 hasConcept C119857082 @default.
- W4210904477 hasConcept C123079801 @default.
- W4210904477 hasConcept C138885662 @default.
- W4210904477 hasConcept C153180895 @default.
- W4210904477 hasConcept C154945302 @default.
- W4210904477 hasConcept C163294075 @default.
- W4210904477 hasConcept C2776401178 @default.
- W4210904477 hasConcept C41008148 @default.
- W4210904477 hasConcept C41895202 @default.
- W4210904477 hasConcept C50644808 @default.
- W4210904477 hasConcept C52622490 @default.
- W4210904477 hasConcept C99498987 @default.
- W4210904477 hasConceptScore W4210904477C107038049 @default.
- W4210904477 hasConceptScore W4210904477C108583219 @default.
- W4210904477 hasConceptScore W4210904477C115961682 @default.
- W4210904477 hasConceptScore W4210904477C119857082 @default.
- W4210904477 hasConceptScore W4210904477C123079801 @default.
- W4210904477 hasConceptScore W4210904477C138885662 @default.
- W4210904477 hasConceptScore W4210904477C153180895 @default.
- W4210904477 hasConceptScore W4210904477C154945302 @default.
- W4210904477 hasConceptScore W4210904477C163294075 @default.
- W4210904477 hasConceptScore W4210904477C2776401178 @default.
- W4210904477 hasConceptScore W4210904477C41008148 @default.
- W4210904477 hasConceptScore W4210904477C41895202 @default.
- W4210904477 hasConceptScore W4210904477C50644808 @default.
- W4210904477 hasConceptScore W4210904477C52622490 @default.
- W4210904477 hasConceptScore W4210904477C99498987 @default.
- W4210904477 hasFunder F4320320006 @default.
- W4210904477 hasFunder F4320321001 @default.
- W4210904477 hasFunder F4320322919 @default.
- W4210904477 hasFunder F4320323067 @default.
- W4210904477 hasFunder F4320335777 @default.
- W4210904477 hasFunder F4320335787 @default.
- W4210904477 hasIssue "5" @default.
- W4210904477 hasLocation W42109044771 @default.
- W4210904477 hasOpenAccess W4210904477 @default.
- W4210904477 hasPrimaryLocation W42109044771 @default.
- W4210904477 hasRelatedWork W2016461833 @default.
- W4210904477 hasRelatedWork W2382607599 @default.
- W4210904477 hasRelatedWork W2732542196 @default.
- W4210904477 hasRelatedWork W2773120646 @default.
- W4210904477 hasRelatedWork W2774265021 @default.
- W4210904477 hasRelatedWork W3156786002 @default.
- W4210904477 hasRelatedWork W3186111093 @default.
- W4210904477 hasRelatedWork W3197541072 @default.
- W4210904477 hasRelatedWork W4312200629 @default.
- W4210904477 hasRelatedWork W2092619848 @default.
- W4210904477 hasVolume "26" @default.
- W4210904477 isParatext "false" @default.
- W4210904477 isRetracted "false" @default.
- W4210904477 workType "article" @default.