FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313244921> ?p ?o ?g. }

• W4313244921 endingPage "91" @default.
• W4313244921 startingPage "91" @default.
• W4313244921 abstract "Advancements in optical satellite hardware and lowered costs for satellite launches raised the high demand for geospatial intelligence. The object recognition problem in multi-spectral satellite imagery carries dataset properties unique to this problem. Perspective distortion, resolution variability, data spectrality, and other features make it difficult for a specific human-invented neural network to perform well on a dispersed type of scenery, ranging data quality, and different objects. UNET, MACU, and other manually designed network architectures deliver high-performance results for accuracy and prediction speed in large objects. However, once trained on different datasets, the performance drops and requires manual recalibration or further configuration testing to adjust the neural network architecture. To solve these issues, AutoML-based techniques can be employed. In this paper, we focus on Neural Architecture Search that is capable of obtaining a well-performing network configuration without human manual intervention. Firstly, we conducted detailed testing on the top four performing neural networks for object recognition in satellite imagery to compare their performance: FastFCN, DeepLabv3, UNET, and MACU. Then we applied and further developed a Neural Architecture Search technique for the best-performing manually designed MACU by optimizing a search space at the artificial neuron cellular level of the network. Several NAS-MACU versions were explored and evaluated. Our developed AutoML process generated a NAS-MACU neural network that produced better performance compared with MACU, especially in a low-information intensity environment. The experimental investigation was performed on our annotated and updated publicly available satellite imagery dataset. We can state that the application of the Neural Architecture Search procedure has the capability to be applied across various datasets and object recognition problems within the remote sensing research field." @default.
• W4313244921 created "2023-01-06" @default.
• W4313244921 creator A5028361092 @default.
• W4313244921 creator A5030797479 @default.
• W4313244921 creator A5033830613 @default.
• W4313244921 creator A5077440677 @default.
• W4313244921 date "2022-12-24" @default.
• W4313244921 modified "2023-10-04" @default.
• W4313244921 title "AutoML-Based Neural Architecture Search for Object Recognition in Satellite Imagery" @default.
• W4313244921 cites W1655957607 @default.
• W4313244921 cites W1745334888 @default.
• W4313244921 cites W1903029394 @default.
• W4313244921 cites W2097117768 @default.
• W4313244921 cites W2109255472 @default.
• W4313244921 cites W2552414813 @default.
• W4313244921 cites W2560023338 @default.
• W4313244921 cites W2565813159 @default.
• W4313244921 cites W2786492053 @default.
• W4313244921 cites W2896720583 @default.
• W4313244921 cites W2903282641 @default.
• W4313244921 cites W2908843432 @default.
• W4313244921 cites W2912002401 @default.
• W4313244921 cites W2927980542 @default.
• W4313244921 cites W2963881378 @default.
• W4313244921 cites W2964081807 @default.
• W4313244921 cites W2966284335 @default.
• W4313244921 cites W2969640942 @default.
• W4313244921 cites W2990536517 @default.
• W4313244921 cites W3015788359 @default.
• W4313244921 cites W3035470482 @default.
• W4313244921 cites W3085633928 @default.
• W4313244921 cites W3086451439 @default.
• W4313244921 cites W3089661409 @default.
• W4313244921 cites W3110613120 @default.
• W4313244921 cites W3146464195 @default.
• W4313244921 cites W3174278368 @default.
• W4313244921 cites W3177052299 @default.
• W4313244921 cites W3184324897 @default.
• W4313244921 cites W4200393246 @default.
• W4313244921 cites W4200571910 @default.
• W4313244921 cites W4205934717 @default.
• W4313244921 cites W4206301980 @default.
• W4313244921 cites W4210839933 @default.
• W4313244921 cites W4281478450 @default.
• W4313244921 doi "https://doi.org/10.3390/rs15010091" @default.
• W4313244921 hasPublicationYear "2022" @default.
• W4313244921 type Work @default.
• W4313244921 citedByCount "2" @default.
• W4313244921 countsByYear W43132449212023 @default.
• W4313244921 crossrefType "journal-article" @default.
• W4313244921 hasAuthorship W4313244921A5028361092 @default.
• W4313244921 hasAuthorship W4313244921A5030797479 @default.
• W4313244921 hasAuthorship W4313244921A5033830613 @default.
• W4313244921 hasAuthorship W4313244921A5077440677 @default.
• W4313244921 hasBestOaLocation W43132449211 @default.
• W4313244921 hasConcept C111919701 @default.
• W4313244921 hasConcept C123657996 @default.
• W4313244921 hasConcept C127313418 @default.
• W4313244921 hasConcept C127413603 @default.
• W4313244921 hasConcept C142362112 @default.
• W4313244921 hasConcept C146978453 @default.
• W4313244921 hasConcept C153349607 @default.
• W4313244921 hasConcept C154945302 @default.
• W4313244921 hasConcept C19269812 @default.
• W4313244921 hasConcept C2778102629 @default.
• W4313244921 hasConcept C41008148 @default.
• W4313244921 hasConcept C50644808 @default.
• W4313244921 hasConcept C62649853 @default.
• W4313244921 hasConcept C9770341 @default.
• W4313244921 hasConcept C98045186 @default.
• W4313244921 hasConceptScore W4313244921C111919701 @default.
• W4313244921 hasConceptScore W4313244921C123657996 @default.
• W4313244921 hasConceptScore W4313244921C127313418 @default.
• W4313244921 hasConceptScore W4313244921C127413603 @default.
• W4313244921 hasConceptScore W4313244921C142362112 @default.
• W4313244921 hasConceptScore W4313244921C146978453 @default.
• W4313244921 hasConceptScore W4313244921C153349607 @default.
• W4313244921 hasConceptScore W4313244921C154945302 @default.
• W4313244921 hasConceptScore W4313244921C19269812 @default.
• W4313244921 hasConceptScore W4313244921C2778102629 @default.
• W4313244921 hasConceptScore W4313244921C41008148 @default.
• W4313244921 hasConceptScore W4313244921C50644808 @default.
• W4313244921 hasConceptScore W4313244921C62649853 @default.
• W4313244921 hasConceptScore W4313244921C9770341 @default.
• W4313244921 hasConceptScore W4313244921C98045186 @default.
• W4313244921 hasIssue "1" @default.
• W4313244921 hasLocation W43132449211 @default.
• W4313244921 hasOpenAccess W4313244921 @default.
• W4313244921 hasPrimaryLocation W43132449211 @default.
• W4313244921 hasRelatedWork W1987569955 @default.
• W4313244921 hasRelatedWork W2037952344 @default.
• W4313244921 hasRelatedWork W2071521913 @default.
• W4313244921 hasRelatedWork W2085580665 @default.
• W4313244921 hasRelatedWork W2386387936 @default.
• W4313244921 hasRelatedWork W2388503282 @default.
• W4313244921 hasRelatedWork W4288260271 @default.
• W4313244921 hasRelatedWork W564495916 @default.
• W4313244921 hasRelatedWork W1629725936 @default.

• next