FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385650167> ?p ?o ?g. }

• W4385650167 endingPage "2228" @default.
• W4385650167 startingPage "2228" @default.
• W4385650167 abstract "This study focuses on overcoming challenges in classifying eye diseases using color fundus photographs by leveraging deep learning techniques, aiming to enhance early detection and diagnosis accuracy. We utilized a dataset of 6392 color fundus photographs across eight disease categories, which was later augmented to 17,766 images. Five well-known convolutional neural networks (CNNs)-efficientnetb0, mobilenetv2, shufflenet, resnet50, and resnet101-and a custom-built CNN were integrated and trained on this dataset. Image sizes were standardized, and model performance was evaluated via accuracy, Kappa coefficient, and precision metrics. Shufflenet and efficientnetb0demonstrated strong performances, while our custom 17-layer CNN outperformed all with an accuracy of 0.930 and a Kappa coefficient of 0.920. Furthermore, we found that the fusion of image features with classical machine learning classifiers increased the performance, with Logistic Regression showcasing the best results. Our study highlights the potential of AI and deep learning models in accurately classifying eye diseases and demonstrates the efficacy of custom-built models and the fusion of deep learning and classical methods. Future work should focus on validating these methods across larger datasets and assessing their real-world applicability." @default.
• W4385650167 created "2023-08-09" @default.
• W4385650167 creator A5017177739 @default.
• W4385650167 creator A5017362365 @default.
• W4385650167 creator A5021209111 @default.
• W4385650167 creator A5029378773 @default.
• W4385650167 creator A5031491228 @default.
• W4385650167 creator A5033195512 @default.
• W4385650167 creator A5038610123 @default.
• W4385650167 creator A5063161766 @default.
• W4385650167 creator A5069595223 @default.
• W4385650167 creator A5076174609 @default.
• W4385650167 creator A5077868844 @default.
• W4385650167 date "2023-08-07" @default.
• W4385650167 modified "2023-10-11" @default.
• W4385650167 title "Classification of Color Fundus Photographs Using Fusion Extracted Features and Customized CNN Models" @default.
• W4385650167 cites W2188948771 @default.
• W4385650167 cites W2344912502 @default.
• W4385650167 cites W2557738935 @default.
• W4385650167 cites W2893365278 @default.
• W4385650167 cites W2894025867 @default.
• W4385650167 cites W2896202701 @default.
• W4385650167 cites W2912806832 @default.
• W4385650167 cites W2943640801 @default.
• W4385650167 cites W2999301272 @default.
• W4385650167 cites W3004396616 @default.
• W4385650167 cites W3014548009 @default.
• W4385650167 cites W3094648158 @default.
• W4385650167 cites W3096061254 @default.
• W4385650167 cites W3115536696 @default.
• W4385650167 cites W3151530204 @default.
• W4385650167 cites W3156742045 @default.
• W4385650167 cites W3176580834 @default.
• W4385650167 cites W3178124254 @default.
• W4385650167 cites W4200164247 @default.
• W4385650167 cites W4205714946 @default.
• W4385650167 cites W4205723032 @default.
• W4385650167 cites W4213446944 @default.
• W4385650167 cites W4214948219 @default.
• W4385650167 cites W4300089448 @default.
• W4385650167 cites W4306249365 @default.
• W4385650167 cites W4313477394 @default.
• W4385650167 cites W4366825494 @default.
• W4385650167 cites W4368368123 @default.
• W4385650167 cites W4372294443 @default.
• W4385650167 cites W4380576865 @default.
• W4385650167 cites W2885446060 @default.
• W4385650167 doi "https://doi.org/10.3390/healthcare11152228" @default.
• W4385650167 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37570467" @default.
• W4385650167 hasPublicationYear "2023" @default.
• W4385650167 type Work @default.
• W4385650167 citedByCount "0" @default.
• W4385650167 crossrefType "journal-article" @default.
• W4385650167 hasAuthorship W4385650167A5017177739 @default.
• W4385650167 hasAuthorship W4385650167A5017362365 @default.
• W4385650167 hasAuthorship W4385650167A5021209111 @default.
• W4385650167 hasAuthorship W4385650167A5029378773 @default.
• W4385650167 hasAuthorship W4385650167A5031491228 @default.
• W4385650167 hasAuthorship W4385650167A5033195512 @default.
• W4385650167 hasAuthorship W4385650167A5038610123 @default.
• W4385650167 hasAuthorship W4385650167A5063161766 @default.
• W4385650167 hasAuthorship W4385650167A5069595223 @default.
• W4385650167 hasAuthorship W4385650167A5076174609 @default.
• W4385650167 hasAuthorship W4385650167A5077868844 @default.
• W4385650167 hasBestOaLocation W43856501671 @default.
• W4385650167 hasConcept C108583219 @default.
• W4385650167 hasConcept C115961682 @default.
• W4385650167 hasConcept C118487528 @default.
• W4385650167 hasConcept C119857082 @default.
• W4385650167 hasConcept C120665830 @default.
• W4385650167 hasConcept C121332964 @default.
• W4385650167 hasConcept C153180895 @default.
• W4385650167 hasConcept C154945302 @default.
• W4385650167 hasConcept C163864269 @default.
• W4385650167 hasConcept C192209626 @default.
• W4385650167 hasConcept C2776391266 @default.
• W4385650167 hasConcept C31972630 @default.
• W4385650167 hasConcept C41008148 @default.
• W4385650167 hasConcept C69744172 @default.
• W4385650167 hasConcept C71924100 @default.
• W4385650167 hasConcept C81363708 @default.
• W4385650167 hasConceptScore W4385650167C108583219 @default.
• W4385650167 hasConceptScore W4385650167C115961682 @default.
• W4385650167 hasConceptScore W4385650167C118487528 @default.
• W4385650167 hasConceptScore W4385650167C119857082 @default.
• W4385650167 hasConceptScore W4385650167C120665830 @default.
• W4385650167 hasConceptScore W4385650167C121332964 @default.
• W4385650167 hasConceptScore W4385650167C153180895 @default.
• W4385650167 hasConceptScore W4385650167C154945302 @default.
• W4385650167 hasConceptScore W4385650167C163864269 @default.
• W4385650167 hasConceptScore W4385650167C192209626 @default.
• W4385650167 hasConceptScore W4385650167C2776391266 @default.
• W4385650167 hasConceptScore W4385650167C31972630 @default.
• W4385650167 hasConceptScore W4385650167C41008148 @default.
• W4385650167 hasConceptScore W4385650167C69744172 @default.
• W4385650167 hasConceptScore W4385650167C71924100 @default.
• W4385650167 hasConceptScore W4385650167C81363708 @default.
• W4385650167 hasIssue "15" @default.

• next