Matches in SemOpenAlex for { <https://semopenalex.org/work/W3136100689> ?p ?o ?g. }
- W3136100689 abstract "Wireless Capsule Endoscopy helps physicians examine the gastrointestinal (GI) tract noninvasively, with the cost of generating many images. Many available datasets, such as KID2 and Kvasir, suffer from imbalance issue which make it difficult to train an effective artificial intelligence (AI) system. Moreover, increasing number of classes makes the problem worse. In this study, an ensemble of one-class classifiers is used for detecting anomaly. This method focuses on learning single models using samples from only one class, and ensemble all models for multiclass classification. A total of 1,778 normal, 227 inflammation, 303 vascular diseases, and 44 polyp images have been used from the KID2 dataset. In the first step, deep features are extracted based on an autoencoder architecture from the preprocessed images. Then, these features are oversampled using Synthetic Minority Over-sampling Technique and clustered using Ordering Points to Identify the Clustering Structure. To create one-class classification model, the Support Vector Data Descriptions are trained on each cluster with the help of Ant Colony Optimization, which is also used for tuning clustering parameters for improving F1-score. This process is applied on each classes and ensemble of final models used for multiclass classification. The entire algorithm ran 5 times and obtained F1-score 96.3 +- 0.2% and macro-average F1-score 85.0 +- 0.4%, for anomaly detection and multiclass classification, respectively. The results are compared with GoogleNet, AlexNet, Resnet50, VGG16 and other published algorithms, and demonstrate that the proposed method is a competitive choice for multiclass class anomaly detection in GI images." @default.
- W3136100689 created "2021-03-29" @default.
- W3136100689 creator A5000597423 @default.
- W3136100689 creator A5017986343 @default.
- W3136100689 creator A5051633467 @default.
- W3136100689 creator A5089274119 @default.
- W3136100689 date "2021-03-15" @default.
- W3136100689 modified "2023-09-26" @default.
- W3136100689 title "Multiclass Anomaly Detection in GI Endoscopic Images using Optimized Deep One-class Classification in an Imbalanced Dataset." @default.
- W3136100689 cites W2052464337 @default.
- W3136100689 cites W2061237952 @default.
- W3136100689 cites W2076464948 @default.
- W3136100689 cites W2120862619 @default.
- W3136100689 cites W2146704338 @default.
- W3136100689 cites W2148143831 @default.
- W3136100689 cites W2154462399 @default.
- W3136100689 cites W2154929945 @default.
- W3136100689 cites W2157427654 @default.
- W3136100689 cites W2162498245 @default.
- W3136100689 cites W2165698076 @default.
- W3136100689 cites W2170505850 @default.
- W3136100689 cites W2334028018 @default.
- W3136100689 cites W2464527493 @default.
- W3136100689 cites W2543580944 @default.
- W3136100689 cites W2550193557 @default.
- W3136100689 cites W2560014990 @default.
- W3136100689 cites W2620841913 @default.
- W3136100689 cites W2804467258 @default.
- W3136100689 cites W2894660140 @default.
- W3136100689 cites W2897749869 @default.
- W3136100689 cites W2898260073 @default.
- W3136100689 cites W2931917481 @default.
- W3136100689 cites W2936503027 @default.
- W3136100689 cites W2958413208 @default.
- W3136100689 cites W2963049059 @default.
- W3136100689 cites W2981035911 @default.
- W3136100689 cites W3015340282 @default.
- W3136100689 cites W3082154143 @default.
- W3136100689 cites W3083232044 @default.
- W3136100689 cites W3097020048 @default.
- W3136100689 cites W3102476541 @default.
- W3136100689 cites W3122757751 @default.
- W3136100689 cites W53035228 @default.
- W3136100689 hasPublicationYear "2021" @default.
- W3136100689 type Work @default.
- W3136100689 sameAs 3136100689 @default.
- W3136100689 citedByCount "0" @default.
- W3136100689 crossrefType "posted-content" @default.
- W3136100689 hasAuthorship W3136100689A5000597423 @default.
- W3136100689 hasAuthorship W3136100689A5017986343 @default.
- W3136100689 hasAuthorship W3136100689A5051633467 @default.
- W3136100689 hasAuthorship W3136100689A5089274119 @default.
- W3136100689 hasConcept C101738243 @default.
- W3136100689 hasConcept C108583219 @default.
- W3136100689 hasConcept C12267149 @default.
- W3136100689 hasConcept C123860398 @default.
- W3136100689 hasConcept C124101348 @default.
- W3136100689 hasConcept C153180895 @default.
- W3136100689 hasConcept C154945302 @default.
- W3136100689 hasConcept C2777212361 @default.
- W3136100689 hasConcept C41008148 @default.
- W3136100689 hasConcept C45942800 @default.
- W3136100689 hasConcept C73555534 @default.
- W3136100689 hasConcept C739882 @default.
- W3136100689 hasConceptScore W3136100689C101738243 @default.
- W3136100689 hasConceptScore W3136100689C108583219 @default.
- W3136100689 hasConceptScore W3136100689C12267149 @default.
- W3136100689 hasConceptScore W3136100689C123860398 @default.
- W3136100689 hasConceptScore W3136100689C124101348 @default.
- W3136100689 hasConceptScore W3136100689C153180895 @default.
- W3136100689 hasConceptScore W3136100689C154945302 @default.
- W3136100689 hasConceptScore W3136100689C2777212361 @default.
- W3136100689 hasConceptScore W3136100689C41008148 @default.
- W3136100689 hasConceptScore W3136100689C45942800 @default.
- W3136100689 hasConceptScore W3136100689C73555534 @default.
- W3136100689 hasConceptScore W3136100689C739882 @default.
- W3136100689 hasLocation W31361006891 @default.
- W3136100689 hasOpenAccess W3136100689 @default.
- W3136100689 hasPrimaryLocation W31361006891 @default.
- W3136100689 hasRelatedWork W2091389753 @default.
- W3136100689 hasRelatedWork W2092892517 @default.
- W3136100689 hasRelatedWork W2519242446 @default.
- W3136100689 hasRelatedWork W2593987079 @default.
- W3136100689 hasRelatedWork W2597091454 @default.
- W3136100689 hasRelatedWork W2785928966 @default.
- W3136100689 hasRelatedWork W3011115931 @default.
- W3136100689 hasRelatedWork W3031552518 @default.
- W3136100689 hasRelatedWork W3084024556 @default.
- W3136100689 hasRelatedWork W3116030381 @default.
- W3136100689 hasRelatedWork W3117417736 @default.
- W3136100689 hasRelatedWork W3127482607 @default.
- W3136100689 hasRelatedWork W3129153478 @default.
- W3136100689 hasRelatedWork W3137364660 @default.
- W3136100689 hasRelatedWork W3146861394 @default.
- W3136100689 hasRelatedWork W3160921291 @default.
- W3136100689 hasRelatedWork W3181411924 @default.
- W3136100689 hasRelatedWork W3193334866 @default.
- W3136100689 hasRelatedWork W3206778595 @default.
- W3136100689 hasRelatedWork W3168811482 @default.
- W3136100689 isParatext "false" @default.