FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385355027> ?p ?o ?g. }

• W4385355027 endingPage "356" @default.
• W4385355027 startingPage "343" @default.
• W4385355027 abstract "An image processing technique makes the medical field vibrant by providing decisions based on the image's diagnosis. Images obtained in the various phases of diagnosis are utilized to retrieve the results and infer the severity of diseases in the affected person—features of the data act as significant points in the phase of discovery and treatment. Various images such as chest X-ray (CXR), computed tomography (CT), and magnetic resonance images are available to make a thorough analysis of the health condition of individuals. First-level inference helps to provide a glimpse, but a detailed analysis can be obtained by applying the relevant learning algorithms. A recent threat facing the medical sector and people generally is the COVID-19 virus that seriously affects the respiratory system of humans. The symptoms are very similar to pneumonia, which disturbs the efficient functioning of the lung. Capturing CT images of the lungs and applying the deep learning (DL) concept helps classify the images as COVID or non-COVID. Herein we propose a deep convolution neural network model named the Deep Convolution Classification Model, an 11-layered architectural model for recognizing COVID-19 cases from chest CT images. The various layers, namely Convolution, Maxpooling, Dropout, Flatten, and Dense, are stacked to classify the input images. The total number of images considered in our classification work is 746, of which 349 are COVID CT scans, and the remainder are non-COVID. The entire dataset is segregated for training and testing in the ratio of 70:30. Layered architecture is deployed and receives appreciable values in performance metrics. Compared with the existing approaches, the accuracy of the designed system is 93.68%, losses are very minimal, the area under the curve (AUC) is 0.8903, and the precision is 99.57%. Fine tuning and fixing of the values for the hyperparameters for the different layers makes the system very reliable and almost perfect." @default.
• W4385355027 created "2023-07-29" @default.
• W4385355027 creator A5034177663 @default.
• W4385355027 creator A5035288030 @default.
• W4385355027 date "2023-01-01" @default.
• W4385355027 modified "2023-09-24" @default.
• W4385355027 title "Deep convolution classification model-based COVID-19 chest CT image classification" @default.
• W4385355027 cites W2912564039 @default.
• W4385355027 cites W2963901018 @default.
• W4385355027 cites W3006110666 @default.
• W4385355027 cites W3008985036 @default.
• W4385355027 cites W3012817508 @default.
• W4385355027 cites W3012919504 @default.
• W4385355027 cites W3013099522 @default.
• W4385355027 cites W3015538848 @default.
• W4385355027 cites W3017403618 @default.
• W4385355027 cites W3019980738 @default.
• W4385355027 cites W3021137017 @default.
• W4385355027 cites W3030109869 @default.
• W4385355027 cites W3038780555 @default.
• W4385355027 cites W3039137888 @default.
• W4385355027 cites W3046500052 @default.
• W4385355027 cites W3048749423 @default.
• W4385355027 cites W3080406710 @default.
• W4385355027 cites W3081923509 @default.
• W4385355027 cites W3082245570 @default.
• W4385355027 cites W3082357942 @default.
• W4385355027 cites W3086039674 @default.
• W4385355027 cites W3086462707 @default.
• W4385355027 cites W3088680016 @default.
• W4385355027 cites W3088864412 @default.
• W4385355027 cites W3099905444 @default.
• W4385355027 cites W3101606529 @default.
• W4385355027 cites W3105282616 @default.
• W4385355027 cites W3109783949 @default.
• W4385355027 cites W3173114814 @default.
• W4385355027 cites W4200182115 @default.
• W4385355027 cites W4225113120 @default.
• W4385355027 cites W4226150890 @default.
• W4385355027 cites W4281710262 @default.
• W4385355027 doi "https://doi.org/10.1016/b978-0-443-19413-9.00022-9" @default.
• W4385355027 hasPublicationYear "2023" @default.
• W4385355027 type Work @default.
• W4385355027 citedByCount "0" @default.
• W4385355027 crossrefType "book-chapter" @default.
• W4385355027 hasAuthorship W4385355027A5034177663 @default.
• W4385355027 hasAuthorship W4385355027A5035288030 @default.
• W4385355027 hasConcept C108583219 @default.
• W4385355027 hasConcept C115961682 @default.
• W4385355027 hasConcept C142724271 @default.
• W4385355027 hasConcept C153180895 @default.
• W4385355027 hasConcept C154945302 @default.
• W4385355027 hasConcept C2776214188 @default.
• W4385355027 hasConcept C2779134260 @default.
• W4385355027 hasConcept C3008058167 @default.
• W4385355027 hasConcept C41008148 @default.
• W4385355027 hasConcept C45347329 @default.
• W4385355027 hasConcept C50644808 @default.
• W4385355027 hasConcept C524204448 @default.
• W4385355027 hasConcept C71924100 @default.
• W4385355027 hasConcept C75294576 @default.
• W4385355027 hasConcept C81363708 @default.
• W4385355027 hasConceptScore W4385355027C108583219 @default.
• W4385355027 hasConceptScore W4385355027C115961682 @default.
• W4385355027 hasConceptScore W4385355027C142724271 @default.
• W4385355027 hasConceptScore W4385355027C153180895 @default.
• W4385355027 hasConceptScore W4385355027C154945302 @default.
• W4385355027 hasConceptScore W4385355027C2776214188 @default.
• W4385355027 hasConceptScore W4385355027C2779134260 @default.
• W4385355027 hasConceptScore W4385355027C3008058167 @default.
• W4385355027 hasConceptScore W4385355027C41008148 @default.
• W4385355027 hasConceptScore W4385355027C45347329 @default.
• W4385355027 hasConceptScore W4385355027C50644808 @default.
• W4385355027 hasConceptScore W4385355027C524204448 @default.
• W4385355027 hasConceptScore W4385355027C71924100 @default.
• W4385355027 hasConceptScore W4385355027C75294576 @default.
• W4385355027 hasConceptScore W4385355027C81363708 @default.
• W4385355027 hasLocation W43853550271 @default.
• W4385355027 hasOpenAccess W4385355027 @default.
• W4385355027 hasPrimaryLocation W43853550271 @default.
• W4385355027 hasRelatedWork W2470368200 @default.
• W4385355027 hasRelatedWork W2766604260 @default.
• W4385355027 hasRelatedWork W2912288872 @default.
• W4385355027 hasRelatedWork W2986507176 @default.
• W4385355027 hasRelatedWork W2996856019 @default.
• W4385355027 hasRelatedWork W3011074480 @default.
• W4385355027 hasRelatedWork W3018421652 @default.
• W4385355027 hasRelatedWork W3160711233 @default.
• W4385355027 hasRelatedWork W4220996320 @default.
• W4385355027 hasRelatedWork W4312417841 @default.
• W4385355027 isParatext "false" @default.
• W4385355027 isRetracted "false" @default.
• W4385355027 workType "book-chapter" @default.