FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3197863338> ?p ?o ?g. }

• W3197863338 endingPage "209" @default.
• W3197863338 startingPage "193" @default.
• W3197863338 abstract "A leading widespread upsurge was identified as a severe acute respiratory syndrome (SARS) coronavirus “COVID-19.” It has blowout a global threat to human existence, throughout the world with millions of recognized instances and griefs, originating from Wuhan, China, to every other part of the universe by demeaning activities put in place to regulate it. Various actions are ongoing to combat the increase of this dangerous disease, such as health precautions and measures, money, substructures, databases, protective devices, and medications, among other necessities, yet interminable upsurge of the disease post a constant interruption to the universe. Several widespread innovative forecast methods have emerged in predicting COVID-19 globally to obtain keen results and impressive, relevant preemptive procedures. This study aims to apply a machine learning method for prediction of COVID-19 incidence, using KPCA-SVM. Its objectives are to use recent cases and their gene data, by imploring KPCA to fetch relevant latent components. The reduced output is classified and evaluated in terms of the performance metrics. This study is implemented in MATLAB. The algorithms used for the prediction are KPCA and SVM. The results are evaluated using accuracy, sensitivity, specificity, F-score, Matthews correlation coefficient, precision, and negative predictive value. This study uses the KPCA to fetch relevant information for the enormous data and classified using the L-SVM and SVM-RBF; it achieved 93% and 87% accuracy, respectively. The necessity to identify suitable prognostic suggestions for COVID-19 must regulate the difficulties in apprehending the disease’s increase. In this investigation, a machine learning prediction approach is projected for COVID-19 to convey the importance of principal frameworks for enhancements and evolving quicker and capable conduct for evaluating, classifying, and predicting health status concerning actions and symptoms observed, to help healthcare persons recognize and record incidence to verify qualified healthcare across nations." @default.
• W3197863338 created "2021-09-13" @default.
• W3197863338 creator A5006333857 @default.
• W3197863338 creator A5021046956 @default.
• W3197863338 creator A5022507170 @default.
• W3197863338 creator A5064136287 @default.
• W3197863338 creator A5071054943 @default.
• W3197863338 date "2021-09-02" @default.
• W3197863338 modified "2023-10-17" @default.
• W3197863338 title "Machine Learning Approach Using KPCA-SVMs for Predicting COVID-19" @default.
• W3197863338 cites W2030035529 @default.
• W3197863338 cites W2772178611 @default.
• W3197863338 cites W2950722229 @default.
• W3197863338 cites W2955053048 @default.
• W3197863338 cites W2969376125 @default.
• W3197863338 cites W3004234114 @default.
• W3197863338 cites W3005477624 @default.
• W3197863338 cites W3011056788 @default.
• W3197863338 cites W3011403448 @default.
• W3197863338 cites W3012054129 @default.
• W3197863338 cites W3013998834 @default.
• W3197863338 cites W3014486945 @default.
• W3197863338 cites W3014846667 @default.
• W3197863338 cites W3017185871 @default.
• W3197863338 cites W3017985416 @default.
• W3197863338 cites W3019119825 @default.
• W3197863338 cites W3019662005 @default.
• W3197863338 cites W3030585150 @default.
• W3197863338 cites W3035086245 @default.
• W3197863338 cites W3082692902 @default.
• W3197863338 cites W3086174161 @default.
• W3197863338 cites W3105297460 @default.
• W3197863338 cites W3123133508 @default.
• W3197863338 cites W3125830233 @default.
• W3197863338 cites W3125977574 @default.
• W3197863338 cites W4211230579 @default.
• W3197863338 doi "https://doi.org/10.1007/978-3-030-72752-9_10" @default.
• W3197863338 hasPublicationYear "2021" @default.
• W3197863338 type Work @default.
• W3197863338 sameAs 3197863338 @default.
• W3197863338 citedByCount "7" @default.
• W3197863338 countsByYear W31978633382022 @default.
• W3197863338 countsByYear W31978633382023 @default.
• W3197863338 crossrefType "book-chapter" @default.
• W3197863338 hasAuthorship W3197863338A5006333857 @default.
• W3197863338 hasAuthorship W3197863338A5021046956 @default.
• W3197863338 hasAuthorship W3197863338A5022507170 @default.
• W3197863338 hasAuthorship W3197863338A5064136287 @default.
• W3197863338 hasAuthorship W3197863338A5071054943 @default.
• W3197863338 hasConcept C111919701 @default.
• W3197863338 hasConcept C119857082 @default.
• W3197863338 hasConcept C12267149 @default.
• W3197863338 hasConcept C124101348 @default.
• W3197863338 hasConcept C126322002 @default.
• W3197863338 hasConcept C154945302 @default.
• W3197863338 hasConcept C2779134260 @default.
• W3197863338 hasConcept C2780365114 @default.
• W3197863338 hasConcept C3008058167 @default.
• W3197863338 hasConcept C41008148 @default.
• W3197863338 hasConcept C524204448 @default.
• W3197863338 hasConcept C71924100 @default.
• W3197863338 hasConceptScore W3197863338C111919701 @default.
• W3197863338 hasConceptScore W3197863338C119857082 @default.
• W3197863338 hasConceptScore W3197863338C12267149 @default.
• W3197863338 hasConceptScore W3197863338C124101348 @default.
• W3197863338 hasConceptScore W3197863338C126322002 @default.
• W3197863338 hasConceptScore W3197863338C154945302 @default.
• W3197863338 hasConceptScore W3197863338C2779134260 @default.
• W3197863338 hasConceptScore W3197863338C2780365114 @default.
• W3197863338 hasConceptScore W3197863338C3008058167 @default.
• W3197863338 hasConceptScore W3197863338C41008148 @default.
• W3197863338 hasConceptScore W3197863338C524204448 @default.
• W3197863338 hasConceptScore W3197863338C71924100 @default.
• W3197863338 hasLocation W31978633381 @default.
• W3197863338 hasOpenAccess W3197863338 @default.
• W3197863338 hasPrimaryLocation W31978633381 @default.
• W3197863338 hasRelatedWork W1017828488 @default.
• W3197863338 hasRelatedWork W1996541855 @default.
• W3197863338 hasRelatedWork W2355927362 @default.
• W3197863338 hasRelatedWork W2961085424 @default.
• W3197863338 hasRelatedWork W3195168932 @default.
• W3197863338 hasRelatedWork W4285260836 @default.
• W3197863338 hasRelatedWork W4286629047 @default.
• W3197863338 hasRelatedWork W4306321456 @default.
• W3197863338 hasRelatedWork W4306674287 @default.
• W3197863338 hasRelatedWork W4224009465 @default.
• W3197863338 isParatext "false" @default.
• W3197863338 isRetracted "false" @default.
• W3197863338 magId "3197863338" @default.
• W3197863338 workType "book-chapter" @default.