FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3080451640> ?p ?o ?g. }

• W3080451640 endingPage "105675" @default.
• W3080451640 startingPage "105675" @default.
• W3080451640 abstract "• Ensemble methods can help improve prediction outcomes for complex traits. • Multiple regression and naive Bayes improve recall, AUC and balanced accuracy for some data sets. • Multiple logistic regression was the ensemble method with the best performance overall. • Continuous outcomes result in higher model performance than binary prediction outcomes. Cow survival is a complex trait that combines traits like milk production, fertility, health and environmental factors such as farm management. This complexity makes survival difficult to predict accurately. This is probably the reason why few studies attempted to address this problem and no studies are published that use ensemble methods for this purpose. We explored if we could improve prediction of cow survival to second lactation, when predicted at five different moments in a cow’s life, by combining the predictions of multiple (weak) methods in an ensemble method. We tested four ensemble methods: majority voting rule, multiple logistic regression, random forest and naive Bayes. Precision, recall, balanced accuracy, area under the curve (AUC) and gains in proportion of surviving cows in a scenario where the best 50% were selected were used to evaluate the ensemble model performance. We also calculated correlations between the ensemble models and obtained McNemar’s test statistics. We compared the performance of the ensemble methods against those of the individual methods. We also tested if there was a difference in performance metrics when continuous (from 0 to 1) and binary (0 or 1) prediction outcomes were used. In general, using continuous prediction output resulted in higher performance metrics than binary ones. AUCs for models ranged from 0.561 to 0.731, with generally increasing performance at moments later in life. Precision, AUC and balanced accuracy values improved significantly for the naive Bayes and multiple logistic regression ensembles in at least one data set, although performance metrics did remain low overall. The multiple logistic regression ensemble method resulted in equal or better precision, AUC, balanced accuracy and proportion of animals surviving on all datasets and was significantly different from the other ensembles in three out of five moments. The random forest ensemble method resulted in the least significant improvement over the individual methods." @default.
• W3080451640 created "2020-09-01" @default.
• W3080451640 creator A5002999108 @default.
• W3080451640 creator A5027326994 @default.
• W3080451640 creator A5027741500 @default.
• W3080451640 creator A5039020647 @default.
• W3080451640 creator A5070260526 @default.
• W3080451640 creator A5076137207 @default.
• W3080451640 creator A5086160927 @default.
• W3080451640 date "2020-10-01" @default.
• W3080451640 modified "2023-10-17" @default.
• W3080451640 title "Improving predictive performance on survival in dairy cattle using an ensemble learning approach" @default.
• W3080451640 cites W1501190346 @default.
• W3080451640 cites W1534477342 @default.
• W3080451640 cites W1817561967 @default.
• W3080451640 cites W1831050183 @default.
• W3080451640 cites W1851683475 @default.
• W3080451640 cites W1981399499 @default.
• W3080451640 cites W1981609576 @default.
• W3080451640 cites W1988474781 @default.
• W3080451640 cites W1991860357 @default.
• W3080451640 cites W2004053254 @default.
• W3080451640 cites W2006617902 @default.
• W3080451640 cites W2023294425 @default.
• W3080451640 cites W2032478721 @default.
• W3080451640 cites W2036599383 @default.
• W3080451640 cites W2038705219 @default.
• W3080451640 cites W2048175932 @default.
• W3080451640 cites W2050055089 @default.
• W3080451640 cites W2053717624 @default.
• W3080451640 cites W2054723079 @default.
• W3080451640 cites W2062976607 @default.
• W3080451640 cites W2078729141 @default.
• W3080451640 cites W2091855602 @default.
• W3080451640 cites W2096352448 @default.
• W3080451640 cites W2099454382 @default.
• W3080451640 cites W2101807845 @default.
• W3080451640 cites W2122892819 @default.
• W3080451640 cites W2126648000 @default.
• W3080451640 cites W2126652700 @default.
• W3080451640 cites W2137997998 @default.
• W3080451640 cites W2151314772 @default.
• W3080451640 cites W2156907337 @default.
• W3080451640 cites W2161336914 @default.
• W3080451640 cites W2177094773 @default.
• W3080451640 cites W2218361137 @default.
• W3080451640 cites W2244486986 @default.
• W3080451640 cites W2407994760 @default.
• W3080451640 cites W2510431732 @default.
• W3080451640 cites W2540422813 @default.
• W3080451640 cites W2562319768 @default.
• W3080451640 cites W2587532477 @default.
• W3080451640 cites W2761033249 @default.
• W3080451640 cites W2769845653 @default.
• W3080451640 cites W2780934445 @default.
• W3080451640 cites W2807352940 @default.
• W3080451640 cites W2885770726 @default.
• W3080451640 cites W2911964244 @default.
• W3080451640 cites W2963864906 @default.
• W3080451640 cites W2969301077 @default.
• W3080451640 cites W3000393559 @default.
• W3080451640 cites W3004797226 @default.
• W3080451640 cites W3005480524 @default.
• W3080451640 cites W3104887532 @default.
• W3080451640 cites W3121452939 @default.
• W3080451640 cites W4212883601 @default.
• W3080451640 cites W4246259708 @default.
• W3080451640 cites W4301480657 @default.
• W3080451640 doi "https://doi.org/10.1016/j.compag.2020.105675" @default.
• W3080451640 hasPublicationYear "2020" @default.
• W3080451640 type Work @default.
• W3080451640 sameAs 3080451640 @default.
• W3080451640 citedByCount "4" @default.
• W3080451640 countsByYear W30804516402021 @default.
• W3080451640 countsByYear W30804516402022 @default.
• W3080451640 countsByYear W30804516402023 @default.
• W3080451640 crossrefType "journal-article" @default.
• W3080451640 hasAuthorship W3080451640A5002999108 @default.
• W3080451640 hasAuthorship W3080451640A5027326994 @default.
• W3080451640 hasAuthorship W3080451640A5027741500 @default.
• W3080451640 hasAuthorship W3080451640A5039020647 @default.
• W3080451640 hasAuthorship W3080451640A5070260526 @default.
• W3080451640 hasAuthorship W3080451640A5076137207 @default.
• W3080451640 hasAuthorship W3080451640A5086160927 @default.
• W3080451640 hasBestOaLocation W30804516401 @default.
• W3080451640 hasConcept C105795698 @default.
• W3080451640 hasConcept C107673813 @default.
• W3080451640 hasConcept C119857082 @default.
• W3080451640 hasConcept C119898033 @default.
• W3080451640 hasConcept C12267149 @default.
• W3080451640 hasConcept C151956035 @default.
• W3080451640 hasConcept C154945302 @default.
• W3080451640 hasConcept C169258074 @default.
• W3080451640 hasConcept C186282968 @default.
• W3080451640 hasConcept C207201462 @default.
• W3080451640 hasConcept C33923547 @default.
• W3080451640 hasConcept C41008148 @default.
• W3080451640 hasConcept C45804977 @default.

• next