Çetin, Serkant Ali2021-01-082021-01-082019-04-301434-60521434-6044https://hdl.handle.net/11411/3061https://doi.org/10.1140/epjc/s10052-019-6847-8The performance of identification algorithms (taggers) for hadronically decaying top quarks and W bosons in pp collisions at = 13TeV recorded by the ATLAS experiment at the Large Hadron Collider is presented. A set of techniques based on jet shape observables are studied to determine a set of optimal cut-based taggers for use in physics analyses. The studies are extended to assess the utility of combinations of substructure observables as a multivariate tagger using boosted decision trees or deep neural networks in comparison with taggers based on two-variable combinations. In addition, for highly boosted top-quark tagging, a deep neural network based on jet constituent inputs as well as a re-optimisation of the shower deconstruction technique is presented. The performance of these taggers is studied in data collected during 2015 and 2016 corresponding to 36.1fb-1 for the tt and +jet and 36.7-1 for the dijet event topologies.eninfo:eu-repo/semantics/openAccessArticle2-s2.0-8506512303010.1140/epjc/s10052-019-6847-8Q1WOS:000466407600007