Matches in SemOpenAlex for { <https://semopenalex.org/work/W3109051320> ?p ?o ?g. }
Showing items 1 to 85 of
85
with 100 items per page.
- W3109051320 abstract "We propose a model that combines only simple techniques to meet the challenge of cooking activity recognition. The challenge dataset is basically small, consisting only of four subjects where three are used for training and one for validation. In order not to overfit the small training data, we employed two simple classifiers, LightGBM and Naive Bayes, which suited the task. To prevent leakage from other subject data during training, we used Leave One Subject Out cross validation. Further, we incorporated a post-processing step wherein the Naive Bayes corrects the macro-activity classification outcomes that have been derived by LightGBM, based on the combinations of macro and micro activities that are likely to occur. We hypothesized that this added post-processing will improve the macro-activity recognition, and with it, our model may be able to adapt well and generalize to other small datasets. As a result, our proposed model achieved an average accuracy of 0.557 when classifying macro and micro activities from a small dataset." @default.
- W3109051320 created "2020-12-07" @default.
- W3109051320 creator A5014746910 @default.
- W3109051320 creator A5055168543 @default.
- W3109051320 creator A5058060139 @default.
- W3109051320 creator A5062786880 @default.
- W3109051320 date "2020-11-21" @default.
- W3109051320 modified "2023-10-16" @default.
- W3109051320 title "Let’s Not Make It Complicated—Using Only LightGBM and Naive Bayes for Macro- and Micro-Activity Recognition from a Small Dataset" @default.
- W3109051320 cites W2038746778 @default.
- W3109051320 cites W2180635266 @default.
- W3109051320 cites W2270470215 @default.
- W3109051320 cites W2553915786 @default.
- W3109051320 cites W2736191430 @default.
- W3109051320 cites W2736707111 @default.
- W3109051320 cites W2790414609 @default.
- W3109051320 cites W2794717185 @default.
- W3109051320 cites W2916712302 @default.
- W3109051320 cites W2941398656 @default.
- W3109051320 cites W2949676527 @default.
- W3109051320 cites W2965144482 @default.
- W3109051320 cites W2972317743 @default.
- W3109051320 cites W2972454934 @default.
- W3109051320 cites W2973204573 @default.
- W3109051320 cites W2990615181 @default.
- W3109051320 cites W3109800024 @default.
- W3109051320 doi "https://doi.org/10.1007/978-981-15-8269-1_3" @default.
- W3109051320 hasPublicationYear "2020" @default.
- W3109051320 type Work @default.
- W3109051320 sameAs 3109051320 @default.
- W3109051320 citedByCount "0" @default.
- W3109051320 crossrefType "book-chapter" @default.
- W3109051320 hasAuthorship W3109051320A5014746910 @default.
- W3109051320 hasAuthorship W3109051320A5055168543 @default.
- W3109051320 hasAuthorship W3109051320A5058060139 @default.
- W3109051320 hasAuthorship W3109051320A5062786880 @default.
- W3109051320 hasConcept C107673813 @default.
- W3109051320 hasConcept C119857082 @default.
- W3109051320 hasConcept C12267149 @default.
- W3109051320 hasConcept C124101348 @default.
- W3109051320 hasConcept C127413603 @default.
- W3109051320 hasConcept C153180895 @default.
- W3109051320 hasConcept C154945302 @default.
- W3109051320 hasConcept C166955791 @default.
- W3109051320 hasConcept C199360897 @default.
- W3109051320 hasConcept C201995342 @default.
- W3109051320 hasConcept C207201462 @default.
- W3109051320 hasConcept C22019652 @default.
- W3109051320 hasConcept C2780451532 @default.
- W3109051320 hasConcept C41008148 @default.
- W3109051320 hasConcept C50644808 @default.
- W3109051320 hasConcept C52001869 @default.
- W3109051320 hasConceptScore W3109051320C107673813 @default.
- W3109051320 hasConceptScore W3109051320C119857082 @default.
- W3109051320 hasConceptScore W3109051320C12267149 @default.
- W3109051320 hasConceptScore W3109051320C124101348 @default.
- W3109051320 hasConceptScore W3109051320C127413603 @default.
- W3109051320 hasConceptScore W3109051320C153180895 @default.
- W3109051320 hasConceptScore W3109051320C154945302 @default.
- W3109051320 hasConceptScore W3109051320C166955791 @default.
- W3109051320 hasConceptScore W3109051320C199360897 @default.
- W3109051320 hasConceptScore W3109051320C201995342 @default.
- W3109051320 hasConceptScore W3109051320C207201462 @default.
- W3109051320 hasConceptScore W3109051320C22019652 @default.
- W3109051320 hasConceptScore W3109051320C2780451532 @default.
- W3109051320 hasConceptScore W3109051320C41008148 @default.
- W3109051320 hasConceptScore W3109051320C50644808 @default.
- W3109051320 hasConceptScore W3109051320C52001869 @default.
- W3109051320 hasLocation W31090513201 @default.
- W3109051320 hasOpenAccess W3109051320 @default.
- W3109051320 hasPrimaryLocation W31090513201 @default.
- W3109051320 hasRelatedWork W11919366 @default.
- W3109051320 hasRelatedWork W12783365 @default.
- W3109051320 hasRelatedWork W13749590 @default.
- W3109051320 hasRelatedWork W14973754 @default.
- W3109051320 hasRelatedWork W2651071 @default.
- W3109051320 hasRelatedWork W2777878 @default.
- W3109051320 hasRelatedWork W5005022 @default.
- W3109051320 hasRelatedWork W5410279 @default.
- W3109051320 hasRelatedWork W7299809 @default.
- W3109051320 hasRelatedWork W7465187 @default.
- W3109051320 isParatext "false" @default.
- W3109051320 isRetracted "false" @default.
- W3109051320 magId "3109051320" @default.
- W3109051320 workType "book-chapter" @default.