Matches in SemOpenAlex for { <https://semopenalex.org/work/W3040691887> ?p ?o ?g. }
- W3040691887 endingPage "107013" @default.
- W3040691887 startingPage "107013" @default.
- W3040691887 abstract "Human preference-based control in buildings may achieve maximum occupant satisfaction as well as energy savings. Adaptive and online learning methods are needed for learning human preferences, using the minimum amount of data possible with quantified uncertainty. This paper presents an online visual preference elicitation learning framework, developed for efficiently learning occupants' visual preference profiles and hidden satisfaction utility functions in daylit offices. A combination of Thompson sampling and pure exploration (uncertainty learning) methods was used in the sequential elicitation framework, to determine the set of successive visual preference queries (for visual conditions) with most information gain. In this way, a balance between exploration and exploitation is realized and the area around the satisfaction utility maximum is learned with minimum number of steps. Experiments with human subjects were conducted in private sidelit offices to demonstrate the feasibility and performance of the learning framework. A single-variable model (vertical illuminance) was used to demonstrate the method and visualize results. The entropy of the distribution of the most preferred visual condition is computed for each learned preference profile to quantify the certainty and evaluate the learning efficiency. Our method learns most individual visual preferences to an acceptable certainty level within one day, and indicates the need for personalization. Finally, we discuss the integration of visual preferences into control applications. A switching algorithm is proposed, shifting iteratively between the learning and control modes depending on the certainty of the learned preference model. This work contributes to developing comprehensive online learning methods towards preference-based tuned indoor environments." @default.
- W3040691887 created "2020-07-16" @default.
- W3040691887 creator A5015716594 @default.
- W3040691887 creator A5017500444 @default.
- W3040691887 creator A5023374050 @default.
- W3040691887 creator A5029168423 @default.
- W3040691887 creator A5043072708 @default.
- W3040691887 date "2020-08-01" @default.
- W3040691887 modified "2023-09-27" @default.
- W3040691887 title "Efficient learning of personalized visual preferences in daylit offices: An online elicitation framework" @default.
- W3040691887 cites W1750524653 @default.
- W3040691887 cites W1965154918 @default.
- W3040691887 cites W1969879150 @default.
- W3040691887 cites W1970952940 @default.
- W3040691887 cites W1985484348 @default.
- W3040691887 cites W1995875735 @default.
- W3040691887 cites W1997001039 @default.
- W3040691887 cites W1998007112 @default.
- W3040691887 cites W1998498767 @default.
- W3040691887 cites W2000041175 @default.
- W3040691887 cites W2030501831 @default.
- W3040691887 cites W2035596690 @default.
- W3040691887 cites W2039887695 @default.
- W3040691887 cites W2039900281 @default.
- W3040691887 cites W2040661936 @default.
- W3040691887 cites W2042291475 @default.
- W3040691887 cites W2047186970 @default.
- W3040691887 cites W2061144551 @default.
- W3040691887 cites W2075729977 @default.
- W3040691887 cites W2085816689 @default.
- W3040691887 cites W2086627390 @default.
- W3040691887 cites W2100951418 @default.
- W3040691887 cites W2126849655 @default.
- W3040691887 cites W2143032245 @default.
- W3040691887 cites W2154023516 @default.
- W3040691887 cites W2158125716 @default.
- W3040691887 cites W2221739275 @default.
- W3040691887 cites W2515013069 @default.
- W3040691887 cites W2583261040 @default.
- W3040691887 cites W2600511347 @default.
- W3040691887 cites W2614899167 @default.
- W3040691887 cites W2790054465 @default.
- W3040691887 cites W2793776490 @default.
- W3040691887 cites W2800070685 @default.
- W3040691887 cites W2901147498 @default.
- W3040691887 cites W2908456052 @default.
- W3040691887 cites W2922653791 @default.
- W3040691887 cites W2936062817 @default.
- W3040691887 cites W2937246084 @default.
- W3040691887 cites W3003725787 @default.
- W3040691887 cites W3020858386 @default.
- W3040691887 cites W4234228486 @default.
- W3040691887 doi "https://doi.org/10.1016/j.buildenv.2020.107013" @default.
- W3040691887 hasPublicationYear "2020" @default.
- W3040691887 type Work @default.
- W3040691887 sameAs 3040691887 @default.
- W3040691887 citedByCount "5" @default.
- W3040691887 countsByYear W30406918872021 @default.
- W3040691887 countsByYear W30406918872022 @default.
- W3040691887 countsByYear W30406918872023 @default.
- W3040691887 crossrefType "journal-article" @default.
- W3040691887 hasAuthorship W3040691887A5015716594 @default.
- W3040691887 hasAuthorship W3040691887A5017500444 @default.
- W3040691887 hasAuthorship W3040691887A5023374050 @default.
- W3040691887 hasAuthorship W3040691887A5029168423 @default.
- W3040691887 hasAuthorship W3040691887A5043072708 @default.
- W3040691887 hasBestOaLocation W30406918871 @default.
- W3040691887 hasConcept C105795698 @default.
- W3040691887 hasConcept C107457646 @default.
- W3040691887 hasConcept C119857082 @default.
- W3040691887 hasConcept C136764020 @default.
- W3040691887 hasConcept C154945302 @default.
- W3040691887 hasConcept C181204326 @default.
- W3040691887 hasConcept C183003079 @default.
- W3040691887 hasConcept C2524010 @default.
- W3040691887 hasConcept C2777868144 @default.
- W3040691887 hasConcept C2781249084 @default.
- W3040691887 hasConcept C33923547 @default.
- W3040691887 hasConcept C41008148 @default.
- W3040691887 hasConcept C7493553 @default.
- W3040691887 hasConceptScore W3040691887C105795698 @default.
- W3040691887 hasConceptScore W3040691887C107457646 @default.
- W3040691887 hasConceptScore W3040691887C119857082 @default.
- W3040691887 hasConceptScore W3040691887C136764020 @default.
- W3040691887 hasConceptScore W3040691887C154945302 @default.
- W3040691887 hasConceptScore W3040691887C181204326 @default.
- W3040691887 hasConceptScore W3040691887C183003079 @default.
- W3040691887 hasConceptScore W3040691887C2524010 @default.
- W3040691887 hasConceptScore W3040691887C2777868144 @default.
- W3040691887 hasConceptScore W3040691887C2781249084 @default.
- W3040691887 hasConceptScore W3040691887C33923547 @default.
- W3040691887 hasConceptScore W3040691887C41008148 @default.
- W3040691887 hasConceptScore W3040691887C7493553 @default.
- W3040691887 hasFunder F4320306076 @default.
- W3040691887 hasLocation W30406918871 @default.
- W3040691887 hasOpenAccess W3040691887 @default.
- W3040691887 hasPrimaryLocation W30406918871 @default.
- W3040691887 hasRelatedWork W1562775108 @default.