Matches in SemOpenAlex for { <https://semopenalex.org/work/W4308488376> ?p ?o ?g. }
- W4308488376 endingPage "105468" @default.
- W4308488376 startingPage "105468" @default.
- W4308488376 abstract "University campuses are comprised of many different types of buildings and thus, to improve their energy efficiency, the benchmarking of these buildings is fundamental. In this regard, this study aimed to develop an energy consumption benchmark for university buildings in Brazil. The benchmark was based on a database obtained through parametric building energy simulation by employing an archetype of a university building, developed by the Brazilian Council for Sustainable Construction (CBCS), and a set of parameter variations. The database was obtained considering nine building parameters (e.g., occupancy, internal loads and envelope features), resulting in 23,256 cases aimed at representing the variety of university buildings countrywide. Therefore, this process is innovative since a benchmark is developed for multiple buildings across the country rather than for only one building on a specific university building or campus. Three machine learning techniques were compared to develop the benchmark, multiple linear regression (MLR), support vector machine (SVM) and artificial neural network (ANN). The SVM method had the lowest mean absolute error, root mean absolute error and the highest R2 value, and thus it was adopted to develop the benchmark and efficiency scales. The efficiency scale was used to classify the buildings into ‘efficient’, ‘typical’ or ‘inefficient’, and supports the identification of good practice or inefficiency." @default.
- W4308488376 created "2022-11-12" @default.
- W4308488376 creator A5018118580 @default.
- W4308488376 creator A5053654677 @default.
- W4308488376 creator A5081140910 @default.
- W4308488376 date "2023-01-01" @default.
- W4308488376 modified "2023-09-27" @default.
- W4308488376 title "Applying machine learning to develop energy benchmarking for university buildings in Brazil" @default.
- W4308488376 cites W1971763233 @default.
- W4308488376 cites W1977525662 @default.
- W4308488376 cites W1985885136 @default.
- W4308488376 cites W1990910451 @default.
- W4308488376 cites W1992120390 @default.
- W4308488376 cites W1998913785 @default.
- W4308488376 cites W1999979720 @default.
- W4308488376 cites W2000548672 @default.
- W4308488376 cites W2002474764 @default.
- W4308488376 cites W2014484342 @default.
- W4308488376 cites W2016480649 @default.
- W4308488376 cites W2024075368 @default.
- W4308488376 cites W2028647114 @default.
- W4308488376 cites W2029767409 @default.
- W4308488376 cites W2033065921 @default.
- W4308488376 cites W2043674345 @default.
- W4308488376 cites W2046270768 @default.
- W4308488376 cites W2050696861 @default.
- W4308488376 cites W2057320261 @default.
- W4308488376 cites W2064316277 @default.
- W4308488376 cites W2069912221 @default.
- W4308488376 cites W2073796776 @default.
- W4308488376 cites W2074676349 @default.
- W4308488376 cites W2078102233 @default.
- W4308488376 cites W2084412545 @default.
- W4308488376 cites W2085510419 @default.
- W4308488376 cites W2088646625 @default.
- W4308488376 cites W2091693228 @default.
- W4308488376 cites W2135078545 @default.
- W4308488376 cites W2141278974 @default.
- W4308488376 cites W2156302255 @default.
- W4308488376 cites W2161257182 @default.
- W4308488376 cites W2164709595 @default.
- W4308488376 cites W2169790708 @default.
- W4308488376 cites W2201221078 @default.
- W4308488376 cites W2472326376 @default.
- W4308488376 cites W2523043834 @default.
- W4308488376 cites W2537907331 @default.
- W4308488376 cites W2762577631 @default.
- W4308488376 cites W2766250018 @default.
- W4308488376 cites W2767678610 @default.
- W4308488376 cites W2773309836 @default.
- W4308488376 cites W2774481247 @default.
- W4308488376 cites W2783365607 @default.
- W4308488376 cites W2789243543 @default.
- W4308488376 cites W2887100796 @default.
- W4308488376 cites W2922147260 @default.
- W4308488376 cites W2937014336 @default.
- W4308488376 cites W2941915216 @default.
- W4308488376 cites W2953634225 @default.
- W4308488376 cites W2971662304 @default.
- W4308488376 cites W2994770671 @default.
- W4308488376 cites W3001035162 @default.
- W4308488376 cites W3024140953 @default.
- W4308488376 cites W3104887532 @default.
- W4308488376 cites W3111640765 @default.
- W4308488376 cites W3119926900 @default.
- W4308488376 cites W3165283252 @default.
- W4308488376 cites W3173228546 @default.
- W4308488376 cites W3207824859 @default.
- W4308488376 cites W4205682326 @default.
- W4308488376 cites W4225726285 @default.
- W4308488376 doi "https://doi.org/10.1016/j.jobe.2022.105468" @default.
- W4308488376 hasPublicationYear "2023" @default.
- W4308488376 type Work @default.
- W4308488376 citedByCount "1" @default.
- W4308488376 countsByYear W43084883762022 @default.
- W4308488376 crossrefType "journal-article" @default.
- W4308488376 hasAuthorship W4308488376A5018118580 @default.
- W4308488376 hasAuthorship W4308488376A5053654677 @default.
- W4308488376 hasAuthorship W4308488376A5081140910 @default.
- W4308488376 hasBestOaLocation W43084883761 @default.
- W4308488376 hasConcept C105795698 @default.
- W4308488376 hasConcept C107053488 @default.
- W4308488376 hasConcept C127413603 @default.
- W4308488376 hasConcept C144133560 @default.
- W4308488376 hasConcept C160331591 @default.
- W4308488376 hasConcept C162853370 @default.
- W4308488376 hasConcept C170154142 @default.
- W4308488376 hasConcept C186370098 @default.
- W4308488376 hasConcept C2778215892 @default.
- W4308488376 hasConcept C33923547 @default.
- W4308488376 hasConcept C41008148 @default.
- W4308488376 hasConcept C86251818 @default.
- W4308488376 hasConceptScore W4308488376C105795698 @default.
- W4308488376 hasConceptScore W4308488376C107053488 @default.
- W4308488376 hasConceptScore W4308488376C127413603 @default.
- W4308488376 hasConceptScore W4308488376C144133560 @default.
- W4308488376 hasConceptScore W4308488376C160331591 @default.
- W4308488376 hasConceptScore W4308488376C162853370 @default.