FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3209633679> ?p ?o ?g. }

• W3209633679 endingPage "108449" @default.
• W3209633679 startingPage "108449" @default.
• W3209633679 abstract "To enhance the energy efficiency of heating, ventilation and air conditioning (HVAC) systems, which is a non-linear and complicated system, machine learning has been used intensively. However, traditional white-box machine-learning models with good interpretability often do not have satisfactory accuracy, while black-box machine-learning models that are more accurate could not be interpreted easily, which impedes its application. In this study, we propose a method to interpret a neural network (NN) model using gradients of the model, which quantifies the marginal influence of inputs to the output, based on the chain rule. Then the NN model is compared with other machine-learning models (the linear regression model and the XGBoost model) in accuracy, interpretability, and robustness. We then compare our result with the correlation analysis, a widely used method to extract the relation between the outputs (in this case, energy consumption) and inputs. Further, we perform feature selection based on gradients of the NN model, reducing 40% calculation time without sacrificing model accuracy. The feature importance given by the NN model is proved to be reasonable and informative compared with the other two models. The scope of this study is neither to verify the superiority of the NN model, nor to predict the energy consumption accurately. Instead, the goal of this study is to provide a method to interpret the results of NN models." @default.
• W3209633679 created "2021-11-08" @default.
• W3209633679 creator A5008020574 @default.
• W3209633679 creator A5017804963 @default.
• W3209633679 creator A5056053058 @default.
• W3209633679 creator A5074494339 @default.
• W3209633679 date "2022-02-01" @default.
• W3209633679 modified "2023-10-12" @default.
• W3209633679 title "Interpreting the neural network model for HVAC system energy data mining" @default.
• W3209633679 cites W1967379861 @default.
• W3209633679 cites W1972971274 @default.
• W3209633679 cites W1973944436 @default.
• W3209633679 cites W1983377448 @default.
• W3209633679 cites W1987801135 @default.
• W3209633679 cites W2059270403 @default.
• W3209633679 cites W2062690987 @default.
• W3209633679 cites W2077249004 @default.
• W3209633679 cites W2344175847 @default.
• W3209633679 cites W2460994027 @default.
• W3209633679 cites W2464948348 @default.
• W3209633679 cites W2521479021 @default.
• W3209633679 cites W2580203704 @default.
• W3209633679 cites W2605614336 @default.
• W3209633679 cites W2620512989 @default.
• W3209633679 cites W2737452968 @default.
• W3209633679 cites W2738868428 @default.
• W3209633679 cites W2765721716 @default.
• W3209633679 cites W2767542146 @default.
• W3209633679 cites W2774931648 @default.
• W3209633679 cites W2795237036 @default.
• W3209633679 cites W2808872741 @default.
• W3209633679 cites W2836487175 @default.
• W3209633679 cites W2900724415 @default.
• W3209633679 cites W2905345781 @default.
• W3209633679 cites W2907978107 @default.
• W3209633679 cites W2912831070 @default.
• W3209633679 cites W2913362352 @default.
• W3209633679 cites W2921349661 @default.
• W3209633679 cites W2936274103 @default.
• W3209633679 cites W2938754359 @default.
• W3209633679 cites W2940870102 @default.
• W3209633679 cites W2945958815 @default.
• W3209633679 cites W2951505812 @default.
• W3209633679 cites W2957897705 @default.
• W3209633679 cites W2979420812 @default.
• W3209633679 cites W2988123653 @default.
• W3209633679 cites W2989354373 @default.
• W3209633679 cites W3006268427 @default.
• W3209633679 cites W3010838291 @default.
• W3209633679 cites W3012198078 @default.
• W3209633679 cites W3043389165 @default.
• W3209633679 cites W3045520824 @default.
• W3209633679 cites W3081299715 @default.
• W3209633679 cites W3083964105 @default.
• W3209633679 cites W3088895585 @default.
• W3209633679 cites W3106680740 @default.
• W3209633679 cites W3126675208 @default.
• W3209633679 cites W3130041319 @default.
• W3209633679 cites W3133083558 @default.
• W3209633679 cites W3137725309 @default.
• W3209633679 cites W3152454181 @default.
• W3209633679 cites W3155554243 @default.
• W3209633679 cites W3156755729 @default.
• W3209633679 doi "https://doi.org/10.1016/j.buildenv.2021.108449" @default.
• W3209633679 hasPublicationYear "2022" @default.
• W3209633679 type Work @default.
• W3209633679 sameAs 3209633679 @default.
• W3209633679 citedByCount "7" @default.
• W3209633679 countsByYear W32096336792022 @default.
• W3209633679 countsByYear W32096336792023 @default.
• W3209633679 crossrefType "journal-article" @default.
• W3209633679 hasAuthorship W3209633679A5008020574 @default.
• W3209633679 hasAuthorship W3209633679A5017804963 @default.
• W3209633679 hasAuthorship W3209633679A5056053058 @default.
• W3209633679 hasAuthorship W3209633679A5074494339 @default.
• W3209633679 hasConcept C103742991 @default.
• W3209633679 hasConcept C104317684 @default.
• W3209633679 hasConcept C105795698 @default.
• W3209633679 hasConcept C119599485 @default.
• W3209633679 hasConcept C119857082 @default.
• W3209633679 hasConcept C122346748 @default.
• W3209633679 hasConcept C124101348 @default.
• W3209633679 hasConcept C127413603 @default.
• W3209633679 hasConcept C138885662 @default.
• W3209633679 hasConcept C148483581 @default.
• W3209633679 hasConcept C154945302 @default.
• W3209633679 hasConcept C163175372 @default.
• W3209633679 hasConcept C180932941 @default.
• W3209633679 hasConcept C185592680 @default.
• W3209633679 hasConcept C186370098 @default.
• W3209633679 hasConcept C2776401178 @default.
• W3209633679 hasConcept C2780165032 @default.
• W3209633679 hasConcept C2781067378 @default.
• W3209633679 hasConcept C33923547 @default.
• W3209633679 hasConcept C41008148 @default.
• W3209633679 hasConcept C41895202 @default.
• W3209633679 hasConcept C50644808 @default.
• W3209633679 hasConcept C55493867 @default.

• next