Utilize este identificador para referenciar este registo:
http://hdl.handle.net/10071/26678
Autoria: | Labiadh, M. Obrecht, C. Ferreira da Silva, C. Ghodous, P. Benabdeslem, K. |
Data: | 2023 |
Título próprio: | Query-adaptive training data recommendation for cross-building predictive modeling |
Título da revista: | Knowledge and Information Systems |
Volume: | 65 |
Número: | 2 |
Paginação: | 707 - 732 |
Referência bibliográfica: | Labiadh, M., Obrecht, C., Ferreira da Silva, C., Ghodous, P., & Benabdeslem, K. (2023). Query-adaptive training data recommendation for cross-building predictive modeling. Knowledge and Information Systems, 65(2), 707-732. http://dx.doi.org/10.1007/s10115-022-01771-9 |
ISSN: | 0219-1377 |
DOI (Digital Object Identifier): | 10.1007/s10115-022-01771-9 |
Palavras-chave: | Training data recommendation Similarity learning Domain generalization Knowledge transfer Data-driven modeling Building energy |
Resumo: | Predictive modeling in buildings is a key task for the optimal management of building energy. Relevant building operational data are a prerequisite for such task, notably when deep learning is used. However, building operational data are not always available, such is the case in newly built, newly renovated, or even not yet built buildings. To address this problem, we propose a deep similarity learning approach to recommend relevant training data to a target building solely by using a minimal contextual description on it. Contextual descriptions are modeled as user queries. We further propose to ensemble most used machine learning algorithms in the context of predictive modeling. This contributes to the genericity of the proposed methodology. Experimental evaluations show that our methodology offers a generic methodology for cross-building predictive modeling and achieves good generalization performance. |
Arbitragem científica: | yes |
Acesso: | Acesso Aberto |
Aparece nas coleções: | ISTAR-RI - Artigos em revistas científicas internacionais com arbitragem científica |
Ficheiros deste registo:
Ficheiro | Tamanho | Formato | |
---|---|---|---|
article_90089.pdf | 629,58 kB | Adobe PDF | Ver/Abrir |
Todos os registos no repositório estão protegidos por leis de copyright, com todos os direitos reservados.